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

2026-03-13

AI Summary

This work addresses the challenge of identity switches in online multi-object tracking caused by target overlap and occlusion, which often lead to error propagation through incorrect associations. To mitigate this issue, the authors propose a lightweight online post-association correction framework that explicitly rectifies matching errors induced by overlap during inference. The approach integrates an IoA-based appearance update suppression mechanism with local appearance similarity refinement, effectively curbing error accumulation without requiring global optimization or re-identification modules. Evaluated on MOT17, the method achieves 81.73 MOTA, 82.81 IDF1, and 66.95 HOTA, with a remarkably low long-term identity switch rate of 29.55%, significantly outperforming existing online trackers.

Technology Category

• Computer Vision: Motion & Tracking
• Intelligent Robots: State Estimation
• Search and Optimization: Mixed Discrete/Continuous Search

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Systems and Infrastructure for Web, Mobile and WoT: Web performance, measurement, and characterization

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.

Problem

• multi-object tracking
• identity switches
• object overlap
• occlusions
• online tracking

Innovation

• post-association correction
• overlap-aware tracking
• IoA-based filtering
• online multi-object tracking
• identity switch mitigation