WATANABE TOSHINORI

Emeritus Professor etc.Emeritus Professor
  • Profile:
    A. Information Systems research & development at HITACHI Ltd.

    (1) Management and production support systems,

    (2) LSI design automation systems (Circuit rewriting, function simulation, Layout design),

    (3) Nonlinear programming system and its applications to automatic circuit device modelling,

    (4) Design and implementation of a Parallel LSI layout problem solver in FGCS (Fifth Generation Computer Project)

    (5) Learning machine TAMPOPO and its application to an fully autonomous resource managing OS.

    B. After coming to UEC

    (6) Adaptive information systems (Automatic knowledge discovery and applicatons to multimedia data

    analyses),

    (7) Event systems (Representation and analysis of (Information) systems from the viewpoint of events).

Degree

  • Dr.Eng., The University of Tokyo

Research Keyword

  • System Semantics
  • Distributed Concurrent Systems
  • Web Analysis
  • Image Processing
  • Adaptive Systems
  • Information Systems
  • System Design
  • System Modeling
  • システム意味論
  • 並行分散システム
  • Web処理
  • 画像処理
  • 適応システム
  • 情報システム
  • システム設計
  • システムモデリング

Field Of Study

  • Informatics, Intelligent informatics

Educational Background

  • Jun. 1971
    The University of Tokyo, Faculty of Engineering, 航空学科

Member History

  • 1986
    学会誌編集委員 論文査読委員, 情報処理学会, Society

Paper

  • An effective Method for Image Matching based on modified LBP and SIFT
    YiNan Wang; Nuo Zhang; Toshinori Watanabe; Hisashi Koga
    Proc. VISIGRAPP 2012, 2012, 410-413, Feb. 2012, Peer-reviwed
    International conference proceedings, English
  • Texture Image Analysis Using LBP and Data Compression
    Nuo Zhang; Toshinori Watanabe
    Proc. VISIGRAPP 2012, 7, 24-26, 2012, Peer-reviwed
    International conference proceedings, English
  • MIXED-LSH: Reduction of Remote Accesses in Distributed Locality-Sensitive Hashing based on L-1-distance
    Hisashi Koga; Masayuki Oguri; Toshinori Watanabe
    2012 IEEE 26TH INTERNATIONAL CONFERENCE ON ADVANCED INFORMATION NETWORKING AND APPLICATIONS (AINA), IEEE, 26, 175-182, 2012, Peer-reviwed, Locality-Sensitive Hashing (LSH) is a well-known approximate nearest-neighbor search algorithm for high-dimensional data. Though LSH searches nearest-neighbor points for a query very fast, LSH has a drawback that the space complexity is very large. For this reason, so as to apply LSH to a large dataset, it is crucial to implement LSH in distributed environments which consist of multiple nodes. One simple and natural method to implement LSH in the distributed environment is to have every node keep the same number of hash tables. However, this method increases remote accesses, because many nodes are accessed to access all the hash tables. Thus, this simple method will suffer from the long query response time, if the communication delay is the bottleneck. This paper proposes to reduce remote accesses by assigning hash buckets smartly to the nodes. In particular, our method assigns hash buckets from different hash tables to the same node, if the hash buckets store the same points. Due to this strategy, our method can access multiple hash buckets that should be accessed in processing a query with a single remote access, thereby decreasing remote accesses.
    International conference proceedings, English
  • CTFI: Adaptive Pattern Analysis of Internet Traffic Using Time Series Compressibility
    Ushio Ozeki; Toshinori Watanabe; Hisashi Koga
    Proc. IWSSIP 2012, 2012, 2012, Peer-reviwed
    International conference proceedings, English
  • Scalable Object Discovery: A Hash-Based Approach to Clustering Co-occurring Visual Words
    Gibran Fuentes Pineda; Hisashi Koga; Toshinori Watanabe
    IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS, IEICE-INST ELECTRONICS INFORMATION COMMUNICATIONS ENG, E94D, 10, 2024-2035, Oct. 2011, Peer-reviwed, We present a scalable approach to automatically discovering particular objects (as opposed to object categories) from a set of images. The basic idea is to search for local image features that consistently appear in the same images under the assumption that such co-occurring features underlie the same object. We first represent each image in the set as a set of visual words (vector quantized local image features) and construct an inverted file to memorize the set of images in which each visual word appears. Then, our object discovery method proceeds by searching the inverted file and extracting visual word sets whose elements tend to appear in the same images; such visual word sets are called co-occurring word sets. Because of unstable and polysemous visual words, a co-occurring word set typically represents only a part of an object. We observe that co-occurring word sets associated with the same object often share many visual words with one another. Hence, to obtain the object models, we further cluster highly overlapping co-occurring word sets in an agglomerative manner. Remarkably, we accelerate both extraction and clustering of co-occurring word sets by Min-Hashing. We show that the models generated by our method can effectively discriminate particular objects. We demonstrate our method on the Oxford buildings dataset. In a quantitative evaluation using a set of ground truth landmarks, our method achieved higher scores than the state-of-the-art methods.
    Scientific journal, English
  • New Dissimilarity Measure for Recognizing Noisy Subsequence Trees
    Hisashi Koga; Hiroaki Saito; Toshinori Watanabe; Takanori Yokoyama
    INTERNATIONAL JOURNAL OF INTELLIGENT SYSTEMS, WILEY-BLACKWELL, 26, 5, 474-496, May 2011, Peer-reviwed, Tree is a data structure used to express various objects such as semistructured data and genes. When objects are represented as trees, computing tree similarity is essential for pattern recognition and retrieval. This paper considers the noisy subsequence tree recognition problem whose purpose is to recognize the original tree, given its noisy subsequence tree. Previous research on this problem relied on constrained tree edit distance to measure the dissimilarity. However, the number of relabelings must be predetermined to compute it.
    This paper proposes a new dissimilarity measure for this problem. Our dissimilarity measure is obtained by counting the node edit operations included in the unit-cost tree edit distance that contribute to the matching of node labels. The number of relabelings need not be specified to compute our dissimilarity measure. Moreover, our measure achieves more accurate recognition performance and faster execution speed than the constrained tree edit distance. Our measure is also useful to solve the tree inclusion problem which is the problem of deciding whether a tree includes another tree and shows the extent of approximate tree inclusion when a tree incompletely includes another tree. (C) 2011 Wiley Periodicals, Inc.
    Scientific journal, English
  • Text-Transformed Image Classification Based on Data Compression
    Nuo Zhang; Toshinori Watanabe
    International Conference on Data Engineering and Internet Technology (DEIT 2011),, 742-747, Mar. 2011, Peer-reviwed
    International conference proceedings, English
  • Compression-Based Dendrogram Aping for Classifier Generation
    S. Kobayashi; T. Watanabe; H. Koga
    Proc. ESA-EUSC-JRC 2011, 33-36, Mar. 2011, Peer-reviwed
    International conference proceedings, English
  • High speed computation of approximate image-MST
    Weng HongBing; T.Watanabe; H.Koga
    Proc. ESA-EUSC-JRC 2011, 125-128, Mar. 2011, Peer-reviwed
    International conference proceedings, English
  • Noisy Vector Elimination by Bi-Directional Zero Comparison
    Takanori Yokoyama; Toshinori Watanabe
    Lecture Notes in Computer Science, (LNCS), Vol.6468-6469, Nov. 2010, Peer-reviwed
    International conference proceedings, English
  • New Application of Graph Mining to Video Analysis
    H. Koga; T. Tsuji; T. Yokoyama; T. Watanabe
    Proc. IDEAL2010, 11, Sep. 2010
    International conference proceedings, English
  • Hash-based Object Discovery by Clustering Frequent Visual Word Sets, Gibran Fuentes Pineda
    Gibran Fuentes Pineda; Hisashi Koga; Toshinori Watanabe
    Proc. ICPR2010, ICPR2010, Aug. 2010, Peer-reviwed
    International conference proceedings, English
  • パッシブRTT推定法を使用したAQMアルゴリズム''
    星原 隼人; 古賀 久志; 渡辺 俊典
    情報処理学会論文誌, Vol. 51, No. 2, pp. 466-477, 2010年2月, 51, 2, Feb. 2010, Peer-reviwed
    Scientific journal, Japanese
  • 頻出グラフマイニングを利用した動画像解析
    辻 智和; 古賀久志; 横山貴紀; 渡辺俊典
    電子情報通信学会論文誌D, Vol. J93-D, No. 2, pp. 86-99, 2010年2月, D, Vol. J93-D, 2, Feb. 2010, Peer-reviwed
    Scientific journal, Japanese
  • Object discovery by clustering correlated visual word sets
    Gibran Fuentes Pineda; Hisashi Koga; Toshinori Watanabe
    Proceedings - International Conference on Pattern Recognition, 750-753, 2010, This paper presents a novel approach to discovering particular objects from a set of unannotated images. We aim to find discriminative feature sets that can effectively represent particular object classes (as opposed to object categories). We achieve this by mining correlated visual word sets from the bag-of-features model. Specifically, we consider that a visual word set belongs to the same object class if all its visual words consistently occur together in the same image. To efficiently find such sets we apply Min-LSH to the occurrence vector of the each visual word. An agglomerative hierarchical clustering is further performed to eliminate redundancy and obtain more representative sets. We also propose a simple and efficient strategy for quantizing the feature descriptors based on locality-sensitive hashing. By experiment, we show that our approach can efficiently discover objects against cluster and slight viewpoint variations. © 2010 IEEE.
    International conference proceedings, English
  • Image representation and classification based on data compression
    Nuo Zhang; Toshinori Watanabe
