Ship surveillance using space-borne synthetic aperture radar (SAR), taking advantages of high resolution over wide swaths and\r\nall-weather working capability, has attracted worldwide attention. Recent activity in this field has concentratedmainly on the study\r\nof ship detection, but the classification is largely still open. In this paper, we propose a novel ship classification scheme based on\r\nanalytic hierarchy process (AHP) in order to achieve better performance.The main idea is to apply AHP on both feature selection\r\nand classification decision. On one hand, the AHP based feature selection constructs a selection decision problem based on several\r\nfeature evaluation measures (e.g., discriminability, stability, and information measure) and provides objective criteria to make\r\ncomprehensive decisions for their combinations quantitatively. On the other hand, we take the selected feature sets as the input\r\nof KNN classifiers and fuse the multiple classification results based on AHP, in which the feature sets� confidence is taken into\r\naccount when the AHP based classification decision is made. We analyze the proposed classification scheme and demonstrate its\r\nresults on a ship dataset that comes from TerraSAR-X SAR images.
Loading....