A Regional SAR Dark Spot Detection Method Based on GMTRJ Algorithm

Abstract

Generalized Multiple-Try Reversible Jump (GMTRJ) is a recent algorithm which makes it possible to improve the accurate tuning of the jump proposals in the Reversible Jump Markov Chain Monte Carlo algorithm. In this paper, the GMTRJ algorithm is combined the regular tessellation and the Bayesian paradigm to propose a regional synthetic aperture radar (SAR) dark spot detection method. First, the regular tessellation and the Bayesian paradigm are applied to build a regional SAR dark spot detection model; then the GMTRJ algorithm is designed to simulate from the detection model to obtain the optimal regional detection result. As the blocks may cross the boundaries between dark spot and ocean background regions, a refined operation is designed to improve the detection accuracy of boundaries. We present test results demonstrating the feasibility and advantages of the GMTRJ algorithm on simulating from the detection model, and illustrating the feasibility of the refined SAR dark spot detection operation on improving the detection accuracy of boundaries.