Enregistré dans:
Détails bibliographiques
Auteur principal: Chen, Yu-Hsi
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2503.17237
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866908451259547648
author Chen, Yu-Hsi
author_facet Chen, Yu-Hsi
contents 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 well-established YOLOv5 with DeepSORT combination, we present a tracking framework built on YOLOv12 and BoT-SORT, enhanced with tailored training and inference strategies. We evaluate our approach following the 4th Anti-UAV Challenge metrics and reach competitive performance. Notably, we achieved strong results without using contrast enhancement or temporal information fusion to enrich UAV features, highlighting our approach as a "Strong Baseline" for multi-UAV tracking tasks. 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 .
format Preprint
id arxiv_https___arxiv_org_abs_2503_17237
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Strong Baseline: Multi-UAV Tracking via YOLOv12 with BoT-SORT-ReID
Chen, Yu-Hsi
Computer Vision and Pattern Recognition
Artificial Intelligence
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 well-established YOLOv5 with DeepSORT combination, we present a tracking framework built on YOLOv12 and BoT-SORT, enhanced with tailored training and inference strategies. We evaluate our approach following the 4th Anti-UAV Challenge metrics and reach competitive performance. Notably, we achieved strong results without using contrast enhancement or temporal information fusion to enrich UAV features, highlighting our approach as a "Strong Baseline" for multi-UAV tracking tasks. 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 .
title Strong Baseline: Multi-UAV Tracking via YOLOv12 with BoT-SORT-ReID
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2503.17237