LightTrack: A Generic Framework for Online Top-Down Human Pose Tracking

Abstract

In this paper, we propose a novel effective light-weight framework, called LightTrack, for online human pose tracking. The proposed framework is designed to be generic for top-down pose tracking and is faster than existing online and offline methods. Single-person Pose Tracking (SPT) and Visual Object Tracking (VOT) are incorporated into one unified functioning entity, easily implemented by a replaceable single-person pose estimation module. Our framework unifies single-person pose tracking with multi-person identity association and sheds first light upon bridging keypoint tracking with object tracking. We also propose a Siamese Graph Convolution Network (SGCN) for human pose matching as a Re-ID module in our pose tracking system. In contrary to other Re-ID modules, we use a graphical representation of human joints for matching. The skeleton-based representation effectively captures human pose similarity and is computationally inexpensive. It is robust to sudden camera shift that introduces human drifting. To the best of our knowledge, this is the first paper to propose an online human pose tracking framework in a top-down fashion. The proposed framework is general enough to fit other pose estimators and candidate matching mechanisms. Our method outperforms other online methods while maintaining a much higher frame rate, and is very competitive with our offline state-of-the-art. We make the code publicly available at: https://github.com/Guanghan/lighttrack.

9 pages, 6 figures, 6 tables

References in corpus (14)

• Deep Residual Learning for Image Recognition
• R-FCN: Object Detection via Region-based Fully Convolutional Networks
• Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition
• Associative Embedding: End-to-End Learning for Joint Detection and Grouping
• Stacked Hourglass Networks for Human Pose Estimation
• Feature Pyramid Networks for Object Detection
• Deformable Convolutional Networks
• Convolutional Pose Machines
• Cascaded Pyramid Network for Multi-Person Pose Estimation
• Rethinking on Multi-Stage Networks for Human Pose Estimation
• Bottom-up Object Detection by Grouping Extreme and Center Points
• Learning Feature Pyramids for Human Pose Estimation
• RMPE: Regional Multi-person Pose Estimation
• Joint Flow: Temporal Flow Fields for Multi Person Tracking

Cited by in corpus (3)

• Learning to Generate Diverse Dance Motions with Transformer
• Self-supervised Keypoint Correspondences for Multi-Person Pose Estimation and Tracking in Videos
• 15 Keypoints Is All You Need