    Proceedings of the ACM Symposium on Applied Computing, 25, 1, 981-982, 2010, Peer-reviwed, With the development of the information technology, the number of different electronic information has been increased rapidly. In which, for enormous number of digital images the demand of automatic classification technology exceeded human processing capacity. As an automatic classification technique, representing and classifying text-transformed image based on data compression is proposed in this paper. In the step of transforming image into text, image is divided into segments which are replaced as characters. Then, the similarity between compressibility vectors is used in the classification step. In which, we focus on the compressibility of the text string. Finally, the effectivity of the proposed method is verified in our experiments. © 2010 ACM.
    International conference proceedings, English
  • Documents Representation Based on Independent Compressibility Feature Space
    Nuo Zhang; Toshinori Watanabe
    Proceedings of ICAART'10, INSTICC, 10, 1, 217-222, 2010, Peer-reviwed
    International conference proceedings, English
  • New Application of Graph Mining to Video Analysis
    Hisashi Koga; Tsuji Tomokazu; Takanori Yokoyama; Toshinori Watanabe
    INTELLIGENT DATA ENGINEERING AND AUTOMATED LEARNING - IDEAL 2010, SPRINGER-VERLAG BERLIN, 6283, 86-93, 2010, Peer-reviwed, Given a graph, frequent graph mining extracts subgraphs appearing frequently as useful knowledge. This paper proposes to exploit graph mining that discovers knowledge without supervision to realize unsupervised image analysis. In particular, we present a background subtraction algorithm from videos in which the background model is acquired without supervision. The targets of our algorithm are videos in which a moving object passes in front of a surveillance camera. After transforming each video frame into a region adjacency graph, our method discovers the subgraph representing the background, exploiting the fact that the background appears in more frames than the moving object.
    International conference proceedings, English
  • Document Relation Analysis Based on Compressibility Vector
    Nuo Zhang; Daisuke Matsuzaki; Toshinori Watanabe; Hisashi Koga
    Proceedings of ICAART09, 255-260, Jan. 2009, Peer-reviwed
    International conference proceedings, English
  • Noisy MPEG Motion Vector Reduction for Motion Analysis
    Takanori Yokoyama; Shuhei Ota; Toshinori Watanabe
    AVSS: 2009 6TH IEEE INTERNATIONAL CONFERENCE ON ADVANCED VIDEO AND SIGNAL BASED SURVEILLANCE, IEEE, 6, 274-279, 2009, Peer-reviwed, In MPEG standards, motion compensation is used for inter-frame compression. Motion compensation generates motion vectors in order to predict the current frame regions from previously decoded frames. These motion vectors represent motion information between regions in different frames and are useful in motion analysis. However, the motion vectors of homogeneous, low-textured, and line regions tend to be unstable and noisy; therefore, it becomes difficult to conduct motion analysis. In this paper, we propose a noisy motion vector reduction method for motion analysis using MPEG motion vectors by introducing a global motion estimation method and a zero-comparison method. The proposed method outputs local motion vectors that are free of noise and high-quality global motion vectors that can be used for object detection, tracking, etc. Further, this method works even for videos captured by a moving camera. We demonstrate the effectiveness of the proposed method through several experiments using actual videos.
    International conference proceedings, English
  • Motion Vector Based Moving Object Detection and Tracking in the MPEG Compressed Domain
    Takanori Yokoyama; Toshiki Iwasaki; Toshinori Watanabe
    CBMI: 2009 INTERNATIONAL WORKSHOP ON CONTENT-BASED MULTIMEDIA INDEXING, IEEE, 201-206, 2009, Peer-reviwed, As MPEG standards prevail, the opportunities to handle MPEG compressed videos increase, and the video indexing and management that can directly process the compressed videos become important. MPEG video coding standards use motion compensation to compress video data, and the motion compensation generates motion vectors that contain motion information similar to optical flows between regions in different frames. Although motion vectors are useful for video analysis, they are not always generated along moving objects, and it is difficult to analyze moving objects using only these vectors. In this paper, we propose a moving object detection and tracking method in the MPEG compressed domain for video surveillance and management. In our method, we introduce images that record moving regions and accumulate unmoving regions in which the moving objects are expected to exist after the current frame. By utilizing these images, we can detect and track moving objects using only motion vectors even if the motion vectors of moving objects become zero vectors due to their behaviors and are lost due to their picture type. We demonstrate the effectiveness of the proposed method through several experiments using actual videos acquired by an MPEG video camera.
    International conference proceedings, English
  • Noisy MPEG Motion Vector Reduction for Motion Analysis
    Takanori Yokoyama; Shuhei Ota; Toshinori Watanabe
    AVSS: 2009 6TH IEEE INTERNATIONAL CONFERENCE ON ADVANCED VIDEO AND SIGNAL BASED SURVEILLANCE, IEEE, 274-279, 2009, In MPEG standards, motion compensation is used for inter-frame compression. Motion compensation generates motion vectors in order to predict the current frame regions from previously decoded frames. These motion vectors represent motion information between regions in different frames and are useful in motion analysis. However, the motion vectors of homogeneous, low-textured, and line regions tend to be unstable and noisy; therefore, it becomes difficult to conduct motion analysis. In this paper, we propose a noisy motion vector reduction method for motion analysis using MPEG motion vectors by introducing a global motion estimation method and a zero-comparison method. The proposed method outputs local motion vectors that are free of noise and high-quality global motion vectors that can be used for object detection, tracking, etc. Further, this method works even for videos captured by a moving camera. We demonstrate the effectiveness of the proposed method through several experiments using actual videos.
    International conference proceedings, English
  • Documents clustering based on optimized compressibility vector space
    Nuo Zhang; Toshinori Watanabe
    Proceedings - 2009 International Conference on Computational Intelligence and Software Engineering, CiSE 2009, 1, 1, 2009, Peer-reviwed, To access and store large-scale electrical documents becomes possible due to the high performance of computer hardware and broadband accessible network. In order to handle these increasing number of documents properly, a efficient document representation model is as important as the classification algorithms. Several text representation methods, such as bagof-words and N-gram models, have been widely used. Another representation approach named pattern representation scheme using data compression (PRDC) has been proposed lately. It does not only independently process data of linguistic text, but also processes multimedia data effectively. In this study, we will propose a method to improve PRDC approach and compare it with the two aforementioned methods. The performances will be compared in terms of clustering ability. Experiment results will show that the proposed method can provide better performance than that of the other two methods and also the PRDC. ©2009 IEEE.
    International conference proceedings, English
  • Unsupervised Object Discovery from Images by Mining Local Features Using Hashing
    Gibran Fuentes Pineda; Hisashi Koga; Toshinori Watanabe
    PROGRESS IN PATTERN RECOGNITION, IMAGE ANALYSIS, COMPUTER VISION, AND APPLICATIONS, PROCEEDINGS, SPRINGER-VERLAG BERLIN, 5856, 978-985, 2009, Peer-reviwed, In this paper, we propose a new methodology for efficiently discovering objects from images without supervision. The basic idea is to search for frequent patterns of closely located features in a set of images and consider a frequent pattern as a meaningful object class. We develop a system for discovering objects from segmented images. This system is implemented by hashing only. We present experimental results to demonstrate the robustness and applicability of our approach.
    International conference proceedings, English
  • Motion Vector Based Moving Object Detection and Tracking in the MPEG Compressed Domain
    Takanori Yokoyama; Toshiki Iwasaki; Toshinori Watanabe
    CBMI: 2009 INTERNATIONAL WORKSHOP ON CONTENT-BASED MULTIMEDIA INDEXING, IEEE, 1, 201-206, 2009, Peer-reviwed, As MPEG standards prevail, the opportunities to handle MPEG compressed videos increase, and the video indexing and management that can directly process the compressed videos become important. MPEG video coding standards use motion compensation to compress video data, and the motion compensation generates motion vectors that contain motion information similar to optical flows between regions in different frames. Although motion vectors are useful for video analysis, they are not always generated along moving objects, and it is difficult to analyze moving objects using only these vectors. In this paper, we propose a moving object detection and tracking method in the MPEG compressed domain for video surveillance and management. In our method, we introduce images that record moving regions and accumulate unmoving regions in which the moving objects are expected to exist after the current frame. By utilizing these images, we can detect and track moving objects using only motion vectors even if the motion vectors of moving objects become zero vectors due to their behaviors and are lost due to their picture type. We demonstrate the effectiveness of the proposed method through several experiments using actual videos acquired by an MPEG video camera.
    International conference proceedings, English
  • MPEGビデオデータの動きベクトルを用いた圧縮領域における移動物体の検出と追跡
    岩崎敏紀; 横山貴紀; 渡辺俊典; 古賀久志
    電子情報通信学会論文誌D, J91-D, 6, 1592-1603, Jun. 2008, Peer-reviwed
    Scientific journal, Japanese
  • 近傍集合表現を利用した画像からのオブジェクト抽出
    古賀 久志; 杉山 英行; 杉内 崇浩; 渡辺 俊典; 横山 貴紀
    電子情報通信学会論文誌D, J91-D, 5, 1418-1433, May 2008, Peer-reviwed
    Scientific journal, Japanese
  • Proposal of an Integrated Management Model to Reinforce IS Organizations
    K. Uchida; T. Watanabe
    J. of IPSJ, 49, 2, 910-921, Feb. 2008, Peer-reviwed
    Scientific journal, Japanese
  • 超解像処理を用いたブレ画像修復手法
    牟田桂介; 横山貴紀; 渡辺俊典; 古賀久志
    電子情報通信学会論文誌 D, Vol.J90-D, No.6, pp., 2007年6月., J90-D, 06, 1532-1541, Jun. 2007
