摘要
高光谱数据对地物具有更高的光谱分辨率,但是由于高光谱数据巨大的数据量以及相邻波段之间的强相关性,导致了对这种数据的许多分类方法达不到应有的效果,从而在某种程度上制约了其广泛的应用。研究表明,特征提取的理论与方法对高光谱信息的优化处理是十分有效的。实验结果表明,在一定的分类精度范围内,减低维数而不丢失信息,可以提高分类器的效能,实现高维遥感数据的优化处理和高效利用。
Hyperspectral data have a high spectral resolution for the objects of the earth. However, many analysis approaches of hyperspectral data do not provide a promising result because of its great data volume and strong correlation between its neighboring bands. Consequently, it restricts the efficiency and broad application of high resolution data. The research indicates that feature extraction is the highly effective theory and method to optimize hyperspectral data and information. The result of experiment shows that with a given precision of classification, the reduction in dimensionality without loss of information improves the classifier performance, and helps to achieve the aims of optimal process and effective utilization of hyperspectral remote sensing data.
出处
《水土保持通报》
CSCD
北大核心
2006年第6期89-91,共3页
Bulletin of Soil and Water Conservation
基金
西北大学2005校内基金
科研启动基金
基础测绘科技项目(146014020201-05)
关键词
特征提取
数据降维
高光谱数据
影像分类
feature extraction
reduction of data dimensionality
hyperspectral data
image classification
