An unsupervised ocean surface waves suppression algorithm based on sub-aperture SAR images

• Published in: International journal of remote sensing Vol. 44; no. 5; pp. 1460 - 1483
• Main Authors: Zhu, Yuting, Chao, Xiaopeng, Wang, Xiaoqing, Chen, Jian, Huang, Haifeng
• Format: Journal Article
• Language: English
• Published: London Taylor & Francis 04.03.2023; Taylor & Francis Ltd
• Subjects: Algorithms; Aperture imaging; Deep learning; Methods; Ocean surface; ocean surface waves; Ocean waves; Oceanography; Oceans; Radar imaging; regularizer; SAR (radar); Sea state; Sea states; Sea surface; Seawater; Signal to noise ratio; sub-aperture; suppression; Surface layers; Surface water waves; Surface waves; Synthetic aperture radar; Training; unsupervised; Unsupervised learning
• ISSN: 0143-1161; 1366-5901
• DOI: 10.1080/01431161.2023.2184216

Ocean waves are the richest small-scale texture on the sea surface, from which valuable information can be inversed. In general, synthetic aperture radar (SAR) images of surface waves will inevitably have an impact on some oceanography follow-up applications due to the intricate motion of the waves. However, existing suppression methods based on image geometric properties or deep learning-based have limitations. Owing to the lack of clean images and the uncertainty of the statistical characteristics of seawater, these methods suppress ocean surface waves while harming other target information. To address this issue, we propose an unsupervised wave suppression algorithm based on sub-aperture SAR images named SAR-Noise2Noise (SAR-N2N). First, SAR-N2N exploits the geometric and time-varying relationship of the sub-aperture images to suppress the wave target selectively through sub-aperture image cancellation. Second, through the method of unsupervised learning, only noisy images are used to suppress ocean surface waves, avoiding heavy dependence on the assumption of the wave distribution. Finally, the proposed regularizer is used as an additional loss to form an end-to-end training process. We explain our approach from a theoretical perspective and further validate it through extensive experiments, including synthetic experiments with various ocean wave distributions in simulated SAR images and real-world images. Training on collocations over SAR images, we demonstrate on test data from simulated images that SAR-N2N can improve peak signal-to-noise ratio (PSNR) up to dB compared with the classical approach. Furthermore, it improves the equivalent number of looks (ENL) value of real-world SAR images by a factor of . All results and the methods are novel in terms of the accuracy achieved, combining the classical approach with deep learning techniques. We conclude that SAR-N2N has the potential to make useful contributions to several oceanographic applications as well as to the near real time (NRT) processing of multiparametric sea states.