【摘要】 以2008年经Savitzky-Golay滤波技术平滑处理的MODIS EVI时间序列数据为数据源,采用支持向量机分类法对年EVI矢量模、年EVI最大值和年EVI最小值3个指标组成的影像进行土地覆盖分类,并利用验证样本对分类结果进行精度评价。试验结果表明:采用选用的3个指标不仅能减少分类的数据量、加快分类速度,而且还能减少其他无效信息对分类的干扰,提高分类的精度。更多还原

【Abstract】 By using MODIS EVI(16-day,250m) time series smoothed by Savitzky-Golay filter in 2008,this work chose modulus of vector,maximum and minimum EVI three indices in one year to do classification.Then the land cover map was generated using support vector machine(SVM) classification method.The classification accuracy was assessed using validation samples and the result indicates that three classification indices used in the paper could not only reduce the data volume and quicken the speed of classification,but also could reduce the disturbance of other invalidation information to classification and get better classification accuracy.更多还原