Change detection method integrating gray value, spatial information and category knowledge

Abstract

The invention is applicable to the technical field of remote sensing, and provides an unsupervised remote sensing image change detection method, which comprises the following steps: acquiring two stages of remote sensing images, and generating differential images of the two stages of remote sensing images; identifying, by a threshold technology, a pixel region in the differential image that is almost determinable to change; using an S-type function to define the supervised membership degree that the identified almost determinable pixels belong to a change class and an invariable class; calculating a fuzzy membership function of the differential image through a step-by-step iteration process according to the gray value, the spatial information and the supervised membership of the pixel of the differential image; and carrying out defuzzification on the fuzzy membership function to obtain a change detection result of the two stages of remote sensing images. According to the method, the gray value and the spatial information of the differential image and the category knowledge of the pixels of the area which can be determined nearly are utilized synergistically, so that the reliabilityof remote sensing change detection and the precision of a detection result are improved. 本发明适用于遥感技术领域，提供了一种非监督的遥感影像变化检测方法，所述方法包括：获取两期遥感影像，生成两期所述遥感影像的差分影像；通过阈值技术识别所述差分影像中几乎可确定是否发生变化的像元区域；利用S‑型函数定义所识别的几乎可确定像元属于变化类和未变化类的监督隶属度；根据所述差分影像像元的灰度值、空间信息和所述监督隶属度，通过逐步迭代过程计算所述差分影像的模糊隶属度函数；对所述模糊隶属度函数进行去模糊化，得到两期所述遥感影像的变化检测结果。本发明协同利用差分影像的灰度值、空间信息和几乎可确定区域的像元的类别知识，提高了遥感变化检测的可靠性和检测结果的精度。