Updated on 2022/12/23

写真a

 
MIGITA Tsuyoshi
 
Organization
Faculty of Natural Science and Technology Assistant Professor
Position
Assistant Professor
External link

Degree

  • 博士(情報工学) ( 広島市立大学 )

Research Interests

  • Computer Vision

  • コンピュータ・ビジョン

Research Areas

  • Informatics / Intelligent robotics

  • Informatics / Perceptual information processing

Education

  • Hiroshima City University   大学院情報科学研究科   情報科学専攻

    - 2004

      More details

    Country: Japan

    researchmap

  • Hiroshima City University   大学院情報科学研究科  

    - 2000

      More details

    Country: Japan

    researchmap

  • Hiroshima City University   情報科学部   知能情報システム工学科

    - 1998

      More details

    Country: Japan

    researchmap

Research History

  • Okayama University   The Graduate School of Natural Science and Technology   Assistant Professor

    2007.4

      More details

    Country:Japan

    researchmap

  • Okayama University   工学部   Research Assistant

    2003.6

      More details

    Country:Japan

    researchmap

Professional Memberships

 

Papers

  • A faster algorithm to search for generalized Moore graphs Reviewed

    Taku Hirayama, Tsuyoshi Migita, Norikazu Takahashi

    2022 IEEE Region 10 Conference (TENCON2022)   2022.11

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    researchmap

  • Deep learning of OpenStreetMap images labeled using road traffic accident data Reviewed

    Kaito Arase, Zhijian Wu, Tsuyoshi Migita, Norikazu Takahashi

    2022 IEEE Region 10 Conference (TENCON2022)   2022.11

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    researchmap

  • An algorithm for updating betweenness centrality scores of all vertices in a graph upon deletion of a single edge Reviewed

    Yoshiki Satotani, Tsuyoshi Migita, Norikazu Takahashi

    Journal of Complex Networks   10 ( 4 )   2022.6

     More details

    Language:English   Publishing type:Research paper (scientific journal)   Publisher:Oxford University Press (OUP)  

    Abstract

    Betweenness centrality (BC) is a measure of the importance of a vertex in a graph, which is defined using the number of the shortest paths passing through the vertex. Brandes proposed an efficient algorithm for computing the BC scores of all vertices in a graph, which accumulates pair dependencies while traversing single-source shortest paths. Although this algorithm works well on static graphs, its direct application to dynamic graphs takes a huge amount of computation time because the BC scores must be computed from scratch every time the structure of graph changes. Therefore, various algorithms for updating the BC scores of all vertices have been developed so far. In this article, we propose a novel algorithm for updating the BC scores of all vertices in a graph upon deletion of a single edge. We also show the validity and efficiency of the proposed algorithm through theoretical analysis and experiments using various graphs obtained from synthetic and real networks.

    DOI: 10.1093/comnet/cnac033

    researchmap

  • Uncalibrated Photometric Stereo Using Superquadrics with Texture Estimation Reviewed

    Tsuyoshi Migita, Ayane Okada, Norikazu Takahashi

    Communications in Computer and Information Science   1578 CCIS   34 - 48   2022.5

     More details

    Authorship:Lead author, Corresponding author   Language:English   Publishing type:Research paper (international conference proceedings)  

    When a 3D scene is captured in several 2D images, a compact description (or parameters) of the 3D scene can be estimated from the images. Such an inference is formulated as the inverse of rendering computer graphics and is important for various applications, such as object recognition, inspection, and/or VR. In the present paper, we extend a photometric stereo method in such a way as to estimate the texture of the object in addition to previous estimation of parameters describing the objects and light sources. To do so, we need a realistic minimization method, combined with a method to obtain the Jacobian of the cost function with respect to the texture. We implemented this method and verified the validity of the framework using synthetic and real-world data.

    DOI: 10.1007/978-3-031-06381-7_3

    Scopus

    researchmap

  • A novel update rule of HALS algorithm for nonnegative matrix factorization and Zangwill’s global convergence Reviewed

    Takehiro Sano, Tsuyoshi Migita, Norikazu Takahashi

    Journal of Global Optimization   84   755 - 781   2022.4

     More details

    Language:English   Publishing type:Research paper (scientific journal)  

    Nonnegative Matrix Factorization (NMF) has attracted a great deal of attention as an effective technique for dimensionality reduction of large-scale nonnegative data. Given a nonnegative matrix, NMF aims to obtain two low-rank nonnegative factor matrices by solving a constrained optimization problem. The Hierarchical Alternating Least Squares (HALS) algorithm is a well-known and widely-used iterative method for solving such optimization problems. However, the original update rule used in the HALS algorithm is not well defined. In this paper, we propose a novel well-defined update rule of the HALS algorithm, and prove its global convergence in the sense of Zangwill. Unlike conventional globally-convergent update rules, the proposed one allows variables to take the value of zero and hence can obtain sparse factor matrices. We also present two stopping conditions that guarantee the finite termination of the HALS algorithm. The practical usefulness of the proposed update rule is shown through experiments using real-world datasets.

    DOI: 10.1007/s10898-022-01167-7

    Scopus

    researchmap

  • An Algorithm for Randomized Nonnegative Matrix Factorization and Its Global Convergence Reviewed

    Takao Masuda, Tsuyoshi Migita, Norikazu Takahashi

    IEEE Symposium Series on Computational Intelligence (IEEE SSCI 2021)   2021.12

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    researchmap

  • Distributed HALS Algorithm for NMF based on Simple Average Consensus Algorithm Reviewed

    Keiju Hayashi, Tsuyoshi Migita, Norikazu Takahashi

    The 2021 IEEE International Conference on Progress in Informatics and Computing (PIC-2021)   41 - 47   2021.12

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    researchmap

  • Uncalibrated Photometric Stereo Using Superquadrics with Cast Shadow. Reviewed

    Frontiers of Computer Vision - 27th International Workshop(IW-FCV)   1405   267 - 280   2021.7

     More details

    Authorship:Corresponding author   Language:English   Publishing type:Research paper (international conference proceedings)   Publisher:Springer  

    Formulated as an inverse problem of computer graphics, inverse rendering (or photometric stereo) can estimate parameters, such as the shapes and configurations of objects and light sources in the scene, from a set of images. Such results can be useful for applications including recognition, inspection, and/or VR. In the present paper, we extend previous studies in such a way as to incorporate more complex image formation models, specifically superquadrics with cast shadows, that are implemented on a standard graphics API and verify the framework on synthetic and real-world data.

    DOI: 10.1007/978-3-030-81638-4_22

    Web of Science

    researchmap

  • Distributed algorithm for principal component analysis based on power method and average consensus algorithm Reviewed

    Norikazu Takahashi, Mutsuki Oura, Tsuyoshi Migita

    Proceedings of 2020 IEEE International Conference on Progress in Informatics and Computing, PIC 2020   16 - 21   2020.12

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    Principal component analysis is one of the most important methods of multivariate analysis, and has been applied in a wide range of fields such as statistical analysis, machine learning, pattern recognition, signal processing, and communication. Recently, using the idea of multi-agent networks, distributed algorithms for principal component analysis have been proposed for the case where the data matrix is partitioned either row-wise or column-wise. In this paper, considering the case where the data matrix is partitioned both row-wise and column-wise, we propose a new algorithm that allows a multi-agent network to perform principal component analysis in a distributed manner. We also verify its validity by numerical experiments. The proposed algorithm is based on the power method for principal component analysis and the average consensus algorithm.

