Multi-Person 3D Pose Estimation and Tracking in Sports
- 1 June 2019
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 2487-2496
- https://doi.org/10.1109/cvprw.2019.00304
Abstract
We present an approach to multi-person 3D pose estimation and tracking from multi-view video. Following independent 2D pose detection in each view, we: (1) correct errors in the output of the pose detector; (2) apply a fast greedy algorithm for associating 2D pose detections between camera views; and (3) use the associated poses to generate and track 3D skeletons. Previous methods for estimating skeletons of multiple people suffer long processing times or rely on appearance cues, reducing their applicability to sports. Our approach to associating poses between views works by seeking the best correspondences first in a greedy fashion, while reasoning about the cyclic nature of correspondences to constrain the search. The associated poses can be used to generate 3D skeletons, which we produce via robust triangulation. Our method can track 3D skeletons in the presence of missing detections, substantial occlusions, and large calibration error. We believe ours is the first method for full-body 3D pose estimation and tracking of multiple players in highly dynamic sports scenes. The proposed method achieves a significant improvement in speed over state-of-the-art methods.Keywords
This publication has 31 references indexed in Scilit:
- 3D Pictorial Structures Revisited: Multiple Human Pose EstimationIEEE Transactions on Pattern Analysis and Machine Intelligence, 2015
- Efficient ConvNet-based marker-less motion capture in general scenes with a low number of camerasPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2015
- 3D Pictorial Structures for Multiple Human Pose EstimationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2014
- DeepPose: Human Pose Estimation via Deep Neural NetworksPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2014
- 3D Pictorial Structures for Multiple View Articulated Pose EstimationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2013
- Poselet Conditioned Pictorial StructuresPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2013
- (MP)2T: Multiple People Multiple Parts TrackerLecture Notes in Computer Science, 2012
- Loose-limbed People: Estimating 3D Human Pose and Motion Using Non-parametric Belief PropagationInternational Journal of Computer Vision, 2011
- Joint Multi-Layer Segmentation and Reconstruction for Free-Viewpoint Video ApplicationsInternational Journal of Computer Vision, 2010
- Pictorial Structures for Object RecognitionInternational Journal of Computer Vision, 2005