An Adaptive Hierarchical Detection Method for Ship Targets in High-Resolution SAR Images

An Adaptive Hierarchical Detection Method for Ship Targets in High-Resolution SAR Images

Yi Liang, Kun Sun, Yugui Zeng, Guo-Fei Li, Mengdao Xing

With the improvement of image resolution in synthetic aperture radars (SARs), sea clutter characteristics become more complex, which poses new challenges to traditional ship target detection missions. In this paper, to detect ship targets quickly and efficiently in a complex background, we propose an adaptive hierarchical detection method based on a coarse-to-fine mechanism. This method constructs a new visual attention mechanism to strengthen ship targets and obtain the candidate targets adaptively by the means dichotomy method. On this basis, the precise detection results of the targets are obtained using the speed block kernel density estimation method, which maintains constant false alarm characteristics. Compared with existing methods, the adaptive hierarchical detection method has simple, fast, and accurate characteristics. Experiments based on GF-III satellite and airborne SAR datasets are presented to demonstrate the effectiveness of the proposed method.

2020

ship detection, saliency method, superpixel segmentation, kernel density estimation, synthetic aperture radar

DOI: 10.3390/rs12020303

Remote Sensing

MDPI AG

Science

EN