Method and device for detecting change of SAR images

Abstract

The invention is applicable to the field of remote sensing and provides a method and device for detecting the change of SAR images. The method includes the steps of preprocessing SAR images of two periods; generating differential images according to the preprocessed SAR images of two periods; generating a fuzzy membership function Uu of an unchanged class [omega]u and a fuzzy membership function Uc of a changing class [omega]c through the differential images by using a fuzzy local information C-means clustering algorithm with adaptive distance; dividing the unchanged class [omega]u into the interior and fuzzy boundaries according to the fuzzy membership function Uu of the unchanged class [omega]u and dividing the changed classes [omega]c into the interior and fuzzy boundaries according to the fuzzy membership function Uc of the changing class [omega]c; and de-fuzzifying pixels in the interiors and fuzzy boundaries of the unchanged class [omega]u and the changing class [omega]c respectively. According to the invention, the accuracy of the fuzzy membership function in the SAR image change detection and the classification accuracy of the fuzzy boundary pixels are improved and thus a relatively good SAR image change detection result can be obtained. 本发明适用于遥感领域，提供了一种SAR影像变化检测方法及装置，所述方法包括：对两期SAR影像进行预处理；根据预处理后的两期SAR影像生成差分影像；采用自适应距离的模糊局部信息C均值聚类算法，通过所述差分影像生成未变化类ωu的模糊隶属度函数Uu和变化类ωc的模糊隶属度函数Uc；采用模糊拓扑理论，根据所述未变化类ωu的模糊隶属度函数Uu将所述未变化类ωu划分为内部和模糊边界，以及根据所述变化类ωc的模糊隶属度函数Uc将所述变化类ωc划分为内部和模糊边界；分别对所述未变化类ωu和变化类ωc的内部和模糊边界中的像素进行去模糊化。本发明提高了SAR影像变化检测中模糊隶属度函数的准确性、模糊边界像素的分类精度，从而能够获得较优的SAR影像变化检测结果。