摘要
针对基于像元光谱特征提取沙化土地信息分类精度偏低的问题,以Landsat-5TM为数据源,基于面向对象的方法对沙化土地遥感信息提取技术进行研究。首先采用多尺度分割法对影像进行分割以获得同质区域,然后结合野外调查数据制成不同地物类型的多种特征图,从而确定提取目标地物的特征并建立沙化和非沙化地物提取决策树,最后对影像进行模糊分类,并对分类结果进行精度评价。结果表明,基于面向对象提取沙化土地信息的总精度达84.89%,Kappa系数为0.8077。研究结果为后续深入研究奠定了基础。
For the problem of low classification accuracy of sandy lands based on spectral feature of remote sensing images,a methodology by applying object-oriented method for extracting sandy lands information was studied by Landsat-5 TM image data in this paper. First, the muir-scale image segmentation was con- ducted to obtain homogeneous areas of objects. Then, based on field survey data, a variety of feature dia- grams of different land surface types were made to select the features of target objects and establish the de- cision tree for classification of sandy and non-sandy lands. Finally, the fuzzy image classification with the decision tree was implemented, accuracy of classification was validated by ground truth data. The result showed that the overall accuracy reached 84.89% and the Kappa coefficient was 0. 8077, which indicated that the object-oriented method for extracting sandy lands information could provide a foundation for fur- ther study on extraction of sandy land information.
出处
《遥感技术与应用》
CSCD
北大核心
2012年第5期770-777,共8页
Remote Sensing Technology and Application
基金
国家"十二五"科技支撑计划项目(2011BAH23B04)资助
关键词
沙化土地
面向对象
多尺度影像分割
Sandy lands
Object-oriented method
Multi-scale image segmentation
