Hiroshi MASUDA
| Department of Mechanical and Intelligent Systems Engineering | Professor |
| Cluster III (Fundamental Science and Engineering) | Professor |
Researcher Information
Research Keyword
Field Of Study
Career
Research Activity Information
Award
- Sep. 2023
精密工学会
断面推定に基づく一般化円柱の検出と形状再構成
精密工学会 ベストプレゼンテーション賞, 小森谷沙希 - Mar. 2022
精密工学会
点群の深層学習のためのCADモデルからの学習データ生成（第2報）
精密工学会ベストプレゼンテーション賞, 南雲 拓真
Japan society - Sep. 2021
精密工学会
寸法計測に適した点群レジストレーション手法の検討
精密工学会ベストプレゼンテーション賞, 川崎春菜
Japan society - Apr. 2018
日本機械学会
三次元計測に基づく燃焼炉の保守支援
若手優秀講演フェロー賞, 篠崎有希
Japan society - Mar. 2018
日本機械学会
柱状物体に適した大規模点群のレジストレーションに関する研究
Best Presentation Award, 松本裕稀
Japan society - Mar. 2015
精密工学会
立体視に適した大規模点群のレンダリング （第２報）
2015年度精密工学会春季大会学術講演会 ベストプレゼンテーション賞, 岡本 大樹
Japan society - Jun. 2014
Computer-Aided Design and Applications, 国際会議の最優秀論文（発表８９件中１件）
the 11th Annual International CAD Conference, Overall Best Paper Award
International society - Oct. 2011
日本機械学会
日本機械学会 優秀講演表彰 - Oct. 2011
日本品質管理工学会
日本品質管理工学会 品質技術賞 - Mar. 2011
精密工学会
精密工学会 論文賞 - Feb. 2009
画像電子学会
グラフィックスとCAD研究会 優秀研究発表賞（共著学生の受賞） - Nov. 2007
NICOGRAPH
NICOGRAPH 最優秀論文賞 - Jun. 2006
映像情報メディア学会
デジタルコンテンツシンポジウム 船井賞（共著学生の受賞） - Jun. 2002
画像電子学会
グラフィクスとCADシンポジウム 優秀研究発表賞（共著学生の受賞） - May 2002
NICPGRAPH
NICOGRAPH International Best Paper Award
Paper
- Point cloud Classification for Components of Industrial Facilities Using Laplacian Features
Takeshi Otsuka; Kosei Otani; Hiroshi Masuda
Corresponding, The 20th International Conference on Precision Engineering (ICPE2024), S19-06, 25 Oct. 2024
International conference proceedings, English - Point Cloud Segmentation of Production Lines in Factories
Kakeru Takeda; Hiroshi Masuda
Corresponding, he 20th International Conference on Precision Engineering (ICPE2024), OS19-05, 25 Oct. 2024
English - Generation of Training Data from CAD Models Suitable for Component Recognition from Point Clouds of Industrial Plants
Kosei Otani; Takuma Nagumo; Hiroshi Masuda
Corresponding, The 20th International Conference on Precision Engineering (ICPE2024), OS19-04, 25 Oct. 2024
International conference proceedings, English - Extraction and Reconstruction of Articulated Robots from Point Clouds of Manufacturing Plants
Kota Kawasaki; Kakeru Takeda; Hiroshi Masuda
Corresponding, The 21th Annual International CAD Conference (CAD'24), U-turn Press LLC, 131-135, 02 Jul. 2024, Peer-reviwed
International conference proceedings, English - Finite element analysis with deformed shape constraints generated by laser‐scanned point clouds
Hibiya Haraki; Yasunori Yusa; Hiroshi Masuda
International Journal for Numerical Methods in Engineering, Wiley, 125, 19, 26 Jun. 2024, Peer-reviwed, Abstract
This article proposes a computational method for finite element analysis with deformed shape constraints for analyzing constructed structures to account for deformations that occur before shape measurement by a terrestrial laser scanner (TLS). In this method, point clouds obtained by a TLS are considered as a partial surface of the deformed structure. An analysis model is assumed to be created from CAD data or drawings. The analysis is performed under deformed shape constraints, namely, the deformed surface constraints or the normal vector constraints, which are generated by the point clouds. These constraints are introduced to reproduce the current displacements and stresses for the structure through the analysis. This method was applied to analyses of a plate and a desk using point clouds, which were created virtually on a computer or obtained by a TLS in the numerical examples. The results showed that this method can consider unexpected deformations that occur before laser scanning. Although the computed stresses oscillated when the scanned point cloud was used due to measurement errors and conventional point cloud processing methods, the stress values were responsive enough to indicate unnatural shapes of the deformed structure. Moreover, the oscillation was observed only in areas with constraints, whereas it was not seen in areas without constraints.
Scientific journal, English - Efficient Calculation of Multi-Scale Features for MMS Point Clouds
Keita Hiraoka; Genki Takahashi; Hiroshi Masuda
Corresponding, The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Copernicus GmbH, XLVIII-2-2024, 145-151, 11 Jun. 2024, Peer-reviwed, Abstract. Point clouds acquired by Mobile Mapping System (MMS) are useful for creating 3D maps that can be used for autonomous driving and infrastructure development. However, many applications require semantic labels to each point of the point clouds, and the manual labeling process is very time consuming and expensive. Therefore, there is a strong need to develop a method to automatically assigning semantic labels. For automatic labeling tasks, classification methods using multiscale features are effective because multiscale features include features of various scales of roadside objects. Multiscale features are calculated using points inside spheres of multiscale radii centered at each point in a point cloud. When calculating multiscale features that are useful for classifying MMS point clouds, it is necessary to calculate features using relatively large radii. However, when calculating multiscale features using wide range of neighbor points, existing methods, such as kd-tree, require unacceptably long computation time for neighbor search. In this paper, we propose a method to calculate multiscale features in practical time for semantic labeling of large-scale point clouds. In our method, an MMS point cloud is first divided into small spherical regions. Then, radius search using multiscale radii is performed, and multiscale features are calculated using those neighbor points. Our experimental results showed that our method achieved significantly faster computational performance than conventional methods, and multiscale features could be calculated from large-scale point clouds in practical time.
International conference proceedings - Detection of Multiscale Deterioration from Point-Clouds of Furnace Walls
Tomoko Aoki; Erika Yamamoto; Hiroshi Masuda
Corresponding, International Journal of Automation Technology, Fuji Technology Press Ltd., 17, 6, 610-618, 05 Nov. 2023, Peer-reviwed, Deterioration surveys of large structures such as furnaces have been mainly conducted by visual inspection, but it is desirable to automatically detect deterioration using point clouds captured by the terrestrial laser scanner. In this study, we propose flexible methods for detecting various scales of cracks, delamination, and adhesion on furnace walls by using a machine learning technique. Since small cracks have few geometrical features, they are detected from the reflection intensity images generated by projecting a point cloud onto a two-dimensional plane. For detecting cracks on the image, we use the U-Net fine-tuned by crack images denoised with a median filter. For detecting delamination and adhesion, a wall surface is approximated by a smooth B-spline surface, and deterioration is detected as differences between the point cloud and the approximated surface. However, in this method, the resolution of the B-spline surface has to be carefully determined according to the expected deterioration sizes. To robustly detect deterioration at various scales, we introduce multiscale 3D features, and detect deterioration using both multiscale 3D features and 2D features. In actual walls, it is difficult to distinguish between cracks and delamination because delamination grows from cracks. To detect both types of deterioration in a uniform manner, we combine the two detectors and propose an integrated detector for detecting deterioration at various scales. Our experimental results showed that our methods could stably detect various scales of degradation on furnace walls.
Scientific journal, English - Shape Reconstruction of Structural Members of Steel Tower Considering Symmetrical Relationships
Kota Kawasaki; Hiroshi Masuda
Corresponding, Computer-Aided Design and Applications, 20, 5, 814-825, Jan. 2023, Peer-reviwed
Scientific journal, English - Detection of Multiscale Deterioration from Point-Clouds of Furnace Walls
T. Aoki, E. Yamamoto, H. Masuda
Corresponding, Proc of The 19th International Conference on Precision Engineering (ICPE2022), D60, 30 Nov. 2022, Peer-reviwed, False
International conference proceedings, English - Point Cloud Segmentation for Pipelines in Industrial Facilities Using Recurrent Networks
Kohei Shigeta; Hiroshi Masuda
Computer-Aided Design and Applications, 20, 4, 786-796, 01 Nov. 2022, Peer-reviwed
Scientific journal, English - ACCURATE CALCULATION OF TREE STEM TRAITS IN FORESTS BY LOCAL CORRECTION OF POINT CLOUD REGISTRATION
H. Kawasaki; H. Masuda
The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Copernicus GmbH, XLIII-B2-2022, 209-214, 30 May 2022, Peer-reviwed, Abstract. In recent years, it has become important in forestry and forest research to accurately calculate tree stem traits from point clouds captured using the terrestrial laser scanner. However, it is difficult to accurately align a large number of trees in a forest over a large area. Therefore, the reliability of traits calculated from point clouds has been problematic. In this paper, we propose a method to automatically correct misaligned point-clouds and calculate accurate tree stem traits. In our method, a different registration matrix is calculated for each tree to correct the misalignment. When the target tree is specified, point-clouds measured in the vicinity of the target tree and points of the neighbor trees are selected for multi-view registration, and a registration matrix suitable for the target tree is calculated. The experimental results show that the proposed method is effective in correcting misalignment and precisely calculating tree stem traits.
Scientific journal, English - MMS点群データの自動ラベリングに適した点群特徴量
高橋元気; 増田宏
写真測量とリモートセンシング（写真測量学会論文誌）, 60, 5, 266-275, 01 Nov. 2021, Peer-reviwed
Scientific journal, Japanese - Data Augmentation of Classifiers for Components in Industrial Plants Using CAD Models
Kohei Shigeta; Hiroshi Masuda
Computer-Aided Design and Applications, 18, 5, 890-899, 01 Sep. 2021, Peer-reviwed
Scientific journal, English - Efficient Calculation Method for Tree Stem Traits from Large-Scale Point Clouds of Forest Stands
H. Masuda; Y. Hiraoka; K. Saito; S. Eto; M. Matsushita; M. Takahashi
Remote Sensing, MDPI AG, 13, 13, 2467-2476, 25 Jun. 2021, Peer-reviwed, With the use of terrestrial laser scanning (TLS) in forest stands, surveys are now equipped to obtain dense point cloud data. However, the data range, i.e., the number of points, often reaches the billions or even higher, exceeding random access memory (RAM) limits on common computers. Moreover, the processing time often also extends beyond acceptable processing lengths. Thus, in this paper, we present a new method of efficiently extracting stem traits from huge point cloud data obtained by TLS, without subdividing or downsampling the point clouds. In this method, each point cloud is converted into a wireframe model by connecting neighboring points on the same continuous surface, and three-dimensional points on stems are resampled as cross-sectional points of the wireframe model in an out-of-core manner. Since the data size of the section points is much smaller than the original point clouds, stem traits can be calculated from the section points on a common computer. With the study method, 1381 tree stems were calculated from 3.6 billion points in ~20 min on a common computer. To evaluate the accuracy of this method, eight targeted trees were cut down and sliced at 1-m intervals; actual stem traits were then compared to those calculated from point clouds. The experimental results showed that the efficiency and accuracy of the proposed method are sufficient for practical use in various fields, including forest management and forest research.
Scientific journal, English - Extraction of Guardrails from MMS Data Using Convolutional Neural Network
Hiroki Matsumoto; Yuma Mori; Hiroshi Masuda
International Journal of Automation Technology, 15, 3, 258-267, 01 May 2021, Peer-reviwed
Scientific journal, English - Deterioration Detection for Wall Surfaces of Large-Scale Structure Using Dense Point Cloud
E. Yamamoto; I. Yoshiuchi; H. Masuda
Proc of The 18th International Conference on Precision Engineering (ICPE2020), D-5-5, 23 Nov. 2020, Peer-reviwed
International conference proceedings, English - Precise Calculation of Cross Sections and Volume for Tree Stem Using Point Clouds
S. Eto; H. Masuda; Y. Hiraoka; M. Matsushita; M. Takahashi
ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Copernicus GmbH, XLIII-B2-2020, B2, 205-210, 12 Aug. 2020, Peer-reviwed, Abstract. Woody biomass is an important parameter in forestry and forest research. In order to estimate of woody biomass, it is important to precisely and efficiently calculate section areas and volumes of tree stems in the forest. In this paper, we propose a method for calculating the cross-sectional area and the stem volume of trees from point clouds captured using the terrestrial laser scanner. In our method, each point cloud is converted into a wireframe model, and cross-section points are calculated as intersection between the wireframe and the horizontal planes placed at equal intervals. Cross-sectional shapes on each horizontal plane are approximated as n-sided polygons and refined using the subdivision scheme. The section areas and stem volumes are calculated using the subdivision curves of stem contours. In our evaluation, our method could calculate section areas and stem volumes of trees with sufficient accuracy in practical use.
Scientific journal, English - Reconstruction of Road-Crossing Power and Communication Lines from Mobile Mapping Data
K. Tajima; H. Masuda
ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, V-2-2020, 297-304, 01 Aug. 2020, Peer-reviwed
Scientific journal, English - 移動計測車両に搭載されたレーザスキャナによる蓋付きU字溝の自動抽出
高橋元気; 増田宏
日本土木学会論文誌, 76, 1, 63-73, 01 Jun. 2020, Peer-reviwed
Scientific journal, Japanese - Detection of Steel Materials and Bolts from Point-Clouds of Power Transmission Pylon
Iku Yoshiuchi; Yuki Shinozaki; Hiroshi Masuda
Computer-Aided Design and Applications, 17, 3, 575-584, 26 Sep. 2019, Peer-reviwed
Scientific journal, English - Detection of Steel Materials and Bolts from Point-Clouds of Power Transmission Pylon
Iku Yoshiuchi; Yuki Shinozaki; Hiroshi Masuda
The 16th Annual International CAD Conference (Proc. of CAD'19), 462-466, 26 Jun. 2019, Peer-reviwed
International conference proceedings, English - Extraction and Shape Reconstruction of Guardrails Using Mobile Mapping Data
H. Mstsumoto; Y. Mori; H. Masuda
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci, XLII-2, W13, 1061-1068, 12 Jun. 2019, Peer-reviwed
International conference proceedings, English - Trajectory-Based Visualization of MMS Point Clouds
G. Takahashi; H. Masuda
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLII-2/W13, XLII-2, W13, 1127-1133, 12 Jun. 2019, Peer-reviwed
International conference proceedings, English - A Static Method for Estimating the Effective Spot Shape of Terrestrial Laser Scanners
Ichiro Tanaka; Hiroshi Masuda
The 17th International Conference on Precision Engineering (ICPE2018), D-5-6, 15 Nov. 2018, Peer-reviwed
International conference proceedings, English - Diagnosis of Deflection of Large-Scale Structures Using Dense Point-Clouds
Yuki SHINOZAKI; Nanami MIZUGUCHI; Yoshitaka MIDORIKAWA; Hiroshi MASUDA
Proc of The 17th International Conference on Precision Engineering (ICPE2018), D-5-5, 12 Nov. 2018, Peer-reviwed
International conference proceedings, English - Efficient Non-Rigid Registration for Point-Clouds of Pole-Like Objects
Hiroki MATSUMOTO; Yoshitaka MIDORIKAWA; Hiroshi MASUDA
Proc of The 17th International Conference on Precision Engineering (ICPE2018), D-5-7, 12 Nov. 2018, Peer-reviwed
International conference proceedings, English - Extraction of Rotational Surfaces and Generalized Cylinders from Point-Clouds Using Section Curves
Yoshitaka Midorikawa; Hiroshi Masuda
International Journal of Automation Technology, 12, 6, 901-910, 01 Nov. 2018, Peer-reviwed
Scientific journal, English - Shape Reconstruction of Guardrails on Roads Using Point Clouds and Images from Mobile Mapping Systems
Y. Mori; H. Masuda
Proc. of 2018 Asian Conference on Design and Digital Engineering (ACDDE 2018), Article No. 20, 01 Nov. 2018, Peer-reviwed
International conference proceedings, English - Adaptive Segmentation of Large-Scale Anisotropic Point-Clouds Captured by Mobile Mapping Systems
Yuma Mori; Keisuke Kohira; Hiroshi Masuda
Computer-Aided Design and Applications, 16, 3, 466-477, 01 Oct. 2018, Peer-reviwed
Scientific journal, English - Extraction of Surfaces Using Section Curves for Engineering Plants
Yoshitaka Midorikawa; Hiroshi Masuda
Proceedings of ASME 2018 Computers and Information in Engineering Conference, IDETC2018, 85359, 27 Aug. 2018, Peer-reviwed
International conference proceedings, English - Point-Based Virtual Environment for Supporting Deterioration Diagnosis of Production Facilities
Yuki Shinozaki; Hiroshi Masuda
Proceedings of ASME 2018 Computers and Information in Engineering Conference, IDETC2018, 85696, 27 Aug. 2018, Peer-reviwed
International conference proceedings, English - Segmentation of Large-Scale Anisotropic Point-Clouds Captured by Mobile Mapping Systems
Yuma Mori; Keisuke Kohira; Hiroshi Masuda
The 15th Annual International CAD Conference (Proc. of CAD'18), 293-297, 11 Jul. 2018, Peer-reviwed
International conference proceedings, English - Detection of Deterioration of Furnace Walls Using Large-Scale Point-Clouds
Y. Shinozaki; K. Kohira; H. Masuda
Computer-Aided Design and Applications, 15, 4, 575-584, 12 Jan. 2018, Peer-reviwed
Scientific journal, English - Shape Reconstruction of Trees in Massive-Scale Forests for Evaluation of Morphological Traits
Kazuto Saito; Hiroshi Masuda; Yuichiro Hiraoka; Michinari Matsushita; Makoto Takahashi
Proc. of SilviLaser 2017, Session 4, 167, 10 Oct. 2017, Peer-reviwed
International conference proceedings, English - Above-Ground Phenotyping of the Japanese Cedar Individuals in a Progeny Test Site Using Terrestrial LiDAR
Yuichiro Hiraoka; Kazuto Saito; Michinari Matsushita; Makoto Takahashi; Hiroshi Masuda
Proc. of SilviLaser 2017, Session 6, 99, 10 Oct. 2017, Peer-reviwed
International conference proceedings, English - POINT-CLOUD COMPRESSION for VEHICLE-BASED MOBILE MAPPING SYSTEMS USING PORTABLE NETWORK GRAPHICS
K. Kohira; H. Masuda
ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Copernicus GmbH, 4, 2, 99-106, 12 Sep. 2017, Peer-reviwed, A mobile mapping system is effective for capturing dense point-clouds of roads and roadside objectsï1/4 Point-clouds of urban areas, residential areas, and arterial roads are useful for maintenance of infrastructure, map creation, and automatic driving. However, the data size of point-clouds measured in large areas is enormously large. A large storage capacity is required to store such point-clouds, and heavy loads will be taken on network if point-clouds are transferred through the network. Therefore, it is desirable to reduce data sizes of point-clouds without deterioration of quality. In this research, we propose a novel point-cloud compression method for vehicle-based mobile mapping systems. In our compression method, point-clouds are mapped onto 2D pixels using GPS time and the parameters of the laser scanner. Then, the images are encoded in the Portable Networking Graphics (PNG) format and compressed using the PNG algorithm. In our experiments, our method could efficiently compress point-clouds without deteriorating the quality.
