【摘要】：傳統(tǒng)的土地利用調(diào)查方法更新周期長(zhǎng)、工作量大、效率低且成本較高,遙感影像分類技術(shù)能夠快速、準(zhǔn)確地分析土地利用情況,掌握真實(shí)的土地基礎(chǔ)數(shù)據(jù),在土地利用調(diào)查中具有廣泛的應(yīng)用前景和巨大的應(yīng)用價(jià)值。而傳統(tǒng)基于像元的分類方法完全依靠地物的光譜信息,忽略了高分辨率影像中豐富的空間信息導(dǎo)致分類結(jié)果會(huì)受到異物同譜現(xiàn)象和椒鹽噪聲的干擾。針對(duì)這一問題,本文將面向?qū)ο蠓诸惙椒ㄒ�入到土地調(diào)查中,這種方法很好的克服了傳統(tǒng)分類法的弊端,且其分類結(jié)果可直接以矢量多邊形的形式輸出,能夠直接導(dǎo)入到GIS環(huán)境下進(jìn)行編輯處理與應(yīng)用分析。本文以2010年的IKONOS高分辨率遙感影像作為數(shù)據(jù)源,以東北大學(xué)及附近區(qū)域作為實(shí)驗(yàn)區(qū),針對(duì)面向?qū)ο蠓诸惙椒ㄟM(jìn)行了大量的實(shí)驗(yàn),重點(diǎn)從以下幾個(gè)方面做了分析和研究：1)在分割過程中加入紋理濾波和邊緣檢測(cè)層,并通過多次試驗(yàn)得到最優(yōu)分割參數(shù)。實(shí)驗(yàn)對(duì)比各類地物在不同尺度下的RMAS值,確定出每一類地物對(duì)應(yīng)的最佳尺度,結(jié)合層次間的拓?fù)潢P(guān)系,最終建立一個(gè)由50、70和90三個(gè)尺度層組成的網(wǎng)絡(luò)結(jié)構(gòu)。2)根據(jù)國(guó)家現(xiàn)行土地分類標(biāo)準(zhǔn),結(jié)合影像目視解譯和實(shí)地調(diào)查確定研究區(qū)包含的類別。分析研究描述地物類別的最佳特征或特征組合,建立分類規(guī)則樹,并將面向?qū)ο蠓ǚ诸惤Y(jié)果與傳統(tǒng)基于像元法分類結(jié)果進(jìn)行對(duì)比。在面向?qū)ο蠓诸惖玫降氖噶拷Y(jié)果圖上對(duì)應(yīng)實(shí)地選取地物樣本,分別對(duì)地物樣本的長(zhǎng)、寬及面積進(jìn)行量測(cè)與計(jì)算。3)采用面向?qū)ο蠹夹g(shù)對(duì)兩期Landsat-7影像進(jìn)行分類,基于分類結(jié)果構(gòu)建變化檢測(cè)規(guī)則,提取地物類別的變化圖斑,并對(duì)變化圖斑的面積進(jìn)行統(tǒng)計(jì)分析。實(shí)驗(yàn)結(jié)果表明,面向?qū)ο蠓诸惙椒ǖ目傮w分類精度為90.68%,比傳統(tǒng)基于像元的最大似然法總體精度提高了18.98%,將其應(yīng)用到土地利用調(diào)查中,實(shí)現(xiàn)了土地利用分類過程的自動(dòng)化。但由于面向?qū)ο蠓诸惙ǖ玫降氖噶繉?duì)象邊界多呈現(xiàn)鋸齒狀,圖上量測(cè)的部分結(jié)果并非其直線距離,致使與實(shí)地同名地物間存在一定的誤差,故需要對(duì)其邊界進(jìn)行平滑處理后方能入庫(kù)。此外,將面向?qū)ο蠓诸惣夹g(shù)與變化檢測(cè)相結(jié)合的方法,能夠快速、準(zhǔn)確的檢測(cè)出土地的變化信息,為及時(shí)完善和更新土地利用數(shù)據(jù)庫(kù)提供了先進(jìn)的技術(shù)手段。
[Abstract]:Traditional land use survey methods have long updating period, large workload, low efficiency and high cost. Remote sensing image classification technology can analyze the land use situation quickly and accurately, and master the real land basic data. It has wide application prospect and great application value in land use survey. However, the traditional pixel based classification method completely depends on the spectral information of the ground object, and neglects the abundant spatial information in the high-resolution image, which results in the interference of the classification results from the phenomenon of foreign body isospectrum and the salt and pepper noise. In order to solve this problem, this paper introduces the object-oriented classification method into the land survey. This method overcomes the disadvantages of the traditional classification method, and the classification results can be directly output in the form of vector polygons. Can be directly imported into the GIS environment for editing processing and application analysis. In this paper, the IKONOS high-resolution remote sensing image in 2010 is used as the data source, and the Northeast University and its adjacent areas are used as the experimental areas. A large number of experiments have been carried out on the object-oriented classification method. The following aspects are analyzed and studied: 1) texture filtering and edge detection layer are added in the segmentation process and the optimal segmentation parameters are obtained through several experiments. By comparing the RMAS values of all kinds of ground objects at different scales, the optimal scale of each kind of ground objects is determined, and the topological relationship between layers is combined. Finally, a network structure consisting of three scales of 50, 70 and 90 is established. 2) according to the current national land classification standards, combined with image visual interpretation and field investigation, the types of the study area are determined. In this paper, the best feature or combination of features to describe ground objects is analyzed, and the classification rule tree is established, and the results of object-oriented classification are compared with the traditional classification results based on pixel method. In the vector result map of object oriented classification, the object samples are selected in the field, and the length, width and area of the object samples are measured and calculated respectively. 3) the object oriented technology is used to classify the two Landsat-7 images. Based on the classification results, the change detection rules are constructed, and the change patterns of the ground objects are extracted, and the area of the change patterns is analyzed statistically. The experimental results show that the overall classification accuracy of the object-oriented classification method is 90.68, which is 18.98 higher than that of the traditional maximum likelihood method based on pixel. It is applied to the land use survey to realize the automation of the land use classification process. However, the boundary of vector objects obtained by object-oriented classification is serrated, and some of the measured results on the map are not linear distance, which leads to some errors between the vector objects and the objects of the same name in the field. Therefore, it is necessary to smooth the boundary before it can be stored. In addition, the combination of object-oriented classification technology and change detection can quickly and accurately detect the land change information, and provide an advanced technical means for the timely improvement and updating of land use database.
【學(xué)位授予單位】：東北大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2013
【分類號(hào)】：P237

