基于表征转换机的SAR图像目标分割方法

摘要

针对SAR(Synthetic Aperture Radar)图像中的目标分割问题，由于目标与杂波空间模式(像素强度和分布)不同，通过分析图像空间模式的方式可达到分辨目标和杂波并分割目标的目的。该文基于表征转换机理论提出一种有效的SAR图像目标分割方法，该算法分析SAR图像中的空间模式，计算其与参考杂波图像的相似程度，最后将与参考杂波相似程度较高的部分消除以达到分割目标的目的，并在衡量相似度部分使用基于累积直方图的自动阈值选取办法。仿真和实测数据的实验验证了此算法的有效性。%Differences between the spatial pattern (pixel intensity and distribution) of targets and clutter allow target segmentation to be achieved by analyzing spatial patterns in Synthetic Aperture Radar (SAR) images. This paper thus proposes a target segmentation method for SAR images based on the appearance conversion machine theory. The proposed method analyses the spatial patterns in SAR images and calculates the degree of similarity between the SAR image and the reference clutter images. Subsequently, regions that show high similarity to reference clutter images are erased so that segmentation can be achieved. To evaluate the degree of similarity, we also use an automatic threshold selection method based on the cumulative histogram of the similarity imge. Experimental results using simulation and real data verify the effectiveness of the proposed method.