A Unified Multi-view Multi-person Tracking Framework

TL;DR

This paper introduces a unified framework for 3D multi-view multi-person tracking that effectively handles both footprint and pose tracking without modifications, leveraging multi-frame and multi-view data for improved accuracy.

Contribution

It proposes a novel unified framework that bridges footprint and pose tracking in 3D multi-view scenarios, enabling robust tracking with simple inputs.

Findings

Achieved state-of-the-art results on Campus and Shelf datasets for 3D pose tracking.

Obtained comparable results on WILDTRACK and MMPTRACK datasets for footprint tracking.

Demonstrated robustness and versatility of the unified approach.

Abstract

Although there is a significant development in 3D Multi-view Multi-person Tracking (3D MM-Tracking), current 3D MM-Tracking frameworks are designed separately for footprint and pose tracking. Specifically, frameworks designed for footprint tracking cannot be utilized in 3D pose tracking, because they directly obtain 3D positions on the ground plane with a homography projection, which is inapplicable to 3D poses above the ground. In contrast, frameworks designed for pose tracking generally isolate multi-view and multi-frame associations and may not be robust to footprint tracking, since footprint tracking utilizes fewer key points than pose tracking, which weakens multi-view association cues in a single frame. This study presents a Unified Multi-view Multi-person Tracking framework to bridge the gap between footprint tracking and pose tracking. Without additional modifications, the framework can adopt monocular 2D bounding boxes and 2D poses as the input to produce robust 3D trajectories for multiple persons. Importantly, multi-frame and multi-view information are jointly employed to improve the performance of association and triangulation. The effectiveness of our framework is verified by accomplishing state-of-the-art performance on the Campus and Shelf datasets for 3D pose tracking, and by comparable results on the WILDTRACK and MMPTRACK datasets for 3D footprint tracking.