Occlusion-Robust Online Multi-Object Visual Tracking using a GM-PHD Filter with CNN-Based Re-Identification

TL;DR

This paper introduces an online multi-object tracking method combining a GM-PHD filter with deep learning-based re-identification, effectively handling occlusions and improving accuracy over existing methods.

Contribution

It integrates deep appearance features into the GM-PHD filter framework and employs additional unassigned track prediction to enhance occlusion robustness.

Findings

Outperforms state-of-the-art trackers on MOT16, MOT17, and HiEve datasets.

Achieves higher tracking accuracy and better object identification.

Effectively handles occlusions and miss-detections.

Abstract

We propose a novel online multi-object visual tracker using a Gaussian mixture Probability Hypothesis Density (GM-PHD) filter and deep appearance learning. The GM-PHD filter has a linear complexity with the number of objects and observations while estimating the states and cardinality of time-varying number of objects, however, it is susceptible to miss-detections and does not include the identity of objects. We use visual-spatio-temporal information obtained from object bounding boxes and deeply learned appearance representations to perform estimates-to-tracks data association for target labeling as well as formulate an augmented likelihood and then integrate into the update step of the GM-PHD filter. We also employ additional unassigned tracks prediction after the data association step to overcome the susceptibility of the GM-PHD filter towards miss-detections caused by occlusion. Extensive evaluations on MOT16, MOT17 and HiEve benchmark datasets show that our tracker significantly outperforms several state-of-the-art trackers in terms of tracking accuracy and identification.