融合多特征的高分辨率遥感影像变化检测  

High-resolution Remote Sensing Image Change Detection Based on Multiple Feature Fusion

作　　者：葛楚婷 丁海勇 GE Chuting;DING Haiyong(School of Remote Sensing and Geomatics Engineering,Nanjing University of Information Science and Technology,Nanjing 210044,China)

机构地区：[1]南京信息工程大学遥感与测绘工程学院,南京210044

出　　处：《遥感信息》2022年第6期101-107,共7页Remote Sensing Information

基　　金：国家自然科学基金项目(41571350)。

摘　　要：针对单一特征难以反映目标物的全面信息,不能有效地进行变化检测的问题,提出一种顾及光谱、纹理和结构特征的遥感影像变化检测框架。该方法由3部分组成:利用光谱特征及决策融合方法获得目标物的光谱变化信息;通过构建多尺度灰度共生矩阵纹理特征集和方向梯度直方图特征集,获得目标物在纹理特征和几何特征方面的变化信息;对光谱、纹理和结构特征变化结果进行分析,基于逻辑运算进行融合,并结合形态学算子对检测结果进行后处理,获得最终的综合变化图斑。选取3组涉及不同地物变化的高分辨率遥感影像开展变化检测实验,并与其他方法进行对比分析。结果表明,该算法框架可以有效集成多特征的优势,显著提高变化检测过程的适用性和鲁棒性。A single feature is difficult to reflect the comprehensive change information,so it cannot be effectively used for change detection.Therefore,we propose a new change detection framework in which the spectral features,texture features and structural features are integrated to get the change information of objects.The framework has three components:the spectral features are extracted,and majority voting decision fusion methods are applied to get the spectral change information;the texture feature set and structure feature set are obtained respectively by multi-scale grey level co-occurrence matrix and histogram of oriented gradient,which are used to obtain the change information of target objects in terms of texture feature and geometric feature;the spectral,texture,and structural features are analyzed and logically fused to get the initial results.Meanwhile,the mathematical morphology operation is performed as a post-processing on the initial results to get the final comprehensive change pattern.To evaluate the performance of the proposed method,three sets of high-resolution remote sensing images involving different ground changes are selected to carry out change detection experiments,and the comparative analysis with other methods is made.The experimental results show that the proposed method can effectively integrate the advantages of multiple features and significantly improve the applicability and robustness of the change detection.

关 键 词：变化检测 多特征 HOG 形态学算子 决策融合 

分 类 号：P237[天文地球—摄影测量与遥感]