Anomaly detection in multi-polarimetric radar images

An anomaly detection algorithm for SAR (synthetic aperture radar) images, making use of multi-polarized data, is developed. The processing contains several stages including: calibration of the images, information parameters extraction and speckle filtering, suspect pixels detection and morphology operator application. The developed algorithm is independent of the anomaly radar cross section; it depends only on the physical structure. The proposed processing is non-iterative, adaptive and automatic. Performance evaluation shows improved performance of the algorithm over the common alternatives.