強力基準線：基於YOLOv12與BoT-SORT-ReID的多無人機追蹤系統

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

March 21, 2025

作者: Yu-Hsi Chen

cs.AI

摘要

在熱紅外影像中檢測和追蹤多架無人機（UAV）由於低對比度、環境噪聲以及目標尺寸小等問題，本質上具有挑戰性。本文提供了一種直接的方法來應對熱紅外影像中的多無人機追蹤，利用了檢測與追蹤領域的最新進展。我們並未依賴於YOLOv5與DeepSORT的組合，而是提出了一個基於YOLOv12和BoT-SORT的追蹤框架，並通過定制的訓練與推理策略進行了增強。我們按照第四屆反無人機挑戰賽的指標評估了我們的方法，並展示了具有競爭力的性能。值得注意的是，我們在未使用對比度增強或時間信息融合來豐富無人機特徵的情況下，取得了優異的結果，這凸顯了我們的方法作為多無人機追蹤任務的“強基準”地位。我們提供了實現細節、深入的實驗分析以及潛在改進的討論。代碼可在https://github.com/wish44165/YOLOv12-BoT-SORT-ReID 獲取。

English

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 .