基于KPCA和Kmeans++的遥感影像变化检测研究  

Research on remote sensing image change detection based on KPCA and Kmeans++

作　　者：冯永亮[1] 申少格 FENG Yongliang;SHEN Shaoge(School of Information Engineering,Xi’an University,Xi’an 710065,China)

机构地区：[1]西安文理学院信息工程学院,陕西西安710065

出　　处：《电子设计工程》2021年第21期57-60,共4页Electronic Design Engineering

基　　金：陕西省自然科学基金(2018JM6100);西安市科技计划项目(2019218014GXRC016CG017-GXYD16.1);西安文理学院2020年大学生创新创业训练计划项目(S202011080020)。

摘　　要：针对多光谱遥感影像在低维空间难以区分这一问题,提出一种基于KPCA和Kmeans++的变化检测方法。对不同时相的遥感影像进行大气校正、几何校正和图像配准,求出影像差值,利用KPCA方法将低维空间数据映射为高维特征向量,获得主成分信息,形成差异图像,再通过Kmeans++聚类,生成结果图像。实验表明,新方法检测效果良好,精度较高。Aiming at the problem that multispectral remote sensing images are difficult to distinguish in low⁃dimensional space,a change detection method is proposed based on KPCA and Kmeans++.Radiation correction,geometric correction and image registration are performed on remote sensing images of different time phases,and the image difference is calculated.The KPCA method is used to map low⁃dimensional spatial data to high⁃dimensional feature vectors to obtain principal component information and form difference images.Through Kmeans++clustering,the resulting image is generated.Experiments show that the new method has a good detection effect and high accuracy.

关 键 词：KPCA Kmeans 遥感影像 变化检测 

分 类 号：TN98[电子电信—信息与通信工程]