Pose Flow: Efficient Online Pose Tracking

TL;DR

Pose Flow introduces an efficient online pose tracking method using pose flows and a novel non-maximum suppression technique, significantly improving accuracy and maintaining real-time performance in multi-person pose tracking.

Contribution

It proposes a new online optimization framework for pose association and a pose flow NMS method, advancing the state-of-the-art in multi-person pose tracking.

Findings

Outperforms previous methods by 13 mAP and 25 MOTA on standard datasets.

Achieves online 10 FPS tracking with minimal extra computation.

Demonstrates robustness in reducing redundant pose flows and linking disjoint ones.

Abstract

Multi-person articulated pose tracking in unconstrained videos is an important while 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 the association of cross-frame poses and form pose flows (PF-Builder). Second, a novel pose flow non-maximum suppression (PF-NMS) is designed to robustly reduce redundant pose flows and re-link temporal disjoint ones. Extensive experiments show that our method significantly outperforms best-reported results on two standard Pose Tracking datasets 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 pose tracker is very minor, guaranteeing online 10FPS tracking. Our source codes are made publicly available(https://github.com/YuliangXiu/PoseFlow).