基于PCA信息熵特征融合的遥感影像变化检测  

Remote sensing images change detection based on PCA information entropy feature fusion

作　　者：火久元[1,2,3] 刘梦 HUO Jiuyuan;LIU Meng(School of Electronic and Information Engineering,Lanzhou Jiaotong University,Lanzhou 730070,China;Lanzhou Ruizhiyuan Information Technology Co.,Ltd.,Lanzhou 730070,China;National Cryosphere Desert Data Center,Lanzhou 730070,China)

机构地区：[1]兰州交通大学电子与信息工程学院,甘肃兰州730070 [2]兰州瑞智元信息技术有限责任公司,甘肃兰州730070 [3]国家冰川冻土沙漠科学数据中心,甘肃兰州730070

出　　处：《Journal of Measurement Science and Instrumentation》2023年第4期398-412,共15页测试科学与仪器（英文版）

基　　金：National Natural Science Foundation of China(No.61862038);Gansu Province Science and Technology Program(No.20JR10RA213);Gansu Province Science and Technology Program-Innovation Fund for Small and Medium-sized Enterprises(No.21CX6JA150);Foundation of a Hundred Youth Talents Training Program of Lanzhou Jiaotong University。

摘　　要：为提高遥感影像变化检测的准确率,本研究结合遥感影像中丰富的纹理信息与邻域信息,引入信息论中信息熵的概念,从特征融合的角度提出了一种基于主成分分析(PCA)信息熵融合纹理特征与邻域特征的遥感影像变化检测方法。首先,通过灰度共生矩阵提取遥感影像的纹理特征,邻域对数比算子提取遥感影像的邻域特征,然后,利用PCA将纹理特征与邻域特征进行特征融合获得主特征信息。其次,计算每个主特征的信息熵,以熵权法为各个主特征分别赋予权重,获得融合后的差异图。最后,利用模糊C均值(FCM)聚类将融合差异图划分为两类,得到变化检测结果。实验结果表明,该方法能够充分利用纹理特征与邻域特征,减小斑点噪声带来的影响,显著提高遥感影像变化检测的精度。In order to make full use of texture information and neighborhood information provided by remote sensing images to improve the accuracy of change detection,a change detection method of remote sensing images is proposed based on principal component analysis(PCA)information entropy fusion of texture and neighborhood features from the perspective of feature fusion.Firstly,texture features of remote sensing images are extracted by gray-level co-occurrence matrix(GLCM),and neighborhood features are extracted by logarithmic ratio of neighborhood.Then,the texture features and neighborhood features are fused by PCA method to obtain principal feature information.Secondly,the information entropy of each principal feature is calculated,and the entropy weight method is used to assign weight to each principal feature to obtain the fusion difference image.Finally,fuzzy c-means(FCM)clustering algorithm is used to divide the fusion difference image into two categories to obtain the change detection results.Experimental results show that the proposed method can make full use of texture features and neighborhood features,reduce the influence brought by speckle noises,and significantly improve the accuracy of change detection of remote sensing image.

关 键 词：PCA信息熵 遥感影像(GLCM) 灰度共生矩阵 纹理特征 邻域特征 

分 类 号：TP751[自动化与计算机技术—检测技术与自动化装置]