    DOI: 10.1109/PIC50277.2020.9350816

    Scopus

    researchmap

  • A Genetic Algorithm for Finding Regular Graphs with Minimum Average Shortest Path Length. Reviewed

    Reiji Hayashi, Tsuyoshi Migita, Norikazu Takahashi

    2020 IEEE Symposium Series on Computational Intelligence(SSCI)   2431 - 2436   2020.12

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)   Publisher:IEEE  

    The problem of finding a simple regular graph with the specified order and degree that minimizes the average shortest path length has a long history in graph theory. Recently this problem has attracted a great deal of attention in relation to the design of computer networks in data centers. In this paper, we propose a genetic algorithm for finding an approximate solution to this problem. Because the search space is the set of all simple regular graphs with the specified order and degree, conventional genetic algorithms cannot be directly applied. We propose in this paper new crossover and mutation operators that guarantee the simplicity and regularity of graphs. We also evaluate the effectiveness of the proposed method experimentally.

    DOI: 10.1109/SSCI47803.2020.9308205

    Web of Science

    researchmap

    Other Link: https://dblp.uni-trier.de/db/conf/ssci/ssci2020.html#HayashiMT20

  • Element-Wise Alternating Least Squares Algorithm for Nonnegative Matrix Factorization on One-Hot Encoded Data Reviewed

    Zhuo Wu, Tsuyoshi Migita, Norikazu Takahashi

    Communications in Computer and Information Science   1333   342 - 350   2020.11

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    Matrix factorization is a popular technique used in recommender systems based on collaborative filtering. Given a matrix that represents ratings of items by users, one can obtain latent feature vectors of the users and the items by applying one of the existing matrix factorization algorithms. In this paper, we focus our attention on matrices obtained from categorical ratings using one-hot encoding, and propose an element-wise alternating least squares algorithm to obtain latent feature vectors from such matrices. We next show that the proposed algorithm has the global convergence property in the sense of Zangwill. We also show through experiments using a benchmark dataset that the proposed algorithm is effective for prediction of unknown ratings.

    DOI: 10.1007/978-3-030-63823-8_40

    Scopus

    researchmap

  • Uncalibrated Photometric Stereo Using Quadric Surfaces with Two Cameras. Reviewed

    Frontiers of Computer Vision - 26th International Workshop(IW-FCV)   1212   318 - 332   2020.5

     More details

    Authorship:Corresponding author   Language:English   Publishing type:Research paper (international conference proceedings)   Publisher:Springer  

    Inverse rendering is a method for estimating object shapes and lighting conditions from a set of images. In the present paper, we propose an uncalibrated photometric stereo method that approximates the shapes of the target objects using quadric surfaces (ellipsoids or hyperboloids), and this shape representation allows us to use multiple cameras in order to reduce the GBR ambiguity. The proposed method uses the Levenberg-Marquardt method to minimize the differences between the input images and generated images calculated based on the estimated parameters and the image formation model. It is important to define each term in the cost function depending on the inside or outside of the contour of the estimated quadric surface and/or the target object. The proposed method has been verified on several sets of real images, namely, Vase, Grapes, and Snacks, and we found that the method required less than 100 iterations. On the other hand, there is room for improvement regarding the accuracy of the estimation by taking into account the shadows of the target objects and using a more advanced reflection model.

    DOI: 10.1007/978-981-15-4818-5_24

    Web of Science

    researchmap

    Other Link: https://dblp.uni-trier.de/db/conf/fcv/fcv2020.html#NasuMST20

  • An Infinity Norm-Based Pseudo-Decentralized Discrete-Time Algorithm for Computing Algebraic Connectivity. Reviewed

    IEEE Symposium Series on Computational Intelligence(SSCI)   1292 - 1298   2019.12

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)   Publisher:IEEE  

    In some applications of multiagent networks, it is desired that each agent can evaluate how well the network is connected. In this paper, we propose a novel discrete-time algorithm for each agent to compute the algebraic connectivity of the network in a pseudo-decentralized manner. The proposed algorithm requires less computational cost than the conventional algorithm. We also analyze the dynamical behavior of the proposed algorithm and prove under some assumptions on the parameter values and the initial state values of the agents that all agents can compute the algebraic connectivity.

    DOI: 10.1109/SSCI44817.2019.9002875

    Web of Science

    researchmap

    Other Link: https://dblp.uni-trier.de/db/conf/ssci/ssci2019.html#ShimadaMT19

  • A Distributed HALS Algorithm for Euclidean Distance-Based Nonnegative Matrix Factorization. Reviewed

    IEEE Symposium Series on Computational Intelligence(SSCI)   1332 - 1337   2019.12

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)   Publisher:IEEE  

    This paper proposes a distributed algorithm for multiple agents to perform the Nonnegative Matrix Factorization (NMF) based on the Euclidean distance. The matrix to be factorized is partitioned into multiple blocks, and each block is assigned to one of the agents forming a two-dimensional grid network. Each agent handles a small number of entries of the factor matrices corresponding to the assigned block, and updates their values by using information coming from the neighbors. It is shown that the proposed algorithm simulates the hierarchical alternating least squares method, which is well known as a fast algorithm for NMF based on the Euclidean distance, by making use of a finite-time distributed consensus algorithm.

    DOI: 10.1109/SSCI44817.2019.9003158

    Web of Science

    researchmap

    Other Link: https://dblp.uni-trier.de/db/conf/ssci/ssci2019.html#DomenMT19

  • New Rules for Choosing Values of Consensus Weights in Distributed Training of Neural Networks Reviewed

    Kazuaki Harada, Tsuyoshi Migita, Norikazu Takahashi

    Proc. 2019 International Symposium on Nonlinear Theory and Its Applications   2019.12

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    researchmap

  • A Genetic Algorithm for Maximizing Algebraic Connectivity of Graphs by Adding Multiple Edges Reviewed

    Hiroki Tajiri, Tsuyoshi Migita, Norikazu Takahashi

    Proc. 2019 International Symposium on Nonlinear Theory and Its Applications   2019.12

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

    researchmap

  • A Damped Newton Algorithm for Nonnegative Matrix Factorization Based on Alpha-Divergence. Reviewed

    6th International Conference on Systems and Informatics(ICSAI)   463 - 468   2019.11

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)   Publisher:IEEE  

    DOI: 10.1109/ICSAI48974.2019.9010306

    researchmap

    Other Link: https://dblp.uni-trier.de/db/conf/icsai/icsai2019.html#SanoMT19

  • Batch Estimation for Face Modeling with Tracking on Image Sequence Reviewed

    Tsuyoshi Migita, Ryuichi Saito, Takeshi Shakunaga

    Proc. IW-FCV2019   2019.2

     More details

    Authorship:Lead author   Language:English   Publishing type:Research paper (international conference proceedings)  

    researchmap

  • Real-Time Human Body Tracking with Estimation of Physical Size Reviewed

    Tsuyoshi Migita, Kohei Hase, Takeshi Shakunaga

    FCV2016   5 - 10   2016

     More details

    Authorship:Lead author   Language:English   Publishing type:Research paper (international conference proceedings)  

    researchmap

  • Specular-Free Residual Minimization for Photometric Stereo with Unknown Light Sources. Reviewed

    Tsuyoshi Migita, Kazuhiro Sogawa, Takeshi Shakunaga

    Advances in Image and Video Technology - 5th Pacific Rim Symposium   7087   178 - 189   2011

     More details

    Authorship:Lead author   Language:English   Publishing type:Research paper (international conference proceedings)   Publisher:Springer  

    We address a photometric stereo problem that has unknown lighting conditions. To estimate the shape, reflection properties, and lighting conditions, we employ a nonlinear minimization that searches for parameters that can synthesize images that best fit the input images. A similar approach has been reported previously, but it suffers from slow convergence due to specular reflection parameters. In this paper, we introduce specular-free residual minimization that avoids the negative effects of specular reflection components by projecting the residual onto the complementary space of the light color. The minimization process simultaneously searches for the optimal light color and other parameters. We demonstrate the effectiveness of the proposed method using several real and synthetic image sets.