    Scientific journal, Japanese
  • Fast agglomerative hierarchical clustering algorithm using Locality-Sensitive Hashing
    Hisashi Koga; Tetsuo Ishibashi; Toshinori Watanabe
    KNOWLEDGE AND INFORMATION SYSTEMS, SPRINGER LONDON LTD, 12, 1, 25-53, May 2007, Peer-reviwed, The single linkage method is a fundamental agglomerative hierarchical clustering algorithm. This algorithm regards each point as a single cluster initially. In the agglomeration step, it connects a pair of clusters such that the distance between the nearest members is the shortest. This step is repeated until only one cluster remains. The single linkage method can efficiently detect clusters in arbitrary shapes. However, a drawback of this method is a large time complexity of O(n(2)), where n represents the number of data points. This time complexity makes this method infeasible for large data. This paper proposes a fast approximation algorithm for the single linkage method. Our algorithm reduces the time complexity to O(nB) by rapidly finding the near clusters to be connected by Locality-Sensitive Hashing, a fast algorithm for the approximate nearest neighbor search. Here, B represents the maximum number of points going into a single hash entry and it practically diminishes to a small constant as compared to n for sufficiently large hash tables. Experimentally, we show that (1) the proposed algorithm obtains clustering results similar to those obtained by the single linkage method and (2) it runs faster for large data than the single linkage method.
    Scientific journal, English
  • 投票機構による動作オブジェクトのオンラインリアルタイム学習と認識
    吉岡泰智; 渡辺俊典; 古賀久志; 横山貴紀
    電子情報通信学会和文論文誌, J90-D, No.1, 83-93, Jan. 2007, Peer-reviwed
    Scientific journal, Japanese
  • DR Image and Fractal Correlogram: A New Image Feature Representation Based on Fractal Codes and Its Application to Image Retrieval
    Takanori Yokoyama; Toshinori Watanabe
    LNCS, 4351, 428-439, Jan. 2007, Peer-reviwed
    International conference proceedings, English
  • A novel document analysis method using compressibility vector
    Nuo Zhang; Toshinori Watanabe; Daisuke Matsuzaki; Hisashi Koga
    PROCEEDINGS OF THE FIRST INTERNATIONAL SYMPOSIUM ON DATA, PRIVACY, AND E-COMMERCE, IEEE COMPUTER SOC, 38-+, 2007, Peer-reviwed, Similarity analysis and keyword extraction are widely used as document relation analysis techniques. These methods are based on dictionary-base morphological analysis. However they cannot meet the need when Internet grows fast and new words appear but dictionary can not be renewed fast enough. In this study, we propose a new document relation analysis method based on the document's compressibility. The effectiveness of the proposed method will be examined in simulations.
    International conference proceedings, English
  • Moving region detection by transportation problem solving
    Takanori Yokoyama; Sho Furukawa; Toshinori Watanabe
    ISM 2007: NINTH IEEE INTERNATIONAL SYMPOSIUM ON MULTIMEDIA, PROCEEDINGS, IEEE COMPUTER SOC, 86-91, 2007, Peer-reviwed, In this paper we propose a novel moving region detection method from the viewpoint of solving the transportation problem. This method extracts the relations between regions as a solution to the transformation problem between pixels belonging to adjacent frames. Moving regions are detected by utilizing the properties of these relations. This method does not require any models such as prior knowledge or particular assumptions about moving objects or backgrounds in a video. Since the method adaptively detects moving regions from input frame data, it can deal with the fluctuations of moving objects or backgrounds. We demonstrate the effectiveness of the proposed method through several experiments conducted using actual videos.
    International conference proceedings, English
  • A New Similarity Measure between Trees by Decomposition of Unit-cost Edit Distance
    H. Koga; H. Saito; T. Watanabe; Y. Yokoyama
    Springer LNCS: Proc. 8th International Conference on Intelligent Data Engineering and Automated Learning, LNCS 4881, 643-652, 2007, Peer-reviwed
    International conference proceedings, English
  • A New Stable AQM Algorithm exploiting RTT Estimation
    Hayato Hoshihara; Hisashi Koga; Toshinori Watanabe
    Proc. IEEE Conference on Local Computer Networks (LCN), 143-150, Nov. 2006, Peer-reviwed
    International conference proceedings, English
  • Similarity-Based Retrieval Method for Fractal Coded Images in the Compressed Data Domain
    Takanori Yokoyama; Toshinori Watanabe; Hisashi Koga
    CIVR 2005, LNCS, 3568, 385-394, Jul. 2005, Peer-reviwed
    International conference proceedings, English
  • Similarity-Based Retrieval Method for Fractal Coded Images in the Compressed Data Domain
    Takanori Yokoyama; Toshinori Watanabe; Hisashi Koga
    LNCS3568, 385-394, Jul. 2005
    International conference proceedings, English
  • Locality-Sensitive Hashingを用いた階層的クラスタリング手法
    石橋徹夫; 古賀久志; 渡辺俊典
    電子情報通信学会論文誌, J88-D-Ⅰ, 4, 852—863, Apr. 2005, Peer-reviwed
    Scientific journal, Japanese
  • Similarity-Based Retrieval Method for Fractal Coded Images in the Compressed Data Domain
    Takanori Yokoyama; Toshinori Watanabe; Hisashi Koga
    LNCS3568, 385-394, 2005, Peer-reviwed
    International conference proceedings, English
  • 画像の最小全域木の局所構造に着目し たアピアランスベース3D物体認識手法
    朝日和哉; 渡辺俊典; 菅原 研; 横山貴紀
    電子情報通信学会論文誌, J87-D-Ⅱ, 6, 1279—1288, Jun. 2004, Peer-reviwed
    Scientific journal, Japanese
  • Collecting Behavior of Interacting Robots with Virtual Pheromone
    T. Kazama; K. Sugawara; T. Watanabe
    Proc. of the 7th Intl. Symposium on Distributed Robotic Systems, 331-340, Jun. 2004, Peer-reviwed
    International conference proceedings, English
  • フラクタル符号に基づく圧縮領域における類似画像検索手法
    横山貴紀; 菅原 研; 渡辺俊典
    情報処理学会論文誌 データベース, 45, SIG4(TOD21), 11-22, Mar. 2004, Peer-reviwed
    Scientific journal, Japanese
  • 最小全域木の適応閾値切断による画像分割方式
    角田夏貴; 渡辺俊典; 菅原研
    電子情報通信学会論文誌, J87-D-II, No. 2, 586-594, 2004, Peer-reviwed
    Scientific journal, Japanese
  • Similarity-based image retrieval system using partitioned iterated function system codes
    T. Yokoyama; K. Sugawara; T. Watanabe
    Artificial Life Robotics, 8, 118-122, 2004
    Scientific journal, English
  • Image Retrieval Exploiting the Similarity of Vectorized Fractal Code Sets
    Takanori Yokoyama; Toshinori Watanabe; Hisashi Koga
    SCIS&ISIS 2004, 2004, Peer-reviwed
    International conference proceedings, English
  • Fast Hierarchical Clustering Algorithm Using Locality-Sensitive Hashing
    H.Koga; T. Itabashi; T. Watanabe
    Proc. of the DS 2004, LNAI, 3245, 114-128, 2004, Peer-reviwed
    International conference proceedings, English
  • Similarity-based Image Retrieval System Using PIFS Codes
    Takanori Yokoyama; Toshinori Watanabe; Ken Sugawara
    Proc. Artificial Life and Robotics, 106-109, Jan. 2003
    International conference proceedings, English
  • A Study on Foraging Behavior of Simple Multi-robot System
    K.Sugawara; T.Watanabe
    Proc. of the 2002 IEEE/RSJ Intl. Conference on Intelligent Robots and Systems, 2702-2707, Oct. 2002
    International conference proceedings, English
  • Ill-Configured Object Representation by Neighbour Set with Applications to Aerial Image Analyses
    T.Watanabe; K.Sugawara
    Proc. of the ISPRS Commission III, 34, 3A, 387-393, Sep. 2002, Peer-reviwed
    International conference proceedings, English
  • Applications of Neighbour Set to Aerial Image Analysis
    T.Watanabe; K.Sugawara
    Proc. of the IGARSS 2002, 2516-2518, Jun. 2002
    International conference proceedings, English
  • A New Pattern Representation Scheme using Data Compression
    T.Watanabe; K.Sugawara
    IEEE Trans. PAMI, 24, 5, 579-590, May 2002, Peer-reviwed
    Scientific journal, English
  • A study on foraging behavior of simple multi-robot system
    Ken Sugawara; Toshinori Watanabe
    IECON Proceedings (Industrial Electronics Conference), 4, 3085-3090, 2002, This paper presents the cooperative behavior of multi-robot system in which each robot has a very simple interaction method. The task of the robots is to collect pucks distributed in the field. In this paper, we choose three types of puck distributions and evaluate the performance of the group. At first, we take up the task to collect pucks to unfixed point, and discuss their performance focusing on the relationship between the number of robots and the number of pucks in the largest puck cluster. Secondly, we take up the task to collect pucks to fixed point. In this paper, we especially take up two types of puck distribution, fractal distribution field and clockface arranged distribution field, and discuss their performance. Thirdly, we take up the task to collect pucks in case that the interaction range between each robot is finite. Here we show the performance of the group focusing on the relation between the number of robot, interaction range, and the number of collected pucks per a robot. Lastly, we refer to the relation between their collective foraging behavior and emergence of swarm intelligence mainly focusing on the number effect of the system.
    International conference proceedings, English
  • Cooperative foraging behaviour of multi robot system with simple interaction
    K. Sugawara; M. Sano; I. Yoshihara; K. Abe; T. Watanabe
    Proc. of the International conference on control, automation and systems, 1114-1117, Oct. 2001, Peer-reviwed
    International conference proceedings, English
  • A New Universal Media Featuring Scheme using Data Compression
    T.Watanabe; K.Sugawara; Hee Chun Park
    Proc. of the Int. Conf. on Media Futures,Florence,Italy, 261-264, May 2001, Peer-reviwed
    International conference proceedings, English
  • Cooperative Behavior of Multi Robot System with Simple Interaction
    Ken Sugawara; Masaki Sano; Ikuo Yoshihara; Kenichi Abe; Toshinori Watanabe
    Proc. of The Sixth Int.Symp. on Artificial Life and Robotics, 109-112, Jan. 2001
    International conference proceedings, English
  • Classification and Function Prediction of the Protein by using Data Compression
    Ken Sugawara; Toshinori Watanabe
    Proc. of The Sixth Int.Symp. on Artificial Life and Robotics, 246-249, Jan. 2001
    International conference proceedings, English
  • Classification and function estimation of protein by using data compression and genetic algorithms
    S Chiba; K Sugawara; T Watanabe
