文献类型：会议论文

英文题名：Supervised Wishart classifier for rice mapping using multi-temporal envisat ASAR APS data

作者：Chen, E.X.[1] Li, Z.Y.[1] Tan, B.X.[1] Pang, Y.[1] Tian, X.[1] Li, B.B.[2]

第一作者：陈尔学

通信作者：Chen, E.X.|[a0005727ad9cc65ae3950]陈尔学;

机构：[1] Institute of Forest Resources Information Technique, Chinese Academy of Forestry, Beijing, 100091, China; [2] Institute of Agriculture Modernization, Jiangsu Academy of Agriculture Sciences, 210014, Nanjing, China

会议论文集：Proceedings of Envisat Symposium 2007

会议日期：April 23, 2007 - April 27, 2007

会议地点：Montreux, Switzerland

语种：英文

外文关键词：Crops - Image classification - Maximum likelihood - Polarization - Remote sensing

年份：2007

摘要：For the operational application of multi-temporal ENVISAT ASAR APS data to rice mapping, a complex Wishart distribution based multi-temporal classifier was evaluated in this paper. The classification accuracy of this classifier was quantitatively compared with commonly used classifiers for optical remote sensing image classification including maximum likelihood classifier and minimum euclidean classifier with only intensity SAR images being used for classification. It has been shown that classification accuracy can be improved significantly if the Wishart classifier is applied to the multi-temporal dual polarization datasets instead of applying it to one dual polarization dataset; Wishart classifier achieved the highest overall classification accuracy, which is recommended for operational rice mapping using multi-temporal ENVISAT APS data.