International conference proceedings, English - Detection of Deterioration of Furnace Walls Using Large-Scale Point-Clouds
Yuki Shinozaki; Keisuke Kohira; Hiroshi Masuda
The 14th Annual International CAD Conference (Proc. of CAD'17), 242-246, 10 Aug. 2017, Peer-reviwed
International conference proceedings, English - Automated Extraction of Tree Parameters from Large-Scale Point-Clouds
Saito Kazuto; Masuda Hiroshi; Hiraoka Yuichiro; Matsushita Michinari; Takahashi Makoto
Proceedings of JSPE Semestrial Meeting, The Japan Society for Precision Engineering, 2017, 551-552, 2017, Peer-reviwed, 森林内の樹木育成状況を効率的に把握するには、レーザ計測によって得られる三次元計測点群が有用である。計算機処理により、これらいくつかの樹木パラメータを取得する手法は多く提案されている。本手法では特に、樹木の遺伝子解析に向けた詳細で精密な樹木パラメータを、森林における大規模な点群から自動で、また実用的な時間で取得する手法について検討し、実測値との比較検討を行う。
Japanese - Classification of rode-side objects using Point Clouds and Images from Mobile Mapping Systems
Mori Yuma; Tann Tourthang; Kohira Keisuke; Masuda Hiroshi
Proceedings of JSPE Semestrial Meeting, The Japan Society for Precision Engineering, 2017, 567-568, 2017, 本研究では，移動計測データから道路周辺の地物を自動分類することを目的とする．点群データは，大きさ，位置などの情報を持つ．一方，画像からは，物体の色情報を取得することができる．前報では，点群による物体認識と，点群を利用して作成された画像による物体認識の結果を比較した．本稿では，移動計測で取得された点群と画像の情報を組み合わせて，道路周辺地物の分類に適する特徴量を検討する．
Japanese - Point-based shape monitoring of plate bending for large-scale storage tanks
Kenta Fukano; Hiroshi Masuda; Ataru Kobayashi; Kazuki Ikeda
Proceedings of the ASME Design Engineering Technical Conference, American Society of Mechanical Engineers (ASME), 1, 68105, 2017, Peer-reviwed, Storage tanks are constructed using thousands of large curved steel plates, which are manufactured from flat plates. In conventional manufacturing of curved plates, operators fit wooden templates to specific positions on steel plates and measure differences between the current shape and the template. However, it is costly to create many wooden templates for a variety of plates. In addition, it is timeconsuming and requires skills to precisely place wooden templates on specific positions to measure differences. In this paper, we discuss methods to automatically calculate differences of shapes during bending processes without wooden templates. We capture dense points on steel plates using a terrestrial laser scanner, and analyze shapes of curved plates using point-clouds. In our method, the system extracts only the points on curved plates, and tracks the amount of deformation on reference lines defined on the plates. Corresponding positions between intermediate curved plates and the original flat shape are calculated using mesh flattening techniques. In our experiments, our method could calculate the amount of differences of steel plates in reasonable performance and precision.
International conference proceedings, English - Mobile Laser Scanning System for Capturing Point-Clouds of Engineering Plants
Masaya SUZUKI; Takeru NIWA; Kiichiro ISHIKAWA; Hiroshi MASUDA
Proc of The 16th International Conference on Precision Engineering, B204-8190, 14 Nov. 2016, Peer-reviwed
International conference proceedings, English - Segmentation and Reconstruction of Tree Shapes from Large-Scale Point-Clouds
Kazuto SAITO; Hiroshi MASUDA
Proc of The 16th International Conference on Precision Engineering, B203-8191, 14 Nov. 2016, Peer-reviwed
International conference proceedings, English - Segmentation and Recognition of Pole-like Objects from Mobile Laser Scanning Data
Keisuke KOHIRA; Kenta FUKANO; Hiroshi MASUDA
Proc of The 16th International Conference on Precision Engineering, B202-8091, 14 Nov. 2016, Peer-reviwed
International conference proceedings, English - Reconstruction of Polygonal Prisms from Point-Clouds of Engineering Plants
Akisato Chida; Hiroshi Masuda
Journal of Computational Design and Engineering, 3, 4, 322-329, 30 Sep. 2016, Peer-reviwed
Scientific journal, English - Interactive collision detection for engineering plants based on large-scale point-clouds
Takeru Niwa; Hiroshi Masuda
Computer-Aided Design and Applications, Taylor and Francis Inc., 13, 4, 511-518, 03 Jul. 2016, Peer-reviwed, In this paper, we discuss interactive collision detection for large-scale point-clouds. The state-of-the-art laser scanners enable us to capture dense point-clouds from engineering plants. Dense point-clouds are useful for simulating renovation tasks of engineering plants. However, it is difficult to interactively calculate collisions between 3D models and huge point-clouds. We propose an efficient collision detection method for large-scale point-clouds, and discuss an interactive system for collision detection. In our method, collisions are evaluated on two-resolution depth-maps. Our method allows us to precisely and efficiently detect collisions with large-scale point-clouds. The experimental results showed that our system could interactively detect collisions in large-scale point-clouds.
Scientific journal, English - 三次元計測点群に基づく樹木の形状再構成 第３報
齋藤 和人; 増田 宏; 平岡 裕一郎; 松下 通也; 高橋 誠
精密工学会学術講演会講演論文集, 公益社団法人 精密工学会, 2016, 0, 489-490, 2016, Peer-reviwed, 森林内の樹木育成状況を計算機を用いて効率的に把握するには、森林の三次元計測点群から精密な樹木モデルを再構成する必要がある。前報では、点群の断面形状を利用した幹の一般化円筒モデル生成手法と、メッシュモデルを利用した局所的な枝のモデル化手法について報告した。本報では、これまでに得た部分的なモデルを利用し、骨格を含む樹木全体の形状モデルを生成する手法について述べる。
Japanese - 移動計測データからのメッシュ生成とセグメンテーション（第3報）
小平 圭祐; 深野 健太; 増田 宏
精密工学会学術講演会講演論文集, 公益社団法人 精密工学会, 2016, 781-782, 2016, 車両にレーザスキャナを搭載した移動計測装置(MMS)により，道路周辺の地物情報を点群として高速かつ広範囲に取得することが可能になった．前報では，メッシュの断面線を用いた，車速に依存しない柱状物体の抽出手法を示した．本報では，付属物が人工物か自然物かを判別するとともに，機械学習を用いることで，より高精度なセグメンテーション手法を提案する．
Japanese - 大規模点群の衝突判定を用いた配置検討システム
丹羽 健; 増田 宏
精密工学会学術講演会講演論文集, 公益社団法人 精密工学会, 2016, 769-770, 2016, 生産設備は繰り返し改修されることにより長期間活用されているため，改修作業の効率化が求められている．我々はこれまでに，レーザ計測によって得た生産設備の大規模な点群モデルと仮想物体との衝突を高速に判定する手法を提案した．本研究では，提案した衝突判定法を基に，点群モデルへの編集機能を加えたインタラクティブな仮想物体の配置検討システムについて検討する．
Japanese - Registration of point-clouds from terrestrial and portable laser scanners
Takuma Watanabe; Takeru Niwa; Hiroshi Masuda
International Journal of Automation Technology, Fuji Technology Press, 10, 2, 163-171, 2016, Peer-reviwed, We proposed a registration method for aligning shortrange point-clouds captured using a portable laser scanner (PLS) to a large-scale point-cloud captured using a terrestrial laser scanner (TLS). As a PLS covers a very limited region, it often fails to provide sufficient features for registration. In our method, the system analyzes large-scale point-clouds captured using a TLS and indicates candidate regions to be measured using a PLS. When the user measures a suggested region, the system aligns the captured shortrange point-cloud to the large-scale point-cloud. Our experiments show that the registrationmethod can adequately align point-clouds captured using a TLS and a PLS.
Scientific journal, English - REFINEMENT OF COLORED MOBILE MAPPING DATA USING INTENSITY IMAGES
T. Yamakawa; K. Fukano; R. Onodera; H. Masuda
XXIII ISPRS CONGRESS, COMMISSION I, COPERNICUS GESELLSCHAFT MBH, 3, 1, 167-173, 2016, Peer-reviwed, Mobile mapping systems (MMS) can capture dense point-clouds of urban scenes. For visualizing realistic scenes using point-clouds, RGB colors have to be added to point-clouds. To generate colored point-clouds in a post-process, each point is projected onto camera images and a RGB color is copied to the point at the projected position. However, incorrect colors are often added to point-clouds because of the misalignment of laser scanners, the calibration errors of cameras and laser scanners, or the failure of GPS acquisition. In this paper, we propose a new method to correct RGB colors of point-clouds captured by a MMS. In our method, RGB colors of a point-cloud are corrected by comparing intensity images and RGB images. However, since a MMS outputs sparse and anisotropic point-clouds, regular images cannot be obtained from intensities of points. Therefore, we convert a point-cloud into a mesh model and project triangle faces onto image space, on which regular lattices are defined. Then we extract edge features from intensity images and RGB images, and detect their correspondences. In our experiments, our method worked very well for correcting RGB colors of point-clouds captured by a MMS.
International conference proceedings, English - A POINT-BASED VIRTUAL REALITY SYSTEM FOR SUPPORTING PRODUCT DEVELOPMENT
Hiroki Okamoto; Hiroshi Masuda
PROCEEDINGS OF THE ASME INTERNATIONAL DESIGN ENGINEERING TECHNICAL CONFERENCES AND COMPUTERS AND INFORMATION IN ENGINEERING CONFERENCE, 2016, VOL 1B, AMER SOC MECHANICAL ENGINEERS, IDETC2016-59756, 2016, Peer-reviwed, In this paper, we discuss methods to efficiently render stereoscopic scenes of large-scale point clouds on inexpensive VR systems. Recently, terrestrial laser scanners are significantly improved, and they can easily capture tens of millions points in a short time from large fields, such as engineering plants. If 3D stereoscopic scenes of large-scale point-clouds could be easily rendered using inexpensive devices, they might be involved in casual product development phases. However, it is difficult to render a huge number of points using common PCs, because VR systems require high frame rates to avoid VR sickness. To solve this problem, we introduce an efficient culling method for large-scale point-clouds. In our method, we project all points onto angle-space panoramic images, whose axes are the azimuth and elevation angles of head directions. Then we eliminate occluded and redundant points according to the resolutions of devices. Once visible points are selected, they can be rendered in high frame rates. Visible points are updated when the user stays at a certain position to observe target objects. Since points are processed on image space in our method, preprocessing is very fast. In our experiments, our method could render stereoscopic views of large-scale point-clouds in high frame rates.
International conference proceedings, English - TIN generation and point-cloud compression for vehicle-based mobile mapping systems
Hiroshi Masuda; Jun He
ADVANCED ENGINEERING INFORMATICS, ELSEVIER SCI LTD, 29, 4, 841-850, Oct. 2015, Peer-reviwed, The vehicle-based mobile mapping system (MMS) is effective for capturing dense 3D data of roads, roadside objects and buildings. Since discrete points are not convenient for many application systems, a triangulated irregular network (TIN) is often generated from point-clouds. However, TIN data require two or three times larger storage than point-clouds. If TIN models can be promptly generated while loading point-clouds, it would not be necessary to store huge TIN models on a hard disk. In this paper, we propose two efficient TIN generation methods according to types of laser scanners. One is the line-by-line TIN generation method, and the other is the GPS-time based method. These methods can quickly generate TIN models based on scan lines of laser scanners. In addition, we introduce a new compression method to reduce the loading time of point-clouds. Our compression method is also based on the scan lines of laser scanners. Since points captured by a MMS tend to be positioned on nearly straight lines, their data size can be significantly reduced by coding the second order differences. (C) 2015 Elsevier Ltd. All rights reserved.
Scientific journal, English - 大規模点群のための高速な干渉判定手法
丹羽 健; 増田 宏
精密工学会論文誌, 81, 8, 788-792, 05 Aug. 2015, Peer-reviwed
Scientific journal, Japanese - Interactive Collision Detection for Engineering Plants based on Large-Scale Point-Clouds
Takeru Niwa; Hiroshi Masuda
Proc. of the 12th Annual International CAD Conference, 389-394, 23 Jun. 2015, Peer-reviwed
International conference proceedings, English - Classification for Roadside Objects Based on Simulated Laser Scanning
Kenta Fukano; Hiroshi Masuda
Proceedings of the 2nd International Conference on Civil and Building Engineering Informatics, Article 26, 23 Apr. 2015, Peer-reviwed
International conference proceedings, English - Reconstruction of Polygonal Faces from Large-Scale Point-Clouds of Engineering Plants
Hiroshi Masuda; Takeru Niwa; Ichiro Tanaka; Ryo Matsuoka
Computer-Aided Design and Applications, Taylor and Francis, 12, 5, 555-563, 09 Apr. 2015, Peer-reviwed
Scientific journal, English - 大規模点群の衝突判定を用いた経路探索シミュレーション（第2報）
丹羽 健; 増田 宏
精密工学会学術講演会講演論文集, 公益社団法人 精密工学会, 2015, 49-50, 2015, 生産設備は繰り返し改修されることで長期間活用されているため，改修作業の効率化が求められている．そこで本研究では，レーザ計測によって得た大規模点群に基づく保守改修のための搬入経路探索シミュレーションの開発を目的とする．本報では，点群モデルへのインタラクティブな編集機能を加えることで経路探索に自由度を持たせることを検討する．また，編集による点群モデル中の空白を考慮した衝突判定法についても論ずる．
Japanese - 移動計測データに基づく地物分類のための学習データ生成手法（第2報）
深野 健太; 増田 宏
精密工学会学術講演会講演論文集, 公益社団法人 精密工学会, 2015, 497-498, 2015, 移動計測データ内の地物点群の分類には機械学習による自動分類手法が多く用いられているが，この手法には多くの学習データが必要となってくる．前報では，移動計測のシミュレーションに基づいて計算機上で学習用の点群を自動生成する手法を提案した．本稿では，地物のバリエーションをモデル化し，より実測に近い学習用点群を生成する手法を提案する．
Japanese - 移動計測データからのメッシュ生成とセグメンテーション（第2報）
小平 圭祐; 深野 健太; 増田 宏
精密工学会学術講演会講演論文集, 公益社団法人 精密工学会, 2015, 75-76, 2015, 車両にレーザスキャナを搭載した移動計測装置(MMS)によって，道路周辺の点群を高速かつ広範囲に取得することが可能になった．本研究の前報では，レーザスキャナの回転周波数とGPS時刻を用いて，高密度な点群からメッシュを高速に生成する手法を示した．しかしながら，メッシュの裏返りなどの問題が発生していた．本研究では，その改善手法を示すとともに，新しい地物セグメンテーション手法を提案する．
Japanese - DETECTION AND CLASSIFICATION OF POLE-LIKE OBJECTS FROM MOBILE MAPPING DATA
K. Fukano; H. Masuda
ISPRS GEOSPATIAL WEEK 2015, COPERNICUS GESELLSCHAFT MBH, II-3, W5, 57-64, 2015, Peer-reviwed, Laser scanners on a vehicle-based mobile mapping system can capture 3D point-clouds of roads and roadside objects. Since roadside objects have to be maintained periodically, their 3D models are useful for planning maintenance tasks. In our previous work, we proposed a method for detecting cylindrical poles and planar plates in a point-cloud. However, it is often required to further classify pole-like objects into utility poles, streetlights, traffic signals and signs, which are managed by different organizations. In addition, our previous method may fail to extract low pole-like objects, which are often observed in urban residential areas. In this paper, we propose new methods for extracting and classifying pole-like objects. In our method, we robustly extract a wide variety of poles by converting point-clouds into wireframe models and calculating cross-sections between wireframe models and horizontal cutting planes. For classifying pole-like objects, we subdivide a pole-like object into five subsets by extracting poles and planes, and calculate feature values of each subset. Then we apply a supervised machine learning method using feature variables of subsets. In our experiments, our method could achieve excellent results for detection and classification of pole-like objects.
