本文選題：機(jī)載激光掃描　切入點(diǎn)：建筑物提取　出處：《武漢大學(xué)》2013年博士論文

【摘要】：經(jīng)過近二十多年的發(fā)展,機(jī)載激光掃描系統(tǒng)(Airborne laser scanning system, ALS)已經(jīng)從最初的實(shí)驗(yàn)室研究階段發(fā)展成為成熟的商業(yè)產(chǎn)品,具備數(shù)據(jù)采集速度快、處理周期短、高精度、高密度、獲取成本較低等優(yōu)點(diǎn),能夠直接、快速的采集大面積區(qū)域的空間三維信息,正日益成為空間數(shù)據(jù)采集技術(shù)的一個(gè)新的發(fā)展方向。機(jī)載激光掃描數(shù)據(jù)被廣泛的應(yīng)用于3D城市建模、電力線走廊三維制圖、數(shù)字高程模型生成、植被檢測以及環(huán)境研究等領(lǐng)域。建筑物作為人們生活和工作的重要場所,是城市空間中的重要實(shí)體,其位置邊界信息是地籍圖生成、建筑物三維重建、地圖更新以及變形監(jiān)測等應(yīng)用方面的寶貴數(shù)據(jù)源。因此,研究機(jī)載激光掃描數(shù)據(jù)中的建筑物目標(biāo)提取具有非常重要的意義。 從機(jī)載激光掃描數(shù)據(jù)中提取建筑物目標(biāo)一直是攝影測量與遙感、計(jì)算機(jī)視覺等領(lǐng)域的研究熱點(diǎn)。近年來,國內(nèi)外對基于機(jī)載激光掃描數(shù)據(jù)的建筑物目標(biāo)提取進(jìn)行了廣泛的研究。但是由于建筑物及其周圍地形的多樣性和復(fù)雜性,使建筑物的提取具有較多的困難,至今還沒有一種適用于任何數(shù)據(jù)質(zhì)量以及任何場景的建筑物提取方法。同時(shí)由于機(jī)載激光掃描數(shù)據(jù)具有離散隨機(jī)性以及分布不均勻性等特性,對建筑物的提取也帶來了一定的困難。針對上述問題,本文研究了利用標(biāo)記點(diǎn)過程從機(jī)載激光掃描數(shù)據(jù)中直接提取建筑物的方法。該方法是一種基于目標(biāo)的、穩(wěn)健的且能準(zhǔn)確從點(diǎn)云數(shù)據(jù)中提取建筑物目標(biāo)的方法。該方法首先構(gòu)建出面向建筑物提取的Gibbs能量模型,然后對該能量模型進(jìn)行優(yōu)化求解以獲取初步的建筑物區(qū)域,最后對初步獲取的建筑物區(qū)域進(jìn)行精細(xì)處理,從而得到精確的建筑物輪廓。本文的主要研究內(nèi)容如下： 1、介紹了本文的研究背景和意義以及機(jī)載激光掃描系統(tǒng)及其應(yīng)用。針對機(jī)載激光掃描數(shù)據(jù)的特點(diǎn)以及目前建筑物提取的難點(diǎn),提出了本文的研究目標(biāo)。針對機(jī)載激光掃描數(shù)據(jù)中建筑物目標(biāo)的提取以及標(biāo)記點(diǎn)過程方法用于幾何目標(biāo)提取這兩個(gè)方面的研究現(xiàn)狀進(jìn)行了綜述,總結(jié)了目前從機(jī)載激光掃描數(shù)據(jù)中進(jìn)行建筑物目標(biāo)提取的難點(diǎn)和不足及其可能的發(fā)展趨勢。 2、介紹了利用標(biāo)記點(diǎn)過程方法進(jìn)行幾何目標(biāo)提取的研究背景,并簡要敘述了點(diǎn)過程和標(biāo)記點(diǎn)過程的理論。根據(jù)建筑物在機(jī)載激光掃描數(shù)據(jù)中的幾何形狀特點(diǎn),確定了將長方體作為建筑物的幾何標(biāo)記模型。根據(jù)建筑物在散亂點(diǎn)云中的結(jié)構(gòu)特征以及建筑物目標(biāo)之間的相互關(guān)系構(gòu)建了能直接從點(diǎn)云數(shù)據(jù)中提取建筑物目標(biāo)的Gibbs能量模型,有效的將建筑物目標(biāo)的空間信息和空間關(guān)系引入到新構(gòu)建的Gibbs能量模型中,為建筑物目標(biāo)的準(zhǔn)確提取奠定了基礎(chǔ)。 3、針對構(gòu)建出的Gibbs能量模型的函數(shù)屬于非線性函數(shù),難以從理論上進(jìn)行分析并獲取對應(yīng)的解析解的情況,本文采用RJMCMC方法與模擬退火算法相結(jié)合的方法獲取Gibbs能量模型的全局最優(yōu)解。雖然該求解方法能夠從任何的初始狀態(tài)下收斂到全局最優(yōu)解,但運(yùn)行效率卻比較低,故本文對該求解方法進(jìn)行了優(yōu)化,以有效的提高算法的運(yùn)行效率,節(jié)省運(yùn)行時(shí)間。 4、求解Gibbs能量模型后可以初步的獲取建筑物區(qū)域。但是這些區(qū)域的邊界可能并不精確,也不完整,同一個(gè)建筑物可能由多個(gè)區(qū)域構(gòu)成,同時(shí)其中也可能存在一些錯(cuò)誤提取的區(qū)域。因此本文對初步獲取的建筑物區(qū)域進(jìn)行精細(xì)化處理。利用建筑物目標(biāo)的幾何屬性特征結(jié)合區(qū)域生長算法剔除錯(cuò)誤提取的地面點(diǎn)、樹冠點(diǎn)、噪聲點(diǎn)以及樹冠等非建筑物目標(biāo)；然后對鄰接區(qū)域進(jìn)行合并并利用改進(jìn)的凸包算法求取每個(gè)建筑物目標(biāo)的精確輪廓。 5、采用ISPRS機(jī)構(gòu)提供的基準(zhǔn)測試數(shù)據(jù)驗(yàn)證本文提出的算法的準(zhǔn)確性和有效性。對本文提出的算法中用到的參數(shù)進(jìn)行分析和探討,并對實(shí)驗(yàn)結(jié)果進(jìn)行精度評價(jià)與分析。最后以F1Measure作為度量建筑物目標(biāo)提取的精度評價(jià)標(biāo)準(zhǔn),將本文提出的方法與其它的建筑物提取方法進(jìn)行比較。詳盡的實(shí)驗(yàn)結(jié)果及其評價(jià)數(shù)據(jù)證明了本文提出的算法的準(zhǔn)確性和有效性。