    PROCEEDINGS OF THE 2001 CONGRESS ON EVOLUTIONARY COMPUTATION, VOLS 1 AND 2, IEEE, 839-844, 2001, Protein has a complicated spatial structure and has chemical and physical functions that originate from the structure. It is important to predict the structure and functions of the protein from a DNA sequence or an amino acid sequence from a viewpoint of biology, medical science, protein engineering and so on. But at present no method is available to predict them accurately from the sequence. Instead, there are some approaches to estimate the functions approximately based on a similarity retrieval of sequences. We propose a new method for similarity retrieval of amino acid sequence based on the concept of homology retrieval using data compression. Introduction of the compression by dictionary technique enables us to describe the text data as an n-dimensional vector using n dictionaries which are generated by compessing n typical texts, and it also enables us to classify them based on their similarity. To classify the data clearly, it is effective to use ideal character strings as dictionaries. In this paper, we introduce genetic algorithm for dictionary generation and classify the amino acid sequences. Effectiveness of our proposal is examined using real genome data.
    International conference proceedings, English
  • Classification and function estimation of protein by using data compression and genetic algorithms
    S Chiba; K Sugawara; T Watanabe
    PROCEEDINGS OF THE 2001 CONGRESS ON EVOLUTIONARY COMPUTATION, VOLS 1 AND 2, IEEE, 839-844, 2001, Peer-reviwed, Protein has a complicated spatial structure and has chemical and physical functions that originate from the structure. It is important to predict the structure and functions of the protein from a DNA sequence or an amino acid sequence from a viewpoint of biology, medical science, protein engineering and so on. But at present no method is available to predict them accurately from the sequence. Instead, there are some approaches to estimate the functions approximately based on a similarity retrieval of sequences. We propose a new method for similarity retrieval of amino acid sequence based on the concept of homology retrieval using data compression. Introduction of the compression by dictionary technique enables us to describe the text data as an n-dimensional vector using n dictionaries which are generated by compessing n typical texts, and it also enables us to classify them based on their similarity. To classify the data clearly, it is effective to use ideal character strings as dictionaries. In this paper, we introduce genetic algorithm for dictionary generation and classify the amino acid sequences. Effectiveness of our proposal is examined using real genome data.
    International conference proceedings, English
  • Map Generation from Aerial Imagery using Data Compression
    Toshinori Watanabe; Ken Sugawara; Hiroshi Sugihara
    IAPR Workshop on Machine Vision Applic ations(MVA2000), 596-599, Dec. 2000
    International conference proceedings, English
  • Collective Behavior of Multi-robot System with Simple Interation
    K. Sugawara; T. Watanabe
    Proc. Fifth Int. Symp. on Artificial Life and Robotics, 725-727, Jan. 2000
    International conference proceedings, English
  • Collective Behavior of Multi-agent System with Simple Interaction
    K. Sugawara; M. Sato; I. Yoshihara; K. Abe; T. Watanabe
    Proc. Fifth Int. Symp. on Artificial Life and Robotics, 725-727, 2000, Peer-reviwed
    International conference proceedings, English
  • OSR : Online Sketch Recognition by Data Compression Technique
    近藤邦広; 加藤直樹; 渡辺俊典
    Journal of Information Processing Society of Japan, Information Processing Society of Japan (IPSJ), 38, 12, 2468-2478, 1997, Peer-reviwed, Aiming the development of flexible user-interface that will be a basic technology for future HI (Human-Interface), online sketch recognition problem is considered and a new solution is given. Sketch stroke stream is filtered by a set of data compressors, giving a feature vector composed of compression ratios. Modified LZ77-LZB is used to avoid the need of compressor pre-training, thereby realizing rapid construction of feature extractors. A new scheme for vector selection that incorporates both local and global features of a sketch is also proposed. Prototype system is detailed and experiment results illustrating the usefulness of this approach are given.
    Scientific journal, English
  • Adaptability of ANATA : an Antonomous Network Administrator Using TAMPOPO Learning Machine
    T.Takahara; T.Yanagisawa; T.Watanabe
    Transactions of Information Processing Society of Japan, 35, 10, 2090-2103, 1994
    Scientific journal, English
  • TAMPOPO-An Evolutionary Learning Machine based on the principle of Realtime Minimum Skyline Detection
    T. Watanabe
    Advances in Softwave Science and Technology, 5, 65-90, 1993, Peer-reviwed
    Scientific journal, English
  • 並列推論マシン上でのLSIレイアウトシステムCo-HLEX
    渡辺俊典; 小松啓子; 小田理; 山口英之
    ICOT TECHNICAL REPORT: TR-0759, Apr. 1992
    Research institution, Japanese
  • A Realtime Minimum Skyline Detector for Unknown Time Varying Nonlinear Functions
    T.Watanabe
    Computer Software, 9, 4, 1992
    Scientific journal, English
  • Co-HLEX : Co-operative Recursive LSI-Layout Problem Solver on Japan's Fifth Generation Parallel Interence Machine
    T. Watanabe; K. Komatsu
    1992, Peer-reviwed
    International conference proceedings, English
  • CMOSメモリーの機能シミュレーションモデルの開発,
    林晋一; 渡辺俊典; 増田弘生; 平井千秋
    電子情報通信学会論文誌, J74-A, 12, 1774-1785, Dec. 1991, Peer-reviwed
    Scientific journal, Japanese
  • DA変換器設計支援のための設計知識表現方式
    林晋一; 渡辺俊典; 大沢秀行; 麻殖生健二
    電子情報通信学会論文誌, J74-A, 10, 1561-1575, Oct. 1991, Peer-reviwed
    Scientific journal, Japanese
  • 後退形/前進形両積分法を併用した機能/回路混在系の新シミュレーション手法
    平井千秋; 渡辺俊典; 林晋一
    情報処理学会論文誌, Information Processing Society of Japan (IPSJ), 32, 8, 1014-1021, Aug. 1991, Peer-reviwed, システムLSIの設計では動特性の計算磯シミュレーションが重要であるが 従来の回路シミュレータでは不可能な場合が多い・理由は 大規模行列計算を時間刻みステップごとに繰り返し シミュレーションに長時間を要するためであるまた 回路シミュレータでは周波数 位相等の機能パラメータを直接表現できないため 機能レベル設計のシミュレーションが行えず 回路の上流設計を支援できない本論文では 従来の回路シミュレータのこの難点を解決する方式と共に 本方式に基づくLSI設計手法を提案する提案は (1)回路シミュレータの基本算法である後退形積分法に連続系シミュレータで用いられてきた前進形積分法を付加する新算法 (2)新算法を実現するための従来シミュレータの改良法 (3)LSIの機能設計から回路設計までを新シミュレータで一貫支援する設計法 の三点である実験の結果 (1)一回のシミュレーション時間に要する時間は従来の1/100以下 (2)LSI設計階后間の自由なプラウジングの可能性 を実証した設計現場にて使用されてきた回路シミュレータは 本提案に基づく小規模の改良により 新時代のニーズであるシステムLSIの機能シミュレータとしても利用できることになる
    Scientific journal, Japanese
  • Co-operative Hierarchical Layout Problem Solver on Parallel Inference Machine
    T. Watanabe; K. Komatsu
    ICOT TECHNICAL REPORT: TR-631, 1-19, Mar. 1991
    Scientific journal, English
  • Co-operative Hierarchical Layout Problem Solver on Parallel Inference Machine
    T. Watanabe; K. Komatsu
    Logic Programming Conference '91, 9-24, 1991, Peer-reviwed
    International conference proceedings, English
  • 並列プログラミングの未来は何色か(パネル討論)
    渡辺俊典
    ICOT Journal, 29, 48-80, 1991
    Research institution, Japanese
  • 並列推論マシン上のLSIレイアウトシステムcoーHLEXの概要
    渡辺俊典; 小松啓子
    KL1シンポジウム, ICOT, 37-42, Feb. 1990, Peer-reviwed
    Research institution, Japanese
  • 私はKL1プログラミングを楽しんでいるか?
    渡辺俊典
    KL1シンポジウム, ICOT, Feb. 1990
    Research institution, Japanese
  • アナログASIC設計技術
    麻殖生健二; 渡辺俊典; 宮本俊介; 岡部隆博
    日立評論, 71, 12, 51-54, Dec. 1989
    Research institution, Japanese
  • 連続系シミュレーション手法によるVTR用カラー信号処理LSIの 機能シミュレーション
    林晋一; 渡辺俊典; 降籏誠; 山本帥久
    電子情報通信学会論文誌, J72-A, 11, 1829-1843, Nov. 1989, Peer-reviwed
    Scientific journal, Japanese
  • A Highly Efficient Design System for Mixed Analog/Digital LSIs
    K. Maio; S. Hayashi; M. Furihata; S. Ogura; T. Watanabe; M. Ishikawa
    ESSCIRC'89, 121-124, Sep. 1989, Peer-reviwed
    International conference proceedings, English
  • Modelling Layout Problem Solving in Logic
    T. Watanabe; S. Hayashi
    Proceedings of the IFIP TC 10/WG10. 2, 181-188, Jun. 1989, Peer-reviwed
    International conference proceedings, English
  • Expert Systems for VLSI Design
    N. Hamada; T. Watanabe; Y. Kobayashi; H. Kida
    Hitachi Review, 37, 5, 339-344, Oct. 1988
    Research institution, English
  • LSI/CAD用エキスパートシステム
    浜田亘曼; 渡辺俊典; 小林康弘
    日立評論, 69, 3, 41-44, Mar. 1987
    Research institution, Japanese
  • Knowledge-Based Optimal IIL Circuit Generator from Conventional Logic Circuit Descriptions
    T. Watanabe; T. Masuishi; T. Nishiyama; N. Horie
    Proceedings of the 23RD Design Automation Conference, 23, 608-614, Jul. 1986, Peer-reviwed
    International conference proceedings, English
  • 知識工学の計算機室機器レイアウトCADへの応用
    渡辺俊典; 安信千津子; 佐々木浩二; 山中止志郎
    日立評論, 67, 12, 41-44, Dec. 1985
    Research institution, Japanese
  • Computer Room Facility Layout in ESP
    T. Watanabe; C. Yasunobu; T. Masuishi
    Third Japanese-Swedish Workshop on Logic Programming, Nov. 1985, Peer-reviwed
    International conference proceedings, English
  • Design of an Expert System for Computer Room Layout
    T.Watanabe; K.Sasaki; C.Yasunobu; Y.Nagai; Y.Iizuka; T.Yamanaka; M.Yamagoshi; T.Tanaka
    Trans. IPSJ, 26, 5, 1985
    Scientific journal, English
  • An Expert System for Computer Room Facility Layout
    T. Watanabe; C. Yasunobu; K. Sasaki; T. Yamanaka
    5th International Workshop: Expert Systems & Their Applications, paper 9A, 1985, Peer-reviwed
    International conference proceedings, English
  • OPTICAL MEASUREMENT OF CARRIER PROFILES IN SILICON
    T MOTOOKA; T WARABISAKO; T TOKUYAMA; T WATANABE
    JOURNAL OF THE ELECTROCHEMICAL SOCIETY, ELECTROCHEMICAL SOC INC, 131, 1, 174-179, 1984, Peer-reviwed
    Scientific journal, English
  • Design of a Knowledge-Based Heuristic Optimizer which Evolves-An Open System Approach-
    T.Watanabe
    Trans. IPSJ, 24, 1, 1983
    Scientific journal, English
  • DANDELION-Duplication and Deletion Strategy which Realizes Autonomous Learner
    T.Watanabe; K.Sasaki; K.Ihara
    Trans. IPSJ, 24, 6, 1983
    Scientific journal, English
  • Materials Requirement Analysis by Linear Programming
    T.Watanabe; Y.Seto; K.Sasaki
    Journal of the Operations Research Society of Japan, 25, 4, 1982
    Scientific journal, English
  • Fault Diagnosis by Mathematical Programming
    T. Watanabe; C. Yasunobu; M. O'kuma
    IEEE Trans. on Relibility, R-30, 4, 1981
    Scientific journal, English
  • Automatic Optimization of LSI circuit paramenters
    T.Watanabe; H.Masuda
    Trans. IECE, J64-D, 9, 1981
    Scientific journal, English

