居民地信息遥感提取方法比较研究  

Methodology of Retrieving Residential Area from Remotely Sensed Image

作　　者：薛辉[1] 倪绍祥[1] 

机构地区：[1]南京师范大学地理科学学院,南京210097

出　　处：《水土保持研究》2006年第5期319-321,共3页Research of Soil and Water Conservation

基　　金：国家自然科学基金(40371081)

摘　　要：准确、客观地提取居民地信息,对于城镇规划和耕地保护等具有十分重要的意义。以河北省青县地区为研究区,基于陆地卫星TM图像,分别利用光谱阈值法、NDBI指数法、监督分类法及非监督分类法提取出了研究区的居民地信息。然后,利用目视解译、屏幕数字化勾绘出的居民地面积,对以上4种方法在居民地信息提取上的效果进行了比较,发现光谱阈值法是提取研究区居民地信息的最好方法。It is extremely important for urban or township planning and farmland protection and so on to extract accurately and objectively the data of residential regions, Taking Qingxian County in Hebei Province of China as the study area,the methodology of retrieving the data of residential regions from Landsat TM image data is dealt with. Four kinds of methods are tested in this study, namely, the spectral threshold, the NDBI index, supervised image classification and non-supervised image classification. Based on the total area of the residential regions which is obtained by visual interpretation of the false-color composite of the TM image as well as by screen digitalizing and delineating the boundaries of the residential rogions, these methods are compared in terms of the precision in retrieval of the residential regions. The results indicate that among them the method of spectral threshold is the best one.

关 键 词：居民地 遥感 信息提取 光谱 

分 类 号：TP79[自动化与计算机技术—检测技术与自动化装置]