摘要
分别从光谱曲线及光谱特征空间入手,对内蒙古突泉与青海同仁研究区野外实测岩石、土壤和植被等3类典型地物的光谱数据进行了分析,发现研究区无论在光谱曲线空间,还是在光谱特征空间,同类地物的分布形态基本一致,而不同之处是由不同地区的地质地貌、生态环境与气候因素决定的,但不影响其空间分布形态的整体特征。通过分析与实验,发现了几种能够在光谱特征空间对上述3类特征地物进行较好区分的波段组合,可以利用这几种波段组合指导根据遥感图像生成的二维散点图对这3类地物的分类,有助于改进遥感蚀变信息提取方法。
From the point of view of spectral curve and spectral feature space and through the analysis of the spectral data of three main ground objects measured in the field,i.e.,rocks,soil and vegetation,in the two study areas of Tuquan in Inner Mongolia and Tongren in Qinghai,the authors found that the feature distribution forms are basically the same in the two study areas in both spectral curve space and spectral feature space,although there exist a bit difference caused by the geological environment,ecological environment and climate factors in different areas.Through the analysis and experiment,it is found that several new band combinations can better distinguish the three main ground objects in the spectral feature space and can also guide the classification of the three main ground objects based on the scatter plots of the remote sensing image.This research is helpful to improving the method for extraction of alteration information.
出处
《国土资源遥感》
CSCD
北大核心
2012年第4期138-145,共8页
Remote Sensing for Land & Resources
关键词
光谱数据分析
光谱空间结构
二维散点图
统计参数
蚀变信息提取
spectral data analysis
spectrum spatial structure
2D scatter plot
statistical parameter
alteration information extraction