4.6 Article

Adversarial Blur-Deblur Network for Robust UAV Tracking

期刊

IEEE ROBOTICS AND AUTOMATION LETTERS
卷 8, 期 2, 页码 1101-1108

出版社

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/LRA.2023.3236584

关键词

Tracking; Generators; Autonomous aerial vehicles; Training; Target tracking; Visualization; Real-time systems; Unmanned aerial vehicle; visual object tracking; adversarial training; realistic blur generator; robust image deblurrer

类别

向作者/读者索取更多资源

This work proposes an adversarial blur-deblur network (ABDNet) for UAV tracking, which includes a deblurrer to recover the visual appearance of the tracked object and a blur generator to produce realistic blurry images for adversarial training. ABDNet is trained with blurring-deblurring loss and tracking loss, and during inference, the blur generator is removed while the deblurrer and the tracker work together for UAV tracking.
Unmanned aerial vehicle (UAV) tracking has been widely applied in real-world applications such as surveillance and monitoring. However, the inherent high maneuverability and agility of UAV often lead to motion blur, which can impair the visual appearance of the target object and easily degrade the existing trackers. To overcome this challenge, this work proposes a tracking-oriented adversarial blur-deblur network (ABDNet), composed of a novel deblurrer to recover the visual appearance of the tracked object, and a brand-new blur generator to produce realistic blurry images for adversarial training. More specifically, the deblurrer progressively refines the features through pixel-wise, spatial-wise, and channel-wise stages to achieve excellent deblurring performance. The blur generator adaptively fuses an image sequence with a learnable kernel to create realistic blurry images. During training, ABDNet is plugged into the state-of-the-art real-time trackers and trained with blurring-deblurring loss as well as tracking loss. During inference, the blur generator is removed, while the deblurrer and the tracker can work together for UAV tracking. Extensive experiments in both public datasets and real-world testing have validated the effectiveness of ABDNet.

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。

评论

主要评分

4.6
评分不足

次要评分

新颖性
-
重要性
-
科学严谨性
-
评价这篇论文

推荐

暂无数据
暂无数据