基于U-net++网络的弱光图像增强方法  

Low-light Image Enhancement Method Based on U-net++Network

作　　者：李华基 程江华[1] 刘通[1] 程榜 赵康成 LI Hua-ji;CHENG Jiang-hua;LIU Tong;CHENG Bang;ZHAO Kang-cheng(College of Electronic Science,National University of Defense Technology,Changsha 410073,China)

机构地区：[1]国防科技大学电子科学学院,长沙410073

出　　处：《计算机科学》2021年第S02期278-282,共5页Computer Science

基　　金：湖南省自然科学基金(2020JJ4670)。

摘　　要：弱光图像增强是计算机视觉中最具挑战性的任务之一,现有算法存在亮度不均、对比度低、颜色失真和噪声严重等问题。文中提出了一种基于改进U-net++网络实现更为自然的暗光增强网络框架。首先,输入弱光图像至改进U-net++网络,利用各层密集连接以增强不同层次图像特征的关联性;其次,把各层次图像特征融合后输入卷积网络层进行细节重建。实验结果证明,该方法在提高图像亮度的同时,更好地恢复了弱光图像的细节特征,并且生成正常光图像的颜色特征更接近自然。在PASCAL VOC测试集上的测试结果显示结构相似度(SSIM)和峰值信噪比(PSNR)两个重要指标分别为0.87和26.36,比同类最优算法分别高出18.6%和11.4%。Low-light image enhancement is one of the most challenging tasks in computer vision.The current algorithms have some problems,such as uneven brightness,low contrast,color distortion and serious noise.In this paper,a more natural dark light enhanced network framework based on improved U-net++network is proposed.First of all,the low light image is input to the improved U-net++network,and the dense connection of each layer is used to enhance the correlation of different levels of image features.Secondly,the image features of each level are fused and input to the convolution network layer for detail reconstruction.The experimental results show that the proposed method not only improves the brightness of the image,but also restores the detail features of the low light image better,and the color feature of the normal light image is closer to the nature.Tests on the PASCAL VOC test set show that the two important indicators,structural similarity(SSIM)and peak signal-to-noise ratio(PSNR),are 0.87 and 26.36,which are 18.6%and 11.4%higher than similar optimal algorithms respectively.

关 键 词：弱光增强 U-net++网络 细节重建 密集连接 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]