1.沈阳理工大学 自动化与电气工程学院;2.中国科学院 沈阳自动化研究所机器人学国家重点实验室;3.中国科学院 机器人与智能制造创新研究院;4.辽宁工程技术大学 电子与信息工程学院
国家自然科学基金项目（No. 91648118，No. 61473280，No. 61991413）辽宁省重点研发计划（No. 2019JH2/10100014）
1.College of Automation and Electrical Engineering, Shenyang Ligong University;2.State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences;3.Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences;4.College of Electronic and Information Engineering, Liaoning Technical University
The National Natural Science Foundation of China (No. 91648118，No. 61473280，No. 61991413) Key Research and Development Plan of Liaoning Province（No. 2019JH2/10100014）
针对水体对光的吸收与散射作用,导致水下拍摄图像存在雾化现象、色彩失真等问题,提出一种基于复原 结构与增强纹理融合的水下图像清晰化算法.首先,通过相对总变差模型将图像分解为结构层与纹理层;其次,基 于背景光的高亮度与平坦特性及颜色信息计算背景光值,利用红色暗通道先验优化透射率,通过逆求解成像模型 得到复原结构层;然后,提出梯度平滑方法用于纹理层,该方法在抑制噪声的同时有效增强纹理细节;最后,融合复 原结构层与增强纹理层,得到清晰且细节丰富的水下图像.将提出算法与现有经典或新颖算法作比较,实验结果表 明,算法良好地将所提出的复原与增强技术相结合,不再局限于解决雾化现象等单一问题,在复杂水下环境具有更 为出众的表现.清晰化处理后的图像良好地平衡了色度、饱和度及清晰度,可有效用于水下机器人等工程实践中.
Aiming at the problems of fogging and color distortion in underwater images caused by the absorption and scattering of light by water, an underwater image sharpening based on fusion of restored structure and enhanced texture is proposed. Firstly, the image is decomposed into structure layer and texture layer by relative total variation model; Secondly, the background light value is calculated based on the high brightness, flat characteristics and color information of the background light, the transmittance is optimized by using the red dark channel prior. The restored structure layer is obtained by inversely solving the imaging model; Then, a gradient smoothing method is proposed for the texture layer, which can effectively enhance the texture details while suppressing the noise; Finally, the restored structure layer and the enhanced texture layer are fused to obtain a clear and detailed underwater image. The proposed algorithm is compared with the existing classical or novel algorithms. The experimental results show that the proposed algorithm combines the restoration and enhancement techniques well, and is no longer limited to solving single problems such as fogging, and has better performance in complex underwater environment. The sharpening image has a good balance of color, saturation and clarity that can be effectively used in engineering practices such as underwater robots.