    DOI: 10.1007/978-3-642-25367-6_16

    Web of Science

    researchmap

    Other Link: https://dblp.uni-trier.de/db/conf/psivt/psivt2011-1.html#MigitaSS11

  • Tracking 3d Pose of Rigid Object by Sparse Template Matching. Reviewed

    Yuki Oka, Toshiyuki Kuroda, Tsuyoshi Migita, Takeshi Shakunaga

    Proceedings of the Fifth International Conference on Image and Graphics(ICIG)   390 - 397   2009

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)   Publisher:IEEE Computer Society  

    Tracking 3d pose of a known object is one of the most important problems in computer vision. This paper proposes an appearance-based approach to this problem by combining the sparse template matching and the particle filter. Although the combination of them has already been discussed for 2d tracker, it has not been applied for efficient 3d tracking. This paper discusses an appearance-based tracker when a surface model of the target 3d object and the initial pose are given. The fundamental framework of the particle filter is provided at first for implementing a pose tracker based on sparse 3d template matching. Then, the coarse-to-fine approach is introduced for efficient implementation. Although the fundamental particle filter often requires a lot of particles for sufficient tracking, the number of particles can be effectively reduced by the coarse-to-fine strategy. Experimental results for both the simulation data and real images show how the proposed method works in frame rate on 3GHz Core 2 Quad(single thread) without using GPU or other special hardware.

    DOI: 10.1109/ICIG.2009.138

    Web of Science

    researchmap

    Other Link: https://dblp.uni-trier.de/db/conf/icig/icig2009.html#OkaKMS09

  • Direct Bundle Estimation for Recovery of Shape, Reflectance Property and Light Position. Reviewed

    Tsuyoshi Migita, Shinsuke Ogino, Takeshi Shakunaga

    Computer Vision - ECCV 2008   5304   412 - 425   2008

     More details

    Authorship:Lead author   Language:English   Publishing type:Research paper (international conference proceedings)   Publisher:Springer  

    Given a set of images captured with a fixed camera while a point light source moves around an object, we can estimate the shape, reflectance property and texture of the object, as well as the positions of the light source. Our formulation is a large-scale nonlinear optimization that allows us to adjust the parameters so that the images synthesized from all of the parameters optimally fit the input images. This type of optimization, which is a variation of the bundle adjustment for structure and motion reconstruction, is often employed to refine a carefully constructed initial estimation. However, the initialization task often requires a great deal of labor, several special devices, or both. In the present paper, we describe (i) an easy method of initialization that does not require any special devices or a precise calibration and (ii) an efficient algorithm for the optimization. The efficiency of the optimization method enables us to use a simple initialization. For a set of synthesized images, the proposed method decreases the residual to zero. In addition, we show that various real objects, including toy models and human faces, can be successfully recovered.

    DOI: 10.1007/978-3-540-88690-7_31

    Web of Science

    researchmap

    Other Link: https://dblp.uni-trier.de/db/conf/eccv/eccv2008-3.html#MigitaOS08

  • Evaluation of Epipole Estimation Methods with/without Rank-2 Constraint across Algebraic/Geometric Error Functions. Reviewed

    Tsuyoshi Migita, Takeshi Shakunaga

    2007 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2007)(CVPR)   1115 - +   2007.6

     More details

    Authorship:Lead author   Language:English   Publishing type:Research paper (international conference proceedings)   Publisher:IEEE Computer Society  

    The best method for estimating the fundamental matrix and/or the epipole over a given set of point correspondences between two images is a nonlinear minimization, which searches a rank-2 fundamental matrix that minimizes the geometric error cost function. When convenience is preferred to accuracy, we often use a linear approximation method, which searches a rank-3 matrix that minimizes the algebraic error. Although it has been reported that the algebraic error causes very poor results, it is currently thought that the relatively inaccurate results of a linear estimation method are a consequence of neglecting the rank-2 constraint, and not a result of exploiting the algebraic error. However, the reason has not been analyzed fully. In the present paper, we analyze the effects of the cost function selection and the rank-2 constraint based on covariance matrix analyses and show theoretically and experimentally that it is more important to enforce the rank-2 constraint than to minimize the geometric cost function.

    DOI: 10.1109/CVPR.2007.383116

    Web of Science

    researchmap

    Other Link: https://dblp.uni-trier.de/db/conf/cvpr/cvpr2007.html#MigitaS07

  • A Real-life Test of Face Recognition System for Dialogue Interface Robot in Ubiquitous Environments. Reviewed

    Fumihiko Sakaue, Makoto Kobayashi, Tsuyoshi Migita, Takeshi Shakunaga

    18th International Conference on Pattern Recognition (ICPR 2006)   1155 - 1160   2006

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)   Publisher:IEEE Computer Society  

    This paper discusses a face recognition system for a dialogue interface robot that really works in ubiquitous environments and reports an experimental result of real-life test in a ubiquitous environment. While a central module of the face recognition system is composed of the decomposed eigenface method, the system also includes a special face detection module and the face registration module. Since face recognition should work on images. captured by a camera equipped on the interface robot, all the methods are tuned for the interface robot. The face detection and recognition modules accomplish robust face detection and recognition when one of the registered users is talking to the robot. Some interesting results are reported with careful analysis of a sufficient real-life experiment.

    DOI: 10.1109/ICPR.2006.157

    Web of Science

    researchmap

    Other Link: https://dblp.uni-trier.de/db/conf/icpr/icpr2006-3.html#SakaueKMS06

  • Estimation of Bidirectional Texture Functions from Bizen-ware Images Reviewed

    T. Migita, S. Sekiguchi, T. Shakunaga

    11th Korea-Japan Joint Workshop on Frontiers of Computer Vision(FCV2005)   171 - 176   2005.1

     More details

    Authorship:Lead author   Language:English   Publishing type:Research paper (international conference proceedings)  

    CiNii Article

    researchmap

  • 非線形最適化による建物画像列からの全周形状一括復元のための初期値設定法 Reviewed

    椋木雅之, 右田剛史, 青山正人, 浅田尚紀

    情報処理学会論文誌   2004

     More details

    Language:Japanese  

    researchmap

  • Large object shape recovery from uncalibrated camera motion by non-linear optimization

    Naoki Asada, Masayuki Mukunoki, Tsuyoshi Migita, Masahito Aoyama

    Sixth IASTED International Conference on Signal and Image Processing   151 - 156   2004

     More details

    Publishing type:Research paper (international conference proceedings)  

    3D recovery of object shape and camera motion from 2D image sequence is formulated as a non-linear optimization problem. Such a non-linear approach ensures the most precise solution, but it involves computational difficulties, i.e. complexity and instability. This paper describes a practical procedure to solve the non-linear optimization problem for object shape and camera motion recovery. First, we discuss the imaging model for large objects such as buildings; one shot and pseudo wide angle models, where the camera motion is modeled as a uniform motion along circular path with gazing at the center. Then, the generalized initial values for circular motion is proposed and "mean appearance ratio (MAR)" of feature points is defined as a measure of stability. Experimental results with synthetic images show that 3D recovery was stably performed from image sequences with MAR over 15%, quasi-stable with over 8.5% for one shot model, and stable with over 10.3%, quasi-stable with over 4. 4% for pseudo wide angle model. 3D shape and motion using real images were recovered successfully from MAR 17% for one shot model and 6% for pseudo wide angle one. These results have demonstrated the robustness of the generalized initial values and effectiveness of MAR for large object shape from uncalibrated camera motion problem.

