基于梯度可感知通道注意力模块的红外小目标检测前去噪网络  

Gradient-aware channel attention network for infrared small target image denoising before detection

作　　者：林再平 罗伊杭 李博扬 凌强 郑晴 杨晶贻 刘丽 吴京[1] LIN Zai-Ping;LUO Yi-Hang;LI Bo-Yang;LING Qiang;ZHENG Qing;YANG Jing-Yi;LIU Li;WU Jing(College of electronic science and technology,National University of Defense Technology,Changsha 410073,China;Department of Military Representative Bureau of Aerospace Systems,Beijing 100000,China;Shanghai Institute of Satellite Engineering,Shanghai 200000,China)

机构地区：[1]国防科技大学电子科学学院,湖南长沙410073 [2]航天系统部装备部军事代表局,北京100000 [3]上海卫星工程研究所,上海200000

出　　处：《红外与毫米波学报》2024年第2期254-260,共7页Journal of Infrared and Millimeter Waves

基　　金：the National Natural Science Foundation of China(62001478,61972435);Aviation Science Foundation Project Contract(ASFC-20165188004);Shanghai Aerospace Science and Technology Innovation Fund(SAST2021-035);Independent Research Fund of Key Laboratory of Military Scientific Research。

摘　　要：红外图像去噪在军事及民用领域应用广泛。现有基于深度学习的图像去噪方法主要为可见光图像设计,此类方法容易过度平滑图像细节,从而导致弱小目标丢失,为后续的检测任务带来困难。为了在去除噪声的同时保留好红外图像中的目标信息,本文提出了一种基于梯度可感知通道注意力模块的红外弱小目标检测前去噪网络。该网络首先采用编码器-解码器结构来去除图像中的加性噪声,然后通过梯度可感知通道注意力模块对图像高频区域进行自适应增强,有效保持红外弱小目标的响应强度。此外,本文提出了领域第一个包含3981张含噪声的红外图像数据集。实验结果表明,该网络能够在有效去除加性噪声的同时避免过度平滑,很好地保留了红外图像中的目标信息,最终实现了在含噪声环境下的高鲁棒性红外弱小目标检测。Infrared small target denoising is widely used in military and civilian fields.Existing deep learningbased methods are specially designed for optical images and tend to over-smooth the informative image details,thus losing the response of small targets.To both denoise and maintain informative image details,this paper pro⁃poses a gradient-aware channel attention network(GCAN)for infrared small target image denoising before detec⁃tion.Specifically,we use an encoder-decoder network to remove the additive noise of the infrared images.Then,a gradient-aware channel attention module is designed to adaptively enhance the informative high-gradient image channel.The informative target region with high-gradient can be maintained in this way.After that,we develop a large dataset with 3981 noisy infrared images.Experimental results show that our proposed GCAN can both effec⁃tively remove the additive noise and maintain the informative target region.Additional experiments of infrared small target detection further verify the effectiveness of our method.

关 键 词：红外小目标 检测前去噪 梯度可感知通道注意力模块 

分 类 号：TP753[自动化与计算机技术—检测技术与自动化装置]