基于gis改进先验概率的遥感土地利用土地覆盖分类研究——以开封市为例-地图学与地理信息系统专业论文.docxVIP

第四章是遥感影像分类与比较分析。介绍了影像分类的具体步骤，包括分类系统的确定、训练区的选择、分类、精度检验、分类结果评价与分析。 第四章是遥感影像分类与比较分析。介绍了影像分类的具体步骤，包括分类 系统的确定、训练区的选择、分类、精度检验、分类结果评价与分析。 第五章是结论。介绍了本文的研究结论、创新与局限性。 关键词： GIS：先验概率；土地利用／土地覆盖： 监督分类 AbstractWith Abstract With the rapid dcvelopmem of remote sensing(RS)tcchn0109y， 恤re is a fhr．r锄ging use of remote sensing image in the field of laIld use八and coVer research．How to inlprove the accuracy of RS interpre诅tion automatically is a challenge in Rs application．On the other hand，tIle existing geographicaI data contain plenty of spatial锄d attribute information．How to印ply geographical data into RS cIassification to improVe me accuracy is one of t11e matters tllat the scholar pays attention to．It is popularIy considered that considering the innucnce of the prior probability accords with Bayes rule趴d ensures the minimal loss in the classi母ing progress．Supponed by the a11alysis and advance process to t11e geogr印hical data using GIS sofc、vare，thc paper discusses the question that whether the accuracy of Bayes supervised classincation wilI be improved considering the innuence of the prior probabiIity． Inthis papcr，usingArcView，inthe pmcessofIalld coVer classificationofKaifeng city，the geographical data such as the Iand use m印are made into Vector m印s，then the assistant data，containing attribute of each land coVer sort，are gained．The proportion based on the assistant data is used as the prior probability t0 replace the prior Value in the conventional supervised cIaSsification；the fhrther iteratiVe prior probability is applied into classifying progress on Lalldsat TM image．The oVerall accuracy and k印pa index are calculated by using the error matrix to check up the classification’s accuracyt The main conclusions are following：(1)Compared wim t}le conventional MLC， the memod of iterative prior probability based on the vector m印can dispeI tlle prior probability’s innuence and the overall accuracy aIld kappa index call be improVed；(2) Tb the types、vitIl greater area tIlan average area of