    Scopus

    researchmap

  • 3次元形状・運動復元のための高速非線形最適化計算法 Reviewed

    右田剛史, 天野 晃, 浅田尚紀

    情報処理学会論文誌   2003

     More details

    Authorship:Lead author   Language:Japanese  

    researchmap

  • Incremental procedure for recovering entire building shape from close range images

    Migita Tsuyoshi, Amano Akira, Asada Naoki

    International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives   34 ( 5W12 )   237 - 240   2003

     More details

    Publishing type:Research paper (international conference proceedings)  

    This paper describes a method for recovering entire 3D shape of a building from an image sequence. This is a kind of “Shape and Motion recovery” problem in the computer vision field, whereas the conventional methods do not work well with the images taken around a large object in the near distance. Since such image sequence is a set of partial observations, the problem of 3D recovery becomes unstable. We first discuss the property of the local minima of the nonlinear optimization function, and then describe an incremental procedure to find the global minimum by avoiding the pseudo solutions. Experiments using the real images have shown that the proposed method successfully recovered the 3D shapes from eleven sets of image sequences.

    Scopus

    researchmap

  • A Unique Recovery of3D Shape and Size from Motion.

    Akira Amano, Tsuyoshi Migita, Naoki Asada

    Proceedings of the IAPR Conference on Machine Vision Applications (IAPR MVA 2000)(MVA)   525 - 528   2000

     More details

    Publishing type:Research paper (international conference proceedings)  

    researchmap

    Other Link: https://dblp.uni-trier.de/rec/conf/mva/2000

  • 級数の再帰的集約による多倍長数の計算法とπの計算への応用 Reviewed

    右田剛史, 天野晃, 浅田尚紀, 藤野清次

    情報処理学会論文誌   40 ( 12 )   4193 - 4200   1999

     More details

    Authorship:Lead author   Language:Japanese  

    researchmap

▼display all

MISC

  • Speeding Up an Algorithm for Searching Generalized Moore Graphs

    電子情報通信学会技術研究報告(Web)   122 ( 65(NLP2022 1-25) )   2022.5

     More details

    Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)  

    J-GLOBAL

    researchmap

  • Visualization of Decisions of CNN Models Trained on Map Images Labeled Based on Traffic Accident Data

    電子情報通信学会技術研究報告(Web)   122 ( 65(NLP2022 1-25) )   2022.5

     More details

    Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)  

    J-GLOBAL

    researchmap

  • Distributed HALS Algorithm for NMF based on Simple Average Consensus Algorithm Reviewed

    Keiju Hayashi, Tsuyoshi Migita, Norikazu Takahashi

    PIC 2021 (December 17-19, 2021) Shanghai,   41 - 47   2021.12

     More details

    Language:English   Publishing type:Research paper, summary (international conference)  

    researchmap

  • べき乗法と平均合意に基づく分散的主成分分析アルゴリズムの性能評価

    大浦 夢月, 右田 剛史, 高橋 規一

    2021年度(第72回) 電気・情報関連学会中国支部連合大会   2021.10

     More details

    Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)  

    researchmap

  • 交通事故危険箇所予測のための地図画像の深層学習

    呉 志堅, 右田 剛史, 高橋 規一

    2021年度(第72回) 電気・情報関連学会中国支部連合大会   2021.10

     More details

    Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)  

    researchmap

  • マルチニューラルネットワークの分散学習におけるパラメータ値送受信法の提案

    萱谷 竜也, 右田 剛史, 高橋 規一

    2021年度(第72回) 電気・情報関連学会中国支部連合大会   2021.10

     More details

    Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)  

    researchmap

  • Modification of Optimization Problem in Randomized NMF and Design of Optimization Method based on HALS Algorithm

    舛田昂生, 右田剛史, 高橋規一

    電子情報通信学会技術研究報告(Web)   121 ( 79(NC2021 1-17) )   2021

     More details

    Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)  

    J-GLOBAL

    researchmap

  • Uncalibrated Photometric Stereo Using Superquadrics with Cast Shadow. Reviewed

    Frontiers of Computer Vision - 27th International Workshop(IW-FCV)   267 - 280   2021

     More details

    Language:English   Publishing type:Research paper, summary (international conference)   Publisher:Springer  

    DOI: 10.1007/978-3-030-81638-4_22

    researchmap

    Other Link: https://dblp.uni-trier.de/db/conf/fcv/fcv2021.html#NasuMT21

  • Graph Structure Optimization Using Genetic Algorithms

    田尻紘生, 右田剛史, 高橋規一

    電子情報通信学会技術研究報告(Web)   120 ( 430(NLP2020 55-65) )   2021

     More details

    Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)  

    J-GLOBAL

    researchmap

  • Proposal of Novel Distributed Learning Algorithms for Multi-Neural Networks

    原田和明, 右田剛史, 高橋規一

    電子情報通信学会技術研究報告(Web)   120 ( 430(NLP2020 55-65) )   2021

     More details

    Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)  

    J-GLOBAL

    researchmap

  • Simplification of Average Consensus Algorithm in Distributed HALS Algorithm for NMF

    林京寿, 右田剛史, 高橋規一

    電子情報通信学会技術研究報告(Web)   121 ( 79(NC2021 1-17) )   2021

     More details

    Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)  

    J-GLOBAL

    researchmap

  • Distributed Algorithm for Principal Component Analysis Based on Power Method and Average Consensus Algorithm Reviewed

    Norikazu Takahashi, Mutsuki Oura, Tsuyoshi Migita

    The 2020 International Conference on Progress in Informatics and Computing (PIC-2020)   2020.12

     More details

    Language:English   Publishing type:Research paper, summary (international conference)  

    researchmap

  • A Genetic Algorithm for Finding Regular Graphs with Minimum Average Shortest Path Length. Reviewed

    2020 IEEE Symposium Series on Computational Intelligence(SSCI)   2431 - 2436   2020

     More details

    Language:English   Publishing type:Research paper, summary (international conference)   Publisher:IEEE  

    DOI: 10.1109/SSCI47803.2020.9308205

    researchmap

    Other Link: https://dblp.uni-trier.de/db/conf/ssci/ssci2020.html#HayashiMT20

  • Uncalibrated Photometric Stereo Using Quadric Surfaces with Two Cameras. Reviewed

    Frontiers of Computer Vision - 26th International Workshop(IW-FCV)   318 - 332   2020

     More details

    Language:English   Publishing type:Research paper, summary (international conference)   Publisher:Springer  

    DOI: 10.1007/978-981-15-4818-5_24

    researchmap

    Other Link: https://dblp.uni-trier.de/db/conf/fcv/fcv2020.html#NasuMST20

  • MODIFIED MULTIPLICATIVE UPDATE RULE FOR GNMF AND ITS GLOBAL CONVERGENCE

    佐野雄大, 右田剛史, 高橋規一

    電子情報通信学会大会講演論文集(CD-ROM)   2020   2020

     More details

    Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)  

    J-GLOBAL

    researchmap

  • Performance Evaluation of GNMF-based Clustering Using Cluster Ensembles

    佐野雄大, 右田剛史, 高橋規一

    人工知能学会全国大会(Web)   34th   2020

     More details

    Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)  

    J-GLOBAL

    researchmap

  • A Projected Consensus-Based Algorithm for Minimizing the Maximum Error of a System of Linear Equations with Nonnegativity Constraints

    川嶌康輔, 右田剛史, 高橋規一

    電子情報通信学会技術研究報告   119 ( 471(NLP2019 113-133) )   2020

     More details

    Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)  

