An equalised global graphical model-based approach for multi-camera object tracking

TL;DR

This paper introduces a global graph model with an improved similarity metric to enhance multi-camera object tracking performance, especially in challenging conditions where single camera tracking is unreliable.

Contribution

It proposes an equalised global graph-based approach that differentiates similarities in single and inter-camera tracking for improved accuracy.

Findings

Outperforms existing methods in multi-camera tracking scenarios.

Effective even with poor single camera tracking conditions.

Utilizes a novel similarity metric for better global optimization.

Abstract

Non-overlapping multi-camera visual object tracking typically consists of two steps: single camera object tracking and inter-camera object tracking. Most of tracking methods focus on single camera object tracking, which happens in the same scene, while for real surveillance scenes, inter-camera object tracking is needed and single camera tracking methods can not work effectively. In this paper, we try to improve the overall multi-camera object tracking performance by a global graph model with an improved similarity metric. Our method treats the similarities of single camera tracking and inter-camera tracking differently and obtains the optimization in a global graph model. The results show that our method can work better even in the condition of poor single camera object tracking.