A Bayesian Framework for Human Body Pose Tracking from Depth Image Sequences

被引:17
|
作者
Zhu, Youding [1 ]
Fujimura, Kikuo [1 ]
机构
[1] Honda Res Inst USA, Mountain View, CA 94041 USA
关键词
human pose tracking; depth images; Bayesian inference;
D O I
10.3390/s100505280
中图分类号
O65 [分析化学];
学科分类号
070302 ; 081704 ;
摘要
This paper addresses the problem of accurate and robust tracking of 3D human body pose from depth image sequences. Recovering the large number of degrees of freedom in human body movements from a depth image sequence is challenging due to the need to resolve the depth ambiguity caused by self-occlusions and the difficulty to recover from tracking failure. Human body poses could be estimated through model fitting using dense correspondences between depth data and an articulated human model (local optimization method). Although it usually achieves a high accuracy due to dense correspondences, it may fail to recover from tracking failure. Alternately, human pose may be reconstructed by detecting and tracking human body anatomical landmarks (key-points) based on low-level depth image analysis. While this method (key-point based method) is robust and recovers from tracking failure, its pose estimation accuracy depends solely on image-based localization accuracy of key-points. To address these limitations, we present a flexible Bayesian framework for integrating pose estimation results obtained by methods based on key-points and local optimization. Experimental results are shown and performance comparison is presented to demonstrate the effectiveness of the proposed approach.
引用
收藏
页码:5280 / 5293
页数:14
相关论文
共 50 条
  • [1] Bayesian 3D Human Body Pose Tracking from Depth Image Sequences
    Zhu, Youding
    Fujimura, Kikuo
    [J]. COMPUTER VISION - ACCV 2009, PT II, 2010, 5995 : 267 - 278
  • [2] An Unsupervised Real-Time Framework of Human Pose Tracking From Range Image Sequences
    Wu, Yongpeng
    Kong, Dehui
    Wang, Shaofan
    Li, Jinghua
    Yin, Baocai
    [J]. IEEE TRANSACTIONS ON MULTIMEDIA, 2020, 22 (08) : 2177 - 2190
  • [3] Human Pose Modelling and Body Tracking from Monocular Video Sequences
    Hooi, Lim Siew
    Sainarayanan, G.
    Fan, Liau Chung
    [J]. ICIAS 2007: INTERNATIONAL CONFERENCE ON INTELLIGENT & ADVANCED SYSTEMS, VOLS 1-3, PROCEEDINGS, 2007, : 571 - 576
  • [4] Human Pose Tracking From Monocular Video by Traversing an Image Motion Mapped Body Pose Manifold
    Basu, Saurav
    Poulin, Joshua
    Acton, Scott T.
    [J]. COMPUTATIONAL IMAGING VIII, 2010, 7533
  • [5] Estimating 3D human body pose from stereo image sequences
    Yang, Hee-Deok
    Park, Sung-Kee
    Lee, Seong-Whan
    [J]. GESTURE IN HUMAN-COMPUTER INTERACTION AND SIMULATION, 2006, 3881 : 172 - 175
  • [6] Constrained optimization for human pose estimation from depth sequences
    Zhu, Youding
    Fujimura, Kikuo
    [J]. COMPUTER VISION - ACCV 2007, PT I, PROCEEDINGS, 2007, 4843 : 408 - +
  • [7] Tracking and learning graphs and pose on image sequences of faces
    Maurer, T
    vonderMalsburg, C
    [J]. PROCEEDINGS OF THE SECOND INTERNATIONAL CONFERENCE ON AUTOMATIC FACE AND GESTURE RECOGNITION, 1996, : 176 - 181
  • [8] Controlled human pose estimation from depth image streams
    Zhu, Youding
    Dariush, Behzad
    Fujimura, Kikuo
    [J]. 2008 IEEE COMPUTER SOCIETY CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS, VOLS 1-3, 2008, : 1544 - +
  • [9] Combining Human Body Shape and Pose Estimation for Robust Upper Body Tracking Using a Depth Sensor
    Probst, Thomas
    Fossati, Andrea
    Van Gool, Luc
    [J]. COMPUTER VISION - ECCV 2016 WORKSHOPS, PT II, 2016, 9914 : 285 - 301
  • [10] Reconstructing 3D human body pose from stereo image sequences using hierarchical human body model learning
    Yang, Hee-Deok
    Lee, Seong-Whan
    [J]. 18TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION, VOL 3, PROCEEDINGS, 2006, : 1004 - +