Side-scan Sonar Submarine Pipeline Image Enhancement Incorporating Gamma Correction and Blurring Algorithms

Abstract

Side-scan sonar can effectively detect the burial state of submarine pipelines. However, when obtaining underwater images, the images generated by side-scan sonar have quality issues due to factors such as seabed interference, energy attenuation, and equipment limitations. For example, there is uneven grayscale. The quality of the image can be optimized by grayscale correction. But the current algorithms do not fully consider the texture details of the image and the scattering noise present in the marine environment. Therefore, this paper proposes a side-scan sonar enhancement method based on a guided filter hierarchical processing strategy. Firstly, the side-scan sonar image is decomposed into basic and detail layers using guided filter. The basic layer components of the image are fused using an adaptive gamma correction combining mean and variance and an improved fuzzy algorithm, aiming at gray scale correction, adjusting image brightness and improving contrast. The detail layer components are processed using a hybrid Butterworth filter combined with a Hamming window to enhance the texture information and remove the noise interference. Finally, the processed basic and detail layer components are reconstructed using weighted fusion to obtain the enhanced side-scan sonar image. Experiments show that the method can effectively achieve gray scale correction. And compared with the existing image enhancement methods, the method in this paper has significant improvement in Peak Signal-to-Noise Ratio (PSNR), Structural Similarity (SSIM), and Universal Quality Index (UQI). The values of the Natural Image Quality Evaluator (NIQE) and the Blind/Referenceless Image Spatial Quality Evaluator (BRISQUE) are decreased.