A Two-Step Ship Target Detection Method in High-Resolution Sar Image Based on Coarse-to-Fine Mechanism

摘要

With the development of synthetic aperture radar technology, the resolution of SAR images becomes higher accompanied by more complex clutter characteristics, which poses challenges to the detection of ship targets. To achieve efficient ship detection in high-resolution synthetic aperture radar images, a two-step ship target detection method based on a coarse-to-fine mechanism is proposed in this paper. First, the SAR image is filtered through the gravitational field method to enhance ship targets. Then the candidate targets are obtained by the improved mean dichotomy method. Finally, the kernel density estimation method is utilized to complete precise detection results. Compared with the conventional ship target detection method, the proposed method is fast and accurate. Experimental results demonstrate the effectiveness of the proposed method.