Team-Aware Football Player Tracking with SAM: An Appearance-Based Approach to Occlusion Recovery

2025-12-09

AI Summary

To address the challenges of dense occlusion, high inter-target similarity, and rapid motion in football player tracking, this paper proposes a lightweight team-aware tracking framework. First, the Segment Anything Model (SAM) is employed for precise initial segmentation and target initialization. Second, a robust re-identification mechanism is constructed by fusing the CSRT tracker with an HSV color histogram appearance model. Third, a team-aware strategy is introduced to enhance occlusion recovery, leveraging contextual team structure. Experimental results demonstrate stable real-time operation at 7.6–7.7 FPS with approximately 1880 MB memory consumption. Tracking success rates reach 100% under mild occlusion, 90% in dense scenarios, and 50% under severe occlusion (≥50% target area obscured); notably, the method exhibits strong robustness in high-density regions such as the penalty area.

Technology Category

• Computer Vision: Motion & Tracking
• Intelligent Robots: State Estimation
• Humans and AI: Teamwork, Team formation

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Security and Privacy: Tracking, profiling, and countermeasures against them
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Football player tracking is challenged by frequent occlusions, similar appearances, and rapid motion in crowded scenes. This paper presents a lightweight SAM-based tracking method combining the Segment Anything Model (SAM) with CSRT trackers and jersey color-based appearance models. We propose a team-aware tracking system that uses SAM for precise initialization and HSV histogram-based re-identification to improve occlusion recovery. Our evaluation measures three dimensions: processing speed (FPS and memory), tracking accuracy (success rate and box stability), and robustness (occlusion recovery and identity consistency). Experiments on football video sequences show that the approach achieves 7.6-7.7 FPS with stable memory usage (~1880 MB), maintaining 100 percent tracking success in light occlusions and 90 percent in crowded penalty-box scenarios with 5 or more players. Appearance-based re-identification recovers 50 percent of heavy occlusions, demonstrating the value of domain-specific cues. Analysis reveals key trade-offs: the SAM + CSRT combination provides consistent performance across crowd densities but struggles with long-term occlusions where players leave the frame, achieving only 8.66 percent re-acquisition success. These results offer practical guidelines for deploying football tracking systems under resource constraints, showing that classical tracker-based methods work well with continuous visibility but require stronger re-identification mechanisms for extended absences.

Problem

• Addresses occlusion recovery in crowded football player tracking
• Combines SAM with CSRT trackers for improved identity consistency
• Evaluates trade-offs between speed, accuracy, and robustness under constraints

Innovation

• SAM-based tracking with CSRT and appearance models
• Team-aware system using HSV histograms for re-identification
• Lightweight method balancing speed, accuracy, and robustness