MambaTrack: Exploiting Dual-Enhancement for Night UAV Tracking

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Chunhui, Liu, Li, Wen, Hao, Zhou, Xi, Wang, Yanfeng
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917891903848448
author Zhang, Chunhui
Liu, Li
Wen, Hao
Zhou, Xi
Wang, Yanfeng
author_facet Zhang, Chunhui
Liu, Li
Wen, Hao
Zhou, Xi
Wang, Yanfeng
contents Night unmanned aerial vehicle (UAV) tracking is impeded by the challenges of poor illumination, with previous daylight-optimized methods demonstrating suboptimal performance in low-light conditions, limiting the utility of UAV applications. To this end, we propose an efficient mamba-based tracker, leveraging dual enhancement techniques to boost night UAV tracking. The mamba-based low-light enhancer, equipped with an illumination estimator and a damage restorer, achieves global image enhancement while preserving the details and structure of low-light images. Additionally, we advance a cross-modal mamba network to achieve efficient interactive learning between vision and language modalities. Extensive experiments showcase that our method achieves advanced performance and exhibits significantly improved computation and memory efficiency. For instance, our method is 2.8$\times$ faster than CiteTracker and reduces 50.2$\%$ GPU memory. Our codes are available at \url{https://github.com/983632847/Awesome-Multimodal-Object-Tracking}.
format Preprint
id arxiv_https___arxiv_org_abs_2411_15761
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle MambaTrack: Exploiting Dual-Enhancement for Night UAV Tracking
Zhang, Chunhui
Liu, Li
Wen, Hao
Zhou, Xi
Wang, Yanfeng
Computer Vision and Pattern Recognition
Night unmanned aerial vehicle (UAV) tracking is impeded by the challenges of poor illumination, with previous daylight-optimized methods demonstrating suboptimal performance in low-light conditions, limiting the utility of UAV applications. To this end, we propose an efficient mamba-based tracker, leveraging dual enhancement techniques to boost night UAV tracking. The mamba-based low-light enhancer, equipped with an illumination estimator and a damage restorer, achieves global image enhancement while preserving the details and structure of low-light images. Additionally, we advance a cross-modal mamba network to achieve efficient interactive learning between vision and language modalities. Extensive experiments showcase that our method achieves advanced performance and exhibits significantly improved computation and memory efficiency. For instance, our method is 2.8$\times$ faster than CiteTracker and reduces 50.2$\%$ GPU memory. Our codes are available at \url{https://github.com/983632847/Awesome-Multimodal-Object-Tracking}.
title MambaTrack: Exploiting Dual-Enhancement for Night UAV Tracking
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2411.15761