3D TRAJECTORIES FOR ACTION RECOGNITION

被引:0
|
作者
Koperski, Michal [1 ]
Bilinski, Piotr [1 ]
Bremond, Francois [1 ]
机构
[1] STARS Team, INRIA Sophia Antipolis, 2004 Route Lucioles,BP93, F-06902 Sophia Antipolis, France
关键词
Computer Vision; Action Recognition;
D O I
暂无
中图分类号
TP301 [理论、方法];
学科分类号
081202 ;
摘要
Recent development in affordable depth sensors opens new possibilities in action recognition problem. Depth information improves skeleton detection, therefore many authors focused on analyzing pose for action recognition. But still skeleton detection is not robust and fail in more challenging scenarios, where sensor is placed outside of optimal working range and serious occlusions occur. In this paper we investigate state-of-the-art methods designed for RGB videos, which have proved their performance. Then we extend current state-of-the-art algorithms to benefit from depth information without need of skeleton detection. In this paper we propose two novel video descriptors. First combines motion and 3D information. Second improves performance on actions with low movement rate. We validate our approach on challenging MSR DailyActivty3D dataset.
引用
收藏
页码:4176 / 4180
页数:5
相关论文
共 50 条
  • [1] Localized Trajectories for 2D and 3D Action Recognition
    Papadopoulos, Konstantinos
    Demisse, Girum
    Ghorbel, Enjie
    Antunes, Michel
    Aouada, Djamila
    Ottersten, Bjorn
    SENSORS, 2019, 19 (16)
  • [2] Coding Kendall's Shape Trajectories for 3D Action Recognition
    Ben Tanfous, Amor
    Drira, Hassen
    Ben Amor, Boulbaba
    2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2018, : 2840 - 2849
  • [3] Action Recognition by 3D Convolutional Network
    Brezovsky, Matus
    Sopiak, Dominik
    Oravec, Milos
    PROCEEDINGS OF ELMAR-2018: 60TH INTERNATIONAL SYMPOSIUM ELMAR-2018, 2018, : 71 - 74
  • [4] 3D CNN for Human Action Recognition
    Boualia, Sameh Neili
    Ben Amara, Najoua Essoukri
    2021 18TH INTERNATIONAL MULTI-CONFERENCE ON SYSTEMS, SIGNALS & DEVICES (SSD), 2021, : 276 - 282
  • [5] 3D Action Recognition in an Industrial Environment
    Hahn, Markus
    Krueger, Lars
    Woehler, Christian
    Kummert, Franz
    HUMAN CENTERED ROBOT SYSTEMS: COGNITION, INTERACTION, TECHNOLOGY, 2009, 6 : 141 - +
  • [6] 3D RANs: 3D Residual Attention Networks for action recognition
    Cai, Jiahui
    Hu, Jianguo
    VISUAL COMPUTER, 2020, 36 (06): : 1261 - 1270
  • [7] Hollywood 3D: What are the Best 3D Features for Action Recognition?
    Simon Hadfield
    Karel Lebeda
    Richard Bowden
    International Journal of Computer Vision, 2017, 121 : 95 - 110
  • [8] Hollywood 3D: What are the Best 3D Features for Action Recognition?
    Hadfield, Simon
    Lebeda, Karel
    Bowden, Richard
    INTERNATIONAL JOURNAL OF COMPUTER VISION, 2017, 121 (01) : 95 - 110
  • [9] 3D RANs: 3D Residual Attention Networks for action recognition
    Jiahui Cai
    Jianguo Hu
    The Visual Computer, 2020, 36 : 1261 - 1270
  • [10] A New Descriptor for Multiple 3D Motion Trajectories Recognition
    Shao, Zhanpeng
    Li, Y. F.
    2013 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA), 2013, : 4749 - 4754