半监督离散势理论在遥感影像变化检测中的应用  

Application of semi-supervised discrete potential theory in remote sensing image change detection

作　　者：谢福鼎[1] 赫佳妮 郑宏亮[2] XIE Fuding;HE Jiani;ZHENG Hongliang(College of Urban and Environment,Liaoning Normal University,Dalian 116029,China;College of Computer science,Liaoning Normal University,Dalian 116081,China)

机构地区：[1]辽宁师范大学城市与环境学院,辽宁大连116029 [2]辽宁师范大学计算机与信息技术学院,辽宁大连116081

出　　处：《测绘通报》2019年第8期54-58,共5页Bulletin of Surveying and Mapping

基　　金：国家自然科学基金(41771178; 61772252)

摘　　要：随着遥感技术的发展,遥感影像变化检测作为一种有效的技术手段,在环境监测、灾害救援等领域发挥了重要作用。然而地物复杂、标记困难等问题导致有效的变化检测存在一定的困难。本文提出了一种基于半监督离散势理论的遥感影像变化检测方法。该方法首先采用一种新的标记样本点的方法得到训练集,然后利用KNN方法构造复杂网络,最后对复杂网络中经典Wu-Huberman算法进行改进并划分网络。所得到的两个社团结构恰好对应了变化部分和不变部分。试验结果表明,基于半监督离散势理论的变化检测方法具有良好的变化检测性能。With the development of remote sensing technology,change detection for remote sensing image provides an effective method in environmental monitoring,disaster relief and many other fields.However,it is still a challenging problem to develop more effective change detection methods due to the complexity of ground-truth and the difficulty of labeling the samples and so on.This paper proposes a remote sensing image change detection method based on semi-supervised discrete potential theory.The suggested method first uses a new method to label the samples to get the training set,then constructs complex network by KNN approach.Finally,it improves the classical Wu-Huberman algorithm in complex network and divides the network.As a result,the obtained two community structures exactly correspond to the change part and the invariant part.Experimental results show that the change detection method based on semi-supervised discrete potential theory has perfect change detection performance.

关 键 词：遥感图像 变化检测 半监督分类 离散势理论 Wu-Huberman算法 

分 类 号：P237[天文地球—摄影测量与遥感]