基于注意力机制与特征重建的水下图像增强  

Underwater Image Enhancement Based on Attention Mechanism and Feature Reconstruction

作　　者：王燕[1] 张金峰 王丽康 范向辉 WANG Yan;ZHANG Jinfeng;WANG Likang;FAN Xianghui(College of Computer and Communication,Lanzhou University of Technology,Lanzhou 730050,China)

机构地区：[1]兰州理工大学计算机与通信学院,甘肃兰州730050

出　　处：《红外技术》2024年第9期1006-1014,共9页Infrared Technology

基　　金：国家自然科学基金(61863025)。

摘　　要：针对现有水下图像增强方法缺少对图像中关键目标物体的关注,对图像边缘细节信息的增强效果不佳等问题,提出一种基于注意力机制与特征重建的水下图像增强方法。首先,残差模块联合CBAM(Convolutional Block Attention Module)模块构建超像素图像增强模型,提升水下图像整体质量的同时改善图像中目标物体的清晰度和可视性;然后,设计一种边缘差分模块,使模型关注图像的高频信息,增强图像中目标物体的边缘细节;最后,构建多粒度特征重建模块,重构超像素图像增强模块的隐藏层特征,还原输入图像,进一步优化模型参数。实验结果表明,相比于对比方法,本文模型在SSIM(Structural Similarity)、PSNR(Peak Signal to Noise Ratio)和UIQM(Underwater Image Quality Measures)三个评价指标上均有提升,具备更好的增强性能。尤其在增强水下图像关键目标物体上具有显著的效果。To address the issues of existing underwater image enhancement methods,which lack focus on critical target objects in images and exhibit poor enhancement effects on edge detail information,in this study,an underwater image enhancement approach is proposed based on an attention mechanism and feature reconstruction.First,a superpixel image enhancement model is constructed by integrating the residual module with the Convolutional Block Attention Module(CBAM),which not only improves the overall quality of underwater images but also enhances the clarity and visibility of target objects in images.Second,an edge difference module is designed to enable the model to focus on high-frequency information in the images,thereby strengthening the edge details of the target objects.Finally,a multi-granularity feature reconstruction module is built to reconstruct the hidden layer features of the superpixel image enhancement model,restore the input image,and further optimize the model parameters.Experimental results demonstrate that when compared with contrastive methods,the proposed model realizes improvements in three evaluation metrics:Structural Similarity(SSIM),Peak Signal to Noise Ratio(PSNR),and Underwater Image Quality Measures(UIQM),indicating better enhancement performance.Notably,it exhibits a remarkable effect in enhancing critical target objects in underwater images.

关 键 词：水下图像增强 超像素图像 注意力机制 边缘差分 多粒度特征重建 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]