A SAR wave-enhanced method combining denoising and texture enhancement for bathymetric inversion

Abstract

The wave phenomena in SAR images are able to provide water depth information. SAR ocean images are often characterized by unclear wave texture and strong speckle noise, which will hinder the bathymetric inversion. Denoising and texture enhancement are two strategies to improve image quality. However, noise reduction may blur textures, while texture enhancement may amplify noise. To address this, we propose a wave texture enhancement method to balance noise reduction and texture preservation. First, an adaptive total variation bounded Hessian method removes noises from SAR ocean images while preserving texture. Next, an improved Frankle-McCann Retinex method enhances ocean wave features in the denoised image without adding noises. Finally, the resulting image is used for wave-based bathymetric inversion experiments conducted at Car Nicobar Island, Chowra Island, and Dongdao Island, covering depths up to 40 m. The proposed method improved bathymetric accuracy, reducing mean absolute error (MAE) by up to 4.69 m and mean relative error (MRE) by up to 18 %. In addition, the proposed method has a positive effect on the estimation of wavelength and period parameters. Experimental results show that blurred ocean surfaces in SAR images significantly affect bathymetric inversion. Thus, wave enhancement is an important step prior to performing bathymetric inversion.