摘要
提出一种多路融合深度聚合学习的水下图像增强算法。首先,利用图像预处理算法,分别获取3条支路(对比度、亮度和颜色)图像属性信息。然后,设计图像属性依赖模块,利用融合网络获取多支路的融合特征,再通过并行图卷积探索潜在的融合图像属性的相关性。接着,引入自注意力深度聚合学习模块,利用序列自注意力和全局属性迭代机制深度挖掘多支路私有域和公有域的交互信息,再通过聚合瓶颈的方式有效提取和整合图像属性之间的重要信息,从而实现更准确的特征表示。最后,引入跳跃连接继续增强图像输出,进一步改善图像增强的效果。大量实验证明,所提方法可有效去除色偏、模糊,提高图像清晰度,并有利于水下图像分割和关键点检测任务。峰值信噪比和结构相似性指标最高可达到23.01 dB和0.90,与次优方法相比提高了5.0%和4.7%;水下彩色图像质量评估和信息熵最高可达0.93和14.33,与次优方法相比提高了2.2%和0.5%。
This paper proposes a multiplexed fusion deep aggregate learning algorithm for underwater image enhancement.First,the image preprocessing algorithm is used to obtain the image attribute information of three branches(contrast,brightness,and colour)respectively.Then,the image attribute dependency module is designed to obtain fusion features of multiplexed using a fusion network,and then explore the potential fused image attribute correlations through parallel graph convolution.A self-attention deep aggregate learning module is introduced to deeply mine the interaction information between the private and public domains of the multiplexed using sequential self-attention and global attribute iteration mechanisms,and also effectively extract and integrate the important information between image attributes by means of aggregation bottlenecks to achieve more accurate feature representation.Finally,skip connections are introduced to continue enhancing the image output to further improve the effect of image enhancement.Numerous experiments have demonstrated that the proposed method can effectively remove colour bias and blurring,and improve image clarity,as well as facilitate underwater image segmentation and key point detection tasks.The peak signal-to-noise ratio and structural similarity metrics can reach the highest values of 23.01 dB and 0.90,which are improved by 5.0%and 4.7%compared with the suboptimal method,while the underwater colour image quality metrics and information entropy metrics have the highest values of 0.93 and 14.33,which are improved by 2.2%and 0.5%compared with the suboptimal method.
作者
陈燕
肖澳
李云
胡小春
井佩光
Chen Yan;Xiao Ao;Li Yun;Hu Xiaochun;Jing Peiguang(School of Computer,Electronics and Information,Guangxi University,Nanning 530004,Guangxi,China;School of Big Data and Artificial Intelligence,Guangxi University of Finance and Economics,Nanning 530003,Guangxi,China;School of Electrical and Information Engineering,Tianjin University,Tianjin 300072,China)
出处
《激光与光电子学进展》
北大核心
2025年第2期332-340,共9页
Laser & Optoelectronics Progress
基金
国家自然科学基金地区基金(62361002)
博士启动基金(852021025)。
关键词
水下图像增强
融合网络
图卷积
自注意力
水下图像分割
关键点检测
underwater image enhancement
fusion networks
graph convolution
self-attention
underwater image segmentation
key point detection
作者简介
通信作者:李云,liyun@guat.edu.cn。