International conference proceedings, English - 大規模点群からの生産設備の形状再構成(第2報) －複数の点群データからの整合的な部材形状の再構成－
松岡 諒; 増田 宏
精密工学会論文誌, 80, 10, 939-943, 05 Oct. 2014, Peer-reviwed
Scientific journal, Japanese - Recognition and Reconstruction of Roadside Objects Based on Mobile Mapping Data
Kenta FUKANO; Shogo OGURI; Hiroshi MASUDA
Proc of The 15th International Conference on Precision Engineering (ICPE2014), Article D24, 25 Jul. 2014, Peer-reviwed
International conference proceedings, English - Point-Based Collision Detection for Planning Maintenance and Reorganization Tasks for Manufacturing Plants
Takeru NIWA; Minako HIRAOKA; Hiroshi MASUDA
Proc of The 15th International Conference on Precision Engineering (ICPE2014), Article D32, 25 Jul. 2014, Peer-reviwed
International conference proceedings, English - 移動計測データに基づく柱状物体の分類に適した幾何特徴量
深野 健太; 増田 宏
日本土木学会論文誌, 日本土木学会, 70, 1, 40-47, 13 Jul. 2014, Peer-reviwed
Scientific journal, Japanese - Reconstruction of Polygonal Faces from Large-Scale Point-Clouds of Engineering Plants
Hiroshi Masuda; Takeru Niwa; Ichiro Tanaka; Ryo Matsuoka
The 11th annual International CAD Conference (CAD'14), Taylor Francis, Article 71, 23 Jun. 2014, Peer-reviwed
International conference proceedings, English - Reconstruction of Structure Shapes of Facilities from Large-scale Point Cloud (1st report)
松岡 諒; 増田 宏
精密工学会論文誌, The Japan Society for Precision Engineering, 80, 6, 604-608, 05 Jun. 2014, Peer-reviwed, The recent progress of laser scanners makes it possible to capture dense point-clouds of large-scale facilities. Large-scale facilities are mainly composed of many primitive surfaces, such as planes, cylinders, cones, spheres, and tori. However, it is not easy to reliably extract these surfaces from point-clouds because it is actually difficult to capture complete point-clouds of surfaces. In this paper, we discuss how to reconstruct pipe structures from insufficiently extracted surfaces. In our method, we first extract planes and cylinders, which can be reliably extracted, and detect the relationship among detected surfaces on a depth image. Then we estimate shapes and locations of various pipe structures using the relationships among surfaces. Finally we verify estimated shapes based on visibility tests and eliminate inconsistent structures. In our experiments, our method could sufficiently reconstruct pipe structures using only a single scanning data.
Scientific journal, Japanese - An Efficient Surface Generation Method for Vehicle-Based Mobile Mapping System
Jun He; Hiroshi Masuda
Proc. of the International Conference on Civil and Building Engineering Infomatics, 31-38, Nov. 2013, Peer-reviwed
International conference proceedings, English - Shape Reconstruction of Poles and Plates from Vehicle-Based Laser Scanning Data
Hiroshi Masuda; Shogo Oguri; He Jun
Proc. of The International Symposium on Mobile Mapping Technology, Article TS04-106, 01 May 2013, Peer-reviwed
International conference proceedings, English - 機械学習を用いた移動計測点群データの分類
深野 健太; 増田 宏
精密工学会学術講演会講演論文集, 公益社団法人 精密工学会, 2013, 625-626, 2013, 移動計測によって得られた点群データには，多くの地物や建物が混在しているので，それらを適切に分割し分類することが重要である．データの分類には機械学習が有効と考えられるが，そのためには対象物を適切なベクトルとして符号化する必要がある．前報において，点群の代表的な幾何特徴量を用いて分類する手法を示したが，本稿では点群のセグメンテーションなどを組み合わせることで，識別能力を向上させる手法について検討する．
Japanese - Collision determination on large Point Cloud Data (2nd report)
Niwa Takeru; Masuda Hiroshi
Proceedings of JSPE Semestrial Meeting, The Japan Society for Precision Engineering, 2013, 635-636, 2013, 工場やプラントの３次元計測では，全域をカバーするために多数の大規模点群データを取得するため，データ量は数億点から数十億点になることが多い．こうしたデータから高精度かつリアルタイムに衝突判定を行うためには，アウトオブコアによる点群の多重解像度化や適切な計測データの選択，ノイズ除去などが重要である．本稿ではこれらの問題について論じる．
Japanese - Reliable surface extraction from point-clouds using scanner-dependent parameters
Hiroshi Masuda; Ichiro Tanaka; Masakazu Enomoto
Computer-Aided Design and Applications, 10, 2, 265-277, 2013, Peer-reviwed, Phase-based and time-of-flight laser scanners can be used to capture dense pointclouds of industrial plants. Our goal is to reconstruct 3D models of components in industrial plants. For robustly extracting surfaces, the standard deviation of residuals in surface fitting has large impact on the result. The standard deviation is one of basic parameters in the least-squares, robust estimate, region growing, and RANSAC. However, it is not easy to estimate the standard deviations of fitting errors in a wide range of field, because the standard deviations vary in a point-cloud, according to the sizes, distances, and materials of scanned objects. In this paper, we investigate the distributions of residuals in surface fitting using experimental data, and derive prediction functions of the standard deviations for measurement errors. Our experimental result shows that our prediction functions are effective for reliably extracting surfaces of diverse sizes, distances, and materials. © 2013 CAD Solutions, LLC.
Scientific journal, English - Reconstruction of Roadways and Walkways Using Point-Clouds from Mobile Mapping System
J. He; H. Masuda
Proc. of 2012 Asian Conference on Design and Digital Engineering (ACDDE 2012), Article 100099, Dec. 2012, Peer-reviwed
International conference proceedings, English - Mesh Generation and Efficient Display of Large-Scale Mobile Mapping Data
He Jun; Masuda Hiroshi
Proceedings of JSPE Semestrial Meeting, The Japan Society for Precision Engineering, 2012, 297-298, 2012, レーザスキャナの進歩により，移動計測装置による点群データは非常に大規模になっている．そのため，表示やメッシュ化においては全データを一括で扱うことは難しく，分割処理が必要となる．本研究では，まず，データを計測ラインに分割したデータ構造を用いて，アウトオブコアでの処理を実現する．次に，点群を階層的にクラスタリングする手法により，高速なメッシュモデル生成と多重解像度による表示手法について検討する．
Japanese - Detection of Surfaces and Edges in Large Point-Clouds Using Region-Growing on Spherical Space
Hiroshi Masuda; Ryo Matsuoka; Yuji Abe
EMERGING TECHNOLOGY IN PRECISION ENGINEERING XIV, TRANSACTION PUBLISHERS, 523-524, 333-+, 2012, Peer-reviwed, Engineering facilities can be digitized as large-scale point-clouds by using the state-of-art mid-range laser scanners. For utilizing captured data in CAD systems, it is important to convert point-clouds to parametric surfaces. In this paper, we describe a method for robustly extract cylindrical faces and planar faces. Edges and silhouette lines have to be generated to construct bounded faces, but unfortunately points on silhouettes are very noisy in the case of mid-range laser scanners. Our method applies region-growing method on spherical space and improves the robustness. In addition, we enhance the region-growing so that surface regions can be propagated to disconnect points using multiple overlapping point-clouds.
International conference proceedings, English - Evaluating Positioning Uncertainty of Spherical Targets in Laser Scanning
Ichiro Tanaka; Hiroshi Masuda; Masakazu Enomoto; Kenjiro T. Miura
EMERGING TECHNOLOGY IN PRECISION ENGINEERING XIV, TRANSACTION PUBLISHERS, 523-524, 356-+, 2012, Spherical targets are useful for registration of point-clouds. In this paper we discuss the positioning uncertainty by laser scanners. We measured spheres of relatively large diameter from about 9m distance, and calculated their positions by the least-squares fitting. The scanning was iterated thirty times and the standard deviations of fitting result were calculated to indicate positioning uncertainty. The result shows smaller positioning uncertainty in comparison with the range noise listed in the specifications.
International conference proceedings, English - 大規模点群データの平滑化手法に関する研究（第3報）GPUを用いたストリーミング処理による大規模点群の高速な平滑化
池田邦彦; 増田宏
精密工学会論文誌, The Japan Society for Precision Engineering, 78, 7, 611-615, 2012, Peer-reviwed, The recent progress of mid/ long-range laser scanners enables to capture large-scale point-clouds in short time. However, point-clouds typically contain many large noises and outliers, therefore, reliable smoothing methods are very important. Although the moving least-squares or the moving robust estimate is powerful smoothing tools, they are very time-consuming for large-scale point-clouds. In this paper, we propose a GPU-based method to accelerate the moving robust estimate. We implemented it on a GPU and evaluated its performance. The result shows that our GPU-based method is much faster than CPU-based smoothing, and it can be applied to large-scale point-clouds.
Scientific journal, Japanese - An integrated processing method for multiple large-scale point-clouds captured from different viewpoints
Yousuke Kawauchi; Shin Usuki; Kenjiro T. Miura; Hiroshi Masuda; Ichiro Tanaka
Computer-Aided Design and Applications, 8, 4, 519-530, 2011, Peer-reviwed, 3D models of industrial plants are useful for simulating maintenance and renovation. We aim to reconstruct 3D models of components from large-scale point-clouds captured for industrial plants. When an engineering facility is measured by a laser scanner, the location of the scanner is restricted in most cases. We have such problems that the components of the engineering facility can be scanned only from one side and they might be partially occluded by other components. In order to solve the problems, we propose a new method which can process multiple large-scale point data captured from different viewpoints without merging them into a huge data which might not be able to be handled on a computer with a limited main memory size. © 2011 CAD Solutions, LLC.
Scientific journal, English - Generation and Representation of Street Shapes for Mobile Mapping System Data
He Jun; Masuda Hiroshi
Proceedings of JSPE Semestrial Meeting, The Japan Society for Precision Engineering, 2011, 145-146, 2011, 本講演では，車載の移動計測装置によって取得された点群データから高速にメッシュデータを生成し，そのデータを省メモリで保持する方法について論じる．移動計測では長距離の計測を行うため，生成されるメッシュデータは非常に大規模になる．そこで，移動計測データの特徴を利用した線形予測符号化を用いてデータ量を圧縮し，実際の計測データを用いてその効果を検証する． - Robust edge detection and GPU-based smoothing for extracting surface primitives from range images
Kunihiko Ikeda; Chihiro Matsunuma; Hiroshi Masuda
Computer-Aided Design and Applications, 8, 4, 603-616, 2011, Peer-reviwed, It is important to construct 3D virtual models of man-made fields in which people work and live. Recent mid-range and long-range laser scanners can be used to acquire 3D shapes of cities, buildings, factories, heavy goods, transportation infrastructure, and so on. However, they tend to produce outliers and very noisy points near silhouettes and sharp edges of objects. This problem makes it difficult to reconstruct bounded faces. In addition, since enormous volumes of point-clouds are captured from a broad range of scenes, efficient processing methods are required. In this paper, we propose a robust edge detection method and an efficient GPU-based smoothing method for reconstructing primitive surfaces. We first calculate straight edge lines and silhouette lines from raw scanned data, and then eliminate noises and outliers by our GPU-based smoothing method for calculating surface equations. Then primitive surfaces are extracted using sharp edges, silhouette lines and surface equations. Our method is useful to robustly extract surface primitives from practical noisy pointclouds. © 2011 CAD Solutions, LLC.
Scientific journal, English - 設計品質管理のための設計プロセス計画と検証及び要求開発のための一手法: 体系的RDCモデルによる設計プロセスの可視化
中沢俊彦; 増田宏
品質管理学会論文誌, 41, 2, 81-93, 2011, Peer-reviwed
Scientific journal, Japanese - 画像特徴量を用いた大規模点群からの円柱面と矩形面の検出
松沼千央; 増田宏
日本機械学会論文集(C編), 76, 772, 540-545, 2010, Peer-reviwed
Scientific journal, Japanese - As-built 3D modeling of large facilities based on interactive feature editing
H. Masuda; Ichiro Tanaka
Computer-Aided Design and Applications, 7, 3, 349-360, 2010, Peer-reviwed, Phase-based and time-of-flight laser scanners can capture dense point-clouds of indoor and outdoor environment. However, such point-clouds usually lack the backsides of objects and the portions occluded by other ones. In this paper, we propose a new modeling methodology which converts a point-cloud to a Mercator image and a mesh model, and enables reconstructing the missing portions interactively by using image-based techniques. The grid mesh format is proposed for quick access to largescale mesh models. A prototype system is implemented to show the efficiency of our method. © 2010 CAD Solutions, LLC.
Scientific journal, English - 画像インタフェースを用いた大規模点群からのソリッドモデリングシステム
増田宏
日本機械学会論文集(C編), The Japan Society of Mechanical Engineers, 76, 771, 2748-2752, 2010, Peer-reviwed, Mid-range and long-range laser scanners are capture dense point-clouds from engineering facilities. The captured point-clouds can be converted to smooth mesh models by using streaming operations. In this paper, we discuss a solid modeling system based on large-scale mesh models. When an engineering facility is measured by a laser scanner, components are scanned only from the limited directions, and they may be partially occluded by other components. To construct solid models using such incomplete mesh models, we introduce modeling and editing operations based on the reflectance images, which can be generated from point-clouds. We also show how to generate 3D models of standard parts.
Scientific journal, Japanese - 大規模点群データの平滑化手法に関する研究（第2報）大規模点群平滑化のためのストリーミング処理
増田宏; 村上健治
精密工学会論文誌, The Japan Society for Precision Engineering, 76, 6, 689-693, 2010, Peer-reviwed, The state-of-the-art phase-based scanner is suitable for acquiring 3D shapes of large facilities, because it can acquire hundreds of millions point data in several minutes. Since acquired data are very noisy, smoothing operations are very important. However, point data from large facilities are too large to process in the memory of common personal computers. This paper proposes a new streaming smoothing operator for very large-scale point-cloud acquired by phase-based or time-of-flight scanners. Our method reads point data on a hard disk and sequentially processes them in a small region on RAM. This method is based on the fact that point data from a laser scanner can be converted into a height-field on a sphere. Our experimental results show that our method could successfully produce a smooth mesh model from large-scale point data with the limited memory size.
Scientific journal, Japanese - 大規模点群データの平滑化手法に関する研究（第1報）, ロバスト推定に基づく平滑化手法
増田宏; 村上健治
精密工学会論文誌, The Japan Society for Precision Engineering, 76, 5, 582-586, 2010, Peer-reviwed, It is widely recognized that task planning based on 3D CAD can reduce the rework of maintenance and renovation of facilities. Therefore, it is very important to acquire 3D shapes of existing facilities. The state-of-the-art phase-based scanner is suitable for this purpose, because it can acquire hundreds of millions point data in several minutes. However, point data captured from the phase-based scanner tend to include quite a lot of outliers. This paper introduces robust smoothing operators for noisy point-cloud. We propose two smoothing methods using robust estimate. One is based on Lorentzian distribution, and the other is based on Tukey's bi-weight estimation. We modified a conventional smoothing method using robust estimate. In our experiments, our two methods could produce good smoothed surface even if point-cloud include a lot of outliers.
Scientific journal, Japanese - Surface Extraction from Incomplete Point Data for Digitizing Factories
Hiroshi Masuda; Satoshi Fuji
The 9th Design Engineering Workshop, 132-137, 26 Oct. 2009, Peer-reviwed
International conference proceedings, English - Extraction of surface primitives from noisy large-scale point-clouds
H. Masuda; Ichiro Tanaka
Computer-Aided Design and Applications, 6, 3, 387-398, 2009, Peer-reviwed, 3D shape acquisition of large facilities, such as industrial plants and power plants, has been receiving increasing attention for simulating complicated maintenance and repair tasks. It is widely recognized that model-based planning based on 3D CAD reduces the rework of maintenance tasks to a large extent. The state-of-the-art phase-based laser scanners are very promising to efficiently capture point-clouds of large facilities
because they can produce hundreds of millions point data in several minutes. However, point data captured from the phase-based scanner tend to include large noise components and quite a lot of outliers. In addition, very large memory space is required to generate solid models by processing very large point-clouds. Therefore, it is preferable to develop techniques that can extract surface primitives, such as planes, cylinders, cones, spheres, and tori from very noisy and large-scale point-clouds. This paper introduces a robust streaming smoothing operator for extracting surface primitives. Our method is based on robust estimate and can be applied to hundreds of million point data. We applied our smoothing operator to point-clouds captured from nuclear power plants, and could successfully extract primitive surfaces from large-scale noisy point data. © 2009 CAD Solutions, LLC.
Scientific journal, English - 視覚的特徴を考慮したメッシュモデルの変形手法
本田浩一郎; 増田宏
映像情報メディア学会誌, 63, 5, 679-684, 2009, Peer-reviwed
Scientific journal, Japanese - 体積を保存する高速なメッシュ変形手法
土場健太郎; 増田宏
映像情報メディア学会誌, 63, 5, 673-678, 2009, Peer-reviwed
Scientific journal, Japanese - Interactive deformation of 3D mesh models
Hiroshi Masuda; Kenta Ogawa
Computer-Aided Design and Applications, 5, 1-4, 47-57, 2008, Peer-reviwed, This paper proposes a framework for interactively deforming 3D mesh models. 3D mesh models are often used in finite element analysis, but existing surface-based deformation methods fail to deform volumetric elements consistently. In the method proposed here, vertices in a 3D mesh model are classified into boundary vertices and interior vertices. Boundary vertices are treated in the same way as a feature-preserving surface-based deformation
a mean curvature constraint is defined at each boundary vertex, and positional constraints and form-feature constraints are optionally specified at boundary vertices. At each interior vertex, a local volume is constructed as a set of polyhedra that share an interior vertex, and a constraint is assigned based on mean value coordinates. The combination of the mean value coordinates and the mean curvature normals work very well to deform both the boundary and interior of 3D mesh models naturally, without complicated weighting schemes or the rotation of constraints for 3D meshes. In this framework, all constraints are represented in linear forms and solved very efficiently using sparse linear system solvers. This research has shown that 3D mesh models can be deformed in an interactive manner and with a practical amount of preprocessing time. © 2008 CAD Solutions, LLC.
