Simple online and real-time tracking with occlusion handling

TL;DR

This paper introduces a fast online multiple object tracking algorithm that relies solely on geometric cues, effectively handling occlusions and re-identification while reducing identity switches and fragmentation.

Contribution

The proposed method uniquely uses only geometric cues for online tracking, improving speed and occlusion handling without appearance-based features.

Findings

Decreased identity switch by 40%

Reduced fragmentation by 28%

Achieved faster processing suitable for online applications

Abstract

Multiple object tracking is a challenging problem in computer vision due to difficulty in dealing with motion prediction, occlusion handling, and object re-identification. Many recent algorithms use motion and appearance cues to overcome these challenges. But using appearance cues increases the computation cost notably and therefore the speed of the algorithm decreases significantly which makes them inappropriate for online applications. In contrast, there are algorithms that only use motion cues to increase speed, especially for online applications. But these algorithms cannot handle occlusions and re-identify lost objects. In this paper, a novel online multiple object tracking algorithm is presented that only uses geometric cues of objects to tackle the occlusion and reidentification challenges simultaneously. As a result, it decreases the identity switch and fragmentation metrics. Experimental results show that the proposed algorithm could decrease identity switch by 40% and fragmentation by 28% compared to the state of the art online tracking algorithms. The code is also publicly available.