MISC

  • フラクタル画像圧縮を用いた類似画像検索システム 圧縮符号データベースを対象とした画像の検索手法について
    横山貴紀; 渡辺俊典
    日本工業出版, Mar. 2003, 画像ラボ, 14, 3, 17-20, Japanese, Introduction other, 0915-6755, 80015781515, AN10164169
  • データ圧縮器空間による手書きスケッチの表現と認識
    渡辺俊典
    日本工業出版, Jun. 1998, 画像ラボ, 9, 6, 20-23, Japanese, Introduction other, 0915-6755, 40005023899, AN10164169
  • 学習機能を備えた最適化アルゴリズム知識ベース
    渡辺俊典
    May 1993, 人工知能学会誌, 8, 3, 272-277, Japanese, Introduction other
  • LSICADにおける階層問題解決モデル
    渡辺俊典; 平井千秋; 林晋一
    Apr. 1991, 電子情報通信学会:第4回/回路とシステム軽井沢ワークショップ研究会, 240-245, Japanese, Introduction other
  • 電子回路レイアウトシステムcoーHLEXの開発状況
    渡辺俊典; 小松啓子
    1991, KL1プログラミングワークショップ'91, ICOT, 37-42, Japanese, Peer-reviwed, Introduction other
  • 並列推論マシン上の回路レイアウトシステム
    渡辺俊典
    1991, 第5世代コンピュータに関するシンポジウム(第8回)予稿集, 15-16, Japanese, Introduction other
  • 計算機室機器レイアウトシステムの開発
    安信千津子; 渡辺俊典; 山中止志郎
    Jan. 1989, 人工知能学会誌, 3, 1, 32-39, Japanese, Introduction other
  • オブジェクト指向言語のレイアウト問題解決への応用とCADデータベースの考察
    渡辺俊典; 近藤秀文
    1989, システム/制御/情報, 33, 8, 407-414, Japanese, Introduction other
  • 知識処理を応用した計算機室機器レイアウトCADシステム
    渡辺俊典
    Mar. 1988, 日本建築学会電子計算機利用委員会, 第10回電子計算機利用シンポジウム, 3323-3326, Japanese, Introduction other
  • 計画/設計型知識システムの事例分析
    渡辺俊典
    Mar. 1987, 計測自動制御学会システム工学部会講習会(東京/大阪) エキスパートシステム:方法論と応用, 67-82, Japanese, Introduction other
  • 課題山積のアナログデジタル共存LSI用CAD
    堀江昇; 伊藤高明; 渡辺俊典; 矢島章夫; 永田穣
    Oct. 1986, 日経エレクトロニクス, 405, 197-214, Japanese, Introduction other

Books and other publications

  • CAD Systems Using AI Techniques
    G.Odawara
    English, Joint work, North holland, 1989
  • Constrained Logic Programming
    English, Joint work, 共立出版, 1989

Lectures, oral presentations, etc.

