Advanced search
1 file | 6.53 MB Add to list

Multiview 3D Markerless Human Pose Estimation from OpenPose Skeletons

(2020)
Author
Organization
Abstract
Despite the fact that marker-based systems for human motion estimation provide very accurate tracking of the human body joints (at mm precision), these systems are often intrusive or even impossible to use depending on the circumstances, e.g.~markers cannot be put on an athlete during competition. Instrumenting an athlete with the appropriate number of markers requires a lot of time and these markers may fall off during the analysis, which leads to incomplete data and requires new data capturing sessions and hence a waste of time and effort. Therefore, we present a novel multiview video-based markerless system that uses 2D joint detections per view (from OpenPose) to estimate their corresponding 3D positions while tackling the people association problem in the process to allow the tracking of multiple persons at the same time. Our proposed system can perform the tracking in real-time at 20-25 fps. Our results show a standard deviation between 9.6 and 23.7 mm for the lower body joints based on the raw measurements only. After filtering the data, the standard deviation drops to a range between 6.6 and 21.3 mm. Our proposed solution can be applied to a large number of applications, ranging from sports analysis to virtual classrooms where submillimeter precision is not necessarily required, but where the use of markers is impractical.
Keywords
Markerless human motion, joint detection, multiview

Downloads

  • (...).pdf
    • full text
    • |
    • UGent only
    • |
    • PDF
    • |
    • 6.53 MB

Citation

Please use this url to cite or link to this publication:

MLA
Slembrouck, Maarten, et al. Multiview 3D Markerless Human Pose Estimation from OpenPose Skeletons. 2020.
APA
Slembrouck, M., Luong, H., Gerlo, J., Schütte, K., Van Cauwelaert, D., De Clercq, D., … Philips, W. (2020). Multiview 3D Markerless Human Pose Estimation from OpenPose Skeletons. Presented at the ACIVS 2020, Advanced Concepts for Intelligent Vision Systems, Auckland.
Chicago author-date
Slembrouck, Maarten, Hiep Luong, Joeri Gerlo, Kurt Schütte, Dimitri Van Cauwelaert, Dirk De Clercq, Benedicte Vanwanseele, Peter Veelaert, and Wilfried Philips. 2020. “Multiview 3D Markerless Human Pose Estimation from OpenPose Skeletons.” In .
Chicago author-date (all authors)
Slembrouck, Maarten, Hiep Luong, Joeri Gerlo, Kurt Schütte, Dimitri Van Cauwelaert, Dirk De Clercq, Benedicte Vanwanseele, Peter Veelaert, and Wilfried Philips. 2020. “Multiview 3D Markerless Human Pose Estimation from OpenPose Skeletons.” In .
Vancouver
1.
Slembrouck M, Luong H, Gerlo J, Schütte K, Van Cauwelaert D, De Clercq D, et al. Multiview 3D Markerless Human Pose Estimation from OpenPose Skeletons. In 2020.
IEEE
[1]
M. Slembrouck et al., “Multiview 3D Markerless Human Pose Estimation from OpenPose Skeletons,” presented at the ACIVS 2020, Advanced Concepts for Intelligent Vision Systems, Auckland, 2020.
@inproceedings{8638312,
  abstract     = {Despite the fact that marker-based systems for human motion estimation provide very accurate tracking of the human body joints (at mm precision), these systems are often intrusive or even impossible to use depending on the circumstances, e.g.~markers cannot be put on an athlete during competition. Instrumenting an athlete with the appropriate number of markers requires a lot of time and these markers may fall off during the analysis, which leads to incomplete data and requires new data capturing sessions and hence a waste of time and effort. Therefore, we present a novel multiview video-based markerless system that uses 2D joint detections per view (from OpenPose) to estimate their corresponding 3D positions while tackling the people association problem in the process to allow the tracking of multiple persons at the same time. Our proposed system can perform the tracking in real-time at 20-25 fps. Our results show a standard deviation between 9.6 and 23.7 mm for the lower body joints based on the raw measurements only. After filtering the data, the standard deviation drops to a range between 6.6 and 21.3 mm. Our proposed solution can be applied to a large number of applications, ranging from sports analysis to virtual classrooms where submillimeter precision is not necessarily required, but where the use of markers is impractical.},
  author       = {Slembrouck, Maarten and Luong, Hiep and Gerlo, Joeri and Schütte, Kurt and Van Cauwelaert, Dimitri and De Clercq, Dirk and Vanwanseele, Benedicte and Veelaert, Peter and Philips, Wilfried},
  keywords     = {Markerless human motion,joint detection,multiview},
  location     = {Auckland},
  title        = {Multiview 3D Markerless Human Pose Estimation from OpenPose Skeletons},
  year         = {2020},
}