Position: Home > Articles > Application of MNF and SVM in Classificationof Remote Sensed Image
Bulletin of Soil and Water Conservation
2009,29
(6)
153-158
MNF和SVM在遥感影像计算机分类中的应用
作 者：
纪娜;李锐;李静
单 位：
杨凌职业技术学院;青海油田公司;长安大学经济与管理学院
关键词：
最小噪声分离变换;支持向量机;黄土高原;遥感图像分类
摘 要：
由于黄土高原地形复杂,单纯采用监督分离变换MNF(Minimum Noise Fraction)变换得到的4个去除噪声波段、归一化植督分类方法很难获得理想的精度,以延安市区为实验区,以TM遥感图像的最小噪声被指数NDVI和该地域的DEM作为数据源,采用支持向量机SVM(Support Vector Machine)的方法对研究区土地利用与覆盖状况进行分类,获得了较理想的分类结果。
译 名：
Application of MNF and SVM in Classificationof Remote Sensed Image
作 者：
JI Na1,2,LI Rui1,3,LI Jing4(1.College of Resources and Environment,Northwest A & F University,Yangling,Shaanxi 712100,China;2.Yangling Vocational and Technical College,Yangling,Shaanxi 712100,China;3.Institute of Soil and Water Conservation,Chinese Academy of Sciences and Ministry of Water Resources, Yangling,Shaanxi 712100,China;4.Engineering College of Armed Police Force,Xi'an,Shaanxi 710086,China)
关键词：
minimum noise fraction(MNF);support vector machine(SVM);Loess Plateau;classification of remote sensed image
摘 要：
The classification accuracy is unsatisfactory in the complicated terrain area of the Loess Plateau when the single supervised classification is used in remote sensing.The paper discusses the extraction of classification information of Yan'an City and nearby area from a TM image and deals with the image classification based on the SVM method integrating the information of MNF,NDVI,and DEM.In comparison with Maximum Likelihood and SVM method of single spectrum,results showed that the objects with the same spectrum are distinguished by using DEM in image classification.Compared with the traditional classification method,the classification based on the information of DEM and multiple bands supported with the SVM method can acquire higher classification effect.
相似文章
-
基于高光谱成像技术识别水稻纹枯病 [李志伟, 袁婧, 丁为民, 杨红兵, 沈少庆, 崔嘉林] 华南农业大学学报 2018 (6) 97-103
