Technical Report for ReID-SAM on SkiTB Visual Tracking Challenge 2025

2025-02-28

AI Summary

To address identity tracking inconsistencies in alpine, ski jumping, and freestyle skiing—caused by high-speed motion, large pose variations, occlusions, and snow-fog interference—this paper proposes ReID-SAM, a unified tracking framework integrating the SAMURAI tracker, OSNet-based re-identification module, and YOLOv11 (or STARK) detector, augmented with a customized post-processing strategy to suppress ID switches. We pioneer the joint modeling of semantic-aware segmentation and re-identification, significantly enhancing identity consistency across drastic pose changes and partial occlusions. Evaluated on the SkiTB benchmark, ReID-SAM achieves an F1-score of 0.870 and sets new state-of-the-art performance on all three sub-tasks. This work delivers a more robust and practical end-to-end visual tracking solution for winter sports analytics.

Technology Category

• Computer Vision: Motion & Tracking
• Constraint Satisfaction and Optimization: Satisfiability Modulo Theories
• Search and Optimization: Sampling/Simulation-based Search

Application Category

• Security and Privacy: Tracking, profiling, and countermeasures against them
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Web Mining and Content Analysis: Topic discovery and tracking

Abstract

This report introduces ReID-SAM, a novel model developed for the SkiTB Challenge that addresses the complexities of tracking skier appearance. Our approach integrates the SAMURAI tracker with a person re-identification (Re-ID) module and advanced post-processing techniques to enhance accuracy in challenging skiing scenarios. We employ an OSNet-based Re-ID model to minimize identity switches and utilize YOLOv11 with Kalman filtering or STARK-based object detection for precise equipment tracking. When evaluated on the SkiTB dataset, ReID-SAM achieved a state-of-the-art F1-score of 0.870, surpassing existing methods across alpine, ski jumping, and freestyle skiing disciplines. These results demonstrate significant advancements in skier tracking accuracy and provide valuable insights for computer vision applications in winter sports.

Problem

• Enhances skier tracking accuracy in challenging skiing scenarios.
• Minimizes identity switches using an OSNet-based Re-ID model.
• Achieves state-of-the-art F1-score of 0.870 on SkiTB dataset.

Innovation

• Integrates SAMURAI tracker with Re-ID module
• Uses OSNet-based Re-ID to reduce identity switches
• Employs YOLOv11 and Kalman filtering for precise tracking