CasCalib: Cascaded Calibration for Motion Capture from Sparse Unsynchronized Cameras

被引:0
|
作者
Tang, James [1 ]
Suri, Shashwat [1 ]
Ajisafe, Daniel [1 ]
Wandt, Bastian [2 ]
Rhodin, Helge [1 ,3 ]
机构
[1] Univ British Columbia, Vancouver, BC, Canada
[2] Linkoping Univ, Linkoping, Sweden
[3] Bielefeld Univ, Bielefeld, Germany
来源
2024 IEEE 18TH INTERNATIONAL CONFERENCE ON AUTOMATIC FACE AND GESTURE RECOGNITION, FG 2024 | 2024年
关键词
REGISTRATION;
D O I
10.1109/FG59268.2024.10581927
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
It is now possible to estimate 3D human pose from monocular images with off-the-shelf 3D pose estimators. However, many practical applications require fine-grained absolute pose information for which multi-view cues and camera calibration are necessary. Such multi-view recordings are laborious because they require manual calibration, and are expensive when using dedicated hardware. Our goal is full automation, which includes temporal synchronization, as well as intrinsic and extrinsic camera calibration. This is done by using persons in the scene as the calibration objects. Existing methods either address only synchronization or calibration, assume one of the former as input, or have significant limitations. A common limitation is that they only consider single persons, which eases correspondence finding. We attain this generality by partitioning the high-dimensional time and calibration space into a cascade of subspaces and introduce tailored algorithms to optimize each efficiently and robustly. The outcome is an easy-to-use, flexible, and robust motion capture toolbox that we release to enable scientific applications, which we demonstrate on diverse multi-view benchmarks. Project website: https://github.com/tangytoby/CasCalib.
引用
收藏
页数:9
相关论文
共 50 条
  • [41] Motion Capture with High-Speed RGB-D Cameras
    Kim, Jongsung
    Kim, Myunggyu
    2014 INTERNATIONAL CONFERENCE ON INFORMATION AND COMMUNICATION TECHNOLOGY CONVERGENCE (ICTC), 2014, : 394 - 395
  • [42] Automatic determination of facial muscle activations from sparse motion capture marker data
    Sifakis, E
    Neverov, I
    Fedkiw, R
    ACM TRANSACTIONS ON GRAPHICS, 2005, 24 (03): : 417 - 425
  • [43] FlyCap: Markerless Motion Capture Using Multiple Autonomous Flying Cameras
    Xu, Lan
    Liu, Yebin
    Cheng, Wei
    Guo, Kaiwen
    Zhou, Guyue
    Dai, Qionghai
    Fang, Lu
    IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS, 2018, 24 (08) : 2284 - 2297
  • [44] Real-Time Human Motion Capture with Multiple Depth Cameras
    Shafaei, Alireza
    Little, James J.
    2016 13TH CONFERENCE ON COMPUTER AND ROBOT VISION (CRV), 2016, : 24 - 31
  • [45] Calibration of a magnetometer array using motion capture equipment
    Chesneau, Charles-Ivan
    Robin, Remi
    Meier, Hendrik
    Hillion, Mathieu
    Prieur, Christophe
    ASIAN JOURNAL OF CONTROL, 2019, 21 (04) : 1459 - 1469
  • [46] Silhouette-based camera calibration from sparse views under circular motion
    Huang, Po-Hao
    Lai, Shang-Hong
    2008 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, VOLS 1-12, 2008, : 2649 - 2656
  • [47] Calibration of outdoor cameras from cast shadows
    Antone, M
    Bosse, M
    2004 IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, MAN & CYBERNETICS, VOLS 1-7, 2004, : 3040 - 3045
  • [48] Structure From Motion on XSlit Cameras
    Yang, Wei
    Zhang, Yingliang
    Ye, Jinwei
    Ji, Yu
    Li, Zhong
    Zhou, Mingyuan
    Yu, Jingyi
    IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2021, 43 (05) : 1691 - 1704
  • [49] Human Motion Capture and Recognition Based on Sparse Inertial Sensor
    Xia, Huailiang
    Zhao, Xiaoyan
    Chen, Yan
    Zhang, Tianyao
    Yin, Yuguo
    Zhang, Zhaohui
    JOURNAL OF ADVANCED COMPUTATIONAL INTELLIGENCE AND INTELLIGENT INFORMATICS, 2023, 27 (05) : 915 - 922
  • [50] Animation of trees in wind using sparse motion capture data
    Jie Long
    Bryce Porter
    Michael Jones
    The Visual Computer, 2015, 31 : 325 - 339