散射光补偿结合色彩保持与对比度均衡的水下图像增强  

Scattered Light Compensation Combined with Color Preservation and Contrast Balance for Underwater Image Enhancement

作　　者：宁泽萌 林森 李兴然 NING Zemeng;LIN Sen;LI Xingran(School of Automation and Electrical Engineering.Shenyang Ligong University,Shenyang 110159,China;Hohai-Lille College,Hohai University,Nanjing 210098,China)

机构地区：[1]沈阳理工大学自动化与电气工程学院,辽宁沈阳110159 [2]河海大学河海里尔学院,江苏南京210098

出　　处：《水下无人系统学报》2024年第5期823-832,共10页Journal of Unmanned Undersea Systems

基　　金：国家重点研发计划项目(2018YFB1403303);辽宁省教育厅高等学校基本科研项目(LJKMZ20220615)。

摘　　要：针对水下图像存在颜色偏差、对比度低及模糊等问题,提出散射光补偿结合色彩保持与对比度均衡的水下图像增强方法。首先,利用相对总变分模型分离图像结构层和纹理层,其中,设计基于RGB空间映射的补偿系数误差矩阵校正结构层色偏,并通过滤波分离与融合增强纹理层,以防止图像的初始特征丢失,增强后的纹理层与结构层叠加得到第1层输出;然后,在对比度均衡模块中,基于空间变换进行保色对比度限制自适应直方图均衡化,进一步提高对比度和亮度;最后,将双层增强结构的结果图融合得到输出图像。通过在不同数据集上与其他算法进行对比,验证文中方法在平衡色差,增强细节和去模糊等方面均具有更好效果,对水下无人系统视觉任务具有实际应用价值。In view of color deviation,low contrast,and blurring in underwater images,an underwater image enhancementmethod based on scattered light compensation combined with color preservation and contrast balance was proposed.Firstly,the relative total variational model was used to separate the structure and texture layer of the image.Specifically,the colordeviation of the structural layer was corrected by defining a compensation coefficient error matrix based on the RGB spatialmapping,and the texture layer was enhanced by filtering separation and fusion to prevent the initial feature loss of the image.The enhanced texture layer was superimposed with the structural layer to obtain the output of the first layer.Besides,in thecontrast balance module,color preservation-contrast limiting adaptive histogram equalization based on spatial transformationwas performed to further improve the contrast and brightness.Finally,the enhanced results of the two layers were fused tooutput the image.Comparison conducted on different datasets verifies that the proposed method has better performance inbalancing color deviation,enhancing details,and deblurring,which has practical application value in unmanned underseasystem-based vision tasks.

关 键 词：水下无人系统 色偏校正 水下图像增强 纹理增强 散射光补偿 

分 类 号：TJ630[兵器科学与技术—武器系统与运用工程]