Distributed Radar Imaging Based on Accelerated ADMM

The ability of widely distributed radar systems to capture diverse spatial
scattering properties substantially improves radar imaging performance.
Traditional imaging methods leverage regularized optimization techniques to
reconstruct sparse images from local sensors and later combine them to create a
global image. Alternatively, we proposed in an earlier work a joint
reconstruction technique based on two problem formulations according to the
optimization framework of the Alternating Direction Method of Multipliers
(ADMM). The joint reconstruction of the global image offers faster convergence,
flexible implementation, and a general distributed reconstruction framework.
However, despite its benefits, ADMM framework still exhibits a slow convergence
rate, making its employment in some contexts impractical. In this paper, we
introduce a heuristic method to accelerate the convergence of the previously
proposed ADMM formulations based on the gradual elimination of the already
converged pixels in accordance with a predetermined criterion. In addition to
reducing running time, the accelerated implementation offers reduced
computational complexity and lower communication cost between the sensors
during iterative updates.