Real-time 3D human motion capture from binocular stereo vision and its use on human body animation

Xupeng Wei M.D.; Zhongzhi Zhang; Shuang Li; Tao Yang; Xiang Zhou

doi:10.1117/12.2542228

Translator Disclaimer

16 October 2019 Real-time 3D human motion capture from binocular stereo vision and its use on human body animation

Xupeng Wei M.D., Zhongzhi Zhang, Shuang Li, Tao Yang, Xiang Zhou

Author Affiliations +

Proceedings Volume 11205, Seventh International Conference on Optical and Photonic Engineering (icOPEN 2019); 112050S (2019) https://doi.org/10.1117/12.2542228
Event: Seventh International Conference on Optical and Photonic Engineering (icOPEN 2019), 2019, Phuket, Thailand

Abstract

Existing motion-capture technologies are implemented through expensive and specialized equipment, which typically requires the wearable devices or the mark of human body joint. This leads to a distinct limitation on the accessibility and popularity for mass market consumer. To address these problems, we present a pipeline for 3D human motion capture from binocular stereo vision, which is based on MobilePose, a supervised learning method for 2D skeletal joint detection in real time. Due to the short time of 2D joint detection and 3D reconstruction, our approach can fulfill 3D human motion capture in real time. Besides, we use the captured 3D motion information to implement a simple application on human body animation. Compared with Microsoft's Kinect method using depth camera, our method is implemented with the available cameras, which is low cost and widely used.

Citation Download Citation

Xupeng Wei M.D., Zhongzhi Zhang, Shuang Li, Tao Yang, and Xiang Zhou "Real-time 3D human motion capture from binocular stereo vision and its use on human body animation", Proc. SPIE 11205, Seventh International Conference on Optical and Photonic Engineering (icOPEN 2019), 112050S (16 October 2019); https://doi.org/10.1117/12.2542228

ACCESS THE FULL ARTICLE