Interferometric Passive Radar Imaging With Deep Denoising Priors

Passive radar has advantages over its active counterpart in terms of cost and stealth. In this article, we address the passive radar imaging problem by interferometric inversion using a spectral estimation method with a priori information within a deep learning framework. Cross-correlating the received signals from different look directions mitigates the influence of shared transmitter related phase components despite lack of a cooperative transmitter, and permits tractable inference via interferometric inversion. To this end, we leverage deep architectures for modeling a priori information and for improving sample efficiency of state-of-the-art interferometric inversion methods. Our approach is comprised of an iterative algorithm based on generalizing the power method, and applies denoisers using plug-and-play and regularization by denoising techniques. We evaluate our approach using simulated data for passive synthetic aperture radar by using convolutional neural networks as denoisers, and compare our results with state-of-the-art. The numerical experiment shows that our method can achieve faster reconstruction and superior image quality in sample starved regimes than the state-of-the-art passive interferometric imaging algorithms.