Iterative Greedy Matching for 3D Human Pose Tracking from Multiple Views
It addresses multi-person 3D pose estimation for applications like surveillance or motion analysis, but appears incremental as it builds on existing 2D systems and matching techniques.
The paper tackles 3D human pose tracking from multiple calibrated cameras by building on a real-time 2D pose estimation system and using greedy bipartite matching for view association, achieving state-of-the-art results on benchmarks.
In this work we propose an approach for estimating 3D human poses of multiple people from a set of calibrated cameras. Estimating 3D human poses from multiple views has several compelling properties: human poses are estimated within a global coordinate space and multiple cameras provide an extended field of view which helps in resolving ambiguities, occlusions and motion blur. Our approach builds upon a real-time 2D multi-person pose estimation system and greedily solves the association problem between multiple views. We utilize bipartite matching to track multiple people over multiple frames. This proofs to be especially efficient as problems associated with greedy matching such as occlusion can be easily resolved in 3D. Our approach achieves state-of-the-art results on popular benchmarks and may serve as a baseline for future work.