A Weak Moving Point Target Detection Method Based on High Frame Rate SAR Image Sequences and Machine Learning

With the video synthetic aperture radar (ViSAR) system proposed, it becomes possible to generate synthetic aperture radar (SAR) images with high frame rate. Benefiting from high frame rate, pixel intensity in a SAR image sequence changes approximately continuously, providing a new way to detect targets in time domain. This paper presents a weak moving point target detection method based on high frame rate SAR image sequences and machine learning. In our method, statistical features are extracted from time domain for distinguishing between background and target. At the same time, the detection problem is transformed into a binary classification problem of determining whether the target exists based on machine learning and these statistical features. The experiments are evaluated using simulated SAR data and the results show that the proposed method can be used to detect moving point targets at a low signal to noise ratio (SNR).