OccluTrack: Rethinking Awareness of Occlusion for Enhancing Multiple Pedestrian Tracking

TL;DR

OccluTrack introduces an adaptive, occlusion-aware approach for multiple pedestrian tracking that improves accuracy by suppressing abnormal motions, extracting discriminative features, and enhancing association methods during partial occlusion.

Contribution

The paper presents a novel pedestrian tracker with a plug-and-play abnormal motion suppression, pose-guided re-identification, and occlusion-aware association, addressing partial occlusion challenges.

Findings

Outperforms state-of-the-art on MOTChallenge and DanceTrack datasets.

Significantly improves IDF1 scores and reduces ID switches.

Demonstrates robustness in occluded pedestrian scenarios.

Abstract

Multiple pedestrian tracking is crucial for enhancing safety and efficiency in intelligent transport and autonomous driving systems by predicting movements and enabling adaptive decision-making in dynamic environments. It optimizes traffic flow, facilitates human interaction, and ensures compliance with regulations. However, it faces the challenge of tracking pedestrians in the presence of occlusion. Existing methods overlook effects caused by abnormal detections during partial occlusion. Subsequently, these abnormal detections can lead to inaccurate motion estimation, unreliable appearance features, and unfair association. To address these issues, we propose an adaptive occlusion-aware multiple pedestrian tracker, OccluTrack, to mitigate the effects caused by partial occlusion. Specifically, we first introduce a plug-and-play abnormal motion suppression mechanism into the Kalman Filter to adaptively detect and suppress outlier motions caused by partial occlusion. Second, we develop a pose-guided re-identification (Re-ID) module to extract discriminative part features for partially occluded pedestrians. Last, we develop a new occlusion-aware association method towards fair Intersection over Union (IoU) and appearance embedding distance measurement for occluded pedestrians. Extensive evaluation results demonstrate that our method outperforms state-of-the-art methods on MOTChallenge and DanceTrack datasets. Particularly, the performance improvements on IDF1 and ID Switches, as well as visualized results, demonstrate the effectiveness of our method in multiple pedestrian tracking.