视觉注意机制的注意残差稠密神经网络弱光照图像增强  

Attentive residual dense network of visual attention mechanism for weakly illuminated image enhancement

作　　者：邓箴 王一斌[2] 刘立波 DENG Zhen;WANG Yi-bin;LIU Li-bo(School of Information Engineering, Ningxia University, Yinchuan 750021, China;School of Engineering, Sichuan Normal University, Chengdu 61000, China)

机构地区：[1]宁夏大学信息工程学院,宁夏银川750021 [2]四川师范大学工学院,四川成都610000

出　　处：《液晶与显示》2021年第11期1463-1473,共11页Chinese Journal of Liquid Crystals and Displays

基　　金：宁夏回族自治区自然科学基金(No.2020AAC03031);宁夏回族自治区青年托举人才工程(No.2017);国家自然基金(No.61862050)。

摘　　要：针对传统的弱光照图像增强算法鲁棒性差,基于神经网络的图像增强算法直接从弱光照图像中估计增强结果,并未注入视觉注意机制,不能有效注意弱光照区域,导致算法增强结果的精度不高等问题,本文提出了注意残差稠密神经网络的弱光照图像增强算法来提高弱光照图像的增强精度和视觉效果。该算法主要包括注意循环网络和残差稠密网络,注意循环网络在光照图的引导下,利用循环网络结构逐步关注图像中的弱光照区域,从而产生由粗到细,逐步优化的光照注意图。而光照注意图则进一步联合弱光照图像作为后续的残差稠密网络的输入,引导残差稠密网络为弱光照区域分配更多的计算资源,更好地学习弱光照图像与增强图像的映射关系,得到准确的图像增强结果。实验表明,本文算法在合成图像及真实图像上均较常用算法有更好的增强效果。Weakly illuminated image enhancement as a kind of pre-processing technologies is widely used in various computer vision tasks.Traditional image enhancement methods has poor robustness.While,methods based on existing convolutional neural networks(CNNs)estimate the enhanced image from weakly illuminated image directly without injecting the visual attention mechanism,ignoring weakly illuminated regions and leading to inaccuracy result.To resolve this problem,we propose an attentive residual dense network for weakly illuminated image enhancement.The proposed network contains two parts:attentive recurrent network and residual dense network.With the guidance of the illumination map,attentive recurrent network focuses more and more on the weakly illuminated regions and generates the attentive illumination map following a coarse-to-fine strategy via the recurrent architecture.This attentive illumination map concatenated with the weakly illuminated image are injected into the subsequent residual dense network to ensure this network assign more computational source to weakly illuminated regions and estimate enhanced image accurately.The experiments demonstrate that our method achieves favorable performance against that of existing image enhancement methods based on synthetic images and real images.

关 键 词：弱光照图像增强 Retinex模型 卷积神经网络 残差稠密网络 注意机制 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]