方差齐性检验与模糊评价的遥感影像变化检测  

Change detection of remote sensing images based on Levene-test and fuzzy evaluation

作　　者：柴文慧[1,2] 王光辉[1,2] 王华斌[2] 杨化超[1] 

机构地区：[1]中国矿业大学环境与测绘学院,江苏徐州221116 [2]国家测绘地理信息局卫星测绘应用中心,北京100830

出　　处：《测绘科学》2017年第4期80-85,128,共7页Science of Surveying and Mapping

基　　金：高分辨率对地观测系统重大专项(AH1601);测绘地理信息公益性行业科研专项(201412007;201512027)

摘　　要：针对高分辨率遥感影像地物空间结构复杂、光谱纹理信息丰富的特点,该文提出一种基于Levene检验及模糊评价的遥感影像变化检测方法。首先,对预处理后的两期影像叠置分割得到图斑对象,提取其光谱、纹理等特征;其次,利用改进的Levene检验法统计各图斑变化信息得到候选变化图斑,经IHS变换获取影像色调信息,结合纹理特征进行变化向量分析;最后,通过迭代的方式确定阈值并计算候选图斑的变化隶属度,确定最终变化区域。选取江苏省某地区ZY-3高分辨率遥感影像进行实验,结果表明:改进的Levene检验法很大程度地减少了后续的计算量,提高了变化检测精度,对于相对辐射差异较大的非变化图斑具有良好的容错性;采用色调-纹理特征及模糊评价法可以有效地降低漏检及虚检率,提高变化检测精度。High-resolution remote sensing images possess complex spatial structure and rich texture information. In this paper, a new method of change detection based on Levene-test and fuzzy evaluation was proposed. First, map-spots were obtained by segmenting two overlapping images which had been pretreated, and features such as spectrum and texture were extracted. Then, changed information of all map-spots which had been treated by the Levene-test were counted to obtain the candidate changed re- gions, and hue information（H component）was extracted through the IHS transform and conducted change vector analysis combined with the texture information. Eventually, the threshold was confirmed by an it eration method, the subject degrees of candidate changed regions were calculated, and final change re- gions were determined. Experimental results on multi-temporal ZY-3 high-resolution images of one area in Jiangsu province showed that through extracting map-spots of larger difference as the candidate changed regions, Levene-test could decrease the computing load and improve the precision of change detection, which showed better fault-tolerant capacity for those unchanged regions which are of relatively large differ- ences; the combination of hue-texture features and fuzzy evaluation method could effectively decrease o- missions and deficiencies and improve the precision of change detection.

关 键 词：高分辨率影像 变化检测 Levene检验 色调-纹理特征 模糊评价 

分 类 号：P208[天文地球—地图制图学与地理信息工程]