Capture and Representation of Human Walking in Live Video Sequences

被引:32
|
作者
Cheng, Jia-Ching [1 ]
Moura, Jose M. F. [1 ]
机构
[1] Carnegie Mellon Univ, Dept Elect & Comp Engn, Pittsburgh, PA 15213 USA
关键词
Capture; cyclic motion; human walkers in real video; motion; recognition; stick model; video contents;
D O I
10.1109/6046.766736
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Extracting human representations from video has vast applications. In this paper, we present a knowledge-based framework to capture metarepresentations for real-life video with human walkers. The system models the human body as an articulated object and the human walking as a cyclic activity with highly correlated temporal patterns. We extract for each of the body parts its motion, shape, and texture. Once available, this structural information can be used to manipulate or synthesize the original video sequence, or animate the walker with a different motion in a new synthesized video.
引用
收藏
页码:144 / 156
页数:13
相关论文
共 50 条
  • [31] Segmentation of multiple human objects in video sequences
    Yang, Hsin-Tai
    Ouyang, Chen-Sen
    Huang, Li-Ming
    Lee, Shie-Jue
    APPLIED ARTIFICIAL INTELLIGENCE, 2007, 21 (09) : 831 - 859
  • [32] AUTOMATICAL GENDER DETECTION FOR UNCONSTRAINED VIDEO SEQUENCES BASED ON COLLABORATIVE REPRESENTATION
    Lu, Lijia
    Liu, Weiyang
    Wen, Yandong
    Zou, Yuexian
    2014 12TH INTERNATIONAL CONFERENCE ON SIGNAL PROCESSING (ICSP), 2014, : 1263 - 1267
  • [33] Dynamics Filter for Walking Trajectories from Human Motion Capture
    Bravo M, Diego A.
    Rengifo R, Carlos F.
    2016 IEEE COLOMBIAN CONFERENCE ON ROBOTICS AND AUTOMATION (CCRA), 2016,
  • [34] Human Walking Capture and its Inspiration to Biped Gait Planning
    Xia, Zeyang
    Chen, Guodong
    Jia, Zhenzhong
    Xiong, Jing
    Chen, Ken
    2009 IEEE INTERNATIONAL CONFERENCE ON MECHATRONICS AND AUTOMATION, VOLS 1-7, CONFERENCE PROCEEDINGS, 2009, : 926 - +
  • [35] An Embedded Human Motion Capture System for An Assistive Walking Robot
    Zong, Cong
    Clady, Xavier
    Chetouani, Mohamed
    2011 IEEE INTERNATIONAL CONFERENCE ON REHABILITATION ROBOTICS (ICORR), 2011,
  • [36] Blind Video Quality Prediction by Uncovering Human Video Perceptual Representation
    Liao, Liang
    Xu, Kangmin
    Wu, Haoning
    Chen, Chaofeng
    Sun, Wenxiu
    Yan, Qiong
    Kuo, C. -C. Jay
    Lin, Weisi
    IEEE TRANSACTIONS ON IMAGE PROCESSING, 2024, 33 : 4998 - 5013
  • [37] A body model server for human motion capture and representation
    Bers, J
    PRESENCE-TELEOPERATORS AND VIRTUAL ENVIRONMENTS, 1996, 5 (04) : 381 - 392
  • [38] Human Performance Capture from Monocular Video in the Wild
    Guo, Chen
    Chen, Xu
    Song, Jie
    Hilliges, Otmar
    2021 INTERNATIONAL CONFERENCE ON 3D VISION (3DV 2021), 2021, : 889 - 898
  • [39] MonoPerfCap: Human Performance Capture From Monocular Video
    Xu, Weipeng
    Chatterjee, Avishek
    Zollhoefer, Michael
    Rhodin, Helge
    Mehta, Dushyant
    Seidel, Hans-Peter
    Theobalt, Christian
    ACM TRANSACTIONS ON GRAPHICS, 2018, 37 (02):
  • [40] Walking with Capture Steps
    Missura, Marcell
    Behnke, Sven
    2014 14TH IEEE-RAS INTERNATIONAL CONFERENCE ON HUMANOID ROBOTS (HUMANOIDS), 2014, : 526 - 526