一种基于变化检测技术的SAR图像舰船目标鉴别方法

该文引入变化检测思想,利用SAR图像中海杂波和目标之间的灰度差异,通过对潜在舰船目标切片的目标像素和背景像素进行分离,计算目标像素聚集度(TPAM)特征,实现对高亮像素在图像切片中聚集程度的定量评估,从而鉴别目标切片中是否包含有舰船目标,有效去除杂波虚警.首先,基于感兴趣区域(ROI)切片中心为目标像素及四周为海杂波的合理假设,构建似然比变化检测量获取差异图像;然后,利用KSW熵阈值选择方法实现差异图像中目标像素和海杂波像素的自动分离,生成二值图像;最后,利用切片中心像素为种子点,对二值图像进行区域生长,计算目标像素聚集度特征,并判断目标切片是否包含舰船目标.基于RADARSAT-1 SAR实测数据的实验结果表明,该文方法得到的目标像素聚集度特征计算简单、稳健性好、可区分度高,具有良好的鉴别性能,能够去除大部分海杂波干扰产生的虚警,有效地降低目标检测虚警率.

A Ship Target Discrimination Method Based on Change Detection in SAR Imagery

In order to reserve ship targets and reduce sea clutters as the false alarms from the SAR Regions Of Interest (ROI) chips, a ship discrimination feature named Target Pixel Aggregative Measure (TPAM) is proposed in this paper. Benefited from the technology of change detection, TPAM using the gray difference in SAR imagery to separate the target pixels and background pixels. Firstly, based on the assumption that the central pixels of a ROI belong to target pixels while the surrounding pixels fall into sea clutters, a change detection measure based on the likelihood ratio is used to generate the residual data. Then the target pixels and background pixels are automatically separated and produce a binary image by the KSW entropy method. Finally, the center of the binary image is used as a seed to implement region growing and TPAM can be obtained to discriminate targets and clutters. Experimental results using RADARSAT-1 SAR data show that the propose discrimination feature is not only simple and robust, but also has a strong differentiate ability, which can eliminate most of false alarms effectively.