Salvato in:
Dettagli Bibliografici
Autori principali: Peng, Chenxu, Wang, Chenxu, Zou, Minrui, Li, Danyang, Yang, Zhengpeng, Dai, Yimian, Cheng, Ming-Ming, Li, Xiang
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2505.04917
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866913826215034880
author Peng, Chenxu
Wang, Chenxu
Zou, Minrui
Li, Danyang
Yang, Zhengpeng
Dai, Yimian
Cheng, Ming-Ming
Li, Xiang
author_facet Peng, Chenxu
Wang, Chenxu
Zou, Minrui
Li, Danyang
Yang, Zhengpeng
Dai, Yimian
Cheng, Ming-Ming
Li, Xiang
contents Infrared object tracking plays a crucial role in Anti-Unmanned Aerial Vehicle (Anti-UAV) applications. Existing trackers often depend on cropped template regions and have limited motion modeling capabilities, which pose challenges when dealing with tiny targets. To address this, we propose a simple yet effective infrared tiny-object tracker that enhances tracking performance by integrating global detection and motion-aware learning with temporal priors. Our method is based on object detection and achieves significant improvements through two key innovations. First, we introduce frame dynamics, leveraging frame difference and optical flow to encode both prior target features and motion characteristics at the input level, enabling the model to better distinguish the target from background clutter. Second, we propose a trajectory constraint filtering strategy in the post-processing stage, utilizing spatio-temporal priors to suppress false positives and enhance tracking robustness. Extensive experiments show that our method consistently outperforms existing approaches across multiple metrics in challenging infrared UAV tracking scenarios. Notably, we achieve state-of-the-art performance in the 4th Anti-UAV Challenge, securing 1st place in Track 1 and 2nd place in Track 2.
format Preprint
id arxiv_https___arxiv_org_abs_2505_04917
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A Simple Detector with Frame Dynamics is a Strong Tracker
Peng, Chenxu
Wang, Chenxu
Zou, Minrui
Li, Danyang
Yang, Zhengpeng
Dai, Yimian
Cheng, Ming-Ming
Li, Xiang
Computer Vision and Pattern Recognition
Infrared object tracking plays a crucial role in Anti-Unmanned Aerial Vehicle (Anti-UAV) applications. Existing trackers often depend on cropped template regions and have limited motion modeling capabilities, which pose challenges when dealing with tiny targets. To address this, we propose a simple yet effective infrared tiny-object tracker that enhances tracking performance by integrating global detection and motion-aware learning with temporal priors. Our method is based on object detection and achieves significant improvements through two key innovations. First, we introduce frame dynamics, leveraging frame difference and optical flow to encode both prior target features and motion characteristics at the input level, enabling the model to better distinguish the target from background clutter. Second, we propose a trajectory constraint filtering strategy in the post-processing stage, utilizing spatio-temporal priors to suppress false positives and enhance tracking robustness. Extensive experiments show that our method consistently outperforms existing approaches across multiple metrics in challenging infrared UAV tracking scenarios. Notably, we achieve state-of-the-art performance in the 4th Anti-UAV Challenge, securing 1st place in Track 1 and 2nd place in Track 2.
title A Simple Detector with Frame Dynamics is a Strong Tracker
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2505.04917