Crashed plane detection based on the fusion of CFAR detection and polarimetric decomposition

Aiming at the problem of high false alarm rate and missing rate with single detection method, an improved target detection algorithm for crashed plane detection is proposed in this paper. The method firstly detects the possible existence of the crashed plane with Yamaguchi decomposition and Constant False Alarm Rate (CFAR). Then, the detection results of the two methods are processed by pre-determination, and the final result is achieved by fusion and complementary detection. Simulation experimental results with real polarimetric data from NASA/JPL UAVSAR system demonstrate that the proposed method decreases the false alarm rate and missing rate effectively.