An interferometric phase noise reduction method based on modified denoising convolutional neural network

Traditional interferometric synthetic aperture radar (InSAR) denoising methods normally try to estimate the phase fringes directly from the noisy interferogram. Since the statistics of phase noise are more stable than the phase corresponding to complex terrain, it could be easier to estimate the phase noise. In this paper, phase noises rather than phase fringes are estimated first, and then they are subtracted from the noisy interferometric phase for denoising. The denoising convolutional neural network (DnCNN) is introduced to estimate phase noise and then a modified network called IPDnCNN is constructed for the problem. Based on the IPDnCNN, a novel interferometric phase noise reduction algorithm is proposed, which can reduce phase noise while protecting fringe edges and avoid the use of filter windows. Experimental results using simulated and real data are provided to demonstrate the effectiveness of the proposed method.