基于改进GAN的图像去雨方法及其在车辆检测上的应用  

IMAGE RAIN REMOVAL METHOD BASED ON IMPROVED GANAND ITS APPLICATION ON VEHICLE DETECTION

作　　者：应保胜[1] 刘畅然 熊豪 石兵华 许小伟[1] Ying Baosheng;Liu Changran;Xiong Hao;Shi Binghua;Xu Xiaowei(School of Automobile and Traffic Engineering,Wuhan University of Science and Technology,Wuhan 430065,Hubei,China;School of Information and Communication Engineering,Hubei University of Economics,Wuhan 430205,Hubei,China)

机构地区：[1]武汉科技大学汽车与交通工程学院,湖北武汉430065 [2]湖北经济学院信息与通信工程学院,湖北武汉430205

出　　处：《计算机应用与软件》2025年第3期183-189,共7页Computer Applications and Software

基　　金：国家自然科学基金项目(51975426,51975428);武汉市科技计划项目(2019010701011393)。

摘　　要：针对雨天行车时,车载摄像头拍摄的图像被镜头前的雨滴或者空中的雨线条纹所遮挡,影响车辆检测的准确度的问题,使用先去雨后检测的思路,提出一种基于改进的生成对抗网络(Generative Adversarial Networks,GAN)图像去雨方法。该方法在GAN的生成网络中加入注意力模块,并在patch-GAN判别网络中加入一层卷积,提取注意力掩码图,进行局部鉴别,提升去雨效果并保留图像细节。对图像进行去雨处理后,再使用YOLOv4算法对去雨后图像进行车辆检测。实验使用多种数据集将该方法与其他方法进行对比实验,结果表明该方法有良好的去雨效果,并能有效提高雨天车辆检测准确率。When driving on a rainy day,the images taken by the on-board camera will be obscured by raindrops in front of the lens or rain streaks in the air,which affects the accuracy of vehicle detection.In order to solve the problem,the idea of rain removal first and then detection is adopted and an image rain removal method based on improved generative adversarial networks(GAN)is proposed.In this method,the attention module was added to the generative network and one layer of convolution was added to the patch-GAN discriminative network to extract attention mask for local discrimination.While the rain removal effect was improved,the image details were also preserved.After the rain was removed from the image,the YOLOv4 algorithm was used for vehicle detection.Multiple data sets were used to comparison experiments of this method with others.The experiments show that this method was effective in rain removal and can effectively improve the accuracy of vehicle detection in rainy days.

关 键 词：图像去雨 生成对抗网络 注意力模块 自编码器 车辆检测 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]