基于叶片高光谱特性分析的树种识别

高光谱遥感技术的出现将为解决森林树种的精细识别难题提供有效的途径。利用高光谱遥感技术进行树种鉴别时,光谱特征的选择及提取是个非常重要的过程。与多光谱数据相比,高光谱数据具有波段多、数据量大、冗余度大等特点。该文利用光谱微分法对原始光谱数据进行处理,分析不同树种原始光谱、光谱一阶微分和光谱二阶微分曲线图,从中选择差异较大的波段用于鉴别不同树种。最后利用欧氏距离对所选择的波段进行检验识别不同树种的效果,检验的结果显示选择的波段能有效地区分不同树种。区分不同树种的有效波段大都位于近红外波段, 并且差异最大的波段也是近红外波段,其分别为1 657～1 666和1 868～1 877 nm。

Tree Species Discrimination Based on Leaf-Level Hyperspectral Characteristic Analysis

The emergence of hyperspectral remote sensing technology will provide chance for solving problems of identifying forest tree species precisely. For discrimination of tree species with hyperspectral remote sensing technology, extraction and selection of the spectral characteristics is a very important process. Compared with multispectral data, hyperspectral data have the characteristics of more bands, larger amount of data and larger redundancy degree. The method of derivative reflectance was used to deal with the original spectral data, analyze and compare curves of the original spectrum, the first derivative reflectance and second derivative reflectance of the different tree species, and the bands with bigger difference were selected to identify the different tree species. Then the Euclidean distance method was used to test the selective bands identifying different tree species, and the results showed that the selective bands could identify different tree species effectively. The bands for identifying different tree species were most near-infrared bands, and the bands with maximum difference derived from the three methods are 1 657-1 666, 1 868-1 877 and 1 868-1 877 nm respectively.