注意力机制引导暗区域的低光照图像增强  

Attentional mechanisms guided low-light image enhancement in dark areas

作　　者：耿馨雨 余磊[1] 唐保香 谢大涛 GENG Xinyu;YU Lei;TANG Baoxiang;XIE Datao(College of Computer and Information Science,Chongqing Normal University,Chongqing 401331,China)

机构地区：[1]重庆师范大学计算机与信息科学学院,重庆401331

出　　处：《微电子学与计算机》2023年第3期20-28,共9页Microelectronics & Computer

基　　金：国家自然科学基金面上项目(72071019);重庆市自然科学基金面上项目(cstc2021jcyj-msxmX0185)。

摘　　要：针对黑暗场景下拍摄的光照图像中所产生的光照不均匀,恢复细节不够清晰等问题,提出了基于深度学习的一种低光照图像增强方法,称为ADLIE(Attention-directed Low-light Image Enhancement)算法.首先,利用双通道注意力机制来引导注意网络,依据输入图像的明暗程度进行区域性的分级划分,同时双通道注意力机制还可以提取更多良好的局部特征信息.然后,将注意图和输入图像一同输入到增强网络中.对不同区域利用不同级别的光照强度来提升图像对比度,达到整体图像的均匀曝光的效果.最后,加入增强模块,利用增强模块中的多层卷积连接恢复图像细节,来获得更自然清晰的高质量图像.此外,采用在真实场景下采集的公开LOL数据集和LSRW数据集进行的实验验证,对比了Retinex、R2RNet等经典的方法,在PSNR(峰值信噪比)、SSIM(结构相似性)、CTRS(对比度)和InformationEntropy(信息熵)等常见的评价指标上的实验结果有了显著的提升.该网络在提高低光照图像整体亮度的同时恢复了图像的细节,减少了颜色失真,避免了全局过度曝光,得到更加清晰自然的图像.A low-light image enhancement method based on deep learning,called ADLIE(Attention-directed Low-light Image Enhancement)algorithm,is proposed for the problems of uneven illumination and lack of clear recovery details produced in the light images captured in dark scenes.First,a dual-channel attention mechanism is used to guide the attention network,which is regionally graded based on the brightness and darkness of the input image,while the dual­channel attention mechanism can also extract more better local feature infbnnation.Then,the attention map is fed into the enhancement network together with the input image.Different levels of light intensity are used for different regions to enhance the image contrast and achieve the effect of uniform exposure of the overall image.Finally,the enhancement module is added to recover the image details using the multi-layer convolutional connections in the enhancement module to obtain a more clearer high quality image.In addition,the experimental validation using open LOL dataset and LSRW dataset collected in real scenes compares classical methods such as Retinex and R2RNet on common evaluation metrics such as PSNR(peak signal-to-noise ratio),SSIM(structural similarity),CTRS(contrast ratio)and Information Entropy(information entropy).The experimental results show a significant improvement.The network restores the details of the image while improving the overall brightness of the low-light image,reduces color distortion,avoids global overexposure,and obtains a clearer and more natural image.

关 键 词：深度学习 注意力机制 低光照图像 图像增强 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]