Improving Multi-Person Pose Tracking with A Confidence Network

TL;DR

This paper introduces a confidence network and improved tracking pipeline to enhance multi-person pose tracking, especially under occlusion and detection failures, achieving state-of-the-art results on PoseTrack datasets.

Contribution

A novel keypoint confidence network and tracking modules that improve detection and tracking robustness in top-down pose estimation methods.

Findings

Achieves state-of-the-art performance on PoseTrack 2017 and 2018 datasets.

Effectively handles occlusion and missed detections in pose tracking.

Universal applicability to human detection and pose estimation tasks.

Abstract

Human pose estimation and tracking are fundamental tasks for understanding human behaviors in videos. Existing top-down framework-based methods usually perform three-stage tasks: human detection, pose estimation and tracking. Although promising results have been achieved, these methods rely heavily on high-performance detectors and may fail to track persons who are occluded or miss-detected. To overcome these problems, in this paper, we develop a novel keypoint confidence network and a tracking pipeline to improve human detection and pose estimation in top-down approaches. Specifically, the keypoint confidence network is designed to determine whether each keypoint is occluded, and it is incorporated into the pose estimation module. In the tracking pipeline, we propose the Bbox-revision module to reduce missing detection and the ID-retrieve module to correct lost trajectories, improving the performance of the detection stage. Experimental results show that our approach is universal in human detection and pose estimation, achieving state-of-the-art performance on both PoseTrack 2017 and 2018 datasets.