文献类型：期刊文献

英文题名：Knowledge-Based Object Oriented Land Cover Classification Using SPOT5 Imagery in Forest-Agriculture Ecotones

作者：Su Wei[1] Zhang Chao[1] Yang Jianyu[1] Wu Honggan[2] Chen Minjie[1] Yue Anzhi[1] Zhang Yingna[1] Sun Chong[1]

第一作者：Su Wei

通信作者：Zhang, C[1]

机构：[1]China Agr Univ, Coll Informat & Elect Engn, Beijing 100083, Peoples R China;[2]Chinese Acad Forestry, Res Inst Forest Resource Informat Tech, Beijing 100091, Peoples R China

年份：2010

卷号：8

期号：1

起止页码：22-31

外文期刊名：SENSOR LETTERS

收录：;EI(收录号：20103013099365);Scopus(收录号：2-s2.0-77954920575);WOS:【SCI-EXPANDED(收录号:WOS:000276693900006)】；

基金：This research is funded by the National High Technology Research and Development Program of China titled The technique of the patch-oriented culture type precision recognition and its application (contract number: 2007AA12Z181). All authors would like to appreciate many experts from Research Institute of Forest Resource Information Techniques of Chinese Academy of Forestry, Institute of Remote Sensing Applications of Chinese Academy of Sciences, China Land Surveying and Planning Institute for their co-operation and support.

语种：英文

外文关键词：Knowledge-Based; Object Oriented Land Cover Classification; Forest-Agriculture Ecotones; Chessboard Segmentation; Multi-Resolution Segmentation

摘要：This paper describes a knowledge-based object oriented classification method using SPOT5 imagery in Forest-Agriculture Ecotones. It is based on optimized application of expert knowledge information extraction from remote sensing imagery, geographic data, investigated data, chessboard image segmentation and multi-resolution image segmentation technique. Due to these capabilities, the method represents a significant improvement in land cover classification. This approach can also be seen as a framework for integrating external knowledge with image classification procedures. Confusion matrix is used to do accuracy assessment and our assessment results show that he knowledge-based object oriented classification improves the total accuracy from 61.352% (pixel-based Minimum Distance classification), 91.30% (object oriented Nearest Neighbor classification) to 94.40%. The result indicates that this method leads to a higher classification accuracy.