    J-GLOBAL

    researchmap

  • A Distributed Algorithm for Solving Sandberg-Willson Equations Based on Sequential Minimization of Convex Quadratic Functions

    武内雅章, 右田剛史, 高橋規一

    電子情報通信学会技術研究報告   119 ( 471(NLP2019 113-133) )   2020

     More details

    Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)  

    J-GLOBAL

    researchmap

  • A Novel Hierarchical Alternating Least Squares Algorithm for L1 Regularized Nonnegative Matrix Factorization

    佐野雄大, 右田剛史, 高橋規一

    情報科学技術フォーラム講演論文集   19th   2020

     More details

    Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)  

    J-GLOBAL

    researchmap

  • A Genetic Algorithm for Minimizing Average Shortest Path Length of Regular Graphs

    林嶺司, 右田剛史, 高橋規一

    電子情報通信学会技術研究報告(Web)   120 ( 26(NLP2020 1-10) )   2020

     More details

    Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)  

    J-GLOBAL

    researchmap

  • Distributed Algorithms based on Multiplicative Update Rules for Nonnegative Matrix Factorization

    道免陽平, 右田剛史, 高橋規一

    電子情報通信学会技術研究報告(Web)   120 ( 245(CAS2020 19-36) )   2020

     More details

    Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)  

    J-GLOBAL

    researchmap

  • Generalization of Pseudo-Decentralized Continuous-Time Algorithms for Estimating Algebraic Connectivity

    島田捷生, 右田剛史, 高橋規一

    電子情報通信学会技術研究報告(Web)   120 ( 245(CAS2020 19-36) )   2020

     More details

    Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)  

    J-GLOBAL

    researchmap

  • Element-Wise Alternating Least Squares Algorithm for Nonnegative Matrix Factorization on One-Hot Encoded Data. Reviewed

    Neural Information Processing - 27th International Conference   342 - 350   2020

     More details

    Language:English   Publishing type:Research paper, summary (international conference)   Publisher:Springer  

    DOI: 10.1007/978-3-030-63823-8_40

    researchmap

    Other Link: https://dblp.uni-trier.de/db/conf/iconip/iconip2020-5.html#WuMT20

  • New Rules for Choosing Values of Consensus Weights in Distributed Training of Neural Networks Reviewed

    Kazuaki Harada, Tsuyoshi Migita, Norikazu Takahashi

    2019 International Symposium on Nonlinear Theory and Its Applications   2019.12

     More details

    Language:English   Publishing type:Research paper, summary (international conference)  

    researchmap

  • A Genetic Algorithm for Maximizing Algebraic Connectivity of Graphs by Adding Multiple Edges Reviewed

    Hiroki Tajiri, Tsuyoshi Migita, Norikazu Takahashi

    2019 International Symposium on Nonlinear Theory and Its Applications   2019.12

     More details

    Language:English   Publishing type:Research paper, summary (international conference)  

    researchmap

  • Batch Estimation for Face Modeling with Tracking on Image Sequence Reviewed

    Tsuyoshi Migita, Ryuichi Saito, Takeshi Shakunaga

    The International Workshop on Frontiers of Computer Vision (IW-FCV2019)   2019.2

     More details

    Authorship:Lead author   Language:English   Publishing type:Research paper, summary (international conference)  

    researchmap

  • An Infinity Norm-Based Pseudo-Decentralized Discrete-Time Algorithm for Computing Algebraic Connectivity. Reviewed

    IEEE Symposium Series on Computational Intelligence(SSCI)   1292 - 1298   2019

     More details

    Language:English   Publishing type:Research paper, summary (international conference)   Publisher:IEEE  

    DOI: 10.1109/SSCI44817.2019.9002875

    researchmap

    Other Link: https://dblp.uni-trier.de/db/conf/ssci/ssci2019.html#ShimadaMT19

  • A Damped Newton Algorithm for Nonnegative Matrix Factorization Based on Alpha-Divergence. Reviewed

    6th International Conference on Systems and Informatics(ICSAI)   463 - 468   2019

     More details

    Language:English   Publishing type:Research paper, summary (international conference)   Publisher:IEEE  

    DOI: 10.1109/ICSAI48974.2019.9010306

    researchmap

    Other Link: https://dblp.uni-trier.de/db/conf/icsai/icsai2019.html#SanoMT19

  • A Distributed HALS Algorithm for Euclidean Distance-Based Nonnegative Matrix Factorization. Reviewed

    IEEE Symposium Series on Computational Intelligence(SSCI)   1332 - 1337   2019

     More details

    Language:English   Publishing type:Research paper, summary (international conference)   Publisher:IEEE  

    DOI: 10.1109/SSCI44817.2019.9003158

    researchmap

    Other Link: https://dblp.uni-trier.de/db/conf/ssci/ssci2019.html#DomenMT19

  • 遺伝アルゴリズムによる代数的連結度最大化

    田尻紘生, 右田剛史, 高橋規一

    情報科学技術フォーラム講演論文集   18th   2019

     More details

    Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)  

    J-GLOBAL

    researchmap

  • マルチエージェントネットワークによる非負値行列因子分解の分散計算

    道免陽平, 右田剛史, 高橋規一

    情報科学技術フォーラム講演論文集   18th   2019

     More details

    Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)  

    J-GLOBAL

    researchmap

  • 光源の異なる画像を用いた楕円体と一葉双曲面のパラメータ推定

    那須巧海, 右田剛史, 尺長健, 高橋規一

    情報科学技術フォーラム講演論文集   18th   2019

     More details

    Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)  

    J-GLOBAL

    researchmap

  • ニューラルネットワークの分散学習における新たな合意重み決定法

    原田和明, 右田剛史, 高橋規一

    情報科学技術フォーラム講演論文集   18th   2019

     More details

    Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)  

    J-GLOBAL

    researchmap

  • 単調方程式のニュートン型解法に基づく新たな非負値行列因子分解アルゴリズム

    佐野雄大, 右田剛史, 高橋規一

    情報科学技術フォーラム講演論文集   18th   2019

     More details

    Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)  

    J-GLOBAL

    researchmap

  • 幾何学的距離に基づく楕円体フィッティングによる実時間人物姿勢追跡

    北村拓也, 右田剛史, 尺長健

    電子情報通信学会技術研究報告   117 ( 443(CNR2017 23-49) )   2018

  • 動画像中の顔追跡による3次元顔モデルの自動生成

    齋藤竜一, 右田剛史, 尺長健

    電子情報通信学会技術研究報告   117 ( 391(PRMU2017 112-144) )   2018

  • A Levenberg-Marquardt-Based Face Tracking Method with Shape Estimation in Real-Time

    筒井健斗, 右田剛史, 尺長健

    電子情報通信学会技術研究報告   115 ( 517(PRMU2015 164-197) )   173 - 178   2016.3

     More details

  • Real-time Human Pose Tracking Using Depth Sensor by Connected Sphere Model

    福山大貴, 右田剛史, 尺長健

    電子情報通信学会技術研究報告   116 ( 208(PRMU2016 54-89) )   2016

  • パーティクルフィルタとLevenberg-Marquardt法による顔・人物姿勢追跡の検討

    筒井健斗, 溝部諒, 右田剛史, 尺長健

    電子情報通信学会技術研究報告   114 ( 410(MVE2014 49-73) )   2015

  • RGBD画像を用いた人物姿勢追跡の高速化と人体モデルパラメータ推定への適用

    長谷康平, 溝部諒, 右田剛史, 尺長健

    情報処理学会研究報告(Web)   2015 ( CVIM-197 )   2015

  • 3d face tracking and recognition for depth-image sensor

    片山聡一朗, 中岸久佳, 右田剛史, 尺長健

    電子情報通信学会技術研究報告   112 ( 385(PRMU2012 84-129) )   199 - 204   2013.1

     More details

    Language:Japanese   Publisher:The Institute of Electronics, Information and Communication Engineers  

    This paper discusses on face tracking and recognition when depth-image sensor is available. For the purpose, our image based approach is extended for covering depth sensor. Experimental results on real depth-image sequences show the effectiveness of the proposed method.

