| 主成分分析技术在遥感蚀变信息提取中的应用研究综述 |
| |
| 引用本文： | 吴志春,叶发旺,郭福生,刘文恒,李华亮,杨羿.主成分分析技术在遥感蚀变信息提取中的应用研究综述[J].地球信息科学,2018,20(11):1644-1656. |
| |
| 作者姓名： | 吴志春 叶发旺 郭福生 刘文恒 李华亮 杨羿 |
| |
| 作者单位： | 1. 东华理工大学放射性地质与勘探技术国防重点学科实验室,南昌 3300132. 东华理工大学地球科学学院,南昌 3300133. 东华理工大学江西省数字国土重点实验室,南昌 3300134.核工业北京地质研究院遥感信息与图像分析技术国家级重点实验室,北京 100029 |
| |
| 基金项目： | 国家自然科学基金（41802247、41603031）;江西省教育厅科技项目（GJJ160584）;放射性地质与勘探技术国防重点学科实验室开放基金项目（RGET1305）;江西省数字国土重点实验室开放基金项目（DLLJ201614） |
| |
| 摘 要： | 主成分分析是目前遥感蚀变异常信息提取常用方法之一,该方法具有对影像大气校正质量要求不高、实现简单、提取效果好、效果稳健等优点,广受地质工作者的青睐。根据输入影像的数量及类型、主成分分析的次数等,本文将主成分分析分为标准主成分分析、特征向量主成分分析、定向主成分分析、二次主成分分析、不同影像间的主成分分析等5种类型。其中,特征向量主成分分析又可细分为4个波段特征向量主成分分析和3个波段特征向量主成分分析。在上述分类的基础上,系统介绍了各种主成分分析及蚀变信息主分量的选择,尤其是对特征向量主成分分析的Crosta技术和定向主成分分析的软落叶技术进行了详细阐述。并以TM/ETM+、ASTER影像为例,对部分应用主成分分析提取蚀变异常信息的实例进行了分析,认为：在基岩裸露区,不同主成分分析都可以很好地提取铁化、泥化蚀变信息;在中、低植被覆盖区,采用标准主成分分析、Crosta技术、改进的Crosta技术、软落叶技术、“掩膜/抑制干扰信息+主成分分析”等方法可以有效地提取蚀变异常信息;高植被覆盖区多采用主成分分析生成的蚀变信息主分量进行彩色合成,再通过对彩色影像进行目视解译的方式判断蚀变的类型和范围。其中,“掩膜+Crosta技术”、“掩膜+软落叶技术”、二次主成分分析等方法在高植被覆盖区也可以取得较好的应用效果;对于干扰信息种类众多、岩性复杂的地区,可根据干扰信息、岩性种类划分成若干个小区,再根据每个小区实际情况采用不同的蚀变提取方法,最后将每个小区内提取的蚀变信息进行合并。
|
| 关 键 词： | 主成分分析 标准主成分分析 特征向量主成分分析 定向主成分分析 Crosta技术 软落叶技术 |
| 收稿时间： | 2018-04-18 |
A Review on Application of Techniques of Principle Component Analysis on Extracting Alteration Information of Remote Sensing |
| |
| WU Zhichun,YE Fawang,GUO Fusheng,LIU Wenheng,LI Hualiang,YANG Yi.A Review on Application of Techniques of Principle Component Analysis on Extracting Alteration Information of Remote Sensing[J].Geo-information Science,2018,20(11):1644-1656. |
| |
| Authors: | WU Zhichun YE Fawang GUO Fusheng LIU Wenheng LI Hualiang YANG Yi |
| |
| Abstract: | The principle component analysis (PCA) technique, as one of the common method of extracting alteration information of remote sensing, is characterized by undemanding quality of atmospheric correction images, easily realization, effective, and steadily i.e., and is widely used by geologists. Based on the number and type of the input images and times of the PCA, this paper subdivided the PCA analysis into the standard principle component analysis (SPCA), feature oriented principal components selection (FPCS), directed principal component analysis (DPCA), the secondary principle component analysis and the principle component analysis of different images, of which the FPCS comprise four bands and three bands principle component analysis. Based on the above mentioned, every PCA and selection criteria have been systematically introduced, especially for the Crosta technique of the FPCS and the software defoliant technique of the DPCA. Images of TM/ETM+、ASTER are selected as examples to analyze the part of application techniques of PCA on extracting alteration information of remote sensing. The results indicate that different PCA all are in favor of extracting information of iron and clay alteration. The methods of SPCA, Crosta technique, modified Crosta technique, software defoliant technique and mask or inhibition of interference information+PCA have been effectively applicated in the medium-low vegetated-covered area. In contrast, in the high vegetated-cover area, the principle component of alteration information derived from PCA was adopted to conduct color composite. The resulted color images were then visual interpreted to estimate the type and extent of alteration. Among these techniques, the “Mask and Crosta technique”, the “Mask and software defoliant technique” and the secondary principle component analysis also can achieve good results in the high vegetated-cover area. For areas characterized by numerous kinds of interference information and complex lithology, firstly, it is practicable to divide the area into several sub-areas based on kinds of interference information and lithology; secondly, different methods of extracting alteration information should be proposed according to the features of every sub-areas; lastly, synthesizing alteration information extracted from every sub-areas. |
| |
| Keywords: | Principal Component Analysis (PCA) Standard Principle Component Analysis (SPCA) Feature Oriented Principal Components Selection (FPCS) Directed Principal Component Analysis (DPCA) Crosta technique software defoliant technique |
|
| 点击此处可从《地球信息科学》浏览原始摘要信息 |
| 点击此处可从《地球信息科学》下载免费的PDF全文 |
|
