本文選題：特征提取 + 建筑物樣本數(shù)據(jù)庫��； 參考：《北京建筑大學(xué)》2015年碩士論文

【摘要】：基于遙感影像處理和特征分析的方法,已經(jīng)成為獲取地面地物信息的主要方式之一,并且已經(jīng)得到了廣泛的應(yīng)用和推廣。二十世紀(jì)至今,遙感平臺(tái)的迅速發(fā)展,遙感器多樣性和精度的快速提高,使得分辨率在空間、光譜、輻射和時(shí)間上不斷完善,在遙感影像上地物的信息也更加細(xì)膩豐富。因此,地面目標(biāo)物的識(shí)別和特征提取的精度明顯得到了改善。在城市高分辨率影像中,占據(jù)了八成左右的地面地物是建筑物和道路。故建筑物的識(shí)取占據(jù)了很大比率。城市建筑物對(duì)城市的運(yùn)行、管理和規(guī)劃有著重要的支撐作用。將來構(gòu)建數(shù)字城市的關(guān)鍵基礎(chǔ)技術(shù)之一就有城市建筑物的識(shí)別。因此研究建筑物的識(shí)別對(duì)城市的發(fā)展具有一定的意義。論文首先對(duì)SQL Server 2008數(shù)據(jù)庫進(jìn)行介紹,包括關(guān)系模型的特點(diǎn)、關(guān)系的規(guī)范化和數(shù)據(jù)庫設(shè)計(jì)原則。接著對(duì)遙感影像實(shí)驗(yàn)區(qū)進(jìn)行選取和描述,從光譜特征、幾何特征和紋理特征對(duì)目標(biāo)進(jìn)行特點(diǎn)分析,提取出相關(guān)特征參數(shù),并進(jìn)行表結(jié)構(gòu)設(shè)計(jì),建立表關(guān)系,對(duì)數(shù)據(jù)進(jìn)行入庫存儲(chǔ),建立建筑物樣本數(shù)據(jù)庫。然后在基于數(shù)據(jù)庫地物光譜特征的基礎(chǔ)上,采用最小距離法、貝葉斯法、神經(jīng)網(wǎng)絡(luò)法和多分類法融合的基于不同權(quán)重綜合分類法等監(jiān)督分類方法對(duì)建筑物進(jìn)行分類識(shí)別,并采用混淆矩陣對(duì)各種方法的分類結(jié)果做了精度評(píng)價(jià)和比較。最后選取出分類精度最高的影像,先用小圖斑剔除法對(duì)影像進(jìn)行后處理,接著以二值圖像的方式提取出影像中的建筑物,并將小連通區(qū)域剔除,最后提取出建筑物邊緣位置信息并標(biāo)注在原始影像上。實(shí)驗(yàn)證明,建筑物樣本數(shù)據(jù)庫可以對(duì)城市建筑物的特征參數(shù)進(jìn)行存儲(chǔ)管理,對(duì)大城市建筑物多樣性有較好的適應(yīng)性,且該數(shù)據(jù)庫可以為以其為基礎(chǔ)的遙感影像建筑物的分類識(shí)別、空間分析提供可靠的基礎(chǔ)數(shù)據(jù)。多分類法融合的基于不同權(quán)重綜合分類法,根據(jù)各個(gè)分類法分類精度比重分配權(quán)重大小,有較強(qiáng)的適應(yīng)能力,與人類對(duì)知識(shí)的認(rèn)知習(xí)慣較符合。建筑物樣本數(shù)據(jù)庫的建立和多分類法融合的基于不同權(quán)重的綜合分類器對(duì)于城市建筑物的識(shí)別有很好的效果,因此有一定的研究意義。
[Abstract]:The method based on remote sensing image processing and feature analysis has become one of the main ways to obtain ground ground information, and has been widely used and popularized. Since twentieth Century, the rapid development of remote sensing platform, the rapid improvement of the diversity and precision of remote sensing devices make the resolution in space, spectrum, radiation and time continuously. The information of ground objects on remote sensing images is also more delicate. Therefore, the accuracy of the recognition and feature extraction of ground objects has been improved obviously. In the urban high resolution images, about 80% of the ground objects occupy the buildings and roads. Operation, management and planning have an important supporting role. One of the key basic technologies for the future construction of digital cities is the identification of urban buildings. Therefore, it is of certain significance to study the identification of buildings for the development of the city. First, the paper introduces the SQL Server 2008 database, including the characteristics of the relationship model and the specification of the relationship. Then we select and describe the remote sensing image experimentation area, analyze the characteristics of the spectral features, geometric features and texture features, extract the related characteristic parameters, design the table structure, establish the table relationship, store the data and establish the database of the building sample. Then the data are based on the number of data. On the basis of the spectral characteristics of the storehouse, using the minimum distance method, the Bayesian method, the neural network method and the multi classification method to classify the buildings on the basis of the different weight comprehensive classification methods, and use the confusion matrix to evaluate and compare the classification results of various methods. Finally, the classification precision is selected. With the highest degree of image, the image is processed by the small plot elimination method first, then the building in the image is extracted with the two value image, and the small connected area is removed. Finally, the information of the building edge position is extracted and labeled on the original image. The experiment shows that the database of the building samples can be characteristic of the urban building. The parameters are stored and managed, and it has good adaptability to the diversity of the buildings in large cities. And the database can be used for classification and identification of remote sensing images based on it, and the spatial analysis provides reliable basic data. The multi classification method is based on the comprehensive classification of different weights, and the weight distribution right is classified according to the various classification methods. There is a strong ability to adapt to the cognitive habits of human knowledge. The establishment of the database of building samples and the integration of multiple classifications based on the multiple classifiers have a good effect on the identification of urban buildings, so there is a certain meaning of research.
【學(xué)位授予單位】：北京建筑大學(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8條

1 劉正軍;張繼賢;孟亞賓;梁欣廉;孫曉霞;;基于分類與形態(tài)綜合的高分辨率影像建筑物提取方法研究[J];測(cè)繪科學(xué);2007年03期

2 陳建杰;葉智宣;;多分類SVM主動(dòng)學(xué)習(xí)及其在遙感圖像分類中的應(yīng)用[J];測(cè)繪科學(xué);2009年04期

3 孫灝;杜培軍;趙衛(wèi)常;;基于多分類器組合的高分辨率遙感影像目標(biāo)識(shí)別[J];地理與地理信息科學(xué);2009年01期

4 趙俊娟,尹京苑,單新建;基于高分辨率衛(wèi)星影像的建筑物輪廓矢量化技術(shù)[J];防災(zāi)減災(zāi)工程學(xué)報(bào);2004年02期

5 承德保;;基于多特征組的遙感圖像中建筑物目標(biāo)自動(dòng)識(shí)別與標(biāo)繪的方法[J];電子與信息學(xué)報(bào);2008年12期

6 謝軍飛,李延明;利用IKONOS衛(wèi)星圖像陰影提取城市建筑物高度信息[J];國(guó)土資源遙感;2004年04期

7 周小成;汪小欽;駱劍承;沈占鋒;吳波;;結(jié)合對(duì)象關(guān)系特征的高分辨率衛(wèi)星影像建筑物識(shí)別方法[J];國(guó)土資源遙感;2008年04期

8 王夢(mèng)秋;萬幼川;李剛;;核聚類改進(jìn)的RBF神經(jīng)網(wǎng)絡(luò)遙感影像分類[J];測(cè)繪科學(xué);2014年01期

，

本文編號(hào)：2099070