多源数据的面向对象国际河流土地覆被分类研究
Object-oriented Landcover Classification of Multi-source Remote Sensing Data in International Trans-boundary River
-
摘要: 作为横跨3个国家(尼泊尔、印度、中国)的国际跨界河流———柯西河流域,地形高差巨大,土地覆被结构组成复杂,进行土地覆被的自动分类研究具有典型意义。基于面向对象方法多源遥感数据、训练规则、丰富的细节信息为复杂土地覆被自动分类研究提供了可能。选择合适的影像分割特征和最优分割尺度,按照数据挖掘中的规则顺序逐步进行各个土地覆被的提取。总体精度说明分类结果与野外点相一致的概率能达到90.05%,说明国际跨界河流土地覆被分类方法是可行的,分类结果是准确、可信的。Abstract: Landcoverclassificationisnoteasyforitsinnercomplexityresultingfromhugeterrainele vationinKosiRiverasinternationaltrans boundaryriver,ithaspossibletoclassificationdifficultiesflowingthroughthreecountries.Theemergencyofmulti sourceremotesensingimagesandtrainingalgorithmmakeitpossibletoclassifythelandcoverforitsampledetailsbasedonobject orientedmethod.Thepaperisaboutlandcoverclassificationmethodselectingfeatureandoptimalscaleofseg mentation,theinnovationofthismethodliesinselectionofproperscaleparameterresultingfromproperimagedataandcertainclassificationorder.Thetotalaccuracyhashighly90.05%comparedwithobjectorientedclassificationresultandactualsamplingpoint,whichisafeasiblemethod,andtheclassificationresultsaremoreaccurate.
下载:
