Underwater Image Enhancement Algorithm Based on Color Compensation and Adaptive Luminance

Aiming at the problems of shallow marine aqua-culture fish images collected by underwater robot such as color distortion, low contrast, and low illumination, this paper proposes an underwater image enhancement algorithm based on color compensation and adaptive luminance. Firstly, according to the attenuation characteristics of RGB color channels, proposes an color compensation algorithm based on color channel attenuation compensation, compensate for the two color channels which have the most severe attenuation to improve the color distortion problem of the images. Secondly, filter the noise generated by the image after color compensation by using a non-local mean denoising method (NL-means). Then, transform the image from RGB color space to HSV color space. In the HSV color space, a global adaptive luminance enhancement method is designed to improve the luminance of the V component and adaptively adjust saturation of the S component. Finally, transform the image from HSV color space to RGB color space to obtain the final enhanced image.The experiment shows that the images enhanced by using this algorithm have natural colors, carry more image information and have good visual effects, which are superior to other comparison algorithms.