FC-Track: Overlap-Aware Post-Association Correction for Online Multi-Object Tracking

TL;DR

FC-Track is a lightweight online multi-object tracking framework that reduces identity switches caused by occlusions and overlaps by using overlap-aware filtering and local correction, achieving high accuracy and low identity switches in real-time.

Contribution

The paper introduces FC-Track, a novel overlap-aware post-association correction method that effectively mitigates identity switches without global optimization or re-identification.

Findings

Achieves 81.73 MOTA on MOT17 with 5.7 FPS.

Reduces long-term identity switches to 29.55%.

Maintains state-of-the-art performance on MOT20.

Abstract

Reliable multi-object tracking (MOT) is essential for robotic systems operating in complex and dynamic environments. Despite recent advances in detection and association, online MOT methods remain vulnerable to identity switches caused by frequent occlusions and object overlap, where incorrect associations can propagate over time and degrade tracking reliability. We present a lightweight post-association correction framework (FC-Track) for online MOT that explicitly targets overlap-induced mismatches during inference. The proposed method suppresses unreliable appearance updates under high-overlap conditions using an Intersection over Area (IoA)-based filtering strategy, and locally corrects detection-to-tracklet mismatches through appearance similarity comparison within overlapped tracklet pairs. By preventing short-term mismatches from propagating, our framework effectively mitigates long-term identity switches without resorting to global optimization or re-identification. The framework operates online without global optimization or re-identification, making it suitable for real-time robotic applications. We achieve 81.73 MOTA, 82.81 IDF1, and 66.95 HOTA on the MOT17 test set with a running speed of 5.7 FPS, and 77.52 MOTA, 80.90 IDF1, and 65.67 HOTA on the MOT20 test set with a running speed of 0.6 FPS. Specifically, our framework FC-Track produces only 29.55% long-term identity switches, which is substantially lower than existing online trackers. Meanwhile, our framework maintains state-of-the-art performance on the MOT20 benchmark.