Pose Flow: Efficient Online Pose Tracking

Multi-person articulated pose tracking in complex unconstrained videos is an important and challenging problem. In this paper, going along the road of top-down approaches, we propose a decent and efficient pose tracker based on pose flows. First, we design an online optimization framework to build association of cross-frame poses and form pose flows. Second, a novel pose flow non maximum suppression (NMS) is designed to robustly reduce redundant pose flows and re-link temporal disjoint pose flows. Extensive experiments show our method significantly outperforms best reported results on two standard Pose Tracking datasets ([Iqbal et al., 2017] and [Girdhar et al., 2017]) by 13 mAP 25 MOTA and 6 mAP 3 MOTA respectively. Moreover, in the case of working on detected poses in individual frames, the extra computation of proposed pose tracker is very minor, requiring 0.01 second per frame only.