Ship Detection Using PolSAR Images Based on Simulated Annealing by Fuzzy Matching

Abstract

Ship detection using polarimetric synthetic aperture radar (PolSAR) images is a major area of interest within the field of target detection. It is because the polarimetric information in PolSAR images is beneficial to extract features corresponding to different ship structures. Most of the work carried out on target detection is by extracting target features combined with detectors such as constant false alarm rate detector (CFAR) and support vector machine (SVM). However, much of the research up to now has been undertaken by adjusting parameters manually which depends on experience to a large extent resulting in unstable consequence and unintelligent detection. In order to achieve the goal of automatic detection, a novel ship detection method based on simulated annealing by fuzzy matching (SAFM) methods is proposed in this letter, noted SAFM for convenience, which can achieve the automatic adjustment of parameters. In addition, this letter applies SAFM to adjust the number of features and parameters of the detector simultaneously through which self-adaptive feature screening and adjustment of parameters in the detector are realized and data characteristics are considered. The experimental results suggested that the method proposed in this letter can achieve automatic detection and get good results on ships, especially for docked ships.