| 基于概率神经网络的遥感影像分类方法 |
| |
| 引用本文： | 巴桑,张正健,刘志红,李祚泳,侯长艳.基于概率神经网络的遥感影像分类方法[J].四川气象,2011(3):26-29. |
| |
| 作者姓名： | 巴桑 张正健 刘志红 李祚泳 侯长艳 |
| |
| 作者单位： | 西藏高原大气环境科学研究所;四川省农业气象中心;成都信息工程学院资源环境学院;湖南常德石门县气象局; |
| |
| 基金项目： | 国家自然科学基金(50779042); 国家发改委重点项目“西藏自治区生态环境遥感监测与服务系统” |
| |
| 摘 要： | 在对数据进行归一化处理的基础上,将概率神经网络用于遥感影像分类,并探讨样本区的选择和高斯基函数标准差对分类精度的影响。用西藏波密地区1999年的TM遥感影像进行分类试验,并将分类结果和经典的最大似然法进行比较。结果表明：概率神经网络的总体分类精度和Kappa系数分别为94.5%和0.934,取得了较为理想的识别和分类效果。
|
| 关 键 词： | 概率神经网络 遥感影像 最大似然法 误差矩阵 分类 |
Remote Sensing Image Classification Based on Probabilistic Neural Network |
| |
| BA Sang,ZHANG Zhengjian,LIU Zhihong,LI Zuoyong,HOU Changyan.Remote Sensing Image Classification Based on Probabilistic Neural Network[J].Journal of Sichuan Meteorology,2011(3):26-29. |
| |
| Authors: | BA Sang ZHANG Zhengjian LIU Zhihong LI Zuoyong HOU Changyan |
| |
| Institution: | BA Sang1,ZHANG Zhengjian2,LIU Zhihong3,LI Zuoyong3,HOU Changyan4(1.Tibet Institute of Plateau Atmospheic and Environmental Sciences,Lhasa,850001,2.Agricultural Meteorology Center of Sichuan Province,Chengdu,610072,3.College of Resources and Environment,Chengdu University of Information Technology,610225 4.Meteorological Bureau of Shimen County,Shimen,415300) |
| |
| Abstract: | This paper has analyzed the remote sensing classification using the probabilistic neural network(PNN) on the basis of data normalization,for the best classification accuracy,the picking of sample area and the standard deviation of the basis Gauss function has been discussed.PNN classification model was applied to classify the TM image in Tibet.Based on error matrix,the classification result of the maximum likelihood was contrasted with that of PNN model.The results show that the overall accuracy and Kappa c... |
| |
| Keywords: | probabilistic neural network remote sensing image maximum likelihood error matrix classification |
| 本文献已被 CNKI 维普 等数据库收录！ |
|
