高光谱数据的光谱信息特点及面向对象的特征参数选择——以北京顺义区为例

波段宽度为纳米级的高光谱数据,具有几十乃至几百个光谱通道,它们各有不同的特点。如何根据具体的应用目的,在这众多的波段中选择出最佳波段和特征参数,对于有效地进行高光谱数据的处理、分析及信息提取至关重要。以北京顺义区高光谱数据为例,首先分析了通道间的相关性,根据通道的相关性大小和分组块状结构特点,将其分为若干组;然后全面分析了高光谱数据的光谱信息特征,在综合考虑各波段的信息含量、波段间的相关性以及地物光谱的吸收特性和可分性等因素
的基础上,提出了面向对象的分层多次选择高光谱数据最佳波段和提取特征参数的基本思路和方法;最后用其它地区的成像光谱数据对此方法进行了验证。

Spectral Characteristics and Feature Selection of Hyperspectral Remote Sensing Data--Taking Shunyi Region of Beijing As a Study Area

Hyperspectral remote sensing data with waveband width of nm level has tens or even several hundreds channels and contains abundant spectral information. Different channels have their own properties and show the spectral characteristics of various objects. Optimum bands selection and feature extraction from the varieties of channels are very important for the effective analysis and information extraction of hyperspectral data. This paper, taking Shunyi region of Beijing as a study area, comprehensively analyzed the spectral feature of hyperspectral data. On the basis of analyzing the information content of bands, correlation among different channels, band separability and spectral absorption characteristics of objects, a fundamental method of optimum band selection and feature extraction from hyperspectral remote sensing data were proposed.Three factors, the information amount of bands, correlation between bands and separability of objects in bands, are considered in selecting bands. The major steps of band selection are:1. Compute the correlation matrix of hyperspectral data, analyze the correlation between bands, and then according to the correlation partition the complete data set into three band groups. The bands in same group are highly correlated and the different groups are relatively independent.2. Considering that hyperspectral data has many channels which appear in groups, define the band index aspi=σiRw+Ra, in whichσiis standard variance of ith band,Rwis absolute value of average correlation coefficient between ith band and other bands in same group,Rais the sum of absolute value of correlation coefficient between ith band and all other bands in different groups.It is evident that with higherσiand lowerRwandRa, thePiis higher and the corresponding bandiis
better in whole. ThusPiis an important parameter in selecting band.3. Select several typical spectral classes as training samples, which are important objects to be classified in study area and have similar spectral feature, compute the separability of classes in different bands by Bhattacharyya distance.4. On the basis of band comprehensive evaluation by band index and separability, select optimum bands bearing abundant information and high separability.The method derived from hyperspectral data of Shunyi region was also applied to different types of hyperspectral data of other regions and similar conclusion was got. It shows that the proposed method in this
paper is of general significance.