Combining Three Matched Filtering Methods for Mineral Information Extraction from Hyperspectral Data

摘要：

Hyperspectral remote sensing has significant advantages in extracting mineral information by its unique multi-spectral data and the related abundance images can help understand geology processes. In this paper, three matched filtering methods including Spectral Angle Mapper, Multi Range Spectral Feature Fitting, and Mixture Tuned Matched Filtering, were combined to identify mineral information. This combination was applied to a hyperspectral remote sensing image acquired at Beiya in Yunnan Province, Southwest China. The result is consistent with the geological maps and previous researches. This combination method significantly unproved the result obtained by each method.

关键词： mineral information extraction matched filtering hyperspectral remote sensing.

作者: Wen Xingping Hu Guangdao Yang Xiaofeng

作者单位: Institute of Mathematic Geology and Remote Sensing Geology, China University of Geosciences, Wuhan 430074, China

会议类型: 国际会议

会议名称: The IPACES 6th Annual Meeting(“现代地球科学，交流与合作国际学术研讨会暨第六届IPACES学术年会)

会议地点: 武汉

会议语种:英文

页码: 294-296

在线出版日期: 2007-04-25（万方平台首次上网日期，不代表论文的发表时间）