Abstract :
In this paper, taking Shaoxing city as a case study area, the extraction of residential information from TM images is discussed. Firstly, the characteristics of different ground object in this area are discussed, secondly, spectral characteristics of residential area and other land-use types on TM image are analyzed to find the possibility of extracting residential area from the back ground objects according to spectral characteristic. Thirdly, a decision tree model is created on the basis of spectral characteristics analysis, use TM3, TM4 and TM5 to extract residential area, bare land and road, and then according to the characteristic of TM1