  • Compression-based semantic-sensitive image segmentation: PRDC-SSIS
    Masahiro Nakajima; Toshinori Watanabe; Hisashi Koga
    Public symposium, English, IEEE International Geoscience and Remote Sensing Symposium (IGARSS), IEEE, Munich
    Jul. 2012
  • Compression-based self-organizing recognizer PRDC-CSOR with preliminary application to EO-image analysis
    Toshinori Watanabe
    Public symposium, English, IEEE International Geoscience and Remote Sensing Symposium (IGARSS), IEEE, Munich
    Jul. 2012
  • A Novel Image Feature Extraction Approach Using Enhanced Edge Information
    Yinan Wang; Nuo Zhang; Toshinori Watanabe; Hisashi Koga
    Oral presentation, English, 信学技報
    Mar. 2012
  • 数式画像をクエリとする類似数式検索システム
    Shirmenbaatar Myagmarsuren; 古賀 久志; 渡辺 俊典
    Oral presentation, Japanese, 第4回データ工学と情報マネジメントに関するフォーラム,DEIM2012
    Mar. 2012
  • Realizing an autonomous recognizer using data compression
    T. Watanabe
    Keynote oral presentation, English, SEVENTH CONFERENCE on IMAGE INFORMATION MINING ESA JRC EUSC 2011, European Image Information Mining Coordination Group (IIMCG), Varese, Italy, International conference
    Mar. 2011
  • エンドホストでのAQMエミュレーションによるTCPコネクション間のスループット公平性改善
    石津圭太; 古賀 久志; 渡辺 俊典
    Public symposium, Japanese, 信学技法 IN2010-204, 電子情報通信学会
    Mar. 2011
  • 背景の分割に対応したグラフマイニングベースの動画像からの背景除去
    青木玄明; 古賀久志; 渡辺俊典; 横山貴紀
    Public symposium, Japanese, 情処研報 2011-CVIM-176, 電子情報通信学会
    Mar. 2011
  • 分散環境でのL1距離ベースLocality-Sensitive Hashingのリモートアクセスの回数削減
    小栗正之; 古賀久志; 渡辺俊典
    Public symposium, Japanese, 第3回データ工学と情報まね自演とに関するフォーラム(DEIM2011), 電子情報通信学会
    Mar. 2011
  • 分散環境におけるL1距離ベースLocality-Sensitive Hashingの通信回数削減手法とその実装評価
    古賀久志; 渡辺俊典
    Oral presentation, Japanese, 信学技報 DE2011-40,信学技報 DE2011-40
    2011
  • SURF特徴点を用いたグラフカットによる動画像からの移動物体自動抽出結果の精度向上
    工藤識実; 古賀久志; 横山貴紀; 渡辺俊典
    Oral presentation, Japanese, 信学技報 PRMU2011-123,信学技報 PRMU2011-123
    2011
  • ユークリッド空間内の点分布の外郭を求めるアルゴリズム
    小林 郁弥; 渡辺 俊典; 古賀 久志
    Oral presentation, Japanese, 信学技報 PRMU2009-171,PRMU
    Jan. 2010
  • グラフカットを用いた動画像からの自動移動物体抽出
    松田 彰浩; 古賀 久志; 渡辺 俊典
    Oral presentation, Japanese, 信学技報 PRMU,PRMU2009
    Jan. 2010
  • Compression based Learning System for Image Analysis
    T.Watanabe
    Invited oral presentation, English, GEOSS Summer School: Advanced Earth Observation Data Understanding, September 3 - September 5, 2009, Sinaia, Romania, ROSA (ROmanian Space Agency), Sinaia, International conference
    Sep. 2009
  • On the possiblility of Highly Automated Image Information Mining: Problems and Possible Solutions
    T. Watanabe
    Invited oral presentation, English, Workshop on Innovative Data Mining Techniques in Support of GEOSS, GEOSS, ROSA, Sinaia, Romania, International conference
    Sep. 2009
  • Compression based Learning System for Image Analysis
    T.Watanabe
    Others, English, GEOSS Summer School: Advanced Earth Observation Data Understanding, September 3 - September 5, 2009, Sinaia, Romania, GEOSS Summer School: Advanced Earth Observation Data Understanding
    Sep. 2009
  • テキスト化を介した画像分類手法の提案
    平井 敦之; 張 諾; 渡辺 俊典; 古賀 久志
    Oral presentation, Japanese, AI研究会
    Jan. 2009
  • 多頻度グラフマイニングを利用した動画の解析
    辻 智和; 古賀 久志; 横山 貴紀; 渡辺 俊典
    Oral presentation, Japanese, PRMU
    Dec. 2008
  • MPEG動きベクトルを用いたグローバルモーション推定に基づく移動物体のリアルタイム抽出
    大田 修平; 横山 貴紀; 渡辺 俊典; 古賀 久志
    Oral presentation, Japanese, 信学技報,PRMU2008-91
    Oct. 2008
  • 映像からの動作オブジェクト自動学習システムAMOR
    徳冨 兼太郎; 渡辺 俊典; 古賀 久志; 横山 貴紀
    Oral presentation, Japanese, 信学技報,電子情報通信学会 PRMU研究会
    Feb. 2008
  • 異種の高速トランスポートプロトコルへの帯域公平性を考慮したUDTの改良
    河野 伸也; 古賀 久志; 渡辺 俊典
    Oral presentation, Japanese, 電子情報通信学会,電子情報通信学会 情報ネットワーク研究会 2007-101
    Dec. 2007
  • 高次元圧縮空間の対話的手法による次元縮小
    山崎 啓介; 張 諾; 渡辺 俊典; 古賀 久志
    Oral presentation, Japanese, 情報処理学会研究報告2007-NL-181
    Sep. 2007
  • Component-based Automatic Object Discovery Using Multiple Phase Hashing
    Gibran Fuentes Pineda; Hisashi Koga; Toshinori Watanabe
    Oral presentation, English, 信学技報,PRMU
    Sep. 2007
  • 輸送問題視点からの適応的な移動領域の抽出と追跡手法
    古川翔; 横山貴紀; 渡辺俊典; 古賀久志
    Oral presentation, Japanese, 画像の認識・理解シンポジウム (MIRU2007) 論文集,画像の認識・理解シンポジウム (MIRU2007)
    Jul. 2007
  • ピット近似関数を用いた非線形関数の局所解集合探索法
    肥塚真由子; 渡辺俊典; 古賀久志
    Oral presentation, Japanese, 情報処理学会,MPS-62
    Dec. 2006
  • 圧縮性とオブジェクトらしさ尺度に着目した画像からのオブジェクト自動抽出法
    杉山英行; 古賀久志; 渡辺俊典; 横山貴紀
    Oral presentation, Japanese, 信学技報
    Nov. 2006
  • 輸送問題の解法に基づく動き領域抽出手法
    古川翔; 横山貴紀; 渡辺俊典; 古賀久志
    Oral presentation, Japanese, 信学技報,PRMU2006-114
    Oct. 2006
  • MPEGビデオデータの動きベクトルを用いた移動物体追跡手法
    岩崎敏紀; 横山貴紀; 渡辺俊典; 古賀久志; 阿部龍士
    Oral presentation, Japanese, 信学技報
    Sep. 2006
  • LZ78の圧縮性を利用した文書検索手法の提案
    木村洋章; 渡辺俊典; 古賀久志; 張諾
    Oral presentation, Japanese, 情報処理学会,2006/FI/84 & 2006/NL/175
    Sep. 2006
  • 圧縮性に注目した文書の関係分析手法
    松崎大輔; 渡辺俊典; 古賀久志; 張諾
    Oral presentation, Japanese, 情報処理学会,2006/FI/84 & 2006/NL/175
    Sep. 2006
  • 木編集距離を利用した木データの構造と内容の類似性を反映する分類手法
