Land Use Classification Based on Remote Sensing Images and Weighted Clustering Method

Quite a few methods have been applied in the remote sensing images processing. Among which the fuzzy clustering method is effective to land use classification. This paper analyzes some of the shortages in basic principles of the fuzzy clustering methods caused by the massive redundant information in multispectral images, and supplies an updated weighted clustering method, which considers the weights of different spectrums according to their effective information capacities. In examination we take the TM images of pan of Beijing city as an example to carry out land use classification. The results of ISODATA clustering method, common fuzzy K-mean clustering method and weighted clustering method are compared.
Kun Wang
State Key Laboratory of Geological Processes and Mineral Resources, China University of Geostiences, Wuhan 430074, Hubei, China
国际会议
The 12th Conference of the International Association for Mathematical Geology(第12届国际数学地质大会)
北京
英文
735-738
2007-08-26(万方平台首次上网日期,不代表论文的发表时间)