    CiNii Article

    CiNii Books

    J-GLOBAL

    researchmap

  • 形状・反射特性・光源の同時推定法の改良と様々な実画像への適用

    槌谷洋介, 右田剛史, 尺長健

    情報処理学会研究報告(CD-ROM)   2012 ( 6 )   2013

  • Stereoscopic Shape Reconstruction from Image Sequence using Spline Interpolation

    WATANABE JUN, MIGITA TSUYOSHI, SHAKUNAGA TAKESHI

    Technical report of IEICE. Multimedia and virtual environment   111 ( 380 )   277 - 284   2012.1

     More details

    Language:Japanese   Publisher:The Institute of Electronics, Information and Communication Engineers  

    We discuss a method for 3d shape reconstruction from a stereoscopic image sequence. Once the depth map and camera parameters are given, any image can be warped to the reference image. Therefore, the depth map and the camera parameters can be estimated by minimizing the sum of the variances among these warped images. The depth map is described by a set of bicubic patches, i.e. each patch is determined by cubic spline interpolation using neighboring 16 points. A regularization term is introduced to the cost function to stabilize the estimation. The method is verified using several real image sets.

    CiNii Article

    CiNii Books

    researchmap

  • Stereoscopic Shape Reconstruction from Image Sequence using Spline Interpolation

    渡邊隼, 右田剛史, 尺長健

    電子情報通信学会技術研究報告   111 ( 378(CQ2011 62-69) )   159 - 166   2012.1

     More details

    Language:Japanese   Publisher:The Institute of Electronics, Information and Communication Engineers  

    We discuss a method for 3d shape reconstruction from a stereoscopic image sequence. Once the depth map and camera parameters are given, any image can be warped to the reference image. Therefore, the depth map and the camera parameters can be estimated by minimizing the sum of the variances among these warped images. The depth map is described by a set of bicubic patches, i.e. each patch is determined by cubic spline interpolation using neighboring 16 points. A regularization term is introduced to the cost function to stabilize the estimation. The method is verified using several real image sets.

    CiNii Article

    CiNii Books

    J-GLOBAL

    researchmap

  • Stereoscopic Shape Reconstruction from Image Sequence using Spline Interpolation

    2012 ( 50 )   1 - 8   2012.1

     More details

  • Implementation and Evaluation of Simultaneous Estimation of Shape, Reflectance and Lighting

    右田剛史, 槌谷洋介, 尺長健

    情報処理学会研究報告(CD-ROM)   2011 ( 6 )   2012

  • Simultaneous Estimation of Shape, Reflectance Property and Lightng Conditions based on Complementary Space of Light Color

    祖川和弘, 右田剛史, 尺長健

    情報処理学会研究報告(CD-ROM)   2010 ( 6 )   2011

  • Specular-Free Residual Minimization for Photometric Stereo with Unknown Light Sources.

    Tsuyoshi Migita, Kazuhiro Sogawa, Takeshi Shakunaga

    Advances in Image and Video Technology - 5th Pacific Rim Symposium   178 - 189   2011

  • Improvement of Stereoscopic Reconstruction with a Spline Surface

    高田潤, 右田剛史, 尺長健

    情報処理学会研究報告(CD-ROM)   2010 ( 6 )   2011

  • Stereoscopic Reconstruction of Facial Shape with a Spline Surface

    永井雄大, 右田剛史, 尺長健

    電子情報通信学会技術研究報告   109 ( 471(HIP2009 118-210) )   2010

  • Recovery of Facial Shape based on Simultaneous Estimation of Shape, Reflectance Property and Light Position

    澤見幸枝, 右田剛史, 尺長健

    電子情報通信学会技術研究報告   109 ( 471(HIP2009 118-210) )   2010

  • Tracking 3d Pose of Rigid Object by Sparse Template Matching.

    Yuki Oka, Toshiyuki Kuroda, Tsuyoshi Migita, Takeshi Shakunaga

    Proceedings of the Fifth International Conference on Image and Graphics(ICIG)   390 - 397   2009

     More details

  • Simultaneous Recovery of Reflectance Property, Shape and Light Position based on Torrance-Sparrow Model

    OGINO Shinsuke, MIGITA Tsuyoshi, SHAKUNAGA Takeshi

    IEICE technical report   107 ( 539 )   557 - 564   2008.3

     More details

    Language:Japanese   Publisher:The Institute of Electronics, Information and Communication Engineers  

    Given a set of images, where a point light source moves around an object, we can formulate recovery of the reflectance property, texture and shape of the object, as well as the positions of the light source. We herein describe an efficient algorithm to address this large-scale nonlinear optimization problem. Various objects, including toy models and human faces, are successfully recovered without any special devices nor a precise calibration.

    CiNii Article

    CiNii Books

    researchmap

  • Report on 2007 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR2007)

    OKATANI Takayuki, SUGIMOTO Shigeki, HIURA Shinsaku, MUKAIGAWA Yasuhiro, KINOSHITA Koichi, NISHIYAMA Masashi, MIGITA Tsuyoshi, OKUTOMI Masatoshi

    IPSJ SIG Notes. CVIM   161   217 - 228   2008.1

     More details

    Language:Japanese   Publisher:Information Processing Society of Japan (IPSJ)  

    This report gives an overview of 2007 IEEE Computer Society Conference on Compute Vision and Pattern Recognition(CVPR2007), held in Minneapolis, Minnesota, USA, from June 19th to 21st, 2007.

    CiNii Article

    CiNii Books

    researchmap

  • Report on 2007 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR2007)

    OKATANI Takayuki, SUGIMOTO Shigeki, HIURA Shinsaku, MUKAIGAWA Yasuhiro, KINOSHITA Koichi, NISHIYAMA Masashi, MIGITA Tsuyoshi, OKUTOMI Masatoshi

    IEICE technical report   107 ( 427 )   249 - 260   2008.1

     More details

    Language:Japanese   Publisher:The Institute of Electronics, Information and Communication Engineers  

    This report gives an overview of 2007 IEEE Computer Society Conference on Compute Vision and Pattern Recognition(CVPR2007), held in Minneapolis, Minnesota, USA, from June 19th to 21st, 2007.

    CiNii Article

    CiNii Books

    researchmap

  • Efficient Object Tracking with 3D Sparse Template in Coarse-to-fine Search

    岡裕希, 黒田利行, 右田剛史, 尺長健

    電子情報通信学会技術研究報告   108 ( 363(PRMU2008 147-188) )   2008

  • Direct Bundle Estimation for Recovery of Shape, Reflectance Property and Light Position.

    Tsuyoshi Migita, Shinsuke Ogino, Takeshi Shakunaga

    Computer Vision - ECCV 2008   412 - 425   2008

  • Simultaneous Recovery of Reflectance Property, Shape and Light Position based on Torrance-Sparrow Model

    荻野真佑, 右田剛史, 尺長健

    情報処理学会研究報告   2008 ( 27(CVIM-162) )   2008

  • Efficient Sparse Template Tracking along with Directional Integral Matching

    黒田利行, 大森誠, 児玉健二, 右田剛史, 尺長健

    電子情報通信学会技術研究報告   108 ( 363(PRMU2008 147-188) )   2008

  • Evaluation of Epipole Estimation Methods with/without Rank-2 Constraint across Algebraic/Geometric Error Functions.

