Geometric Feature Extraction of Ship Target Based on Multi-Resolution Sar Images

As one of the key performance indicators of SAR sensors, resolution, which is determined by the SAR signal bandwidth and plays a very important role in the interpretation of SAR images. The transformed images of high-resolution SAR images at different resolutions contain different layers of information, which can provide complementary resolvability for ship target extraction. In this paper, experiments and analyses are conducted on the effects of multi-resolution SAR images on the extraction accuracy of four parameters: length, width, principal axis angle and geometric center of ship targets. It is concluded that there is an influence on the geometric feature parameters of the ship targets of different resolution SAR images, and for a certain type of typical targets, there exists a critical resolution, which makes the extraction of the relevant parameters with the highest accuracy and the most stable performance.