论文部分内容阅读
提出了一种基于DNA计算的高光谱遥感数据光谱匹配分类新方法。该方法利用DNA编码提取各类地物光谱所携带的物理吸收与反射特征信息,将地物光谱特征转换为DNA编码空间特征,通过DNA计算基因操作寻找各类地物最典型的DNA信息链。在此基础上,利用DNA计算原理建立一系列模糊规则,对高光谱数据进行光谱匹配分类。通过与传统的光谱匹配算法(二值编码,光谱角,光谱差分特征编码)的分类结果进行比较,证明该算法分类精度优于传统高光谱数据的光谱匹配分类方法,具有实用价值。
A new method for spectral matching of hyperspectral remote sensing data based on DNA computing is proposed. The method extracts the physical absorption and reflection characteristic information carried by the spectra of all kinds of terrain using DNA coding, transforms the spectral characteristics of the terrain into the DNA coding space characteristics, and searches for the most typical DNA information chain of various terrain through DNA computing genetic manipulation. On this basis, a series of fuzzy rules are established by using the principle of DNA calculation, and the hyperspectral data is classified by spectrum matching. Compared with the traditional spectral matching algorithms (binary coding, spectral angle, spectral difference feature coding) classification results, the proposed algorithm has better classification accuracy than the traditional hyperspectral data spectral matching classification method, and has practical value.