Multichannel SAR Moving Target Detection via RPCA-Net

Ground moving target indication (GMTI), as a challenging task for synthetic aperture radar (SAR) systems, keeps drawing considerable attention. Robust principal component analysis (RPCA) aiming at separating low-rank and sparse components has been successfully employed in SAR systems GMTI recently. However, its practical application is limited by the heavy computational burden well requirement of manual parameter modification. To cope with this problem, fast free presetting parameters RPCA network (RPCA-Net) proposed SAR-GMTI under strong clutter background. In method, novel model first introduced, where not only terms but also errors are taken into account. Moreover, factorization plus scaled gradient descent (ScaledGD) to acquire background rather than singular value decomposition (SVD). Then, we parameterize our unfold it feedforward neural (FNN) iterative through backpropagation. Compared methods based on traditional models, RPCA-Net can provide higher detection ability faster convergence without empirically. Experiments two groups measured data collected airborne validate superior performance RPCA-Net.