    Tsuyoshi Migita, Takeshi Shakunaga

    2007 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2007)(CVPR)   2007

     More details

  • One Dimensional Epipole Search based on Point Correspondences in Two Uncalibrated Views

    MIGITA Tsuyoshi, SHAKUNAGA Takeshi

    IEICE technical report   105 ( 674 )   241 - 248   2006.3

     More details

    Language:Japanese   Publisher:The Institute of Electronics, Information and Communication Engineers  

    The fundamental matrix can be estimated from 7 or more point correspondences in two uncalibrated views, and essentially it is an epipole search in 2-dimensional space (hemisphere). However, since the corresponding cost function is a non-linear one, unique solution is not guaranteed. While the well-known 8-point algorithm gives an approximate solution, neglecting the rank constraint on the fundamental matrix, we strictly take the constraint into account and obtain a better solution. Specifically, we reduce the problem into a high-order polynomial equation in one variable, which is satisfied by the ratio (e.g. x/z) of all the optimal or locally optimal epipole coordinates (x, y, z). We also show a lower-order equation by introducing an approximation, which still outperforms the 8-point algorithm.

    CiNii Article

    CiNii Books

    researchmap

  • One Dimensional Epipole Search based on Point Correspondences in Two Uncalibrated Views

    右田剛史, 尺長健

    情報処理学会研究報告   2006 ( 25(CVIM-153) )   2006

  • A Real-life Test of Face Recognition System for Dialogue Interface Robot in Ubiquitous Environments.

    Fumihiko Sakaue, Makoto Kobayashi, Tsuyoshi Migita, Takeshi Shakunaga

    18th International Conference on Pattern Recognition (ICPR 2006)   1155 - 1160   2006

     More details

  • One-Dimensional Search for Reliable Epipole Estimation.

    Tsuyoshi Migita, Takeshi Shakunaga

    Advances in Image and Video Technology(PSIVT)   1215 - 1224   2006

  • Evaluation of the effect of rank-2 constraint on the accuracy of epipole estimation

    右田剛史, 尺長健

    情報処理学会研究報告   2006 ( 115(CVIM-156) )   2006

  • Face Discrimination System for Dialog Interface Robot in Ubiquitous Environments

    SAKAUE Fumihiko, MIGITA Tsuyoshi, SHAKUNAGA Takeshi, SATAKE Junji, CHIKAMA Masaki, UEDA Hirotada

    IEICE technical report   105 ( 374 )   27 - 32   2005.10

     More details

    Language:Japanese   Publisher:The Institute of Electronics, Information and Communication Engineers  

    The paper presents a face recognition system for a dialog interface robot in ubiquitous environments. In the system, a decomposed eigenface method is used for the face recognition. The method realizes robust recognition under various lighting conditions. We report experimental results in Ubiquitous Home using the system.

    CiNii Article

    CiNii Books

    researchmap

  • BTF Recovery Based on a Fourier Expansion of BRDF and Its Application to Vitrual Photometric Environment

    江角直起, 右田剛史, 尺長健

    情報処理学会研究報告   2005 ( 18(CVIM-148) )   2005

  • Simultaneous recovery of Bidirectional Texture Function and Shape by Linear Combination of Basis Reflectance Models

    関口真, 右田剛史, 尺長健

    情報処理学会研究報告   2005 ( 18(CVIM-148) )   2005

  • Fast and Stable Method for 3D Shape Recovery from an Image Sequence using Non - Linear Least Squares

    MIGITA T., ASADA N.

    IPSJ SIG Notes. CVIM   2004 ( 40 )   157 - 172   2004.5

     More details

    Language:Japanese   Publisher:Information Processing Society of Japan (IPSJ)  

    Simultaneous recovery of shape and motion from an image sequence is directly formulated as minimization of reprojection errors via the nonlinear least squares. Although several linear foromulations which ensure unique solution are also known, the nonlinear approach can be applied to much broader configurations, and gives more accurate results. We investigate fast optimization algorithm and several methods to avoid local minima for nonlinear reconstruction problem. We test our methods on recovering entire 3D shape from a building image sequence with several hundred images and several hundred feature points.

    CiNii Article

    CiNii Books

    researchmap

    Other Link: http://id.nii.ac.jp/1001/00052498/

  • Batch Structure from Motion for Entire 3D Shape Recovery from a Building Image Sequence Based on Reprojection Error Minimization

    MUKUNOKI M., MIGITA T., AMANO A., AOYAMA M., ASADA N.

    IPSJ SIG Notes. CVIM   2004 ( 6 )   81 - 88   2004.1

     More details

    Language:Japanese   Publisher:Information Processing Society of Japan (IPSJ)  

    We propose a procedure for recovering entire 3D shape from a building image sequence with non-linear optimization method. In this case, the initial values of the unknown variables in the optimization process is crucial. Thus the direct application of the non-linear optimization process has not been fully used in shape recovery. In this paper, first, we investigate an initialization method, which is very simple and relatively generic to the building shape recovery problem. Then, we propose a method for restoring the optimization process from a local minimum. Experimental results using real and synthetic image have shown that our algorithm stably recover 3D shapes.

    CiNii Article

    CiNii Books

    researchmap

    Other Link: http://id.nii.ac.jp/1001/00052536/

  • 少数の画像を用いた全周囲3次元形状モデルの生成

    保田和隆, 右田剛史, 青山正人, 椋木雅之, 浅田尚紀

    情報科学技術フォーラム   FIT 2003   2003

  • 3-D Dense Model Generation from A Sparse Image Sequence

    保田和隆, 右田剛史, 青山正人, 椋木雅之, 浅田尚紀

    情報処理学会研究報告   2003 ( 41(CVIM-138) )   2003

  • A linear Shape from Motion algorithm using rotation information of the cameras.

    右田剛史, 天野晃, 浅田尚紀

    電子情報通信学会技術研究報告   102 ( 156(PRMU2002 31-43) )   2002

  • Entire Building Shape Recovery from Near Distance Images.

    Tsuyoshi Migita, Akira Amano, Naoki Asada

    Proceedings of the IAPR Conference on Machine Vision Applications (IAPR MVA 2002)(MVA)   2002 ( 2(CVIM-131) )   277 - 280   2002

  • A Unique Recovery of 3D Shape and Size from Motion. Reviewed

    Akira Amano, Tsuyoshi Migita, Naoki Asada

    Proceedings of the IAPR Conference on Machine Vision Applications (IAPR MVA 2000)(MVA)   525 - 528   2000

     More details

    Language:English   Publishing type:Research paper, summary (international conference)  

    researchmap

    Other Link: https://dblp.uni-trier.de/rec/conf/mva/2000

  • 因子分解法の不定性解消 接触軌跡を用いたスケールの決定と鏡映の判定

    右田剛史, 天野晃, 浅田尚紀

    電気・情報関連学会中国支部連合大会講演論文集   50th   1999

  • Estimation of Center of Gravity by Integrating Visual and Physical Information

    AMANO Akira, MIGITA Tsuyoshi, ASADA Naoki

    IPSJ SIG Notes. CVIM   1998 ( 103 )   41 - 48   1998.11

     More details

    Language:Japanese   Publisher:Information Processing Society of Japan (IPSJ)  

    The task of computer vision is to recover accurate 3-dimensional shape of objects from 2-dimensional images. In such a vision task, the observer is assumed to be outside of the scene, and this means that the scene configuration are never destroyed by the observre. In this paper, we propose a new paradigm "active recognition", in which the object information is obtained by cooperation of visual and physical systems which can reform the scene configuration. Experiments on the estimation of the center of gravity was performed with a robot arm and a camera that were used to push and track the object. The stable results have shown the effectiveness of the integration of visual and physical information.

