摘要
遥感技术在近几十年来发展迅速,在生态和环境等领域得到了广泛的应用。MODIS是一个比较新的数据源,它的一系列产品中,土地覆盖产品是一个比较重要的产品,在全球和区域模型中经常应用。文章比较全面地介绍了MODIS土地覆盖产品的生成过程,探讨了基于神经网络和基于决策树的土地覆盖分类方法的特点,强调了土地覆盖分类中方向信息的重要性,比较详细地介绍了变化矢量分析方法和基于人工神经网络的土地覆盖变化侦察方法,分析了IGBP定义的全球17种土地覆盖类型,并且与另外的3种分类系统进行了比较。
Remote sensing technology has been rapidly developed in recent decades, and has been widely used in ecology and environment field. MODIS is a new data source, and in its many products, land cover product is an important product, and it has often been used in global and regional models. In the present review, the procedure of producing land cover product is clearly discussed, and the feature of the classification based network or decision tree is introduced. The paper emphasized the importance of direction information in classification, detailed introduction of change vector analysis methods and land cover change detection based artificial nerve network, analyzed global 17 land cover types defined by IGBP, and compared with other 3 classification systems.
出处
《光谱学与光谱分析》
SCIE
EI
CAS
CSCD
北大核心
2010年第7期1848-1852,共5页
Spectroscopy and Spectral Analysis
基金
教育部人文社会科学重点研究基地项目(08JJD790142)
辽宁省教育厅人文社会科学研究项目(2007T095)资助