本文選題：遙感影像 + 改進(jìn)分水嶺分割��； 參考：《江西理工大學(xué)》2015年碩士論文

【摘要】：遙感技術(shù)快速發(fā)展,使得遙感影像分辨率不斷提高,數(shù)據(jù)量急劇增加,因此能夠更加精確地提取和分析影像中所包含的豐富地物信息。然而,目前高分辨率遙感影像信息自動(dòng)提取準(zhǔn)確度不高,建筑物作為其中一類極其重要的人工地物目標(biāo),將其各種信息較好的提取出來對(duì)于推動(dòng)高分辨率遙感影像在目標(biāo)識(shí)別分類以及城市土地規(guī)劃管理等方面具有十分重要的意義。在影像信息提取中分類是一個(gè)關(guān)鍵問題,以核函數(shù)為基礎(chǔ)的支持向量機(jī)(SVM)分類是解決影像目標(biāo)分類問題的一種有效方法。針對(duì)核函數(shù)的選擇不同和核參數(shù)設(shè)置的不同使得基于單核SVM模型的分類性能差異較大而不能準(zhǔn)確提取建筑物的問題,本文提出構(gòu)建多核學(xué)習(xí)支持向量機(jī)(MKSVM)分類模型用于提取影像建筑物。該MKSVM分類模型是針對(duì)不同特征對(duì)建筑物提取所貢獻(xiàn)作用的不同,通過權(quán)重的方式將不同的基核函數(shù)線性相加構(gòu)建的一種分類器,模型包含其中所有基本核函數(shù)的特性,具有很好的學(xué)習(xí)能力、推廣性能和靈活性。本研究在Visual studio 2013平臺(tái)下基于C++語言編寫的ORFEO TOOLBOX(OTB)分布式影像處理算法開源庫(kù),研制面向?qū)ο蟮母叻直媛蔬b感影像建筑物信息提取系統(tǒng),實(shí)現(xiàn)采用兩次分割分類的方式分步提取建筑物。首先通過區(qū)域合并的改進(jìn)分水嶺方法分割影像,并基于光譜特征采用K近鄰監(jiān)督分類提取只包含建筑物、道路和水泥廣場(chǎng)等在內(nèi)的不透水層,在此過程中同時(shí)單獨(dú)提取影像中的藍(lán)色廠房;然后對(duì)不透水層進(jìn)行均值漂移分割,根據(jù)提取的建筑物光譜、紋理和形狀等特征,將樣本輸入到多項(xiàng)式(POLY)與徑向基(RBF)核函數(shù)構(gòu)建的MKSVM分類數(shù)學(xué)模型訓(xùn)練得到分類器;最后根據(jù)訓(xùn)練得到的MKSVM分類器提取建筑物。通過與單核SVM分類提取建筑物結(jié)果進(jìn)行精度比較,相對(duì)RBF核函數(shù),兩個(gè)區(qū)域的MKSVM分類的用戶精度提高了1.5%左右,相對(duì)POLY核函數(shù),兩個(gè)區(qū)域的MKSVM分類的用戶精度提高了3%到5%;兩個(gè)區(qū)域的Kappa系數(shù)也分別提高到了0.8579和0.8415。實(shí)驗(yàn)結(jié)果表明,本文研制的影像建筑物信息提取系統(tǒng)運(yùn)行可靠,通過與單核SVM提取建筑物相比,基于MKSVM的面向?qū)ο蠓诸惙椒ㄌ崛〗ㄖ餃?zhǔn)確率更高,具有更好的分類能力。
[Abstract]:With the rapid development of remote sensing technology, the resolution of remote sensing image is improved and the amount of data is increased rapidly. Therefore, it is possible to extract and analyze the rich information of ground objects in the image more accurately. However, at present, the accuracy of automatic extraction of high-resolution remote sensing image information is not high, and buildings are one of the most important artificial objects. It is very important to extract all kinds of information to promote the high-resolution remote sensing image in target recognition and classification, urban land planning management and so on. Classification is a key problem in image information extraction. Support vector machine (SVM) based on kernel function is an effective method to solve the problem of image target classification. Because of the difference of kernel function selection and kernel parameter setting, the classification performance of SVM model based on single core is very different and the building can not be extracted accurately. In this paper, a multi-kernel learning support vector machine (MKSVM) classification model is proposed to extract image buildings. The MKSVM classification model is a kind of classifier which is constructed by linearly adding different basis kernel functions according to the contribution of different features to the building extraction. The model includes the characteristics of all the basic kernel functions. Good learning ability, promotion performance and flexibility. In this paper, the object oriented building information extraction system of high resolution remote sensing image is developed based on the ORFEO toolkit (OTB) distributed image processing algorithm open source library based on Visual studio 2013. The method of twice segmentation and classification is used to extract buildings step by step. Firstly, the improved watershed method is used to segment the image, and based on the spectral features, K-nearest neighbor supervised classification is used to extract the impervious layer, which includes only buildings, roads and cement squares, etc. In this process, the blue workshop in the image is extracted separately, and then the impermeable layer is segmented by the mean shift, according to the features of the building spectrum, texture and shape, etc. The samples are input into the MKSVM classification mathematical model which is constructed by polynomial (Poly) and radial basis function (RBF) kernel function. Finally, the building is extracted according to the training MKSVM classifier. Compared with the results of single kernel SVM classification, the user accuracy of MKSVM classification in two regions is improved by about 1.5%, and the relative POLY kernel function is compared with RBF kernel function. The user accuracy of MKSVM classification in two regions is improved by 3% to 5%, and the Kappa coefficient of the two regions is increased to 0.8579 and 0.8415 respectively. The experimental results show that the information extraction system of image building developed in this paper is reliable. Compared with single kernel SVM, the object oriented classification method based on MKSVM has higher accuracy and better classification ability.
【學(xué)位授予單位】：江西理工大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2015
【分類號(hào)】：P237

【參考文獻(xiàn)】

相關(guān)期刊論文 前5條

1 陶超;譚毅華;蔡華杰;杜博;田金文;;面向?qū)ο蟮母叻直媛蔬b感影像城區(qū)建筑物分級(jí)提取方法[J];測(cè)繪學(xué)報(bào);2010年01期

2 楊鐘瑾;;核函數(shù)支持向量機(jī)[J];計(jì)算機(jī)工程與應(yīng)用;2008年33期

3 陶陽宇;梁林;徐迎慶;沈向洋;;利用貝葉斯結(jié)構(gòu)模型的復(fù)雜形狀建筑物提取[J];計(jì)算機(jī)輔助設(shè)計(jì)與圖形學(xué)學(xué)報(bào);2010年04期

4 周軍其;李志娟;;空間關(guān)系輔助的面向?qū)ο蠼ㄖ锾崛J];應(yīng)用科學(xué)學(xué)報(bào);2012年05期

5 唐奇;王紅瑞;許新宜;王成;;基于混合核函數(shù)SVM水文時(shí)序模型及其應(yīng)用[J];系統(tǒng)工程理論與實(shí)踐;2014年02期

，

本文編號(hào)：2078705