Scientific journal, English - 設計制約を考慮したアセンブリモデルのメッシュモーフィング
小川健太; 増田宏
日本機械学会論文集 C編, 74, 739, 739-745, 2008, Peer-reviwed
Scientific journal, Japanese - Application of Interactive Deformation to Assembled Mesh Models for CAE Analysis
H. Masuda; K. Ogawa
2007 ASME International Design Engineering Technical Conferences, Paper No. DETC2007-34636, 469-477, 04 Sep. 2007, Peer-reviwed
International conference proceedings, English - Feature-Preserving Deformation for Assembly Models
H. Masuda
Procc. of The 4th annual International CAD Conference (CAD'07), USB, 1-4, 311-320, 25 Jun. 2007, Peer-reviwed
International conference proceedings, English - Preserving form features in interactive mesh deformation
Hiroshi Masuda; Yasuhiro Yoshioka; Yoshiyuki Furukawa
COMPUTER-AIDED DESIGN, ELSEVIER SCI LTD, 39, 5, 361-368, May 2007, Peer-reviwed, Interactive mesh deformation that preserves differential properties is a promising technique for the design of mechanical parts such as automobile sheet-metal panels. However, existing methods lack the ability to manipulate the form features and hard constraints that are commonly used in engineering applications. In this paper, we propose a new deformation framework that precisely preserves the shapes of form features during deformation. Geometrical shapes are interactively deformed so that mean curvature normals are approximately preserved in a least-squares sense and positional constraints and form-feature constraints are precisely satisfied. In our system, the combination of soft and hard constraints is solved using the Lagrange multiplier method. We also show how to constrain the motion of a form feature on a plane or a straight line using linear constraints. The implemented system achieves a real-time response for constrained deformation. (c) 2007 Elsevier Ltd. All rights reserved.
Scientific journal, English - Feature-preserving Deformation for Assembly Models
Hiroshi Masuda
Computer-Aided Design and Applications, 4, 1-4, 311-320, 2007, Peer-reviwed, This paper proposes a framework for interactively deforming assembly models with multiple disconnected meshes. When the user selects a mesh model and deforms it, other mesh models are simultaneously and consistently deformed while the shapes of the form-features are preserved. The method combines surface-based and volume-based deformation. Each model is encoded using differential properties for the surface-based deformation and mean value coordinates for the volume-based deformation. Since the deformation methods are interrelated through linear systems, the deformation of one model can be interactively propagated to the other models. The implemented system can achieve a real-time response for the deformation of assembly models. © 2007 by CAD Solutions.
Scientific journal, English - 厳密制約を用いたインタラクティブなメッシュ変形手法
吉岡康博; 増田宏; 古川慈之
映像情報メディア学会誌, The Institute of Image Information and Television Engineers, 61, 1, 85-90, 2007, Peer-reviwed, Interactive mesh editing techniques typically encode geometric shapes using discrete differential equations and approximately solve them using the least squares method. However, these techniques fail to precisely preserve user-defined constraints. In our method, user-defined constraints, such as positional constraints, are treated as hard constraints, and then the combination of hard and soft constraints is converted into a typical least-squares system using QR decomposition. Our method stably and efficiently calculates vertex positions that preserve differential properties. A well-known problem with hard constraints is over-constraints. If over-constraints are involved, they may cause the solver to halt the computation. We show how our framework resolves over-constrained situations, which include redundant and conflicting constraints.
Scientific journal, Japanese - Interactive mesh deformation using equality-constrained least squares
H. Masuda; Y. Yoshioka; Y. Furukawa
COMPUTERS & GRAPHICS-UK, PERGAMON-ELSEVIER SCIENCE LTD, 30, 6, 936-946, Nov. 2006, Peer-reviwed, Mesh deformation techniques that preserve the differential properties have been intensively studied. In this paper, we propose an equality-constrained least squares approach for stably deforming mesh models while approximately preserving mean curvature normals and strictly satisfying other constraints such as positional constraints. We solve the combination of hard and soft constraints by constructing a typical least squares system using QR decomposition. A well-known problem of hard constraints is over-constraints. We show that the equality-constrained least squares approach is useful for resolving such over-constrained situations. In our framework, the rotations of mean curvature normals, are treated using the logarithms of unit quaternions in R(3). During deformation, mean curvature normals can be rotated while preserving their magnitudes. In addition, we introduce a new modeling constraints called rigidity constraints and show that rigidity constraints can effectively preserve the shapes of feature regions during deformation. Our framework achieves good performance for interactive deformation of mesh models. (c) 2006 Elsevier Ltd. All rights reserved.
Scientific journal, English - Requrement-Definition-Confirmation Modeling Approach to Identifying Uncertainties in the Product Design Process
T.Nakazawa; H. Masuda
ASME 2006 International Design Engineering Technical Conference, DETC-2006-99044, 10-13, 10 Sep. 2006, Peer-reviwed
International conference proceedings, English - A constrained least squares approach to interactive mesh deformation
Yasuhiro Yoshioka; Hiroshi Masuda; Yoshiyuki Furukawa
IEEE INTERNATIONAL CONFERENCE ON SHAPE MODELING AND APPLICATIONS 2006, PROCEEDINGS, IEEE COMPUTER SOC, 153-+, 2006, Peer-reviwed, In this paper we propose a constrained least squares approach for stably computing Laplacian deformation with strict positional constraints. In the existing work on Laplacian deformation, strict positional constraints are described using large values of least squares weights, which often cause numerical problems when Laplacians are described using cotangent weights. In our method, we describe strict positional constraints as hard constraints. We solve the combination of hard and soft constraints by constructing a typical least squares matrix form using QR decomposition. In addition, our method can manage shape deformation under over-constraints, such as redundant and conflicting constraints. Our framework achieves excellent performance for interactive deformation of mesh models.
International conference proceedings, English - Preserving form-features in interactive mesh deformation
Hiroshi Masuda; Yasuhiro Yoshioka; Yoshiyuki Furukawa
GEOMETRIC MODELING AND PROCESSING - GMP 2006, PROCEEDINGS, SPRINGER-VERLAG BERLIN, 4077, 207-220, 2006, Peer-reviwed, Interactive mesh editing techniques that preserve discrete differential properties are promising to support the design of mechanical parts such as automobile sheet metal panels. However, existing methods lack the ability to manipulate form-features and hard constraints, which are common in engineering applications. In product design, some regions on a 3D model are often required to precisely preserve the surface types and parameters during deformation. In this paper, we propose a discrete framework for preserving the shapes of form-features using hard constraints in interactive shape deformation. Deformed shapes are calculated so that form-features translate and rotate while preserving their original shapes according to manipulating handles. In addition, we show how to constrain the motion of form features using linear constraints. The implemented system can achieve a real-time response for constrained deformation.
Scientific journal, English - ハンドル領域の回転とスケーリングを考慮したインタラクティブな メッシュ変形操作
吉岡康博; 増田宏; 古川慈之
映像情報メディア学会誌, The Institute of Image Information and Television Engineers, 60, 12, 2032-2037, 2006, Peer-reviwed, In surface-based interactive mesh deformation, most methods deform 3D mesh models by preserving their mean curvature. However, it is not easy to implicitly rotate normals on mesh models. We propose a new deformation framework for translating, rotating and scaling 3D models in an interactive manner. In our method, normal vectors on a 3D model are interactively rotated by interpolating the quaternion logarithms of rotations. This method allows interactive rotations and produces good results. In addition, we introduce a rigidity-constraint that preserves the relative positions of vertices. This type of constraint is useful for preserving important features on a 3D model. We also demonstrate that our framework can be applied to the scaling, smoothing and enhancement of geometric features on a 3D model.
Scientific journal, Japanese - Interactive feature extraction for cut-and-paste editing
Yasuhiro Yoshioka; Yoshiyuki Furukawa; Hiroshi Masuda
Kyokai Joho Imeji Zasshi/Journal of the Institute of Image Information and Television Engineers, Inst. of Image Information and Television Engineers, 59, 8, 1205-1210, 2005, We propose modeling operations using a volume-based cut-and-paste method for generating rough 3D models. Cut-and-paste editing extracts a characteristic feature from a source model and copies it to a target model. To create such a cut-and-paste technique, we developed a new method that consists of mesh segmentation and volume fitting. In our method, a feature region and its surrounding area are separated from the user-specified area and are used for generating a parametric volume that involves the feature region. In feature pasting, parametric volumes are deformed and pasted to the target model, and then, features inside the volume are adaptively deformed and pasted to the target. Our experimental results show our operations can effectively generate new models by removing, pasting, and deforming partial shapes in existing models.
Scientific journal, Japanese - メッシュモデルの特徴領域抽出と張り付け操作
吉岡康博; 古川慈之; 増田宏
映像情報メディア学会誌, 59, 8, 1205-1210, 2005, Peer-reviwed
Scientific journal, Japanese - パラメトリックボリュームフィッティングを用いた3次元形状モデルのカットアンドペースト編集
古川慈之; 増田宏; 大和裕幸
情報処理学会論文誌, 46, 3, 870-878, 2005, Peer-reviwed
Scientific journal, Japanese - Volume-based Cut-and-Paste Editing for Early Design Phases
H. Masuda; Y. Furukawa; Y. Yoshioka
ASME Computers and Information in Engineering Conference, Paper No. DETC2004-57676, 243-251, Oct. 2004, Peer-reviwed
International conference proceedings, English - 故障報告書分析のためのコーディング手法に関する研究
安藤英幸; 大和裕幸; 中野知彦; 増田宏
日本造船学会論文集, 195, 53-61, 2004, Peer-reviwed
Scientific journal, Japanese - Webベース設計レビューのための３Ｄデータへのアノテーション手法
増田宏; 吉岡康博; 和田顕男; 大和裕幸
日本造船学会論文集, 195, 123-129, 2004, Peer-reviwed
Scientific journal, Japanese - Shape Intrinsic Properties for Free-Form Object Matching
K. H. Ko; T. Maekawa; N. M. Patrikalakis; H. Masuda; F. E. Wolter
Journal of Computing and Information Science in Engineering, 3, 4, 325-333, Dec. 2003, Peer-reviwed, Despite extensive research and rapid increase of computing power, free-form object matching still remains a challenging problem in CAD/CAM areas. In this paper, various object features are discussed, and matching methods which use these features are introduced along with robust computational algorithms for umbilical points and intrinsic wireframes. The similarity of matched objects is assessed with three proposed tests. Each algorithm is demonstrated with examples.
International conference proceedings, English - Shape Intrinsic Fingerprints for Free-Form Object Matching
K. H. Ko; T. Maekawa; N. M; Patrikalakis; H. Masuda; F.-E. Wolter
Proceedings of the Eighth ACM Symposium on Solid Modeling and Applications, 196-207, Jun. 2003, Peer-reviwed
International conference proceedings, English - Cut-and-paste editing based on constrained b-spline volume fitting
Y Furukawa; H Masuda; KT Miura; H Yamato
COMPUTER GRAPHICS INTERNATIONAL, PROCEEDINGS, IEEE COMPUTER SOC, 222-225, 2003, Peer-reviwed, This paper proposes an advanced cut-and-paste editing for three-dimensional models. We introduce a new parameterization technique based on constrained B-spline surface/volume fitting. Our cut-and-paste editing is performed on this parameterization. In our method, a parametric volume is generated so that its isoparametric surface fits to the base surface and the volume bounds the detail. Our volume fitting is realized by the optimization of an objective functional with a smoothness factor We implemented and evaluated our method, and showed that our constrained fitting is effective to edit shapes that may have highly curved areas or handles.
International conference proceedings, English - Compression of NURBS Surfaces with Error Evaluation
Yoshiyuki Furukawa; Hiroshi Masuda
NICOGRAPH Internatinal, 115-120, May 2002, Peer-reviwed
International conference proceedings, English - Managing CAD data as a multimedia data type using digital watermarking
R Ohbuchi; H Masuda
FROM KNOWLEDGE INTENSIVE CAD TO KNOWLEDGE INTENSIVE ENGINEERING, KLUWER ACADEMIC PUBLISHERS, 79, 103-116, 2002, Peer-reviwed, This paper advocates the use of digital watermarking as a part of a scheme to provide security to 3D geometric CAD (GCAD) systems. This paper discusses requirements for and opportunities available to watermark 3D GCAD models in general. The paper then presents approaches to watermark 3D GCAD models defined by using parametric curves and surfaces. In particular, a pair of watermarking algorithms targeting Non-Uniform B-Spline (NURBS) curves and surfaces, one based on reparameterization and the other based on knot insertion, are presented in detail. An important feature of both of the method is that they preserve the exact geometric shape of the target NURBS objects.
International conference proceedings, English - Selective non-uniform subdivision
KT Miura; H Masuda
10TH PACIFIC CONFERENCE ON COMPUTER GRAPHICS AND APPLICATIONS, PROCEEDINGS, IEEE COMPUTER SOC, 457-459, 2002, Peer-reviwed, The control polygons of B-spline subdivision curves are usually refined uniformly using a technique called knot-doubling. This uniform refinement approach would perform unnecessary subdivision steps on portions already close to the limit curve enough and, consequently, cause unnecessary (exponential) increase on the number of line segments in the refined polygons. This paper overcomes this problem by proposing a local refinement technique for the control polygons of B-spline subdivision curves. Local refinement is achieved by selectively inserting new knots at midpoints of knot intervals. Efficient adaptive subdivision can be easily realized based on the new technique.
International conference proceedings, English - テキストマイニングを用いた故障報告書分析手法の研究
安藤 英幸; 大和 裕幸; 堀 晃; 増田 宏; 白山 晋
日本造船学会論文集, The Japan Society of Naval Architects and Ocean Engineers, 192, 192, 475-483, 2002, Peer-reviwed, Machinery maintenance activities should be based on statistics and knowledge of past machinery failures, but it is often difficult to keep gathering those data in engineers' daily works. This paper describes an approach to acquire those data and knowledge from machinery failure reports, which are written as free texts, by applying text mining techniques. The method consists of three stages. The first state is event extraction. The term event represents a status of an object ; "damage of a piston ring" is an example of it. Each machinery failure reports is converted into a set of events in this stage. The second stage is to find relations between the events. To find taxonomic relations, we defined a lexical distance and direction measure to evaluate similarities among events. To find non-taxonomical relations, an association rule mining method is used. The third stage is evaluating extracted relations. Authors tested the proposing knowledge acquisition process with 136 machinery failure reports and expert engineers validated more than 80% relations are correct knowledge.
Scientific journal, Japanese - 米国におけるEラーニング：ビジネスモデルからの体系化
馬場靖憲; 鳥内浩一; 増田宏
研究技術計画, 18, 1-2, 1-14, 2002, Peer-reviwed
Scientific journal, Japanese - セマンティックウェブの造船設計システムへの応用
大和 裕幸; 安藤英幸; 増田宏; 白山晋
日本造船学会論文集, The Japan Society of Naval Architects and Ocean Engineers, 192, 192, 387-396, 2002, Peer-reviwed, This paper presents a design support system for basic design of ships. The system aims at supporting designers by presenting documents needed for each task according to design processes. In order to construct our system, several approaches were adopted. At first, an analysis of basic design process using UML was made. Authors understood its workflow and extracted a data list to make documents for each step of the workflow. Secondly, Semantic Web architecture was introduced to structuralise ship design documents. By applying Semantic Web technology, users can query to collections of documents as if using relational databases. Authors implemented the system and evaluated it through an example of basic design. The system shows its efficiency in the evaluation.
Scientific journal, Japanese - 船形設計のための自由形状データ圧縮
古川慈之; 増田 宏; 大和 裕幸; 白山 晋
日本造船学会論文誌, The Japan Society of Naval Architects and Ocean Engineers, 191, 191, 187-194, 2002, Peer-reviwed, The growth of 3D CAD system in ship hullform design makes curves and surfaces data use prevalent. For transmitting those data on networks in design process, the data size becomes critical. This paper describes a compression method of free-form surface for ship hullform design. It consists of surface interpolation over boundary curves and surface modification using differences between original surfaces and interpolating ones. The differences data is compressed using the discrete cosine transform (DCT). We achieved to balance data size and tolerance by the method. It enables to select effective compression ratio according to objectives of data usage.
Scientific journal, Japanese - Streamline modeling based on potential flow
Y Suzuki; KT Miura; Tanaka, I; H Masuda
NINTH PACIFIC CONFERENCE ON COMPUTER GRAPHICS AND APPLICATIONS, PROCEEDINGS, IEEE COMPUTER SOC, 305-312, 2001, Peer-reviwed, The streamline modeling is a design methodology of fair free-form surfaces where the tangent vectors are specified/manipulated to generate/deform them instead of the control points of the traditional surface representations. Creations and deformations of complex 3D free-form shapes generally require a large amount of labours and costs. Therefore in this paper we propose a new modeling technique based on dynamics of fluid flow in order to create and deform high-quality surfaces more intuitively with less number of parameters based on the streamline modeling. We construct a flow field based on the potential flow, then calculate tangent vectors in the flow field that are required for the streamline modeling. Streamlines are generated by numerically integrating the tangent vectors, then the surface is represented as a set of the streamlines. The deformation of the surafce is performed by changing of the flow field. We have developed a prototype design system using our new modeling technique.
International conference proceedings, English - ポリゴン簡略化手法の数値解析用モデル作成への応用
田中一郎; 増田宏; 三浦憲二郎
日本設計工学会, 日本設計工学会, 36, 4, 35-39, 2001, Peer-reviwed
Scientific journal, Japanese - ウェアラブルシステムの造船作業計測への応用
大和裕幸; 小林郁太郎; 白山 晋; 増田宏; 榎本昌一; 西田尚徳; 中村智和
日本造船学会論文誌, 190, 431-438, 2001, Peer-reviwed
Scientific journal, Japanese - 比較空間を用いたCFDシミュレーションのデータ比較に関する研究
白山晋; 斉藤幸二郎; 大和裕幸; 増田宏; 安藤英幸
日本造船学会論文誌, The Japan Society of Naval Architects and Ocean Engineers, 190, 190, 41-50, 2001, Peer-reviwed, CFD simulations have been utilized to improve a hull form. As a result, a huge amount of numerical data has been acquired. In the verification process of numerical results, comparison among data obtained from different kinds of resources (e.g. experiments, other numerical experiments) plays an important role. Remarking the comparison process among data, it is found that the most difficult issue is the difference of locations that the data is defined. In this paper, we try to solve this problem. First, drawbacks of image data for the comparison in a wide spatial region are clarified. In order to overcome the drawbacks, a concept of the comparison space is introduced. Second, how to construct the comparison space is described. Finally, several numerical experiments are demonstrated to validate our concept. In the case of the linear advection problem, a new characteristic feature of the numerical error is found. In additions, it is shown that the grid dependency on the numerical results can be found out in the wide spatial region.
