Aircraft Detection Based on Eigen Decomposition and Scattering Similarity for PolSAR Image

Aiming at the problem of aircraft detection in complex scene, a novel aircraft detection algorithm based on eigen-decomposition and scattering similarity for PolSAR image is proposed. Firstly, Image denoising is performed by using typical scattering difference index (TSDI) filter. Then, region of interest (ROI) containing airport runway and apron is extracted with the characteristics of scattering power, where suspected aircraft targets may exist. Finally, detection statistics are constructed with eigenvalue and scattering similarity parameters to determine true aircraft from suspected targets. Experimental results with real PolSAR data acquired by USA NASA UAVSAR system show that the proposed method can detect aircrafts in complex scene with low resolution effectively.