    齋藤裕明; 古賀久志; 渡辺俊典; 横山貴紀
    Oral presentation, Japanese, 情報処理学会,DE2006-2
    Jun. 2006
  • 属性付きグラフマッチングアルゴリズムの効率的な実装
    森田昭広; 古賀久志; 渡辺俊典; 横山貴紀
    Oral presentation, Japanese, 情報処理学会研究会,SIGAL105-8
    Mar. 2006
  • フラクタル符号に基づくDR領域画像表現と画像検索への応
    横山 貴紀; 渡辺 俊典
    Public symposium, Japanese, DEWS2006, 情報処理学会
    Mar. 2006
  • A Priority-based QoS Control in Mobile Ad hoc Networks Exploiting Multipath Load-aware Routing
    Aly Niaph; Hisashi Koga; Hiroshi Kitamura; Toshinori Watanebe
    Oral presentation, Japanese, 信学技報
    Mar. 2006
  • 将来の輻輳状態の予測に基づくアクティブキュー管理手法の提案
    星原隼人; 古賀久志; 北村浩; 渡辺俊典
    Oral presentation, Japanese, 電子情報通信学会、信学技法、IN2005-65
    Sep. 2005
  • 投票機構を用いた動作モデルのオンライン自動獲得
    吉岡泰智; 古賀久志; 渡辺俊典; 横山貴紀
    Oral presentation, Japanese, 電子情報通信学会、 PRMU2005-56
    Sep. 2005
  • オンライン実時間PCAを用いた動画からの変動背景の推定
    杉山賢治; 古賀久志; 渡辺俊典; 横山貴紀
    Oral presentation, Japanese, PRMU2004-179
    Feb. 2005
  • クラスタリングアルゴリズムLSH-Linkを利用した動画像からのオブジェクト軌跡の自動抽出
    草場洋明; 古賀久志; 渡辺俊典
    Oral presentation, Japanese, PRMU2004-179
    Feb. 2005
  • オプティカルフローを用いた複雑背景下における人物領域の抽出
    岩崎敏紀; 横山貴紀; 古賀久志; 渡辺俊典
    Oral presentation, Japanese, PRMU2004-179
    Feb. 2005
  • 木のDPマッチングを利用したDTD類似度の考察
    小野里卓也; 古賀久志; 渡辺俊典
    Oral presentation, Japanese, PRMU2004-179
    Feb. 2005
  • 投票機構を用いた人物動作の認識手法
    大藤篤史; 渡辺俊典; 古賀久志
    Oral presentation, Japanese, コンピュータビジョンとイメージメディア146
    Nov. 2004
  • 圧縮率を利用した画像からのオブジェクト自動抽出
    杉内崇浩; 渡辺俊典; 古賀久志
    Oral presentation, Japanese, コンピュータビジョンとイメージメディア146
    Nov. 2004
  • 骨格線を利用したオブジェクト検索手法
    中山仁; 渡辺俊典; 古賀久志
    Oral presentation, Japanese, コンピュータビジョンとイメージメディア146
    Nov. 2004
  • 相互写像に基づくベクトル集合間類似度とその上限値
    横山貴紀; 渡辺俊典; 古賀久志
    Oral presentation, Japanese, 電子情報通信学会技術研究報告,PRMU2004-72
    Sep. 2004
  • 場との相互作用による群ロボットの協調搬送行動
    風間; 菅原,渡辺
    Oral presentation, Japanese, 信学技法,NLP2004-8
    May 2004
  • Locality-Sensitive Hashingを利用した静止画像からのオブジェクト概念発見
    古賀久志; 渡辺俊典
    Oral presentation, Japanese, 信学技法PRMU2003-250
    Feb. 2004
  • Locality-Sensitive Hashingを用いた階層的クラスタリング解析手法の近似解法
    石橋徹夫; 古賀久志; 渡辺俊典; 菅原研
    Oral presentation, Japanese, 信学技法, PRMU2003-251
    Feb. 2004
  • 木のDPマッチングによるオブジェクト類似度の解析
    小野里卓也; 古賀久志; 渡辺俊典
    Oral presentation, Japanese, 信学技法, PRMU2003-249
    Feb. 2004
  • 仮想フェロモンを用いた群ロボットの探索収集行動
    風間; 菅原, 渡辺
    Oral presentation, Japanese, 弟16回自律分散システム・シンポジウム
    Jan. 2004
  • フラクタル符号のベクトル集合間類似度に基づく画像検索手法
    横山貴紀; 渡辺俊典; 古賀久志
    Oral presentation, Japanese, FIT2004(第3回情報科学技術フォーラム)
    2004
  • 画像からのオブジェクト記述の自動抽出
    大田貴彦; 杉内崇浩; 渡辺俊典; 菅原研; 古賀久志
    Oral presentation, Japanese, コンピュータビジョンとイメージメディア141(情報処理学会研究会)
    Nov. 2003
  • MSTを用いたアピアランスベース3D物体認識手法の画像スケール変換下での性能分析
    平橋慶一; 渡辺俊典; 古賀久志; 菅原研
    Oral presentation, Japanese, コンピュータビジョンとイメージメディア141
    Nov. 2003
  • Locality-Sensitive Hashing を用いた階層的クラスタ解析手法の高速化
    石橋徹夫; 古賀久志; 渡辺俊典; 菅原研
    Oral presentation, Japanese, コンピュータビジョンとイメージメディア141
    Nov. 2003
  • 直交する2つの最小全域木(MST) を用いた画像特徴抽出可能性の検討
    狩野哲久; 渡辺俊典; 古賀久志; 菅原研
    Oral presentation, Japanese, コンピュータビジョンとイメージメディア141
    Nov. 2003
  • 場を介して情報授受するロボットシステムについて
    風間; 菅原, 渡辺
    Oral presentation, Japanese, 弟9回創発システム・シンポジウム
    Aug. 2003
  • 多次元特徴量直方体を用いたアピアランスベースオブジェクト認識手法
    朝日和也; 渡辺俊典; 菅原研; 横山貴紀
    Oral presentation, Japanese, 信学技法,PRMU2002-259
    May 2003
  • 最小全域木(MST)の深さ優先探索による画像分割方式
    角田夏貴; 渡辺俊典; 菅原研
    Oral presentation, Japanese, 信学技報, PRMU2003
    Mar. 2003
  • 多次元特徴量直方体を用いたアピアランスベースオブジェクト認識手法
    朝日和哉; 渡辺俊典; 菅原 研; 横山貴紀
    Oral presentation, Japanese, 信学技報, PRMU2002
    Mar. 2003
  • 画像からのオブジェクト定義自動抽出方法の研究
    太田貴彦; 渡辺俊典; 菅原 研
    Oral presentation, Japanese, 信学技報, PRMU2002
    Mar. 2003
  • テンポラルテンプレートを用いた動画像解析手法
    申煕卓; 渡辺俊典
    Oral presentation, Japanese, 第4回動画像処理実利用化ワークショップ
    Mar. 2003
  • 最小全域木(MST) の深さ優先探索による画像分割方式
    角田夏貴; 渡辺俊典; 菅原 研
    Oral presentation, Japanese, 信学技報, PRMU2002-238
    Mar. 2003
  • テンポラルテンプレートを用いた動画解析手法
    申 煕卓; 渡辺俊典; 菅原 研
    Oral presentation, Japanese, 信学技報, PRMU2002
    Oct. 2002
  • 多次元特徴量直方体の相関関係を用いたオブジェクト認識FRCMの機能検証
    朝日和哉; 渡辺俊典; 菅原 研; 横山貴紀
    Oral presentation, Japanese, 信学技報, PRMU2002
    Oct. 2002
  • 画像オブジェクトに関する概念抽出と認識手法
    太田貴彦; 渡辺俊典; 菅原 研
    Oral presentation, Japanese, 信学技報, PRMU2002
    Oct. 2002
  • 最小全域木(MST)の深さ優先探索による画像分割方式
    角田夏貴; 渡辺俊典; 菅原 研
    Oral presentation, Japanese, 信学技報, PRMU2002
    Oct. 2002
  • フラクタル符号の写像対応に基づく特徴量と類似検索について
    横山貴紀; 渡辺俊典; 菅原 研
    Oral presentation, Japanese, 映像情報メディア学会技術報告
    Jul. 2002
  • フラクタル符号に基づく構造的な類似性抽出手法の検討
    横山貴紀; 渡辺俊典; 菅原研; 上野芳郎
    Oral presentation, Japanese, 信学技報PRMU2001-285
    Mar. 2002
  • 画像認識用データ圧縮空間の自動構成方式
    安藤祐樹; 渡辺俊典; 菅原研
    Oral presentation, Japanese, コンピュータビジョンとイメージメディア132-7
    Mar. 2002
  • フラクタル符号に基づく類似性抽出についての検討
    横山貴紀; 渡辺俊典; 菅原研; 上野芳郎
    Oral presentation, Japanese, コンピュータビジョンとイメージメディア132-3
    Mar. 2002
  • 航空写真内オブジェクトに関する半自動概念抽出方式
    久保孝弘; 太田貴彦; 渡辺俊典; 菅原研
    Oral presentation, Japanese, コンピュータビジョンとイメージメディア132-2