Scientific journal, Japanese - Coding topological structure of 3D CAD models
H Masuda; R Ohbuchi
COMPUTER-AIDED DESIGN, ELSEVIER SCI LTD, 32, 5-6, 367-375, May 2000, Peer-reviwed, This paper proposes a loss-less method for encoding and compressing three-dimensional (3D) geometric models that may contain any combinations of wireframe, surface, and solid forms as well as various non-simple topological structure (e.g. cavities and strut edges) that could exist in 3D CAD models. Given a model, our method transforms it into a simple triangular mesh model by applying a sequence of Euler operators. Both the transformation process and the subdivided model are encoded and compressed to produce a compressed model.
We implemented and evaluated our compression algorithm. Experiments with 3D models of mechanical parts showed that, in addition to being able to handle diverse and complex topological types, our method achieved excellent compression ratios. (C) 2000 Elsevier Science Ltd. All rights reserved.
Scientific journal, English - NURBS曲線・曲面を対象とした幾何形状を保存する電子透かし埋め込み手法
大渕竜太郎; 増田宏; 青野雅樹
情報処理学会論文誌, Information Processing Society of Japan (IPSJ), 41, 3, 559-569, 2000, Peer-reviwed, Digital watermarking adds various information to digital contents for copyright management and other applications. 3D model has recently been recognized as a watermarking target data type. However, existing watermarking algorithms target polygonal meshes and their attributes for watermarking so that they can't be readily applied to the majoirty of (geometric) computer aided design (CAD) models for two major reasons. First, these CAD models employ parametric curves and surfaces, not polygonal meshes, as their main shape-defining primitives. Second, most CAD applications do not tolerate modifications of model topology and / or geometry that are introduced by existing watermarking algorithms. This paper proposes a new watermarking algorithm for non-uniform rational B-spline (NURBS) curves and surfaces, which employs rational linear reparameterization for embedding messages. The algorithm exactly preserves the shape, -that is, the geometry and topology-of its watermarking targets. Furthermore, it preserves the data size of the model. We consider these two properties, exact preservation of shape and preservation of data size, to be important in various applications of CAD models. In addition to the shape- and data size-preserving data embedding algorithm for NURBS curves and surfaces, this paper outlines additional methods for embedding data in various types of parametric curves and surfaces.
Scientific journal, Japanese - 船型設計における高品質な曲面生成手法に関する研究
増田宏; 大和裕幸; 古川慈之
日本造船学会論文集, The Japan Society of Naval Architects and Ocean Engineers, 187, 187, 309-319, 2000, Peer-reviwed, This paper describes about the method for fair surface generation in ship hullform design aiming at the automatization of surface fairing. It generates an approximating surface from section curves according to the distribution of curvature. The generated surface has dense parameters in high curvature areas, and sparse parameters in low curvature areas. This method has three advantages described below. First, it can suppress the distortions generated by traditional methods. Second, it can use additional curves that cannot be used in traditional skinning methods. Finally, it can do surface fairing efficiently without the great loss of geometric feature.
Scientific journal, Japanese - 小型滑走挺における操船者の動作の３次元計測に関する研究
増田宏; 和田顕男; 榎本昌一; 大和裕幸; 白山晋
日本造船学会論文誌, The Japan Society of Naval Architects and Ocean Engineers, 188, 173-182, 2000, Peer-reviwed, There is no doubt that a motorboat driver's motion during its turn has a large influence in its speed and stability. Nevertheless, this mechanism has not yet been solved. In this paper, we present a novel system to analyze three dimensional motion of a driver based upon three dimensional measurement with multiple CCD cameras. Using this system, we can calculate the centre of gravity and moment of inertia of a motorboat driver in its turn.
Scientific journal, Japanese - 遺伝アルゴリズム手法による造船組立工程のルール抽出に関する研究
大和裕幸; 白山晋; 増田宏
日本造船学会論文集, The Japan Society of Naval Architects and Ocean Engineers, 188, 559-568, 2000, Peer-reviwed, It seems that each of factories and buildings has such an established construction system that efficiency of work order in each field has been pursued. However, it may be considered that the system has not taken the effect of the assembly sequences on the schedule into account sufficiently. In this paper, a relation between an assembly point and a schedule is examined using a genetic algorithm and a schema analysis, and the effect on the schedule is considered. A new computer aided system enables us to extract some rules from a ship building process will be developed.
Scientific journal, Japanese - ソフトウェアエージェントによる異分野協調業務支援の研究
大和裕幸; 伊藤博子; 白山晋; 増田宏
日本造船学会論文誌, The Japan Society of Naval Architects and Ocean Engineers, 188, 727-735, 2000, Peer-reviwed, This paper proposes the architecture of collaborative working environment ACE, an agent-based collaboration environment. Users of the system can work in collaboration with others via message, which is managed by Message Management System (MMS) at the center of the system. To give collaboration assistance to users, ACE has three agents in MMS and a personal Desktop Agent for each user : Repository Agent collects messages between users, Address Match Agent gives suggestion of members' list for community organization, and Topic Management Agent logs communication session. Agents in the ACE speak Agent Communication Language to provide appropriate information for their users. A simple prototype of ACE system has been built and evaluated by a scenario of distributed ship maintenance, which requires collaboration of workers on land and at sea.
Scientific journal, Japanese - A shape-preserving data embedding algorithm for NURBS curves and surfaces
R Ohbuchi; H Masuda; M Aono
COMPUTER GRAPHICS INTERNATIONAL, PROCEEDINGS, IEEE COMPUTER SOC, 180-187, 1999, Peer-reviwed, Existing data embedding algorithms for polygonal meshes and their attributes can't be applied to the majority of (geometric) computer aided design (CAD) applications, for two major reasons. First, these CAD systems employ parametric curves and surfaces, not polygonal meshes, as their main shape-defining primitives. Second, most CAD applications do not tolerate modifications of model topology and/or geometry that are introduced by existing data embedding algorithms.
This paper proposes a new data embedding algorithm for nan-uniform rational B-spline (NURBS) curves and surfaces, which employs rational linear reparameterization for embedding messages. The algorithm exactly preserves the shape, - that is, the geometry and topology - of its embedding targets. Furthermore, it preserves the data size of the model. We consider these two properties, preservation of shape and preservation of data size, can be significant with regard to the use of data embedding in CAD applications.
In addition to the shape- and data size-preserving data embedding algorithm for NURBS curves and surfaces, this paper outlines additional methods for embedding data in various types of parametric curves and surfaces.
International conference proceedings, English - 周波数領域での曲面データの圧縮と転送
増田宏; 大渕竜太郎; 青野正樹
情報処理学会論文誌, 40, 3, 1188-1195, 1999, Peer-reviwed
Scientific journal, Japanese - Data embedding algorithms for geometrical and non-geometrical targets in three-dimensional polygonal models
R Ohbuchi; H Masuda; M Aono
COMPUTER COMMUNICATIONS, ELSEVIER SCIENCE BV, 21, 15, 1344-1354, Oct. 1998, Peer-reviwed, Three-dimensional (3D) graphics is about to become a full-fledged multimedia data type, prompted by the increasing popularity of virtual reality modeling language (VRML) [15] and imminent standardization of MPEG-4 [16].
This paper presents several algorithms for embedding data in triangular meshes, arguably the most important component in both VRML and MPEG4 in defining arbitrary shapes. A topology-modifying algorithm described in this paper embeds bit string in connectivity of triangles, while another algorithm cuts out patterns from a mesh. Yet another algorithm modifies texture coordinate, a non-geometrical quantity, for embedding.
Watermarks embedded in 3D graphics contents could be used as a tool in managing intellectual property and other issues associated with these contents. (C) 1998 Elsevier Science B.V. All rights reserved.
Scientific journal, English - Watermarking Multiple Object Types in Three-Dimensional Models
R.Ohbuchi; H.Masuda; M.Aono
Proc. of the Workshop on Multimedia and Security at ACM Multimedia '98, 83-91, Sep. 1998, Peer-reviwed
International conference proceedings, English - Watermarking three-dimensional polygonal models through geometric and topological modifications
R Ohbuchi; H Masuda; M Aono
IEEE JOURNAL ON SELECTED AREAS IN COMMUNICATIONS, IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC, 16, 4, 551-560, May 1998, Peer-reviwed, This paper discusses techniques for embedding data into three-dimensional (3-D) polygonal models of geometry. Given objects consisting of points, lines, (connected) polygons, or curved surfaces, the algorithms described in this paper produce polygonal models with data embedded into either their vertex coordinates, their vertex topology (connectivity), or both. Such data embedding can be used, for example, for copyright notification, copyright protection, theft deterrence, and inventory of 3-D polygonal models.
A description of the background and requirements is followed by a discussion of where, and by what fundamental methods, data can be embedded into 3-D polygonal models. The paper then presents several data-embedding algorithms, with examples, based on these fundamental methods. By means of these algorithms and examples, we show that the embedding of data into 3-D polygonal models is a practicable technique.
Scientific journal, English - 位相操作を用いた3次元形状モデルのデータ圧縮法
増田宏; 大渕竜太郎; 青野正樹
情報処理学会論文誌, 39, 7, 2189-2195, 1998, Peer-reviwed
Scientific journal, Japanese - Embedding Data in 3D Models
R.Ohbuchi; H.Masuda; M.Aono
volume 1309 of Lecture Notes in Computer Science, 1-10, Sep. 1997, Peer-reviwed
International conference proceedings, English - A cell based approach for generating solid objects from orthographic projections
H Masuda; M Numao
COMPUTER-AIDED DESIGN, ELSEVIER SCI LTD, 29, 3, 177-187, Mar. 1997, Peer-reviwed, This paper describes an efficient method for converting orthographic projections into solid models based on non-manifold topology and the assumption-based truth maintenance system (ATMS), and then describes an error recovery method for incorrect orthographic projections. A combination of non-manifold modelling and ATMS achieves excellent performance for conversion problems. In our method, all solid candidates are maintained by a cellular model using non-manifold topology. Since a combination of cells in a cellular model determines the shape of a solid, solid models that match orthographic projections can be derived by solving constraints between cells and orthographic projections. A sufficient group of constraints can be expressed as a set of Boolean equations, which can be solved efficiently by using ATMS. Our method can even be applied to incorrect draftings. In actual design, many draftings contain human errors, but conventional methods cannot handle such incorrect draftings. We discuss methods for detecting inconsistent lines that should not have been included, or missing lines that should have been included. (C) 1997 Elsevier Science Ltd.
Scientific journal, English - Watermarking three-dimensional polygonal models
R Ohbuchi; H Masuda; M Aono
ACM MULTIMEDIA 97, PROCEEDINGS, ADDISON-WESLEY PUBL CO, 261-272, 1997, Peer-reviwed, The advantages of digital media such as the Internet and CD-ROMs lie in the fact that their contents are easy to duplicate, edit, and distribute. These advantages, however, are double-edged swords, because they also facilitate unauthorized use of such contents. Data embedding, which places information into the contents themselves, is an approach to address this issue. Embedded information can be used, for example, for copyright protection, theft deterrence, and inventory.
This paper discusses our work on embedding data into three-dimensional (3D) polygonal models of geometry. Given objects consisting of points, lines, polygons, or curved surfaces, the data embedding algorithms described in this paper produce polygonal models with data embedded. Data are placed into 3D polygonal models by modifying either their vertex coordinates, their vertex topology (connectivity), or both.
A brief review of related work and a description of the requirements of data embedding is followed by a discussion of where, and by what fundamental methods, data can be embedded into 3D polygonal models. The paper then presents data-embedding algorithms, with examples, based on these fundamental methods.
International conference proceedings, English - 不完全な三面図からの立体モデルの生成
増田宏; 沼尾雅之
人工知能学会誌, 12, 6, 928-935, 1997, Peer-reviwed
Scientific journal, Japanese - Application Systems for Non-Manifold Topology
H. Masuda
International Workshop on Shape Modeling: Parallelism, Interactivity and Applications, 27-31, Aug. 1994, Peer-reviwed
International conference proceedings, English - Representation and Maintenance of Form-Feature Based on Non-Manifold Geometric Modeling
H. Masuda
Journal of Advanced Automation Technology, 6, 2, 80-85, 1994, Peer-reviwed
Scientific journal, English - 非多様体形状モデラとATMSを用いた三面図からのソリッド合成法
増田宏; 沼尾雅之; 清水周一
情報処理学会論文誌, Information Processing Society of Japan (IPSJ), 35, 3, 453-460, 1994, Peer-reviwed, In this paper, we propose a new method to construct 3D solid models from 2D orthographic projections. We use cell decomposition models as an intermediate representation between the projections and solid models, and divide the whole process into two distinguished part : geometric modeling and symbolic searching. A cell is defined as a 3D closed space bounded by surfaces that are constructed from projections. Since any combination of cells becomes solids, the search process can simply focus on detecting appropriate combinations of the cells. We applied non-manifold modeling technology to represent cell models, and realize an efficient operation for generating boundary represention of candidates without Boolean operations. Then, the assumption-based truth maintenance system (ATMS) is applied to detect the appropriate combinations. ATMS described the problem declaratively and enables a user to define additional heuristics easily. We have developed a 2D-3D construction system by implementing these technologies, and evaluated it by the actual drawing data. The input is three orthographic projections which consist of lines and circular curves. The system constructs all possible solid models that consist of planar faces and analytic surfaces. We showed the performance of the system by comparing the calculation time of several examples.
Scientific journal, Japanese - TOPOLOGICAL OPERATORS AND BOOLEAN OPERATIONS FOR COMPLEX-BASED NONMANIFOLD GEOMETRIC-MODELS
H MASUDA
COMPUTER-AIDED DESIGN, ELSEVIER SCI LTD, 25, 2, 119-129, Feb. 1993, Peer-reviwed, Nonmanifold geometric modelling is used to represent and manipulate wireframe, surface and solid models in a single architecture. It is suitable for improving geometric-modelling environments for product design. The paper reviews some fundamentals of nonmanifold geometric modelling. A mathematical framework is introduced, and the topological structure and basic topological operations are discussed on the basis of the framework. Next, a new method, which can quickly and arbitrarily reshape geometric models defined by Boolean operations, is presented. This method is made possible by the capabilities of nonmanifold geometric modelling, and it can be used for interactive design by trial and error and form-feature modelling.
Scientific journal, English - 非多様体形状モデルを用いた形状特徴の表現と管理
増田宏
精密工学会誌, The Japan Society for Precision Engineering, 59, 6, 956-962, 1993, Peer-reviwed, This paper discusses representation, maintenance, and editing of form-features based on non-manifold geometric modeling. Form-features are very important to maintain meanings of partial shapes, but in conventional solid modeling, it is difficult to represent various forms of partial shapes and maintain them throughout design. These problems can be solved by using a non-manifold geometric modeling system. In our method, the system maintains topological structure that can represent any form-feature as a collection of topological entities. This is realized by subdividing a modeling space into sets of topological entities, and maintaining the relationships between embedded form-features and the topological entities. Form-features, resultant shapes and compound form-features can be extracted from the topological structure. In addition, editing operations based on this representation can cancel or modify form-features very quickly.
