Skeleton Driven Non-rigid Motion Tracking and 3D Reconstruction

被引:0
|
作者
Elanattil, Shafeeq [1 ,2 ]
Moghadam, Peyman [1 ,2 ]
Denman, Simon [2 ]
Sridharan, Sridha [2 ]
Fookes, Clinton [2 ]
机构
[1] CSIRO, DATA61, Robot & Autonomous Syst, Brisbane, Qld 4069, Australia
[2] Queensland Univ Technol, Sch Elect Engn & Comp Sci, Brisbane, Qld, Australia
关键词
D O I
暂无
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
This paper presents a method which can track and 3D reconstruct the non-rigid surface motion of human performance using a moving RGB-D camera. 3D reconstruction of marker-less human performance is a challenging problem due to the large range of articulated motions and considerable non-rigid deformations. Current approaches use local optimization for tracking. These methods need many iterations to converge and may get stuck in local minima during sudden articulated movements. We propose a puppet model-based tracking approach using skeleton prior, which provides a better initialization for tracking articulated movements. The proposed approach uses an aligned puppet model to estimate correct correspondences for human performance capture. We also contribute a synthetic dataset which provides ground truth locations for frame-by-frame geometry and skeleton joints of human subjects. Experimental results show that our approach is more robust when faced with sudden articulated motions, and provides better 3D reconstruction compared to the existing state-of-the-art approaches.
引用
收藏
页码:259 / 266
页数:8
相关论文
共 50 条
  • [1] Complex Non-Rigid Motion 3D Reconstruction by Union of Subspaces
    Zhu, Yingying
    Huang, Dong
    De La Torre, Fernando
    Lucey, Simon
    2014 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2014, : 1542 - 1549
  • [2] SobolevFusion: 3D Reconstruction of Scenes Undergoing Free Non-rigid Motion
    Slavcheva, Miroslava
    Baust, Maximilian
    Ilic, Slobodan
    2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2018, : 2646 - 2655
  • [3] Reconstruction of non-rigid 3D shapes from stereo-motion
    Llado, Xavier
    Del Bue, Alessio
    Oliver, Arnau
    Salvi, Joaquim
    Agapito, Lourdes
    PATTERN RECOGNITION LETTERS, 2011, 32 (07) : 1020 - 1028
  • [4] Ordered Subspace Clustering for Complex Non-Rigid Motion by 3D Reconstruction
    Du, Weinan
    Li, Jinghua
    Wu, Fei
    Sun, Yanfeng
    Hu, Yongli
    APPLIED SCIENCES-BASEL, 2019, 9 (08):
  • [5] Fast 3D tracking of non-rigid objects
    Okada, N
    Hebert, M
    2003 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION, VOLS 1-3, PROCEEDINGS, 2003, : 3497 - 3503
  • [6] Accurate reconstruction of non-rigid 3D shapes
    Koh, Sung Shik
    Zin, Thi Thi
    Hama, Hiromitsu
    ICCE: 2007 DIGEST OF TECHNICAL PAPERS INTERNATIONAL CONFERENCE ON CONSUMER ELECTRONICS, 2007, : 369 - +
  • [7] Rigid and non-rigid face motion tracking by aligning texture maps and stereo 3D models
    Dornaika, Fadi
    Sappa, Angel D.
    PATTERN RECOGNITION LETTERS, 2007, 28 (15) : 2116 - 2126
  • [8] Repeatable Local Coordinate Frames for 3D Human Motion Tracking: from Rigid to Non-Rigid
    Huang, Chun-Hao
    Tombari, Federico
    Navab, Nassir
    2015 INTERNATIONAL CONFERENCE ON 3D VISION, 2015, : 371 - 379
  • [9] Colonoscopic 3D reconstruction by tubular non-rigid structure-from-motion
    Agniva Sengupta
    Adrien Bartoli
    International Journal of Computer Assisted Radiology and Surgery, 2021, 16 : 1237 - 1241
  • [10] Unsupervised 3D Reconstruction and Grouping of Rigid and Non-Rigid Categories
    Agudo, Antonio
    IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2022, 44 (01) : 519 - 532