Pose Flow: Efficient Online Pose Tracking

3 Feb 2018  ·  Yuliang Xiu, Jiefeng Li, Haoyu Wang, Yinghong Fang, Cewu Lu ·

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).

PDF Abstract

Results from the Paper


Ranked #9 on Pose Tracking on PoseTrack2017 (using extra training data)

     Get a GitHub badge
Task Dataset Model Metric Name Metric Value Global Rank Uses Extra
Training Data
Result Benchmark
Keypoint Detection COCO test-challenge Xiu et al. AR 67.5 # 8
ARM 62.5 # 7
Pose Tracking PoseTrack2017 PoseFlow MOTA 50.98 # 9
mAP 62.95 # 8

Methods


No methods listed for this paper. Add relevant methods here