面向地形特征的DEM与影像纹理差异分析  

Research on the Difference between Textures Derived from DEM and Remote-sensing Image for Topographic Analysis

作　　者：刘凯[1,2] 汤国安[1,2] 黄骁力 蒋圣[1,2] 

机构地区：[1]南京师范大学虚拟地理环境教育部重点实验室,南京210023 [2]江苏省地理信息资源开发与利用协同创新中心,南京210023

出　　处：《地球信息科学学报》2016年第3期386-395,共10页Journal of Geo-information Science

基　　金：江苏高校优势学科建设工程资助项目;国家自然科学基金项目(41171320;41271438;41401440)

摘　　要：纹理分析方法在宏观地形特征分析方面具有较大的优势与潜力,但当前缺少对DEM与影像数据纹理特征差异的系统分析研究。本文采用灰度共生矩阵为纹理量化模型,选取了8个不同地貌单元的样本数据,对DEM和遥感影像2类数据的纹理进行了特征值对比分析、纹理特征稳定性分析、纹理特征组间差异性分析。实验结果表明,在所测试的二阶角矩、对比度、方差、熵4个纹理指标中,DEM和影像的对比度特征值间具有显著的相关性;通过不同地貌样区纹理特征值对比分析发现,DEM数据在地形起伏较大区域纹理特征更为明显,遥感影像数据则受地表覆盖物影响较大;从地形特征的稳定性角度分析,DEM数据在丘陵和山地分析有优势,影像数据则在平原和台地分析表现更好;从地形特征差异性角度分析,DEM数据要优于影像数据。进一步采用光照模拟和坡度数据以增加DEM纹理信息,研究结果表明,DEM派生的2类数据在地形量化差异性方面改进明显,并大大优于影像数据。The textural analysis methods have advantage and potential in macro topographic analysis. Currently, based on the texture features of DEM and remote sensing image, some researches are conducted, including quantitative analysis of terrain features, landform classification and the pattern recognition of physiographic units. However, little literatures focus on the difference evaluation of texture features between DEM and image data, which making the theory and methodology scarce for data selection, data fusion and results evolution. In this paper, Gray Level Co- occurrence Matrix（GLCM） model is used for texture analysis in eight sample areas representing different landform types. Second angular moment, contrast, variance and entropy are selected as the quantitative indices. Based on the texture features derived from two different data types, a series of experiments are conducted, including the contrastive analysis of texture features, the stability analysis within same sample area and the divergence analysis among different sample areas. Coefficient of variation is used to evaluate the discrete degree. The results suggest a strong correlation between DEM based contrast and image based contrast. It also proves that the texture features derived from DEM are more evident in high-relief landform, while the image data takes advantage in small-relief area, however, could be affected by the land surface. Considering the stability of topographic analysis, DEM data are more suitable for hill and mountain areas, while the image data achieves better results in the plain area and tableland area. Considering the divergence of topographic analysis, the texture features derived from DEM data vary more obvious among different test areas, with the second angular moment, contrast and entropy getting higher values. These phenomena indicate that the texture features derived from DEM data have stronger discrimination ability. Hillshade data and slope data are employed to enhance the texture information in further analysis, which pr

关 键 词：地形特征 纹理分析 DEM 遥感影像 数字地形分析 

分 类 号：P208[天文地球—地图制图学与地理信息工程]