摘要
以时间分辨率为16d、空间分辨率为250m的MODIS NDVI时间序列数据为主要数据源,利用两种滤波方法对NDVI时间序列进行滤波处理,并基于J-M距离比较了两种方法的类别可分性,同时结合短波红外光谱反射率数据、DEM数据,采用分层分类的方法,对中国东北3省进行了土地覆盖制图研究。在分类过程中,遵循逐级分类、先利用单一特征波段后结合多种特征波段的原则,综合使用阈值法、支持向量机(SVM)、人工神经网络(ANN)、C5.0决策树分类法对研究区内的土地覆盖类别进行逐层分类细化。根据已有的土地覆盖数据和高分辨率遥感影像对最终分类结果进行精度评价,总体分类精度为84.61%,Kappa系数为0.8262。
In this paper,we mainly used MODIS NDVI time-series dataset at 16-days temporal resolution and 250-meters spatial resolution to analyze land cover mapping of northeastern China. We used two different filter methods to fit NDVI time series dataset, and compared their average classes＇ separability based on Jeffries-Matusita distance index. In addition, we made use of hierarchical classification method to com- plete classification, combined with short-wave infrared spectral reflectance data and DEM. We conformed to the principle that separate area hierarchically into several parts first and then classify each part further, and use a single characteristic band first and then multiple feature bands. In the process of classification, we a- dopted threshold value method,support vector machine,artificial net neural and C5.0 decision tree classifi- cation to distinguish each land-cover type hierarchical sification of study area using known land-cover class y. Finally,we evaluated the accuracy of the final clas- fication data and high-resolution remote sensing imagery,overall accuracy is 84.61% ,Kappa coefficient is 0. 8262.
出处
《遥感技术与应用》
CSCD
北大核心
2013年第5期910-919,共10页
Remote Sensing Technology and Application
基金
国家科技支撑计划课题(2011BAH06B02)
林业公益性行业科研专项(200804001)
