孔博, 邓伟, 李爱农, 杨勇. 多源数据的面向对象国际河流土地覆被分类研究[J]. 武汉大学学报 ( 信息科学版), 2015, 40(7): 943-949. doi: 10.13203/j.whugis20130107
引用本文: 孔博, 邓伟, 李爱农, 杨勇. 多源数据的面向对象国际河流土地覆被分类研究[J]. 武汉大学学报 ( 信息科学版), 2015, 40(7): 943-949. doi: 10.13203/j.whugis20130107
KONG Bo, DENG Wei, LI Ainong, YANG Yong. Object-oriented Landcover Classification of Multi-source Remote Sensing Data in International Trans-boundary River[J]. Geomatics and Information Science of Wuhan University, 2015, 40(7): 943-949. doi: 10.13203/j.whugis20130107
Citation: KONG Bo, DENG Wei, LI Ainong, YANG Yong. Object-oriented Landcover Classification of Multi-source Remote Sensing Data in International Trans-boundary River[J]. Geomatics and Information Science of Wuhan University, 2015, 40(7): 943-949. doi: 10.13203/j.whugis20130107

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.

     

/

返回文章
返回