Automatic RFI Identification for Sentinel-1 Based on Siamese-Type Deep CNN Using Repeat-Pass Images
Xingyu Lu, Chenchen Wang, Xiaofeng Xu, Huizhang Yang, Shiyuan Zhang, Ke Tan, Xianglin Bao, Weimin Su, Hong Gu
Abstract
Since the start of the Sentinel-1 mission, numerous cases of severe image degradation caused by RFI have been reported, which puts forward an urgent need for RFI identification and mitigation. In this paper, an automatic RFI identification method is proposed based on a siamese-type deep convolutional neural network (Siam-CNN-RIM). The Siam-CNN-RIM can be served as a pre-processing step before RFI mitigation to identify whether an S-1 image is RFI-contaminated or not. Different from traditional RFI identification networks which only use a single image as input, an additional image in the repeat-pass time-series is also fed into the input of Siam-CNN-RIM as a reference. Both of the input images correspond to the same illuminated area, and pass through the same convolutional layer followed by an energy function, such that the different features caused by RFI can be extracted and the background terrain features can be ignored. This is beneficial for distinguishing the real RFI signatures and the similar terrain signatures that may cause false positives, and thus improving the RFI identification performance. Experimental results show that the proposed method is robust in different scenarios and can achieve more than 97% RFI identification accuracy, even for the open-set task where the test scenarios are not included in the training set.