Scientific journal, Japanese - Form-Feature Representation Based on Non-Manifold Geometric Modeling
H.Masuda
MICAD 92, 17-35, Feb. 1992, Peer-reviwed, Invited
International conference proceedings, English - A Mathematical Theory and Applications of Non-Manifold Geometric Modeling
H.Masuda; K.Shimada; M.Numao; S.Kawabe
IFIP WG 5.2/GI International Symposium on Advanced Geometric Modeling for Engineering Applications, North-Holland, 89-103, 08 Nov. 1989, Peer-reviwed
International conference proceedings, English - Constraint-Based Object Description for Product Modeling
K.Shimada; M.Numao; H.Masuda; S.Kawabe
Computer Applications in Production and Engineering, 95-106, Oct. 1989, Peer-reviwed
International conference proceedings, English - A Framework for 3D Modeling: Constraint-Based Description and Non-Manifold Geometric Modeling
S.Kawabe; K.Shimada; H.Masuda
Organization of Engineering Knowledge for Product Modeling in Computer Integrated Manufacturing, 325-354, Oct. 1988, Peer-reviwed
International conference proceedings, English
MISC
- Growth monitoring and stem shape analysis in a test site by remeasurement using terrestrial LiDAR
Hiraoka Yuichiro; Eto Shinsuke; Matsushita Michinari; Takahashi Makoto; Masuda Hiroshi
[in Japanese], THE JAPANESE FORESTRY SOCIETY, 2021, The Japanese Forest Society Congress, 132nd, 405, Japanese, 2187-6576, 202102268876804298, 130008117800 - Calculation and Accuracy Evaluation of Tree Traits Using Point-Cloud Measured by Terrestrial Laser Scanners
Eto Shinsuke; Masuda Hiroshi; Hiraoka Yuichiro; Matsushita Michinari; Takahashi Makoto[in Japanese]
, THE JAPANESE FORESTRY SOCIETY, 2020, The Japanese Forest Society Congress, 131, 0, 96-96, Japanese, 130007881290 - 高密度点群データを用いた燃焼炉の劣化診断
増田 宏
01 Oct. 2019, 光アライアンス, 30, 10, 38-42, Japanese, Introduction other - 移動計測で取得した点群と画像からの道路周辺地物の自動抽出
増田 宏; 森 悠真
01 Aug. 2019, 画像ラボ, 30, 8, 42-47, Japanese, Introduction other - Evaluation of foliage traits for Cryptomeria japonica based on 3D point clouds
Hiraoka Yuichiro; Etoh Shinsuke; Matsushita Michinari; Takahashi Makoto; Masuda Hiroshi[in Japanese]
, THE JAPANESE FORESTRY SOCIETY, 2019, The Japanese Forest Society Congress, 130, 0, 572-572, Japanese, 130007645719 - Shape Modeling for Surveying Tree Traits Using Terrestrial Laser Scanners
Etoh Shinsuke; Masuda Hiroshi; Hiraoka Yuichiro; Matsushita Michinari; Takahashi Makoto[in Japanese]
, THE JAPANESE FORESTRY SOCIETY, 2019, The Japanese Forest Society Congress, 130, 0, 89-89, Japanese, 130007645898 - 大規模環境の３次元計測と認識・モデル化技術の現状
増田 宏
01 Oct. 2018, 精密工学会誌, 84, 10, 845-848, Japanese, Introduction scientific journal - 三角点 時流を読む：３次元測量データの活用による業務革新
増田 宏
01 May 2018, 測量, 68, 5, 6-7, Japanese, Invited, Introduction scientific journal - Quantitative evaluation of above-ground traits based on point clouds in Cryptomeria japonica
Hiraoka Yuichiro; Saito Kazuto; Matsushita Michinari; Takahashi Makoto; Masuda Hiroshi[in Japanese]
, THE JAPANESE FORESTRY SOCIETY, 2018, The Japanese Forest Society Congress, 129, 0, 108-108, Japanese, 130007375688 - Shape modeling of tree branches and leaves using dense point-clouds
Saito Kazuto; Hiraoka Yuichiro; Matsushita Michinari; Takahashi Makoto; Masuda Hiroshi[in Japanese]
, THE JAPANESE FORESTRY SOCIETY, 2018, The Japanese Forest Society Congress, 129, 0, 90-90, Japanese, 130007376592 - Application of 3D point cloud processing for forest tree improvement
Hiraoka Yuichiro; Saito Kazuto; Matsushita Michinari; Takahashi Makoto; Masuda Hiroshi[in Japanese]
, THE JAPANESE FORESTRY SOCIETY, 2017, The Japanese Forest Society Congress, 128, 0, 358-358, Japanese, 130007021815 - Shape reconstruction of massive trees in forests using dense point-clouds
Saito Kazuto; Hiraoka Yuichiro; Masuda Hiroshi; Matsushita Michinari; Takahashi Makoto[in Japanese]
, THE JAPANESE FORESTRY SOCIETY, 2017, The Japanese Forest Society Congress, 128, 0, 47-47, Japanese, 130007021671 - 大規模環境の3次元計測と認識・モデル化技術について
増田 宏
01 Oct. 2014, 精密工学会誌, 80, 10, 906-909, Japanese, Invited, Introduction scientific journal - 画像インタフェースを用いた大規模点群からの三次元モデリングシステム
増田宏
日本工業出版, Feb. 2012, 画像ラボ, 23, 1, 15-21, Japanese, Introduction other, 0915-6755, 40019197481, AN10164169 - レーザ計測データに基づく形状再構成技術
増田宏
Jan. 2012, 日本船舶海洋工学会誌, 40, 29-34, Japanese, Introduction other - デジタルエンジニアリングによる設計支援
増田 宏
Aug. 2007, 日本機械学会誌／機械工学年鑑 (15-4), 110, 1065, 625, Japanese, Introduction scientific journal - 実用化が進む３D形状圧縮技術
増田 宏
Nov. 2004, 日本設計工学会, 39, 12, 642-647, Japanese, Invited, Introduction scientific journal - ポリゴンモデルの圧縮技術
増田 宏
Apr. 2003, 日本機械学会誌, 69, 4, Japanese, Introduction scientific journal - 最近のモデリング技術
増田 宏
The Institute of Image Information and Television Engineers, Apr. 2003, 映像情報メディア学会, 57, 4, 444-445, Japanese, Introduction scientific journal, 1342-6907, 110003671130, AN10588970 - 八分木を用いたラジアル基底関数による高速3D形状再構築
三浦憲二郎; 曽根順治; 増田宏
2003, Visual Computing グラフィクスとCAD合同シンポジウム予稿集, 2003, 200902295560101696 - (42) セマンティックウェブの造船設計システムへの応用(平成14年秋季講演論文概要)
大和 裕幸; 安藤 英幸; 増田 宏; 白山 晋; 佐藤 昌弘; 唐澤 武郎; 田村 雄介; 釼吉 譲
公益社団法人日本船舶海洋工学会, 10 Sep. 2002, Techno marine : bulletin of the Society of Naval Architects of Japan : 日本造船学会誌, 869, 542-542, Japanese, 0916-8699, 110003861209, AN10373894 - (51) テキストマイニングを用いた故障報告書分析手法の研究(平成14年秋季講演論文概要)
安藤 英幸; 大和 裕幸; 堀 晃; 増田 宏; 白山 晋
公益社団法人日本船舶海洋工学会, 10 Sep. 2002, Techno marine : bulletin of the Society of Naval Architects of Japan : 日本造船学会誌, 869, 544-544, Japanese, 0916-8699, 110003861218, AN10373894 - 造船等海事産業の情報技術適用に関する研究動向
増田 宏; 尊田雅弘
Jul. 2002, 日本造船学会誌, 868, 4, Japanese, Introduction scientific journal - (4)比較空間を用いたCFDシミュレーションのデータ比較に関する研究(平成13年秋季講演論文概要)
白山 晋; 斎藤 幸二郎; 大和 裕幸; 増田 宏; 安藤 英幸
公益社団法人日本船舶海洋工学会, 10 Sep. 2001, Techno marine : bulletin of the Society of Naval Architects of Japan : 日本造船学会誌, 863, 2-2, Japanese, 0916-8699, 110003868636, AN10373894 - (77)ソフトウエアエージェントによる異分野協調業務支援の研究(第1報) : 協調支援環境の構築(平成12年秋季講演論文概要)
大和 裕幸; 伊藤 博子; 増田 宏; 白山 晋
公益社団法人日本船舶海洋工学会, 25 Oct. 2000, Techno marine : bulletin of the Society of Naval Architects of Japan : 日本造船学会誌, 856, 683-683, Japanese, 0916-8699, 110006838115, AN10373894 - (60) 遺伝アルゴリズム手法による造船組立工程のルール抽出に関する研究(平成12年秋季講演論文概要)
大和 裕幸; 白山 晋; 増田 宏; 佐野 毅
公益社団法人日本船舶海洋工学会, 25 Oct. 2000, Techno marine : bulletin of the Society of Naval Architects of Japan : 日本造船学会誌, 856, 678-678, Japanese, 0916-8699, 110006838098, AN10373894 - 3次元CADの現状
増田 宏
May 1999, 日本造船学会誌, 837, Japanese, Introduction scientific journal - 3次元モデルにデータを埋め込む3次元電子透かし
大渕 竜太郎; 増田 宏; 青野 雅樹
1998, 日経コンピュータグラフィックス, 156-163 - Compression of 3D Geometric Models
増田 宏; 青野 雅樹; 大渕 竜太郎
最近, 製造業では設計データの3次元モデル化が急速に進行している。それに伴い, 自動車や家電業界では3Dモデルのデータ量の膨大さが問題になり始めている。一つにはエンジン部品のような複雑な形状を3次元化する必要があるからであり, もう一つには非常に多数の部品を同時に扱う必要性からである。今後, 3Dモデルが設計のマスターモデルになっていくと, データ量の大きい3次元データを多数保持したり, ネットワークを通じて高速にデータをやりとりすることが必要になってくる。しかし, 現状では3次元モデルのデータ量が非常に大きいため, 膨大なデータ容量を必要としたり, データ転送に非常に時間がかかるという問題が生じる。このような問題点を解決する一つの方法は, 3Dモデルデータを圧縮することである。しかし, CADモデルに適した圧縮方法の提案はほとんどなく, また従来のテキストベースの圧縮法を流用しただけでは圧縮率は低い。本稿では, 3次元形状モデルの位相データについて圧縮方法を考え, 実験を行なったので報告する。, 24 Sep. 1997, 全国大会講演論文集, 55, 319-320, Japanese, 110002891756, AN00349328 - 三面図からのソリッドモデル変換技術の現状
増田宏; 沼尾雅之
Jun. 1996, 人工知能学会誌, 11, 4, 542-549, Japanese, Invited, Introduction scientific journal - 非多様体形状の位相表現
増田 宏
Jun. 1994, 日本設計工学会, 29, 7, 233-238, Japanese, Invited, Introduction scientific journal, 80007691402
Books and other publications
Lectures, oral presentations, etc.
- マルチスケール特徴量を用いたMMS 点群ラベリングの高速化（第2報)
平岡慶太; 中野真肇; 高橋元気; 増田 宏
Oral presentation, Japanese, 2024年度精密工学会秋季大会講演論文集
04 Sep. 2024 - 工業設備点群のセマンティックセグメンテーションのための CAD モデルからの学習データ生成
大谷昂星; 増田 宏
Oral presentation, Japanese, 2024年度精密工学会秋季大会講演論文集
04 Sep. 2024 - 大規模点群からの効率的な曲面の検出と統合 (第2報)
長澤祐輔; 武田 駆; 木下洋平; 大塚剛史; 増田 宏
Oral presentation, Japanese, 2024年度精密工学会秋季大会講演論文集
04 Sep. 2024 - 生産設備の点群からの多関節アーム型ロボットの抽出 (第2報)
熊澤一葉; 小森谷沙希; 武田 駆; 増田 宏
Oral presentation, Japanese, 2024年度精密工学会秋季大会講演論文集
04 Sep. 2024 - Reeb グラフを用いた点群からのワイヤハーネスの検出と形状再構成
小森谷沙希; 武田 駆; 河 浩大; 増田 宏
Oral presentation, Japanese, 2024年度精密工学会春季大会
12 Mar. 2024
12 Mar. 2024- 14 Mar. 2024 - 生産設備の点群からの多関節アーム型ロボットの抽出
河崎浩大; 増田 宏
Oral presentation, Japanese, 2024年度精密工学会春季大会
12 Mar. 2024
12 Mar. 2024- 14 Mar. 2024 - 大規模点群からの効率的な曲面の検出と統合
武田 駆; 増田 宏
Oral presentation, Japanese, 2024年度精密工学会春季大会
12 Mar. 2024
12 Mar. 2024- 14 Mar. 2024 - マルチスケール特徴量を用いたMMS点群ラベリングの高速化
平岡慶太; 高橋元気; 増田 宏
Oral presentation, Japanese, 2024年度精密工学会春季大会
12 Mar. 2024
12 Mar. 2024- 14 Mar. 2024 - 点群からの多関節アーム型機器の抽出と形状再構成
河崎浩大; 増田 宏
Oral presentation, 2023年度精密工学会秋季大会講演論文集
15 Sep. 2023 - 木材形質値算出のための高精度な点群レジストレーション（第2報）
川崎春菜; 増田 宏
2023年度精密工学会秋季大会講演論文集
15 Sep. 2023 - 断面推定に基づく一般化円柱の検出と形状再構成
小森谷沙希; 武田 駆; 河 浩大; 増田 宏
Oral presentation, 2023年度精密工学会秋季大会講演論文集
15 Sep. 2023 - ラプラシアン特徴量の工業設備の部材認識の高精度化
大塚剛史; 大谷昂星; 南雲拓真; 増田 宏
Oral presentation, 2023年度精密工学会秋季大会講演論文集
15 Sep. 2023 - テンプレートマッチングを用いた大規模点群からの工業部材検出
木下洋平; 平岡慶太; 武田 駆; 河 浩大; 川崎春菜; 増田 宏
Oral presentation, 2023年度精密工学会秋季大会講演論文集
15 Sep. 2023 - 点群の深層学習のためのCADモデルからの学習データ生成（第3報）
南雲拓真; 増田 宏
Oral presentation, 2023年度精密工学会秋季大会講演論文集
15 Sep. 2023 - 点群と画像の特徴量を用いた道路周辺地物の抽出と分類
平岡慶太; 峯村晃平; 河﨑浩大; 増田 宏
Oral presentation, Japanese, 2022年度精密工学会秋季大会講演論文集
09 Sep. 2022 - 統合特徴量による点群からの工業設備の部材認識
大谷昂星; 南雲拓真; 増田 宏
Oral presentation, Japanese, 2022年度精密工学会秋季大会講演論文集, Domestic conference
09 Sep. 2022 - 機械学習を用いた大型構造物の点群からの劣化検出
青木智子; 山本恵里佳; 増田 宏
Oral presentation, Japanese, 2022年度精密工学会秋季大会講演論文集, Domestic conference
09 Sep. 2022 - 機械学習を用いた点群からの幾何曲面検出
武田駆; 河﨑浩大; 川崎春菜; 増田 宏
Oral presentation, Japanese, 2022年度精密工学会秋季大会講演論文集, Domestic conference
09 Sep. 2022 - 点群の深層学習のためのCADモデルからの学習データ生成（第2報）
南雲拓真; 花井大輝; 重田航平; 増田 宏
Oral presentation, Japanese, 2022年度精密工学会秋春季大会講演論文集
17 Mar. 2022 - 樹木形質値算出のための高精度な点群レジストレーション
川崎春菜; 増田 宏
Oral presentation, Japanese, 2022年度精密工学会春季大会講演論文集
17 Mar. 2022 - 部材間の関係を考慮した大型構造物の形状再構成（第2報）
河﨑浩大; 増田宏
Oral presentation, Japanese, 2022年度精密工学会春季大会講演論文集
17 Mar. 2022 - 点群画像を用いた MMS 点群の構造化
高橋元気; 増田 宏
Oral presentation, Japanese, 精密工学会春季大会講演論文集, Domestic conference
17 Mar. 2022 - 再帰型ネットワークを利用した工業設備の大規模点群からの配管系統の識別
重田航平; 増田宏
Oral presentation, Japanese, 2022年度精密工学会春季大会講演論文集
17 Mar. 2022 - 大規模点群の立体視による大型構造物の劣化検証システム（第2報）
青木智子; 山本恵里佳; 増田宏
Oral presentation, Japanese, 2022年度精密工学会春季大会講演論文集
17 Mar. 2022 - 点群画像を用いたMMS点群からの街路樹の抽出
高橋元気; 増田 宏
