摘要
采用面向对象遥感影像分类方法,进行了高空间分辨率遥感影像信息提取试验,分析了其与基于像元方法的信息提取结果的差异,试验研究表明,在目视效果上,传统方法的分类结果图中椒盐现象非常明显,而面向对象方法可以有效地避免椒盐现象;在分类精度上,面向对象方法分类结果的总体精度、Kappa系数、生产者精度、用户精度、Hellden精度和Short精度均明显高于传统方法,各类地物提取效果显著提高。面向对象方法在高空间分辨率遥感影像信息提取中具有明显的优势。
The object-oriented classification method was used to extract land use/land cover information from high spatial resolution remote sensing images,and the results were compared with the traditional information extraction method.The classification results were easier to understand and interpretative.Overall precision,Kappa,producer precision,user precision,Hellden precision and Short precision of object-oriented classification are better than that of traditional classification method.These experiments show that the object-oriented method is superior to traditional method in high resolution remote sensing information extraction.
出处
《测绘信息与工程》
2010年第3期3-5,共3页
Journal of Geomatics
基金
国家自然科学基金资助项目(50534050)
国家自然科学基金资助项目(50774080)
关键词
面向对象
多尺度分割
最优尺度
object-oriented
multi-scale segmentation
optimal scale
作者简介
张俊，硕士，主要从事遥感图像处理与应用研究。E—mail：zjaust@163．com
