改进的自适应学习注意力网络的水下图像增强  

Improved Adaptive Learning Attention Network for Underwater Image Enhancement

作　　者：许袁 李锋[1] 闫家祥 XU Yuan;LI Feng;YAN Jiaxiang(Ocean College,Jiangsu University of Science and Technology,Zhenjiang,Jiangsu 212100,China)

机构地区：[1]江苏科技大学海洋学院,江苏镇江212100

出　　处：《计算机工程与应用》2024年第24期243-249,共7页Computer Engineering and Applications

基　　金：国家自然科学基金(62276117);江苏省自然基金(BK20211341)。

摘　　要：针对水下图像噪声大、色偏严重和细节模糊等问题,提出了一种基于监督学习的自适应学习注意力网络的水下图像增强算法。利用多尺度融合加强通道之间空间信息的联系;通过并行注意力机制平衡照明特征和颜色信息;采用自适应学习保留浅层信息,学习重要特征信息;构造多项损耗函数,改善网络性能。实验结果表明,相对于已有算法,该算法的峰值信噪比(peak signal-to-noise ratio,PSNR)指标提高了8.99%,结构相似性(structural similarity index,SSIM)指标提高了15.39%,水下彩色图像评价(underwater color image quality evaluation,UCIQE)指标提高了1.92%,具有更好的视觉效果。An underwater image enhancement algorithm based on supervised learning and adaptive learning attention net-work(adaptive learning attention network for underwater image enhancement,LANet)is proposed to solve the problems of high noise,serious color bias and blurred details in underwater images.Firstly,multi-scale fusion is used to strengthen the spatial information connection between channels.Then,the lighting features and color information are balanced by parallel attention mechanism.Then adaptive learning is used to retain shallow information and learn important feature information adaptively.Finally,multiple loss functions are constructed to improve the network performance.The experi-mental results show that compared with the existing algorithm,the peak signal-to-noise ratio(PSNR)index and the struc-tural similarity index(SSIM)index of the proposed algorithm are increased by 8.99%and 15.39%respectively.The under-water color image quality evaluation(UCIQE)index has been improved by 1.92%,with better visual effects.

关 键 词：注意力机制 损失函数 机器视觉 水下图像增强 多尺度 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]