欢迎访问林业资源管理

FOREST RESOURCES WANAGEMENT ›› 2010, Vol. 0 ›› Issue (6): 90-96.

Previous Articles     Next Articles

Study on Remote Sensing Classification of Land Use in the Nature Reserve of the Three Rivers Source Region

ZOU Wentao, ZHANG Huaiqing, JU Hongbo, LIU Hua   

  1. Research Institute of Forest Resource Information Techniques, CAF, Beijing 100091, China
  • Received:2010-09-26 Revised:2010-11-19 Published:2020-12-14

Abstract: This paper took the Suojiaqumahe Nature Reserve, which is located in the source regions of the three rivers (Yangtze River,Yellow River and Lancang River), as the study site. Verification was made on the efficiency of decision tree based on indices from TM image transformation and band operation in alpine land use classifying. And then, the results were compared with the traditional maximum likelihood supervised classification. It showed that the decision tree method based on the indices can improve the overall accuracy by 15.48%, and the overall kappa coefficient by 0.1741. For bottomlands, swamp, high coverage grassland, low coverage grassland and barren land, the users accuracies were increased by 28.13%,25.00%,17.86%,17.86% and 12.50% respectively. For different coverage grassland, barren land, the producers accuracy also increased dramatically. The result indicates that the method based on indices got from image band transformation and band operation is an effective way of alpine land use/land cover remote sensing classification.

Key words: the Three Rivers Source Region, land use, decision tree, feature indices

CLC Number: