SAMIDARE: Advanced Tracking-by-Segmentation for Dense Scenarios

TL;DR

SAMIDARE introduces an advanced tracking-by-segmentation framework that improves multi-object tracking in dense sports scenarios by adaptive mask control and state-aware association, achieving state-of-the-art results.

Contribution

The paper presents novel density-aware mask re-generation, selective memory updates, and state-aware association techniques to enhance segmentation-based multi-object tracking in crowded scenes.

Findings

Outperforms baseline by 2.5 HOTA points

Outperforms baseline by 4.2 IDF1 points

Achieves state-of-the-art performance on SportsMOT dataset

Abstract

Automated sports analysis demands robust multi-object tracking (MOT), yet segmentation-based methods often struggle with mask errors and ID switches in dense scenes. We propose SAMIDARE, a framework that enhances SAM2MOT for crowded scenes through three key components: (1) density-aware mask re-generation and (2) selective memory updates, both for adaptive mask control to preserve target feature integrity, and (3) state-aware association and new track initialization, which improves robustness under mutual occlusions and frequent frame-out events. Evaluated on the SportsMOT dataset, SAMIDARE achieves state-of-the-art performance, outperforming the baseline by 2.5 HOTA and 4.2 IDF1 points on the validation set. These results demonstrate that adaptive feature management using mask control and state-aware association provide a robust and efficient solution for dense sports tracking. Code is available at https://github.com/ZabuZabuZabu/SAMIDARE