测绘学报

• 学术论文 •    

多时相MODIS影像土地覆盖分类比较研究

郭健 张继贤 张永红 曹银璇
  

  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2009-02-25 发布日期:2009-02-25

Study on the Comparison of Land Cover Classification for Multitemporal MODIS Images

  • Received:1900-01-01 Revised:1900-01-01 Online:2009-02-25 Published:2009-02-25

摘要: 首先以黑龙江省多时相MODIS影像为试验数据,利用最大似然分类(MLC)、自组织神经网络(SONN)、支持向量机(SVM)以及决策树分类(DTC)等四种广泛使用的分类方法进行了土地覆盖遥感分类研究。并从分类精度、样本数量对分类器的影响、模型复杂度、参数的选择、分类速度等多个方面对4种分类方法进行了深入比较和分析。综合比较得出决策树分类法最优,而经典方法之一的最大似然分类法最稳定。进而将此二法推广到全国范围的土地覆盖分类试验中,并进行精度对比。本文所得出的结论将对于在类似的应用中如何选择合适的分类方法具有一定的参考价值。

Abstract:

The four broadly used classification methods, which are Maximum Likelihood Classification (MLC), Self-Organized Neural Network (SONN), Support Vector Machine (SVM) and Decision Tree Classification (DTC), are firstly applied for the land cover remote sensing classification based on the multitemporal Moderate Resolution Imaging Spectroradiometer (MODIS) images of Heilongjiang area in this paper. Then, this paper deeply compares the four classifiers through different aspects, as a result, DTC is the best and MLC as one of the classical methods is more stable than other three methods. Therefore, the land cover classification over China is made by DTC and MLC, afterwards compare them again. The conclusions got in this paper are valuable for how to select classifiers in the similar applications.