Achieving SAR Target Detection via a Two-Stage Superpixel-Based CFAR Detector

Aiming at solving the problem that the traditional pixel-level constant false alarm rate (CFAR) target detection algorithms cannot keep the target boundary well and the time consumption is large, a two-stage superpixel-based CFAR detection algorithm is proposed to overcome the above shortcomings. The G0 distribution which can model uniform, uneven and extremely uneven scenes accurately is adopted to realize the global CFAR detection, and the Gamma distribution which can model uniform superpixels is conducted in the local CFAR detection stage. Experiments on real synthetic aperture radar (SAR) images show the effectiveness of the proposed algorithm in reducing false alarms and detecting ship targets.