基于SVM的资源三号影像林地分类及精度评价研究  

Forest Classification and Accuracy Assessment in ZY3 Image with SVM Method

作　　者：侯逸晨[1] 赵鹏祥[1] 杨伟志[1] 张晓莉[1] 

机构地区：[1]西北农林科技大学林学院,陕西杨陵712100

出　　处：《西北林学院学报》2016年第1期180-185,共6页Journal of Northwest Forestry University

基　　金：国家自然科学基金项目:黄土高原天然林林地时空变化及其驱动力研究(30972296)

摘　　要：运用ZY-3影像全色和多光谱影像,采用支持向量机(SVM)法对黄龙山林区蔡家川林场林地进行分类研究,探讨SVM法的分类能力及不同核函数、纹理窗口大小对森林植被分类精度的影响。结果表明:SVM法在研究区ZY-3影像林地分类中精度比传统的极大似然法高;将光谱信息与灰度共生矩阵(GLCM)构造派生的纹理信息结合能有效提高分类精度;采用SVM法分类时不同核函数对分类结果的精度影响不显著;在选用3×3、5×5纹理窗口时分类精度更高。Based on ZY-3 panchromatic and multispectral image, the forest stands in Huanglong Mountain- ous areas were classified by support vector machine （SVM） method. The classification ability of SVM was tested,and the influence of different kernel functions and texture window size on the accuracy of classifica- tion were examined. The data showed that the accuracy of the SVM on forest vegetation classification of ZY-3 image was higher than that of the traditional maximum likelihood method. The accuracy of classifica- tion could be evidently improved by combining spectral information and the image texture information based on gray level co-occurrence matrix （GLCM）. Different kernel functions had no significant influence on the accuracy of classification by using SVM method. In addition, the accuracy of classification was higher with 3×3 or 5×5 windows.

关 键 词：遥感 资源三号影像 森林分类 支持向量机 

分 类 号：S771.8[农业科学—森林工程]