Oral presentation, Japanese, 日本写真測量学会秋季学術講演会, Domestic conference
21 Oct. 2021 - 自律移動ロボットによる工業設備の点群自動計測 ～点群計測のための経路計画～
細田大貴; 増田宏; 石川貴一朗
Oral presentation, Japanese, 2021年度精密工学会秋季大会講演論文集
23 Sep. 2021 - 部材間の関係を考慮した大型構造物の形状再構成
河﨑浩大; 峯村晃平; 増田宏
Oral presentation, Japanese, 2021年度精密工学会秋季大会講演論文集
23 Sep. 2021 - 寸法計測に適した点群レジストレーション手法の検討
川崎春菜; 山本恵里佳; 青木智子; 増田 宏
Oral presentation, Japanese, 2021年度精密工学会秋季大会講演論文集
23 Sep. 2021 - 移動計測による点群と画像を用いた物体の抽出と分類 (第２報)
峯村晃平; 増田宏
Oral presentation, Japanese, 2021年度精密工学会秋季大会講演論文集
23 Sep. 2021 - 点群の深層学習のためのCADモデルからの学習データ生成
南雲拓真; 花井大輝; 重田航平; 増田 宏
Oral presentation, Japanese, 2021年度精密工学会秋季大会講演論文集
23 Sep. 2021 - 構造物表面の部分的なレーザ計測点群を用いた変形解析の検討
原木響也; 遊佐泰紀; 増田宏
Oral presentation, Japanese, 日本機械学会計算力学講演会 (CMD2021) 講演論文集, Domestic conference
21 Sep. 2021 - 広域環境の3D計測と認識：人が活動する場のセンシングとモデル化
増田宏
Nominated symposium, Japanese, 第27回画像センシングシンポジウム, Invited, 画像センシング技術研究会, Domestic conference
11 Jun. 2021 - 構造形状の計測データを活用した有限要素法解析のための計算手法の開発
遊佐泰紀; 増田宏
Oral presentation, Japanese, 計算工学講演会論文集
26 May 2021 - MMSレーザスキャナを用いた蓋付きU字溝の抽出手法の開発
高橋元気; 増田宏
Oral presentation, Japanese, 日本写真測量学会 令和3年度年次学術講演会
20 May 2021 - 地上LiDAR再計測による試験林の成長モニタリングと樹幹形状解析
平岡裕一郎; 江藤信輔; 松下道也; 高橋誠; 増田宏
Poster presentation, Japanese, 第132回日本森林学会大会
23 Mar. 2021 - TLS 点群を用いた森林の樹木形質 の抽出手法
江藤 信輔; 増田 宏; 平岡裕一郎; 松下通也; 高橋誠
Oral presentation, Japanese, 第132回日本森林学会大会
23 Mar. 2021 - マルチスケール特徴量を用いたMMSレーザ点群のラベリング手法の検討
高橋元気; 増田宏
Oral presentation, Japanese, 2021年度精密工学会春季大会講演論文集
16 Mar. 2021 - 工業設備の点群からの部材認識における学習データの検討
花井大輝; 重田航平; 増田宏
Oral presentation, Japanese, 2021年度精密工学会春季大会講演論文集
16 Mar. 2021 - 工業設備の大規模点群からの部材形状の認識と形状再構成
重田航平; 増田宏
Oral presentation, Japanese, 2021年度精密工学会春季大会講演論文集
16 Mar. 2021 - 大規模点群の立体視による大型構造物の劣化検証システム
青木智子; 山本恵里佳; 増田宏
Oral presentation, Japanese, 2021年度精密工学会春季大会講演論文集
16 Mar. 2021 - 構造物の不完全な as-built モデルを用いた応力解析法の検討
遊佐泰紀; 増田 宏
Oral presentation, Japanese, 2021年度精密工学会春季大会講演論文集
16 Mar. 2021 - MMSレーザ点群のスキャンライン正規化による道路縁自動抽出の精度評価
高橋元気; 増田宏
Oral presentation, Japanese, 日本写真測量学会秋季講演会
06 Nov. 2020 - 機械学習を用いたガードレールの抽出と形状再構成 (第2報)
峯村 晃平; 松本 裕稀; 増田 宏
Oral presentation, Japanese, 2020年度精密工学会秋季大会講演論文集
01 Sep. 2020 - 移動計測による点群と画像を用いた線状物体検出（第4報）
田島 晃太; 増田 宏
Oral presentation, Japanese, 2020年度精密工学会秋季大会講演論文集
01 Sep. 2020 - TLS点群を用いた樹木形質の抽出と評価 (第2報)
江藤 信輔; 増田 宏
Oral presentation, Japanese, 2020年度精密工学会秋季大会講演論文集
01 Sep. 2020 - 大規模点群を用いた大型構造物の壁面上の劣化検出
山本 恵里佳; 葭内 郁; 増田 宏
Oral presentation, Japanese, 2020年度精密工学会秋季大会講演論文集
01 Sep. 2020 - 工業設備の大規模点群からの部材形状の抽出と認識（第3報）
重田航平; 増田 宏
Oral presentation, Japanese, 2020年度精密工学会秋季大会講演論文集
01 Sep. 2020 - TLS点群を用いた樹木形質の算出と精度評価
江藤 信輔; 増田 宏; 平岡裕一郎; 松下通也; 高橋誠
Oral presentation, Japanese, 第131回日本森林学会大会
29 Mar. 2020 - 工業設備の大規模点群からの部材形状の抽出と認識（第 2 報）
重田航平; 増田 宏
Oral presentation, Japanese, 2020年度精密工学会春季大会講演論文集
19 Mar. 2020 - 自律移動ロボットによる屋内生産設備の点群データ取得システム（第 2 報）
和田太一; 石川貴一朗; 増田 宏
Oral presentation, Japanese, 2020年度精密工学会春季大会講演論文集
19 Mar. 2020 - 移動計測データからの緊急車両の活動難所判定
中村隆三; 石川貴一朗; 田島晃太; 増田 宏
Oral presentation, Japanese, 2020年度精密工学会春季大会講演論文集
19 Mar. 2020 - 移動計測による点群と画像を用いた線状物体検出（第 3 報）
田島晃太; 増田 宏
Oral presentation, Japanese, 2020年度精密工学会春季大会講演論文集
19 Mar. 2020 - TLS 点群を用いた樹木形質の抽出と評価
江藤信輔; 増田 宏
Oral presentation, Japanese, 2020年度精密工学会春季大会講演論文集
19 Mar. 2020 - ３次元計測点群を用いた燃焼炉の劣化検出―点群画像による劣化検出手法の検討―
山本恵里佳; 葭内 郁; 増田 宏
Oral presentation, Japanese, 2019年度精密工学会秋季大会講演論文集
04 Sep. 2019 - 工業設備の大規模点群からの部材形状の抽出と認識
重田航平; 江藤信輔; 和田太一; 増田 宏
Oral presentation, Japanese, 2019年度精密工学会秋季大会講演論文集
04 Sep. 2019 - 点群データを用いた大型構造物の鋼材抽出とたわみ判定
葭内 郁; 増田 宏
Oral presentation, Japanese, 2019年度精密工学会秋季大会講演論文集
04 Sep. 2019 - 移動計測による点群と画像を用いた物体の抽出と分類
峯村晃平; 田島晃太; 松本裕稀; 増田 宏
Oral presentation, Japanese, 2019年度精密工学会秋季大会講演論文集
04 Sep. 2019 - ３次元点群を用いた杉の葉群形質の評価
平岡裕一郎; 江藤信輔; 松下通也; 高橋 誠; 増田 宏
Oral presentation, Japanese, 日本森林学会
22 Mar. 2019 - TLSを用いた樹木の形質調査のための形状処理手法
江藤信輔; 増田 宏; 平岡裕一郎; 松下通也; 高橋 誠
Oral presentation, Japanese, 日本森林学会
22 Mar. 2019 - 自律移動ロボットによる屋内生産設備の点群データ取得システム
和田太一; 鈴木晶也; 石川貴一朗; 増田 宏
Oral presentation, Japanese, 2019年度精密工学会春季大会講演論文集
15 Mar. 2019 - 点群データからの大型構造物の鋼材検出手法 (第2報)
葭内 郁; 篠崎有希; 増田 宏
Oral presentation, Japanese, 2019年度精密工学会春季大会講演論文集
15 Mar. 2019 - 機械学習を用いたガードレールの抽出と形状再構成
松本裕稀; 森 悠真; 増田 宏
Oral presentation, Japanese, 2019年度精密工学会春季大会講演論文集
15 Mar. 2019 - 移動計測による点群と画像を用いた線状物体検出（第2報）
田島晃太; 森 悠真; 増田 宏
Oral presentation, Japanese, 2019年度精密工学会春季大会講演論文集
15 Mar. 2019 - 大規模点群を用いた樹木の形質評価
江藤信輔; 松本裕稀; 緑川佳孝; 増田 宏
Oral presentation, Japanese, 2019年度精密工学会春季大会講演論文集
15 Mar. 2019 - 点群と画像を用いた道路周辺地物の自動認識
森 悠真; 増田 宏
Poster presentation, Japanese, Vision Engineering Workshop, Domestic conference
06 Dec. 2018 - 大規模環境の3次元計測とモデリング：レーザスキャナの性能向上と応用領域の拡大
増田 宏
Invited oral presentation, Japanese, 精密工学会, Invited, Domestic conference
07 Sep. 2018 - 移動計測による点群と画像を用いた線状物体検出（第1報）
田島晃太; 森 悠真; 増田 宏
Oral presentation, Japanese, 2018年度精密工学会秋季大会講演論文集
07 Sep. 2018 - 大規模点群を用いた樹木の算出と評価
江藤信輔; 緑川佳孝; 松本裕稀; 増田 宏
Oral presentation, Japanese, 2018年度精密工学会秋季大会講演論文集
07 Sep. 2018 - 柱状物体の点群処理に適した非剛体レジストレーション（第2報）
松本裕稀; 緑川佳孝; 増田 宏
Oral presentation, Japanese, 2018年度精密工学会秋季大会講演論文集
07 Sep. 2018 - 三次元計測点群を用いた大型構造物の劣化診断—検出精度と信頼性の評価—
篠崎有希; 増田 宏
Oral presentation, Japanese, 2018年度精密工学会秋季大会講演論文集
07 Sep. 2018 - 点群データからの大型構造物の鋼材検出手法
葭内 郁; 篠崎有希; 緑川佳孝; 増田 宏
Oral presentation, Japanese, 2018年度精密工学会秋季大会講演論文集
07 Sep. 2018 - 点群データを用いたスギにおける地上部形質の定量評価
平岡裕一郎; 齋藤和人; 松下通也; 高橋誠; 増田 宏
Oral presentation, Japanese, 日本森林学会
27 Mar. 2018 - 大規模点群データを用いた樹木の枝葉モデリング手法
齋藤 和人; 平岡裕一郎; 松下通也; 高橋 誠; 増田 宏
Oral presentation, Japanese, 日本森林学会
27 Mar. 2018 - 三次元計測に基づく燃焼炉の保守支援
篠崎有希; 増田 宏
Oral presentation, Japanese, 日本機械学会関東支部第24期講演会
17 Mar. 2018 - 切断点集合を用いた工業設備の高密度点群からの曲面抽出
緑川佳孝; 齋藤和人; 増田 宏
Oral presentation, Japanese, 日本機械学会関東支部第24期講演会
17 Mar. 2018 - 柱状物体に適した大規模点群のレジストレーションに関する研究
松本裕稀; 篠崎有希; 齋藤和人; 増田 宏
Oral presentation, Japanese, 関東学生会第57回学生員卒業研究発表講演会, Domestic conference
16 Mar. 2018 - 移動計測データからの路面の３次元形状モデル生成手法
辺春日; 森優真; 小平圭祐; 増田宏
Oral presentation, Japanese, 関東学生会第57回学生員卒業研究発表講演会, Domestic conference
16 Mar. 2018 - 点群画像を用いた道路縁石の抽出
辺春日; 森佑真; 小平圭祐; 増田宏
Oral presentation, Japanese, 2018年度精密工学会春季大会講演論文集
15 Mar. 2018 - 機械学習を用いた道路周辺地物の自動抽出
森佑真; 増田宏
Oral presentation, Japanese, 2018年度精密工学会春季大会講演論文集
15 Mar. 2018 - 断面推定に基づく大規模点群からの形状再構成(第4報)
緑川佳孝; 齋藤和人; 増田宏
Oral presentation, Japanese, 2018年度精密工学会春季大会講演論文集
15 Mar. 2018 - 柱状物体の点群処理に適した非剛体レジストレーション
松本裕稀; 緑川佳孝; 齋藤和人; 増田宏
Oral presentation, Japanese, 2018年度精密工学会春季大会講演論文集
15 Mar. 2018 - 高密度点群を用いた大型構造物の劣化診断 ～鉄塔の劣化判定～
篠崎有希; 増田宏
Oral presentation, Japanese, 2018年度精密工学会春季大会講演論文集
15 Mar. 2018 - 柱状物体に適し た TLS 点群のレ ジストレーショ ン
松本裕稀; 篠崎有希; 齋藤和人; 増田 宏
Oral presentation, Japanese, 2017年度精密工学会秋季大会講演論文集, 大阪大学, Domestic conference
20 Sep. 2017 - 円孔ターゲット によるレーザス キャナのスポッ ト径の推定
田中一郎; 増田 宏
Oral presentation, Japanese, 2017年度精密工学会秋季大会講演論文集, 大阪大学, Domestic conference
20 Sep. 2017 - 断面推定に基づ く大規模点群か らの形状再構成 （第 3 報）
緑川佳孝; 齋藤和人; 増田 宏
Oral presentation, Japanese, 2017年度精密工学会秋季大会講演論文集, 大阪大学, Domestic conference
20 Sep. 2017 - 点群データを用 いた構造物のた わみ判定
水口七海; 緑川佳孝; 小平圭祐; 増田 宏
Oral presentation, Japanese, 2017年度精密工学会秋季大会講演論文集, 大阪大学, Domestic conference
20 Sep. 2017 - 三次元計測点群 を用いた大型構 造物の劣化診断 （第 3 報）
篠崎有希; 小平圭祐; 増田 宏
Oral presentation, Japanese, 2017年度精密工学会秋季大会講演論文集, 大阪大学, Domestic conference
20 Sep. 2017 - 点群と画像を用 いた道路周辺地 物の自動分類手法（第 3 報）
森 悠真; 増田 宏
Oral presentation, Japanese, 2017年度精密工学会秋季大会講演論文集, 大阪大学, Domestic conference
20 Sep. 2017 - 立体視デバイス を用いた大規模 点群の高速描画
石橋寛史; 齋藤和人; 増田 宏
Oral presentation, Japanese, 2017年度精密工学会秋季大会講演論文集, 大阪大学, Domestic conference
20 Sep. 2017 - 大規模点群を用いた森林の樹木形状生成手法
齋藤 和人; 増田 宏; 平岡裕一郎; 松下通也; 高橋 誠
Oral presentation, Japanese, 2017年度日本森林学会大会
18 Mar. 2017 - 林木育種における新たな3次元点群処理技術の利用
平岡裕一郎; 松下通也; 高橋 誠; 齋藤 和人; 増田 宏
Poster presentation, Japanese, 2017年度日本森林学会大会
17 Mar. 2017 - 大規模点群に基づく樹木のパラメータ自動抽出
齋藤 和人; 増田 宏; 平岡裕一郎; 松下通也; 高橋 誠
Oral presentation, Japanese, 2017年度精密工学会春季大会講演論文集
13 Mar. 2017 - 点群画像を用いた移動計測データ処理
小平 圭祐; 増田 宏
Oral presentation, Japanese, 2017年度精密工学会春季大会講演論文集
13 Mar. 2017 - ３次元計測点群を用いた大型構造物の劣化診断（第２報）
篠崎有希; 鈴木晶也; 増田 宏; 鈴木晶也; 増田 宏
Oral presentation, Japanese, 2017年度精密工学会春季大会講演論文集
13 Mar. 2017 - 点群と画像を用いた道路周辺地物の自動分類手法（第２報）
森 悠真; 小平圭祐; 増田 宏
Oral presentation, Japanese, 2017年度精密工学会春季大会講演論文集
13 Mar. 2017 - 断面推定に基づく大規模点群からの形状再構成（第２報）
緑川佳孝; 齋藤和人; 増田 宏
Oral presentation, Japanese, 2017年度精密工学会春季大会講演論文集
13 Mar. 2017 - 点群画像を用いた移動計測データからのメッシュ生成手法
小平 圭祐; 増田 宏
Poster presentation, Japanese, Vision Engineering Workshop, Domestic conference
09 Dec. 2016 - 森林の大規模点群データに基づく樹幹の検出
齋藤 和人; 増田 宏
Poster presentation, Japanese, Vision Engineering Workshop, Domestic conference
08 Dec. 2016 - 三次元計測点群を用いた大型構造物の劣化診断
篠崎有希; 鈴木晶也; 増田 宏
Oral presentation, Japanese, 2016年度精密工学会秋季大会講演論文集, Domestic conference
06 Sep. 2016 - 点群と画像を用いた道路周辺地物の自動分類手法
森 悠真; 小平圭祐; 増田 宏
Oral presentation, Japanese, 2016年度精密工学会秋季大会講演論文集, Domestic conference
06 Sep. 2016 - 断面推定に基づく大規模点群からの形状再構成 ー大規模点群からの回転体曲面の抽出ー
緑川佳孝; 齋藤和人; 増田 宏
Oral presentation, Japanese, 2016年度精密工学会秋季大会講演論文集, Domestic conference
06 Sep. 2016 - 三次元計測点群に基づく樹木の形状再構成 第３報
齋藤和人; 増田 宏; 平岡裕一郎; 松下通也; 高橋 誠
Oral presentation, Japanese, 2016年度精密工学会秋季大会講演論文集, Domestic conference
06 Sep. 2016 - 大規模点群の衝突判定を用いた配置検討システム
丹羽 健; 増田 宏
Oral presentation, Japanese, 2016年度精密工学会春季大会講演論文集, Domestic conference
15 Mar. 2016 - 三次元計測点群に基づく樹木の形状再構成 第2報
齋藤和人; 丹羽 健; 増田 宏
Oral presentation, Japanese, 2016年度精密工学会春季大会講演論文集, Domestic conference
15 Mar. 2016 - 移動計測データからのメッシュ生成とセグメンテーション（第3報）
小平圭祐; 深野健太; 増田 宏
Oral presentation, Japanese, 2016年度精密工学会春季大会講演論文集, Domestic conference
15 Mar. 2016 - レーザ計測を用いた大型鋼板の工程の支援（第3報）
小林 中; 千田暁慧; 増田 宏
Oral presentation, Japanese, 2016年度精密工学会春季大会講演論文集, Domestic conference
15 Mar. 2016 - レーザ反射強度を用いた色付き点群の補正手法（第二報）
山川 徹; 深野健太; 増田 宏
Oral presentation, Japanese, 2016年度精密工学会春季大会講演論文集, Domestic conference
15 Mar. 2016 - 鋼板の曲げ加工プロセスにおける形状計測とモデリング
千田 暁慧; 増田 宏
Oral presentation, Japanese, 日本機械学会第25回設計工学・システム部門講演会, Domestic conference
23 Sep. 2015 - 大規模点群の立体視による目視検査システム
岡本 大樹; 増田 宏
Oral presentation, Japanese, 日本機械学会第25回設計工学・システム部門講演会, Domestic conference
23 Sep. 2015 - 点群処理技術の概要
増田 宏
Public discourse, Japanese, 精密工学会・大規模環境の３次元計測と認識・モデル化技術専門委員会・点群処理基礎技術講習会, Invited
16 Sep. 2015 - 三次元計測点群に基づく樹木の形状再構成
齋藤和人; 丹羽 健; 増田 宏
Oral presentation, Japanese, 2015年度精密工学会秋季大会講演論文集, Domestic conference
06 Sep. 2015 - 移動計測データからのメッシュ生成とセグメンテーション（第2報）
小平圭祐; 深野健太; 増田 宏