    Mar. 2002
  • 統計的仮説検定を用いた画像分割方式
    大堀敦史; 渡辺俊典; 菅原研; 角田夏貴
    Oral presentation, Japanese, コンピュータビジョンとイメージメディア132-1
    Mar. 2002
  • フラクタル画像圧縮の復元作用に基づく画像分類について
    横山貴紀; 渡辺俊典; 菅原研
    Oral presentation, Japanese, コンピュータビジョンとイメージメディア129-3(情報処理学会研究会),2001年9月13日
    Sep. 2001
  • 単純な相互作用を有する群れロボットの集餌行動
    菅原研; 渡辺俊典
    Oral presentation, Japanese, 第19回日本ロボット学会学術講演会, (2001年9月18-20日)
    Sep. 2001
  • 簡単な線画に対する認識概念形成方式SEQUITUR-2D
    芝清香; シン ヒタク; 渡辺俊典; 菅原研
    Oral presentation, Japanese, コンピュータビジョンとイメージメディア127-5(情報処理学会研究会),2001年5月10日
    May 2001
  • 多次元特徴量直方体の相関関係を用いたオブジェクト認識手法FRCM
    品田岳史; 安藤祐樹; 渡辺俊典; 菅原研
    Oral presentation, Japanese, コンピュータビジョンとイメージメディア127-5(情報処理学会研究会),2000年5月10日
    May 2001
  • 簡素な相互作用をもつアクティブエレメント集合体の振る舞いと機能
    菅原研; 荒井律; 渡辺俊典
    Oral presentation, Japanese, 第13回自律分散システム・シンポジューム,(2001年1月26,27日,福岡 )
    Jan. 2001
  • 目印を持たない大偏差画像の自動マッチング方式MLDI
    西川雄二; 久保孝弘; 渡辺俊典; 菅原研
    Oral presentation, Japanese, 日本写真測量学会,平成13年度年次学術講演会発表論文集
    2001
  • 多次元特徴量直方体の相関関係を用いたオブジェクト認識手法FRCM
    品田岳史; 安藤祐樹; 渡辺俊典; 菅原研
    Oral presentation, Japanese, 日本写真測量学会,平成13年度年次学術講演会発表論文集
    2001
  • 最小全域森を用いた画像のノイズ除去手法MSFNF
    助川勝彦; 大堀敦史; 渡辺俊典; 菅原研
    Oral presentation, Japanese, 日本写真測量学会,平成13年度年次学術講演会発表論文集
    2001
  • 多次元特徴量直方体の相関関係を用いたオブジェクト認識手法FRCM
    品田岳史; 安藤祐樹; 渡辺俊典; 菅原研
    Oral presentation, Japanese, 日本写真測量学会 平成13年度年次学術講演会発表論文集
    2001
  • 目印を持たない大偏差画像の自動マッチング方式MLDI
    西川雄二; 久保孝弘; 渡辺俊典; 菅原研
    Oral presentation, Japanese, 日本写真測量学会 平成13年度年次学術講演会発表論文集
    2001
  • Map Generation from Aerial Imagery using Data Compression
    Toshinori Watanabe; Ken Sugawara; Hiroshi Sugihara
    Others, English, IAPR Workshop on Machine Vision Applic ations(MVA2000)
    Dec. 2000
  • データ圧縮を用いたパターンの万能特徴表現方式UPRDC
    渡辺俊典
    Oral presentation, Japanese, 日本写真測量学会 平成12年度年次学術講演会,2000年6月29日
    Jun. 2000
  • データ圧縮を用いた航空写真からの地図作成方式
    椙原 寛; 渡辺俊典; 助川勝彦; 菅原 研
    Oral presentation, Japanese, 日本写真測量学会 平成12年度年次学術講演会,2000年6月29日
    Jun. 2000
  • 航空写真からのオブジェクト認識手法の研究
    須藤孝史; 西川雄二; 渡辺俊典; 菅原 研
    Oral presentation, Japanese, 日本写真測量学会 平成12年度年次学術講演会,2000年6月29日
    Jun. 2000
  • 画像認識用適応分類機構の提案
    山崎謙次; 渡辺俊典
    Oral presentation, Japanese, 日本写真測量学会 平成12年度年次学術講演会,2000年6月29日
    Jun. 2000
  • シーンの局所的特徴を利用した立体認識手法の研究
    李 容旻; 田中康雄; 渡辺俊典; 品田岳史; 菅原 研
    Oral presentation, Japanese, 日本写真測量学会 平成12年度年次学術講演会,2000年6月29日
    Jun. 2000
  • データ圧縮空間によるタンパクの分類と機能予測
    菅原 研; 渡辺俊典
    Oral presentation, Japanese, 平成12年度電気関係学会北海道支部連合大会
    2000
  • データ圧縮空間を用いたタンパクの分類と機能予測
    千葉慎二; 菅原 研; 渡辺俊典
    Oral presentation, Japanese, SICEシステム/情報部門シンポジウム2000
    2000
  • 簡素な相互作用をもつ群れロボットの集団協調作業
    菅原 研; 渡辺俊典
    Oral presentation, Japanese, SICEシステム/情報部門シンポジウム2000
    2000
  • データ圧縮空間をもちいたタンパクの分類と機能予測
    菅原 研; 渡辺俊典
    Oral presentation, Japanese, 平成12年電気関係学会関西支部連合大会
    2000
  • 簡素な相互作用をもつアクティブエレメント集合体の振る舞いと機能
    菅原 研; 荒井律; 渡辺俊典
    Oral presentation, Japanese, 第13回自律分散システム・シンポジウム
    2000
  • Foraging Bahavior of Multi-robot System and Emergence of Swarm Intelligence
    K. Sugawara; T. Watanabe
    Oral presentation, English, Proc. IEEE Int'l Conf. On Systems, Man, and Cybernetics
    Oct. 1999
  • 加工過程モデルを用いた板金図面からの立体復元
    へぎ誠一; 渡辺俊典
    Oral presentation, Japanese, 情報処理学会研究報告
    Jun. 1999
  • 連続系シミュレータと回路シミュレータの融合による回路解析手法
    平井千秋; 渡辺俊典; 林晋一
    Oral presentation, Japanese, 電気学会研究会資料電子回路研究会, ETC-92-9
    Mar. 1992
  • LSICADにおける階層問題解決モデル
    渡辺俊典; 平井千秋; 林晋一
    Invited oral presentation, Japanese, 電子情報通信学会:第4回/回路とシステム軽井沢ワークショップ研究会
    Apr. 1991
  • 並列推論マシン上の回路レイアウトシステム
    渡辺俊典
    Invited oral presentation, Japanese, 第5世代コンピュータに関するシンポジウム(第8回)予稿集, Tokyo
    1991
  • 並列プログラミングの未来は何色か(パネル討論)
    渡辺俊典
    Others, Japanese, ICOT Journal
    1991
  • 回路/機能混在シミュレーション
    大沢秀行; 佐藤哲雄; 林晋一; 渡辺俊典
    Oral presentation, Japanese, 電気学会研究会 ECTー90ー17
    Dec. 1990
  • 並列推論マシン上のLSIレイアウトシステムcoーHLEXの概要
    渡辺俊典; 小松啓子
    Others, Japanese, KL1シンポジウム, ICOT
    Feb. 1990
  • 私はKL1プログラミングを楽しんでいるか?
    渡辺俊典
    Others, Japanese, KL1シンポジウム, ICOT
    Feb. 1990
  • 知識処理を応用した計算機室機器レイアウトCADシステム
    渡辺俊典
    Invited oral presentation, Japanese, 日本建築学会電子計算機利用委員会, 第10回電子計算機利用シンポジウム
    Mar. 1988
  • 計画/設計型知識システムの事例分析
    渡辺俊典
    Invited oral presentation, Japanese, 計測自動制御学会システム工学部会講習会(東京/大阪) エキスパートシステム:方法論と応用
    Mar. 1987
  • 適応知識ベース(TAMPOPO) を用いた計算機オペレーティングシステムの 自律化資源管理方式の開発
    渡辺俊典
    Oral presentation, Japanese, 情報処理学会OS研究会, オペレーティングシステム34ー4
    Feb. 1987
  • 知識処理の計算機室機器レイアウトCADへの応用
    渡辺俊典; 安信千津子; 佐々木浩二; 山中止志郎
    Oral presentation, Japanese, 情報処理学会記号処理研究会, 記号処理33ー1
    Sep. 1985
  • CO2レーザエリプソメトリーによる半導体中のキャリヤ濃度深さ分布の測定
    本岡輝昭; 蕨迫光紀; 徳山巍; 渡辺俊典
    Oral presentation, Japanese, 応用物理学会結晶工学分科会第82回研究会予稿
    Feb. 1983

Affiliated academic society

  • Komuso-kenkyu-kai
  • IEICE
  • IPSJ,
  • IEEE,

Industrial Property Rights

  • システムの自律化資源管理方式、非破壊診断方式、知識ベース構成方式、学習制御方式、電子回路自動レイアウト方式、など91件、内登録済み17件
    Patent right, 渡辺俊典, 130820, Date applied: 20 Jul. 1983