    CiNii Article

    CiNii Books

    researchmap

  • Recursive Reduction of Series for Multiple-precision Evaluation and its Application to Pi Calculation.

    右田剛史, 天野晃, 浅田尚紀, 藤野清次

    情報処理学会研究報告   98 ( 115(HPC-74) )   1998

  • Integration of Visual and Physical Information for Object Recognition

    MIGITA Tsuyoshi, AMANO Akira, ASADA Naoki

    Proceedings of the IEICE General Conference   363 - 363   1998

     More details

    Language:Japanese   Publisher:The Institute of Electronics, Information and Communication Engineers  

    CiNii Article

    CiNii Books

    researchmap

▼display all

Presentations

  • 形状のブロック分割と基底を用いた表現によるインバースレンダリングの検討

    向山太基, 右田剛史, 尺長健

    MIRU2017  2017  情報処理学会CVIM研究会

     More details

    Event date: 2017.8.7 - 2017.8.10

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:広島国際会議場  

    researchmap

  • Real-Time Human Body Tracking with Estimation of Physical Size International conference

    Tsuyoshi Migita, Kohei Hase, Takeshi Shakunaga

    FCV2016  2016  FCV2016 Committee

     More details

    Event date: 2016.2.17 - 2016.2.19

    Language:English   Presentation type:Oral presentation (general)  

    Venue:Takayama  

    researchmap

  • Estimation of Bidirectional Texture Functions from Bizen-ware Images

    *T. Migita, S. Sekiguchi, T. Shakunaga

    Proc. 11th Korea-Japan Joint Workshop on Frontiers of Computer Vision(FCV2005)  2005 

     More details

    Event date: 2005.1

    Venue:Gwangju, Korea  

    researchmap

  • A Linear Shape from Motion Algorithm using Rotation Information of the Cameras

    Akira Amano, *Tsuyoshi Migita, Naoki Asada

    Vision Interface 2003  2003 

     More details

    Event date: 2003.6.11 - 2003.6.13

    Venue:Halifax, Canada  

    researchmap

  • 近接撮影画像列からの建物の3次元全周復元

    *右田剛史, 天野晃, 浅田尚紀

    画像の理解・認識シンポジウム MIRU 2002  2002 

     More details

    Event date: 2002.7.30 - 2002.8.1

    Venue:名古屋  

    researchmap

  • Stable Recovery of Shape and Motion from Partially Tracked Feature Points with Fast Nonlinear Optimization

    Akira Amano, *Tsuyoshi Migita, Naoki Asada

    The 15th International Conference on Vision Interface (VI2002)  2002 

     More details

    Event date: 2002.5.27 - 2002.5.29

    Venue:Calgary, Canada  

    researchmap

  • A Thin Lens Based Camera Model for Depth Estimation from Defocus and Translation by Zooming

    M. Baba, N. Asada, A. Oda, *T. Migita

    15th International Conference on Vision Interface (VI2002)  2002 

     More details

    Event date: 2002.5.27 - 2002.5.29

    Venue:Calgary, Canada  

    researchmap

  • 原爆ドームの立体表示---建物等の全周囲3次元形状復元---

    *右田剛史, 天野晃, 浅田尚紀

    第3回IEEE広島支部学生シンポジウム  2001 

     More details

    Event date: 2001.12.14 - 2001.12.15

    Venue:広島  

    researchmap

  • 3次元形状復元問題における非線形最適化計算の高速化

    *右田剛史, 天野晃, 浅田尚紀

    第2回IEEE広島支部学生シンポジウム  2001 

     More details

    Event date: 2001.1.13 - 2001.1.14

    Venue:広島  

    researchmap

  • 非線形最適化計算を用いた運動からの形状復元

    *右田剛史, 天野晃, 浅田尚紀

    画像の理解・認識シンポジウム MIRU 2000  2000 

     More details

    Event date: 2000.7.18 - 2000.7.21

    Venue:長野  

    researchmap

  • 能動認識: 因子分解法における形状とサイズ不定性の解消

    天野晃, *右田剛史, 浅田尚紀

    画像の理解・認識シンポジウム MIRU 2000  2000 

     More details

    Event date: 2000.7.18 - 2000.7.21

    Venue:長野  

    researchmap

  • 視覚情報と接触情報の統合による3次元形状復元

    *右田剛史, 天野晃, 浅田尚紀

    第1回IEEE広島支部学生シンポジウム  2000 

     More details

    Event date: 2000.1.18 - 2000.1.19

    Venue:広島  

    researchmap

▼display all

Awards

  • Best Paper Award

    2021.12   IEEE PIC-2021   Distributed HALS Algorithm for NMF based on Simple Average Consensus Algorithm

    Keiju Hayashi, Tsuyoshi Migita, Norikazu Takahashi

     More details

  • Best Paper Award

    2019.2   IW-FCV 2019   Batch Estimation for Face Modeling with Tracking on Image Sequence

    Tsuyoshi Migita, Ryuichi Saito, Takeshi Shakunaga

     More details

  • 電気・情報関連学会中国支部連合大会奨励賞

    2000  

     More details

    Country:Japan

    researchmap

 

Class subject in charge

  • Laboratory Work and Practice on Basic Engineering (2022academic year) 1st and 2nd semester  - 火5~8

  • Laboratory Work and Practice on Basic Engineering (2022academic year) 1st and 2nd semester  - 火5~8

  • Information Technology Experiments B (Media Processing) (2022academic year) Third semester  - 火3~7,木3~7

  • Engineering English (2022academic year) Late  - その他

  • Technical Writing (2022academic year) Prophase  - その他

  • Technical Presentation (2022academic year) Late  - その他

  • Specific Research of Electronics and Information Systems Engineering (2022academic year) Year-round  - その他

  • Laboratory Work and Practice on Basic Engineering (2021academic year) 1st and 2nd semester  - 火5,火6,火7,火8

  • Laboratory Work and Practice on Basic Engineering (2021academic year) 1st and 2nd semester  - 火5,火6,火7,火8

  • Laboratory Work and Practice on Basic Engineering (2021academic year) 1st and 2nd semester  - 火5,火6,火7,火8

  • Information Technology Experiments B (Media Processing) (2021academic year) Third semester  - 火3,火4,火5,火6,火7,木3,木4,木5,木6,木7

  • Engineering English (2021academic year) Late  - その他

  • Technical Writing (2021academic year) Prophase  - その他

  • Technical Presentation (2021academic year) Late  - その他

  • Specific Research of Electronics and Information Systems Engineering (2021academic year) Year-round  - その他

  • Laboratory Work and Practice on Basic Engineering (2020academic year) 1st and 2nd semester  - 火4,火5,火6,火7

  • Laboratory Work and Practice on Basic Engineering (2020academic year) 1st and 2nd semester  - 火4,火5,火6,火7

  • Information Technology Experiments B (Media Processing) (2020academic year) Third semester  - 火3,火4,火5,火6,木3,木4,木5,木6

  • Laboratory Work on Information Technology III (2020academic year) Third semester  - 火3,火4,火5,火6

  • Laboratory Work on Information Technology IV (2020academic year) Third semester  - 木3,木4,木5,木6

  • Engineering English (2020academic year) Late  - その他

  • Technical Writing (2020academic year) Prophase  - その他

  • Technical Presentation (2020academic year) Late  - その他

  • Specific Research of Electronics and Information Systems Engineering (2020academic year) Year-round  - その他

▼display all