Underwater image sharpening method based on light attenuation and depth estimation

Abstract

The invention discloses an underwater image sharpening method based on light attenuation and depth estimation. The method comprises the following steps of: S1, acquiring an underwater image to be processed; S2, performing scene depth estimation operation on the underwater image to be processed to obtain a scene depth map of the underwater image to be processed; S3, extracting a background light value of the underwater image to be processed, performing color preprocessing on the underwater image to be processed according to the extracted background light value, and estimating the light attenuation rate of the underwater image to be processed after color preprocessing; S4, performing water depth value estimation on the underwater image to be processed according to the scene depth map, the background light value and the light attenuation rate of the underwater image to be processed; and S5, restoring the underwater image to be processed according to the estimated water depth value and the scene depth map, the background light value and the light attenuation rate of the underwater image to be processed. Compared with the prior art, the method can improve the accuracy of restoration of the color and contrast of the underwater image, and obtain higher clear imaging quality of the underwater image.

Description

technical field [0001] The invention relates to the field of underwater image processing, in particular to an underwater image sharpening processing method based on light attenuation and depth estimation. Background technique [0002] High-quality underwater images can provide rich visual information and play an important role in close-range underwater engineering. However, light attenuates exponentially when propagating underwater, and this attenuation varies for different wavelengths of light. From public seas to coastal waters, under different water quality conditions, the attenuation of the same wavelength of light is also different. At the same time, the suspended matter and water medium will change the light propagation trajectory, and the reliable information received by the camera will be further reduced. These complications cause underwater images to exhibit different degrees of color distortion. Therefore, the current underwater images acquired by cameras cannot...

AI Technical Summary

Problems solved by technology

However, most of the existing algorithms based on the imaging model use a fixed light attenuation rate to restore the image, and the algorithm is less robust in multi-type underwater image processing; at the same time, the scene depth information related to the depth value can be divided into scene Depth maps and water depth values ​​from the water surface to the target object, there are already some relatively mature scene depth estimation algorithms for images, which are mainly used for scene depth estimation of conventional underwater space scene images, and because underwater images are affected by underwater light and shadow The impact of the environment, if the existing scene depth estimation algorithm is directly used to estimate the scene depth of the underwater image, it will cause a certain estimation error. On the other hand, the underwater scene depth data of the current known image data is relatively scarce, which is not enough Supervised network training for underwater scene depth estimation, so the scheme of implementing underwater scene depth estimation by training a supervised network model is also hindered by technical conditions. In addition, the existing water depth value estimation methods for underwater images are all Generally more complicated and difficult to be widely implemented and applied

All of the above factors have a negative impact on the accuracy and effect of underwater image color and contrast restoration processing.

Images