期刊
IEEE ROBOTICS AND AUTOMATION LETTERS
卷 8, 期 6, 页码 3142-3149出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/LRA.2023.3264711
关键词
Noise reduction; Autonomous aerial vehicles; Transformers; Feature extraction; Decoding; Task analysis; Image restoration; Unmanned aerial vehicle; nighttime aerial tracking; image denoising; cascaded transfomer
类别
This paper proposes an efficient plug-and-play cascaded denoising Transformer (CDT) to suppress cluttered and complex real noise in UAV visual tracking, thereby improving tracking performance.
The automation of unmanned aerial vehicles (UAVs) has been greatly promoted by visual object tracking methods with onboard cameras. However, the random and complicated real noise produced by the cameras seriously hinders the performance of state-of-the-art (SOTA) UAV trackers, especially in low-illumination environments. To address this issue, this work proposes an efficient plug-and-play cascaded denoising Transformer (CDT) to suppress cluttered and complex real noise, thereby boosting UAV tracking performance. Specifically, the novel U-shaped cascaded denoising network is designed with a streamlined structure for efficient computation. Additionally, shallow feature deepening (SFD) encoder and multi-feature collaboration (MFC) decoder are constructed based on multi-head transposed self-attention (MTSA) and multi-head transposed cross-attention (MTCA), respectively. A nested residual feed-forward network (NRFN) is developed to focus more on high-frequency information represented by noise. Extensive evaluation and test experiments demonstrate that the proposed CDT has a remarkable denoising effect and improves UAV nighttime tracking performance.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据