Remote sensing image change detection method, device and terminal

Abstract

The invention is applicable to the field of remote sensing technology, and provides a remote sensing image change detection method and device and a terminal, which generate a difference image group set with complementary information after preprocessing two periods of remote sensing images. Fuzzy C-means clustering is used to obtain the fuzzy segmentation matrix and change detection map of each group of difference images. According to the fuzzy segmentation matrix and the change detection map of each group of difference images, the initial change detection results are obtained by decision-levelfusion of the difference image group set based on similarity theory and fuzzy integral theory. The degree of evidence conflict at each pixel of the difference image set is calculated, and the seriousevidence conflict pixels in the initial change detection results are detected and located, and then the serious evidence conflict pixels are reclassified by using the Indicator Kriging theory. Basedon the difference image group set with complementary information and indicator Kriging theory, the reliability of remote sensing change detection and the precision of change detection results are improved. 本发明适用于遥感技术领域，提供了一种遥感影像变化检测方法、装置及终端，通过对两期遥感影像进行预处理后生成信息互补的差分影像组集合；对差分影像组集合进行模糊C均值聚类得到每组差分影像的模糊分割矩阵和变化检测图；根据得到的每组差分影像的模糊分割矩阵和变化检测图，通过相似度理论和模糊积分理论对差分影像组集合进行决策级融合，得到初始的变化检测结果；计算差分影像组集合在每个像元处的证据冲突程度，探测并定位初始变化检测结果中的证据冲突严重像元，并通过指示克里金理论对证据冲突严重像元重新进行分类。基于信息互补的差分影像组集合和指示克里金理论，实现了提高遥感变化检测的可靠性和变化检测结果的精度。