5 November 2008 A study of land use/land cover information extraction classification technology based on DTC
Author Affiliations +
Proceedings Volume 7144, Geoinformatics 2008 and Joint Conference on GIS and Built Environment: The Built Environment and Its Dynamics; 71440I (2008) https://doi.org/10.1117/12.812708
Event: Geoinformatics 2008 and Joint Conference on GIS and Built Environment: Geo-Simulation and Virtual GIS Environments, 2008, Guangzhou, China
Abstract
Decision Tree Classification (DTC) is one organizational form of the multi-level recognition system, which changes the complicated classification into simple categories, and then gradually resolves it. The paper does LULC Decision Tree Classification research on some areas of Gansu Province in the west of China. With the mid-resolution remote sensing data as the main data resource, the authors adopt decision-making classification technology method, taking advantage of its character that it imitates the processing pattern of human judgment and thinking and its fault-tolerant character, and also build the decision tree LULC classical pattern. The research shows that the methods and techniques can increase the level of automation and accuracy of LULC information extraction, and better carry out LULC information extraction on the research areas. The main aspects of the research are as follows: 1. We collected training samples firstly, established a comprehensive database which is supported by remote sensing and ground data; 2. By utilizing CART system, and based on multiply sources and time phases remote sensing data and other assistance data, the DTC's technology effectively combined the unsupervised classification results with the experts' knowledge together. The method and procedure for distilling the decision tree information were specifically developed. 3. In designing the decision tree, based on the various object of types classification rules, we established and pruned DTC'S model for the purpose of achieving effective treatment of subdivision classification, and completed the land use and land cover classification of the research areas. The accuracy of evaluation showed that the classification accuracy reached upwards 80%.
© (2008) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Ping Wang, Yong-guo Zheng, Feng-jie Yang, Wei-jie Jia, Chang-zhen Xiong, "A study of land use/land cover information extraction classification technology based on DTC", Proc. SPIE 7144, Geoinformatics 2008 and Joint Conference on GIS and Built Environment: The Built Environment and Its Dynamics, 71440I (5 November 2008); doi: 10.1117/12.812708; https://doi.org/10.1117/12.812708
PROCEEDINGS
11 PAGES


SHARE
Back to Top