Free-viewpoint motion recognition using deep alternative learning

被引:0
|
作者
Nagayama I. [1 ]
Uehara W. [1 ]
Shiroma Y. [1 ]
Miyazato T. [1 ]
机构
[1] Graduate School of Science and Engineering, University of the Ryukyus, 1, Senbaru Nishihara, Okinawa
来源
Nagayama, Itaru (nagayama@ie.u-ryukyu.ac.jp) | 1600年 / Institute of Electrical Engineers of Japan卷 / 141期
基金
日本学术振兴会;
关键词
3DCG; Alternative learning; Deep neural network; Machine learning; Motion recognition; Security camera;
D O I
10.1541/ieejias.141.130
中图分类号
学科分类号
摘要
In this study, we aim to develop a robust motion recognition system for an intelligent video surveillance system, that can be used for security, sports and rehabilitation by using extended alternative learning. A robust motion recognition system is necessary for the automated detection of security incidents by using a machine learning approach. However, to avoid the difficulty of collecting a huge training dataset, we propose an alternative learning approach that trains a deep neural network with a 3D-CG dataset to recognize several motions. We present our experimental results on motion recognition from free-viewpoint videos by using deep learning and alternative learning. The trained deep neural network (DNN) is evaluated using actual videos by classifying the different actions performed by real humans in these videos. © 2021 The Institute of Electrical Engineers of Japan.
引用
收藏
页码:130 / 137
页数:7
相关论文
共 50 条
  • [1] Free-Viewpoint TV
    Tanimoto, Masayuki
    Tehrani, Mehrdad Panahpour
    Fujii, Toshiaki
    Yendo, Tomohiro
    IEEE SIGNAL PROCESSING MAGAZINE, 2011, 28 (01) : 67 - 76
  • [2] Deep Blending for Free-Viewpoint Image-Based Rendering
    Hedman, Peter
    Philip, Julien
    Price, True
    Frahm, Jan-Michael
    Drettakis, George
    Brostow, Gabriel
    SIGGRAPH ASIA'18: SIGGRAPH ASIA 2018 TECHNICAL PAPERS, 2018,
  • [3] Deep Blending for Free-Viewpoint Image-Based Rendering
    Hedman, Peter
    Philip, Julien
    Price, True
    Frahm, Jan-Michael
    Drettakis, George
    Brostow, Gabriel
    ACM TRANSACTIONS ON GRAPHICS, 2018, 37 (06):
  • [4] FTV (FREE-VIEWPOINT TV)
    Tanimoto, Masayuki
    2010 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, 2010, : 2393 - 2396
  • [5] FTV: Free-viewpoint Television
    Tanimoto, Masayuki
    SIGNAL PROCESSING-IMAGE COMMUNICATION, 2012, 27 (06) : 555 - 570
  • [6] FTV (free-viewpoint television)
    Tanimoto, Masayuki
    APSIPA TRANSACTIONS ON SIGNAL AND INFORMATION PROCESSING, 2012, 1
  • [7] Free viewpoint action recognition using motion history volumes
    Weinland, Daniel
    Ronfard, Remi
    Boyer, Edmond
    COMPUTER VISION AND IMAGE UNDERSTANDING, 2006, 104 (2-3) : 249 - 257
  • [8] Development of a free viewpoint pedestrian recognition system using deep learning for multipurpose flying drone
    Miyazato, Takaya
    Uehara, Wakaki
    Nagayama, Itaru
    ELECTRONICS AND COMMUNICATIONS IN JAPAN, 2019, 102 (11) : 16 - 24
  • [9] Development of a free viewpoint pedestrian recognition system using deep learning for multipurpose flying drone
    Miyazato T.
    Uehara W.
    Nagayama I.
    IEEJ Transactions on Electronics, Information and Systems, 2019, 139 (09): : 972 - 979
  • [10] Reflectance Estimation for Free-viewpoint Video
    Ash, George
    Tomori, Juraj
    Pelton, Mike
    Dupont, Charles
    SIGGRAPH '21: ACM SIGGRAPH 2021 POSTERS, 2021,