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 李偉;;面向?qū)ο蟮倪b感變化檢測(cè)研究[J];北京測(cè)繪;2013年01期

2 徐登云;李志娟;;面向?qū)ο蟮倪b感影像分類方法在土地覆蓋中的應(yīng)用[J];西部資源;2012年02期

3 曹雨田;閆冬梅;張麗;何挺;;基于QuickBird衛(wèi)星數(shù)據(jù)的土地利用分類規(guī)則集研究[J];地理與地理信息科學(xué);2011年06期

4 初禹;單久庫(kù);侯建國(guó);;GeoEye-1遙感影像融合效果的比較分析[J];測(cè)繪與空間地理信息;2011年03期

5 陳杰;鄧敏;肖鵬峰;楊敏華;梅小明;劉慧敏;;結(jié)合支持向量機(jī)與粒度計(jì)算的高分辨率遙感影像面向?qū)ο蠓诸怺J];測(cè)繪學(xué)報(bào);2011年02期

6 張俊;朱國(guó)龍;李妍;;面向?qū)ο蟾叻直媛视跋裥畔⑻崛≈械某叨刃��?yīng)及最優(yōu)尺度研究[J];測(cè)繪科學(xué);2011年02期

7 侯偉;魯學(xué)軍;張春曉;王靜;;面向?qū)ο蟮母叻直媛视跋裥畔⑻崛》椒ㄑ芯俊�—以四川理縣居民地提取為例[J];地球信息科學(xué)學(xué)報(bào);2010年01期

8 徐健;陳向陽;張海霞;劉偉東;;面向?qū)ο蠓诸惙椒ㄔ谌珖?guó)第二次土地調(diào)查中的應(yīng)用[J];測(cè)繪技術(shù)裝備;2009年02期

9 萬雪;;基于RBF神經(jīng)網(wǎng)絡(luò)的高分辨率遙感影像分類的研究[J];測(cè)繪通報(bào);2009年02期

10 杜施;;遙感技術(shù)在第二次土地調(diào)查中的應(yīng)用[J];國(guó)土資源導(dǎo)刊;2007年05期

相關(guān)博士學(xué)位論文 前5條

1 劉煒;土地利用/覆被變化信息遙感圖像自動(dòng)分類識(shí)別與提取方法研究[D];西北農(nóng)林科技大學(xué);2012年

2 高偉;基于特征知識(shí)庫(kù)的遙感信息提取技術(shù)研究[D];中國(guó)地質(zhì)大學(xué);2010年

3 陳忠;高分辨率遙感圖像分類技術(shù)研究[D];中國(guó)科學(xué)院研究生院（遙感應(yīng)用研究所）;2006年

4 陽愛民;模糊分類模型的研究[D];復(fù)旦大學(xué);2005年

5 黃慧萍;面向?qū)ο笥跋穹治鲋械某叨葐栴}研究[D];中國(guó)科學(xué)院研究生院（遙感應(yīng)用研究所）;2003年

相關(guān)碩士學(xué)位論文 前8條

1 陸超;基于WorldView-2影像的面向?qū)ο笮畔⑻崛〖夹g(shù)研究[D];浙江大學(xué);2012年

2 魏宇峰;高分辨率遙感影像道路信息提取關(guān)鍵技術(shù)研究與實(shí)現(xiàn)[D];北京理工大學(xué);2010年

3 汪求來;面向?qū)ο筮b感影像分類方法及其應(yīng)用研究[D];南京林業(yè)大學(xué);2008年

4 劉常娟;面向?qū)ο蠓诸惙椒ㄔ谕恋卣{(diào)查中的可行性研究[D];中南大學(xué);2008年

5 田新光;面向?qū)ο蟾叻直媛蔬b感影像信息提取[D];中國(guó)測(cè)繪科學(xué)研究院;2007年

6 馬文;高分辨率遙感影像道路分割算法研究[D];河海大學(xué);2006年

7 周春艷;面向?qū)ο蟮母叻直媛蔬b感影像信息提取技術(shù)[D];山東科技大學(xué);2006年

8 孫華;SPOT5在森林資源調(diào)查中的應(yīng)用研究[D];中南林業(yè)科技大學(xué);2006年

，

本文編號(hào)：2280797