|
|||||
|
|
| 多光谱遥感图像土地利用分类区域多中心方法 | |
| 引用本文： | 林剑.多光谱遥感图像土地利用分类区域多中心方法[J].遥感学报,2010,14(1):173-179. |
| 作者姓名： | 林剑 |
| 作者单位： | 1. 湖南科技大学,知识网格实验室,湖南,湘潭,411201;湖南科技大学,地信系,湖南,湘潭,411201 2. 湖南科技大学,地信系,湖南,湘潭,411201 3. 中南大学,信息物理工程学院,湖南,长沙,410083 4. 湖南科技大学,知识网格实验室,湖南,湘潭,411201 |
| 基金项目： | 国家自然科学基金(编号: 60673119), 湖南省自然科学基金(编号: 07JJ5066), 湖南省发展改革委员会, 湘财企指[2008]149号, 湖南省教育厅基金(编号: 06C313)。 |
| 摘 要： | 针对遥感图像土地利用一种类别由多种地物组成,存在难以求取类别光谱特征多元分布模型的问题,分析了多光谱遥感图像土地利用的光谱特征和区域多中心特征,提出了一种光谱信息和区域信息基于规则的区域多中心分类方法,以类别的类内中心集合表征类别模式,以区域为分类单元,以区域单元含类别类内中心数和区域单元中属于某种类别的像元占单元总像元的百分比为分类准则;采用类内中心表征类别模式和基于规则的分类方法,较好地解决了土地利用类别由多种地物组成、类别模式不满足多元正态分布的问题,由于类别区域单元多中心特性差异大,分类规则的建立及训练样本的选择易于实现。实验表明:该方法能提高分类精度4%—6%。 |
| 关 键 词： | 多光谱遥感图像 土地利用分类 区域多中心 |
| 收稿时间： | 1/7/2008 12:00:00 AM |
| 修稿时间： | 2008/10/30 0:00:00 |
Region multi-center method for land use classification of multispectral RS imagery |
|
| LIN Jian.Region multi-center method for land use classification of multispectral RS imagery[J].Journal of Remote Sensing,2010,14(1):173-179. | |
| Authors: | LIN Jian |
| Institution: | 1. Laboratory of Knowledge Grid, Hunan University of Science & Technology, Hunan Xiangtan 411201, China; 2. Department of Geographical Information System, Hunan University of Science and Technology, Hunan Xiangtan 411201, China;2. Department of Geographical Information System, Hunan University of Science and Technology, Hunan Xiangtan 411201, China;3. School of Info-physics and Geomatics Engineering, Central South University, Hunan Changsha 410083, China;1. Laboratory of Knowledge Grid, Hunan University of Science & Technology, Hunan Xiangtan 411201, China |
| Abstract: | A convenient multivariate statistical model is in general not available for the multi-spectral feature of land use (LU) class of remote sensing (RS) image, as one LU class is made up of several ground objects. Analyzing the spectral characteristics of LU of multispectral RS imagery, this paper presents a rule-based region multi-center (RMC) method. In the method, the clas-sification cell is pixel region, the classificatory pattern is a set of the classificatory intra-class centers which is confirmed by clustering the training samples, and the classification rules are the type amounts of intra-class center and the percentage of the pixels belonged to the class from the whole region pixels. RMC method can also be used to recognize the individual LU class from multi-spectral RS image. This method deals with the distribution problem by multi-center and based on rule method. There are much difference of the classificatory center amount and the pixel's percentage among different LU class, so the selection of training area and the determinants of rules are easy. The results of experiment indicate that the LU classification accuracy is in-creased between 4% and 6% with this method. |
| Keywords: | multispectral remote sensing imagery land use classification region multi-center (RMC) |
| 本文献已被 CNKI 万方数据 等数据库收录！ | |
| 点击此处可从《遥感学报》浏览原始摘要信息 | |
| 点击此处可从《遥感学报》下载免费的PDF全文 | |