|
|||||
|
|
| 基于GIS和神经网络的森林植被分类 | |
| 引用本文： | 刘旭升,李锋,昝国胜,张晓丽,王军厚.基于GIS和神经网络的森林植被分类[J].遥感学报,2007,11(5):710-717. |
| 作者姓名： | 刘旭升 李锋 昝国胜 张晓丽 王军厚 |
| 作者单位： | 1. 国家林业局,调查规划设计院,北京,100714,中国 2. 中国科学院,生态环境研究中心,北京,100085,中国 3. 北京林业大学,资源与环境学院,北京,100083,中国 |
| 摘 要： | 本文综述了国际遥感分类研究,使用Landsat7 ETM＋遥感数据和地理辅助数据,应用BP神经网络方法,将莽汉山林场作为研究区进行了遥感影像的分类研究。比较了BP神经网络分类与最大似然、简单和复杂非监督分类法之间的类型与数量精度。BP神经网络分类的总类型精度是70.5%,总数量精度为84.65%,KAPPA系数是0.6455。结果说明BP神经网络的分类质量优于其他方法,其总的类型精度与其他三种分类方法相比分别增加了10.5%、32%和33%,总的质量精度增加了5.3%。因此,辅以地理参考数据的BP神经网络分类可以作为一种有效的分类方法。 |
| 关 键 词： | 遥感 分类 森林 神经网络 |
| 文章编号： | 1007-4619（2007）05-0710-08 |
| 修稿时间： | 2006-08-10 |
Artificial Neural Network Classification for Forest Vegetation Mapping with Combination of Remote Sensing and GIS |
|
| LIU Xu-sheng,LI Feng,ZAN Guo-sheng,ZHANG Xiao-li and WANG Jun-hou.Artificial Neural Network Classification for Forest Vegetation Mapping with Combination of Remote Sensing and GIS[J].Journal of Remote Sensing,2007,11(5):710-717. | |
| Authors: | LIU Xu-sheng LI Feng ZAN Guo-sheng ZHANG Xiao-li and WANG Jun-hou |
| Institution: | 1. Academy of Forest Inventory and Planning, State Forestry Administration, Beijing 100714, China; 2. Research Center for Eco-Environmental Sciences, Chinese Academy of Sciences, Beijing 100085, China; 3. Resource and Environment College, Beijing Forestry University, Beijing 100083, China |
| Abstract: | In this paper, we present the results of our research to evaluate the accuracy of the back propagation neural network method to classify forest vegetation using a 27 July 2001 Landsat 7 ETM+ image of the Manhanshan Forestry Center. The type and quantitative accuracy of the back propagation neural network are compared with the maximum likelihood, the simple and the complex unsupervised classification methods. The total cover type accuracy of back propagation neural network classification is 70.5%, the total quantity accuracy is 84.65%, and the KAPPA coefficient is 0.6455. Our results indicate that the total type accuracy increases 10.5%、32% and 33% respectively compared to the other three classification methods. Total quantitative accuracy increases 5.3%. It is evident that the classification quality of the back propagation neural network is better than the other methods. Therefore, the back propagation neural network is an effective and accurate method of classifying forest vegetation. |
| Keywords: | remote sensing classification forest vegetation back propagation artificial neural network |
| 本文献已被 CNKI 维普 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 | |