A Simple Baseline for Pose Tracking in Videos of Crowded Scenes

TL;DR

This paper introduces a straightforward approach for pose tracking in crowded video scenes, combining multi-object tracking, pose estimation, and optical flow to improve accuracy in complex environments.

Contribution

It presents a simple baseline that integrates detection, tracking, and optical flow for effective pose tracking in crowded scenes, addressing a gap in existing methods.

Findings

Effective in crowded environments

Combines multi-object tracking with optical flow

Achieves promising results in complex event videos

Abstract

This paper presents our solution to ACM MM challenge: Large-scale Human-centric Video Analysis in Complex Events\cite{lin2020human}; specifically, here we focus on Track3: Crowd Pose Tracking in Complex Events. Remarkable progress has been made in multi-pose training in recent years. However, how to track the human pose in crowded and complex environments has not been well addressed. We formulate the problem as several subproblems to be solved. First, we use a multi-object tracking method to assign human ID to each bounding box generated by the detection model. After that, a pose is generated to each bounding box with ID. At last, optical flow is used to take advantage of the temporal information in the videos and generate the final pose tracking result.