论文部分内容阅读
变化检测是资源和环境遥感应用的一个重要内容。在变化矢量分析法的基础上,本文提出采用变化矢量-主成分分析法提取研究区变化信息,首先,对不同时相的遥感影像进行差值运算得到差值影像,再对其进行主成分变换并选取主分量,最后,使用多尺度分割获取影像对象。在影像分割的基础上,采用变化矢量-主成分分析方法构建自动检测规则提取变化信息,并作精度评价。研究表明:基于对象的变化矢量-主成分分析方法不仅可克服传统的基于像元式方法难以利用空间信息的缺陷,有效避免了“椒盐”噪声,而且可将多波段差值信息经主成分变换后集中在几个累计贡献率较高的主成分分量上;同时,结合了变化矢量法与主成分分析法的优点,与单独使用变化矢量分析法相比提取精度明显提高。
Change detection is an important part of remote sensing applications of resources and environment. Based on the change vector analysis method, this paper proposes to extract the change information of the study area by using the method of change vector and principal component analysis. First, the difference image is obtained by performing the difference operation on the remote sensing images of different phases, and then the principal component transformation And select the main component, and finally, use multi-scale segmentation to obtain the image object. On the basis of image segmentation, the change vector - principal component analysis method is used to construct automatic detection rules to extract the change information and make the accuracy evaluation. The research shows that the object-based VECTVM-PCA can not only overcome the shortcomings of the traditional pixel-based method, which is difficult to use spatial information, but also effectively avoid the “salt and pepper” noise. Moreover, In the meantime, combining the advantages of change vector method and principal component analysis, the accuracy of extraction is obviously improved compared with vector-only analysis method alone.