Part-Aware Measurement for Robust Multi-View Multi-Human 3D Pose Estimation and Tracking
This work improves multi-human 3D pose estimation and tracking for applications like surveillance or sports analysis, but it is incremental as it builds on existing multi-view methods with temporal consistency enhancements.
The paper tackles the problem of robust multi-human 3D pose estimation and tracking from multi-view data by addressing noisy predictions and mistaken associations, achieving competitive results of 96.8% on Campus and 97.4% on Shelf benchmarks.
This paper introduces an approach for multi-human 3D pose estimation and tracking based on calibrated multi-view. The main challenge lies in finding the cross-view and temporal correspondences correctly even when several human pose estimations are noisy. Compare to previous solutions that construct 3D poses from multiple views, our approach takes advantage of temporal consistency to match the 2D poses estimated with previously constructed 3D skeletons in every view. Therefore cross-view and temporal associations are accomplished simultaneously. Since the performance suffers from mistaken association and noisy predictions, we design two strategies for aiming better correspondences and 3D reconstruction. Specifically, we propose a part-aware measurement for 2D-3D association and a filter that can cope with 2D outliers during reconstruction. Our approach is efficient and effective comparing to state-of-the-art methods; it achieves competitive results on two benchmarks: 96.8% on Campus and 97.4% on Shelf. Moreover, we extends the length of Campus evaluation frames to be more challenging and our proposal also reach well-performed result.