Target detection based on granularity computing of quotient space theory using SAR image

Target detection is a hot topic and key technique of SAR image interpretation. There are many detection methods, such as CFAR detector and Extended Fractal (EF) feature detector. In order to overcome their shortcomings and combine their merits at the same time, the combination of some different detection methods need be implemented. Granularity computing is just an approach that solves the problem at different granularity space due to different principles. Therefore, SAR image target detection based on granularity synthetic algorithm of quotient space theory is proposed in this paper. Firstly, CFAR detector and EF feature detection method are performed to generate different detection results as coarse granularity spaces. Then combine the different quotient spaces and construct the fine granularity space by using granularity synthesis algorithm. Finally, obtain the final target detection result. The experimental result of RADARSAT-I C band SAR image proves that the proposed algorithm is effective.