Oral presentation, Japanese, 2015年度精密工学会秋季大会講演論文集, Domestic conference
06 Sep. 2015 - 大規模点群の衝突判定を用いた経路探索シミュレーション（第2報）
丹羽 健; 増田 宏
Oral presentation, Japanese, 2015年度精密工学会秋季大会講演論文集, Domestic conference
05 Sep. 2015 - 移動計測ロボットのための最適計測位置の推定
鈴木晶也; 丹羽 健; 増田 宏; 石川貴一朗
Oral presentation, Japanese, 2015年度精密工学会秋季大会講演論文集, Domestic conference
05 Sep. 2015 - レーザ計測を用いた大型鋼板の工程の支援（第２報）—精度評価と非矩形形状への適用—
小林 中; 千田暁慧; 増田 宏
Oral presentation, Japanese, 2015年度精密工学会秋季大会講演論文集, Domestic conference
05 Sep. 2015 - 大規模点群のための高速な衝突判定とその応用
羽健
Public discourse, Japanese, 精密工学会・大規模環境の３次元計測と認識・モデル化技術専門委員会・研究会, Invited, 北海道, Domestic conference
28 Jul. 2015 - レーザ計測を用いた大型鋼板の工程の支援
董盈希; 千田暁慧; 増田 宏
Oral presentation, Japanese, 2015年度精密工学会春季大会講演論文集, Domestic conference
19 Mar. 2015 - 移動計測データに基づく地物分類のための学習データ生成手法（第2報）
深野健太; 増田 宏
Oral presentation, Japanese, 2015年度精密工学会春季大会講演論文集, Domestic conference
19 Mar. 2015 - レーザ反射強度を用いた色付き点群の補正手法
小野寺 亮; 増田 宏
Oral presentation, Japanese, 2015年度精密工学会春季大会講演論文集, Domestic conference
19 Mar. 2015 - 立体視に適した大規模点群のレンダリング（第 2 報）
岡本大樹; 丹羽 健; 増田 宏
Oral presentation, Japanese, 2015年度精密工学会春季大会講演論文集, Domestic conference
19 Mar. 2015 - 大規模点群の衝突判定を用いた経路探索シミュレーション
丹羽 健; 増田 宏
Oral presentation, Japanese, 2015年度精密工学会春季大会講演論文集, Domestic conference
19 Mar. 2015 - 大規模点群からの箱形形状の検出と再構成
千田暁慧; 増田 宏
Oral presentation, Japanese, 2015年度精密工学会春季大会講演論文集, Domestic conference
19 Mar. 2015 - 携帯型レーザスキャナを用いた大規模点群の詳細化
渡邉拓麻; 丹羽 健; 増田 宏
Oral presentation, Japanese, 2015年度精密工学会春季大会講演論文集, Domestic conference
19 Mar. 2015 - 移動計測データからのメッシュ生成とセ グメンテーション
渡邊健士; 深野健太; 増田 宏
Oral presentation, Japanese, 2015年度精密工学会春季大会講演論文集, 東京, Domestic conference
18 Mar. 2015 - レーザ計測による大型構造物の３Dモデル生成技術（基調講演）
増田 宏
Public discourse, Japanese, 第３回いわて３D プリンタ活用研究会, Invited, 岩手県立大学, 岩手県
16 Jan. 2015 - Shape Reconstruction of Large-Scale Environments from Laser Scanning Data
Hiroshi Masuda
Keynote oral presentation, English, International Conference on 3D Vision (3DV), Workshop on 3D Computer Vision in the Built Environment, Invited, 3DV, The University of Tokyo, http://www.3dimpvt.org/workshops/, International conference
09 Dec. 2014 - 点群処理技術の概要
増田宏
Public discourse, Japanese, 精密工学会「点群処理基礎技術講習会」, Invited, 精密工学会・大規模環境の３次元計測と認識・モデル化技術専門委員会, 東京大学, Domestic conference
24 Oct. 2014 - Advanced Shape Reconstruction of Engineering Plants Based on Terrestrial Laser Scanning
Hiroshi Masuda
Invited oral presentation, English, 3D Laser-Scanning and Imaging Symposium Japan 2014, Invited, 動体計測研究会＆精密工学会大規模環境の３次元計測と認識・モデル化技術専門委員会, 東京大学, International conference
26 Sep. 2014 - 移動計測データに基づく地物分類のための学習データ生成手法
深野健太; 増田宏
Oral presentation, Japanese, 2014年度精密工学会秋季大会講演論文集, Domestic conference
16 Sep. 2014 - 移動計測データを用いた道路周辺地物の形状再構成（第４報）
渡辺宇; 小栗昇悟; 増田宏
Oral presentation, Japanese, 2014年度精密工学会秋季大会講演論文集
16 Sep. 2014 - 立体視に適した大規模点群のレンダリング
岡本大樹; 丹羽健; 増田宏
Oral presentation, Japanese, 2014年度精密工学会秋季大会講演論文集
16 Sep. 2014 - 携帯型レーザスキャナを用いた大規模点群の補完手法
渡邉拓麻; 増田宏
Oral presentation, Japanese, 2014年度精密工学会秋季大会講演論文集
16 Sep. 2014 - 大規模点群に基づく生産設備の物体構成面の推定
千田暁慧; 増田宏
Oral presentation, Japanese, 2014年度精密工学会秋季大会講演論文集
16 Sep. 2014 - レーザ計測を用いた大型鋼板の曲率評価
董盈希; 千田暁慧; 増田宏
Oral presentation, Japanese, 2014年度精密工学会秋季大会講演論文集
16 Sep. 2014 - 大規模点群に基づく干渉判定システム
丹羽健; 増田宏
Oral presentation, Japanese, 2014年度精密工学会秋季大会講演論文集
16 Sep. 2014 - 大規模点群データに基づく形状の認識とモデル生成
増田宏
Public discourse, Japanese, 理研セミナー 「広範囲中長距離計測とそのデータ処理を知る」, Invited, 理化学研究所計 測情報処理研究チーム, 埼玉県和光市 理化学研究所大河内記念ホール, Domestic conference
23 May 2014 - ３次元計測に基づく認識とモデル化技術
増田 宏
Invited oral presentation, Japanese, 精密工学会・大規模環境の３次元計測と認識・モデル化技術専門委員会 第11回研究会, Domestic conference
14 Apr. 2014 - 移動計測データに基づく地物分類のための特徴量の同定手法
深野健太; 増田 宏
Oral presentation, Japanese, 2014年度精密工学会春季大会 学術講演会論文集, Domestic conference
19 Mar. 2014 - 移動計測データを用いた道路周辺地物の形状再構成（第３報）
小栗昇悟; 増田 宏
Oral presentation, Japanese, 2014年度精密工学会春季大会 学術講演会論文集, Domestic conference
19 Mar. 2014 - 大規模点群からのプラント設備の形状再構成（第2報）
松岡 諒; 増田 宏
Oral presentation, Japanese, 2014年度精密工学会春季大会 学術講演会論文集, Domestic conference
19 Mar. 2014 - 大規模点群における衝突判定法（第３報）
丹羽 健; 増田 宏
Oral presentation, Japanese, 2014年度精密工学会春季大会 学術講演会論文集, Domestic conference
19 Mar. 2014 - 大規模点群データに基づく認識とモデル化技術
増田 宏
Invited oral presentation, Japanese, 画像応用技術専門委員会 研究会報告 Vol.28, No.5, Invited, Domestic conference
17 Jan. 2014 - 情報技術を用いた社会インフラ強靭化の支援
増田 宏
Nominated symposium, Japanese, 社会インフラ強靭化のための研究開発戦略 ワークショップ, JST/CRDS
Dec. 2013 - 大規模点群を用いた生産ラインの改修支援システム
増田 宏; 平岡 美那子; 松岡諒
Oral presentation, Japanese, 2014年度 日本機械学会 設計工学・システム部門講演会
Oct. 2013 - 【基調講演】 工場・プラント設備の 3 次元計測と大規模点群処理
増田 宏
Others, Japanese, 精密工学会 第362回講習会「３Ｄモデルの価値を引き出す活用法 －もっと使って一歩先へ！」, 精密工学会 講習会
Oct. 2013 - 機械学習を用いた移動計測点群データの分類
深野健太; 増田 宏
Oral presentation, Japanese, 2013年度精密工学会秋季大会学術講演会講演論文集
Sep. 2013 - 移動計測データを用いた道路周辺地物の形状再構成（第２報）
小栗昇悟; 増田 宏
Oral presentation, Japanese, 2013年度精密工学会秋季大会学術講演会
Sep. 2013 - 大規模点群における衝突判定法（第２報）
丹羽健; 増田宏
Oral presentation, Japanese, 2013年度精密工学会秋季大会学術講演会
Sep. 2013 - 大規模点群からのプラント設備の形状再構成
松岡 諒; 増田 宏
Oral presentation, Japanese, 2013年度精密工学会秋季大会学術講演会
Sep. 2013 - 点群処理ライブラリ（PCL）の基礎
増田 宏
Others, Japanese, 精密工学会/大規模環境の３次元計測と認識・モデル化技術専門委員会/点群処理基礎技術講習会, 精密工学会/点群処理基礎技術講習会資料集
Sep. 2013 - 点群からの曲面計算
増田 宏
Others, Japanese, 精密工学会/大規模環境の３次元計測と認識・モデル化技術専門委員会/点群処理基礎技術講習会, 精密工学会/点群処理基礎技術講習会資料集
Sep. 2013 - 大規模環境の３次元計測による大規模点群処理
増田宏
Invited oral presentation, Japanese, 第18回計算工学講演会シンポジウム「ビッグデータのプリ・ポストプロセスの最新動向」, Invited, 計算工学会, Domestic conference
Jun. 2013 - 精密工学会 「大規模環境の３次元計測と認識・ モデル化技術専専門委員会」
増田宏
Others, Japanese, 第9回3次元計測フォーラム, SPAR2013J 第9回3次元計測フォーラム
Jun. 2013 - キーノート：大規模環境の３次元計測とモデリングの研究動向
増田宏
Oral presentation, Japanese, 2013年度精密工学会 春季大会学術講演会
Mar. 2013 - 大規模点群における衝突判定法
平岡美那子; 増田宏
Oral presentation, Japanese, 2013年度,精密工学会春季講演会学術講演会
Mar. 2013 - 不完全な曲面要素からの部材形状再構成
松岡諒; 増田宏
Oral presentation, Japanese, 2013年度精密工学会春季講演会学術講演会
Mar. 2013 - 移動計測データを用いた道路周辺地物の形状再構成
小栗昇悟; 敷地琢也; 増田宏
Oral presentation, Japanese, 2013年度精密工学会春季講演会学術講演会
Mar. 2013 - 移動計測データから車道と歩道の再構築
賀君; 増田宏
Oral presentation, Japanese, 2013年度精密工学会春季講演会学術講演会
Mar. 2013 - Random Forestを用いた道路周辺地物の分類
敷地琢也; 増田宏
Oral presentation, Japanese, 2013年度精密工学会春季講演会学術講演会
Mar. 2013 - 点群と画像を用いたプラント設備の３Dモデリング
増田宏; 松岡諒
Public symposium, Japanese, Vision Engineering Workshop (ViEW 2012), 精密工学会 画像応用技術専門委員会, 神奈川
Dec. 2012 - 車載型移動計測装置による点群データからの道路周辺地物の形状再構成
小栗昇吾; 増田
Public symposium, Japanese, 土木情報学シンポジウム, 土木学会, 東京
Sep. 2012 - レーザスキャナによる設備計測に適した曲面当てはめ手法
増田宏; 榎本昌一
Oral presentation, Japanese, 2012年度 精密工学会 秋季大会学術講演会
Sep. 2012 - シミュレーションに基づくレーザスキャンデータの球あてはめ手法の精度評価
田中一郎; 増田; 宏
Oral presentation, Japanese, 2012年度 精密工学会 秋季大会学術講演会
Sep. 2012 - 位相差方式レーザスキャナの計測誤差の評価と推定
榎本昌一; 増田; 宏
Oral presentation, Japanese, 2012年度 精密工学会 秋季大会学術講演会
Sep. 2012 - 大規模な移動計測データの高速表示とメッシュ生成
賀君 増田
Oral presentation, Japanese, 2012年度 精密工学会 秋季大会学術講演会
Sep. 2012 - 点群と画像の併用による移動計測データからの対話的な形状再構成
小栗昇吾; 増田
Oral presentation, Japanese, 2012年度 精密工学会 秋季大会学術講演会
Sep. 2012 - 大規模点群からのトーラスと楕円体の抽出
松岡諒 増田宏
Oral presentation, Japanese, 2012年度精密工学会 秋季大会学術講演会
Sep. 2012 - 移動計測データのセグメンテーションと地物形状抽出(第2報)
池田邦彦; 小栗昇悟; 増田宏
Oral presentation, Japanese, 2012年度 精密工学会 春季大会学術講演会
Mar. 2012 - 移動計測データからの3次元道路モデルの構築
賀君 増田宏
Oral presentation, Japanese, 2012年度 精密工学会 春季大会学術講演会
Mar. 2012 - 複数のレーザスキャナによる平面計測精度の比較
榎本昌一; 小栗昇悟; 増田 宏 田中一郎
Oral presentation, Japanese, 2012年度 精密工学会 春季大会学術講演会
Mar. 2012 - レーザスキャナを用いた球の位置測定精度評価
佐藤昌幸; 佐藤友哉; 田中; 一郎; 榎本; 昌一 増田 宏
Oral presentation, Japanese, 2012年度 精密工学会 春季大会学術講演会
Mar. 2012 - 大規模点群からの曲面抽出に基づく生産設備の形状再構成
増田宏; 松岡
Oral presentation, Japanese, 2012年度 精密工学会 春季大会学術講演会
Mar. 2012 - 大規模3次元環境計測データのための形状処理技術
増田宏
Public symposium, Japanese, 精密工学会秋季講演会 シンポジウム, 精密工学会秋季講演会 シンポジウム, 金沢大学
Sep. 2011 - キーノートスピーチ：サイバーフィールド構築技術研究の構成
増田宏
Oral presentation, Japanese, 2011年度 精密工学会 秋季大会学術講演会, 金沢大学
Sep. 2011 - 大規模点群の平滑化と評価
池田邦彦; 増田宏
Oral presentation, Japanese, 2011年度 精密工学会 秋季大会学術講演会, 金沢大学
Sep. 2011 - 複数のレーザ計測点群からの曲面抽出
増田宏; 阿部佑二
Oral presentation, Japanese, 2011年度 精密工学会 秋季大会学術講演会, 金沢大学
Sep. 2011 - 位相差方式レーザスキャナを用いた球の位置測定精度評価 (第3報)
田中一郎; 石津秀人; 榎本昌一; 増田宏
Oral presentation, Japanese, 2011年度 精密工学会 秋季大会学術講演会, 金沢大学
Sep. 2011 - 移動計測データのセグメンテーションと地物形状抽出
池田邦彦; 山下沙綾; 増田宏
Oral presentation, Japanese, 2011年度 精密工学会 秋季大会学術講演会, 金沢大学
Sep. 2011 - 移動計測データからの路面形状の抽出と表現
賀 君; 増田宏
Oral presentation, Japanese, 2011年度 精密工学会 秋季大会学術講演会, 金沢大学
Sep. 2011 - モバイルマッピングデータからの自動地物抽出
増田宏
Oral presentation, Japanese, 動体計測/精密工学会サイバーフィールド合同研究会, 東京
Jul. 2011 - キーノートスピーチ：サイバーフィールド構築技術研究の展開
増田宏
Oral presentation, Japanese, 2011年度 精密工学会 春季大会学術講演会, 東京
Mar. 2011 - 大規模点群からのエッジ抽出を用いた円柱面と矩形面の検出 (第２報)
阿部佑二; 池田邦彦; 増田宏
Oral presentation, Japanese, 2011年度 精密工学会 春季大会学術講演会, 東京
Mar. 2011 - 移動計測データからの地物形状抽出
山下沙綾; 池田邦彦; 増田宏
Oral presentation, Japanese, 2011年度 精密工学会 春季大会学術講演会, 東京
Mar. 2011 - レーザスキャナの誤差モデルに基づく異常値除去
布村壮太; 増田宏; 田中一郎
Oral presentation, Japanese, 2011年度 精密工学会 春季大会学術講演会, 東京
Mar. 2011 - GPU を用いた大規模点群の平滑化 (第２報)
池田邦彦; 増田宏
Oral presentation, Japanese, 2011年度 精密工学会 春季大会学術講演会, 東京
Mar. 2011 - ３D顕微計測データを用いたナノ・マイクロ形状モデリング Modeling: Nanoプロジェクトの提案
三浦憲二郎; 臼杵深; 山下淳; 増田宏
Oral presentation, Japanese, 2011年度 精密工学会 春季大会学術講演会, 東京
Mar. 2011 - 位相差方式レーザスキャナを用いた球の位置計測制度評価 (第２報)
石津秀人; 森山皓太; 田中一郎; 増田宏
Oral presentation, Japanese, 2011年度 精密工学会 春季大会学術講演会, 東京
Mar. 2011 - 大規模点群を用いた３次元形状モデリング
増田宏
Oral presentation, Japanese, 動体計測研究会,第99回動体計測研究会, 東京
Jan. 2011 - 大規模点群からのエッジ抽出を用いた円柱面と矩形面の検出
松沼千央; 阿部佑二; 増田宏
Oral presentation, Japanese, 2010年度 精密工学会 秋季大会学術講演会, 名古屋
Sep. 2010 - 複数視点に対する大規模点群データの統合処理
河内陽介; 臼杵 深; 三浦憲二郎; 増田宏; 田中一郎
Oral presentation, Japanese, 2010年度 精密工学会 秋季大会学術講演会, 名古屋
Sep. 2010 - GPUを用いた大規模点群の平滑化
池田邦彦; 増田 宏
Oral presentation, Japanese, 2010年度 精密工学会 秋季大会学術講演会, 名古屋
Sep. 2010 - 位相差方式レーザスキャナを用いた球の位置精度評価
石津秀人; 森山皓太; 阿部佑二; 増田宏
Oral presentation, Japanese, 2010年度 精密工学会 秋季大会学術講演会, 名古屋
Sep. 2010 - 大規模点群からの既知部品の検出とパラメータの同定
藤井智; 増田宏
Oral presentation, Japanese, 2010年度 精密工学会 春季大会学術講演会, 東京
Mar. 2010
Courses
- マシンデザインB
The University of Electro-Communications - マシンデザインB
電気通信大学 - 設計システム工学特論
The University of Electro-Communications - 設計工学
The University of Electro-Communications - マシンデザイン II
The University of Electro-Communications - マシンデザイン II
電気通信大学 - 設計工学特論
The University of Electro-Communications - 設計工学特論
電気通信大学 - 設計システム工学特論
The University of Electro-Communications - 設計システム工学特論
電気通信大学 - マシンデザインIＩ
The University of Electro-Communications - マシンデザインIＩ
電気通信大学 - 設計工学
The University of Electro-Communications - 設計工学
電気通信大学
