Strong Baseline: Multi-UAV Tracking via YOLOv12 with BoT-SORT-ReID

2025-03-21

AI Summary

To address the challenges of low contrast, severe environmental noise, and small target size in thermal infrared (TIR) video for multi-UAV tracking, this paper proposes a lightweight and efficient end-to-end framework integrating the YOLOv12 detector with the BoT-SORT tracker—extended for the first time with a ReID module tailored to the TIR modality. Departing from conventional contrast enhancement and explicit temporal feature fusion, our approach relies on customized training strategies and inference optimizations to establish a strong baseline, significantly improving robustness to small targets without explicit feature enhancement. Evaluated on the 4th Anti-Drone Challenge benchmark, our method achieves 68.3% MOTA and 74.1% IDF1, outperforming existing approaches. The source code and comprehensive experimental analysis are publicly released.

Technology Category

• Computer Vision: Motion & Tracking
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Machine Learning: Multi-instance/Multi-view Learning

Application Category

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

Abstract

Detecting and tracking multiple unmanned aerial vehicles (UAVs) in thermal infrared video is inherently challenging due to low contrast, environmental noise, and small target sizes. This paper provides a straightforward approach to address multi-UAV tracking in thermal infrared video, leveraging recent advances in detection and tracking. Instead of relying on the YOLOv5 with the DeepSORT pipeline, we present a tracking framework built on YOLOv12 and BoT-SORT, enhanced with tailored training and inference strategies. We evaluate our approach following the metrics from the 4th Anti-UAV Challenge and demonstrate competitive performance. Notably, we achieve strong results without using contrast enhancement or temporal information fusion to enrich UAV features, highlighting our approach as a"Strong Baseline"for the multi-UAV tracking task. We provide implementation details, in-depth experimental analysis, and a discussion of potential improvements. The code is available at https://github.com/wish44165/YOLOv12-BoT-SORT-ReID .

Problem

• Detecting and tracking multiple UAVs in thermal infrared video
• Addressing challenges like low contrast and small target sizes
• Improving performance with YOLOv12 and BoT-SORT framework

Innovation

• Uses YOLOv12 for UAV detection
• Applies BoT-SORT-ReID for tracking
• Omits contrast enhancement and temporal fusion