[Abstract]:After nearly more than 20 years of development, the airborne laser scanning system (Airborne laser scanning system, ALS) from the initial stage of the development of laboratory research into a mature commercial product, with fast data sampling, short treatment period, high precision, high density, low cost to obtain advantages, direct, three-dimensional information acquisition in large area the regional fast, has become a new development direction of spatial data acquisition technology. Airborne laser scanning data is widely used in the 3D city power line corridor modeling, 3D drawing, digital elevation model generation, field detection of vegetation and environmental research. The building as an important place for people to live and work, is an important entity in the city space, the location of the boundary information is the cadastral map generation, three-dimensional reconstruction of the building, the number of valuable map updates and deformation monitoring applications Therefore, it is very important to study the extraction of building targets in the airborne laser scanning data.
The target of building extraction from airborne laser scanning data is photogrammetry and remote sensing, research hotspot in the field of computer vision. In recent years, domestic and foreign to the airborne laser scanning data of buildings based on target extraction has been extensively studied. But because the buildings and the surrounding terrain for the diversity and complexity of the building extraction has more the difficulties, there is not an applicable to any data quality as well as building any scene extraction methods. At the same time as the airborne laser scanning data has the characteristics such as uneven distribution of discrete random and extraction of buildings, also brought some difficulties. To solve the above problems, this paper studies the marked point process method of direct extraction of buildings from airborne laser scanning data. This method is based on the target, robust and accurate from the point cloud data Method for extracting building targets. Firstly, construct the Gibbs energy model to building extraction, then the energy model is optimized to obtain the initial building area, and finally obtain preliminary fine processing on building area, to obtain accurate outline of buildings. The main contents of this paper are as follows:
1, introduces the research background and the significance as well as the airborne laser scanning system and its application. According to the characteristics of airborne laser scanning data and the current difficulties of building extraction, put forward the research goal of this paper. Point extraction and marking for the building by airborne laser scanning data process method for target geometric object extraction research status of the two the paper summarized, summed up the current from airborne laser scanning data were extracted and difficult building problems and the possible development trend.
2, introduces the research background of geometric object extraction using marked point process, and a brief description of the process and the marked point process theory. According to the geometry characteristics of the building in the airborne laser scanning data, determine the cuboid as geometric marking model. According to the building the relationship between structural features in the scattered the point cloud and the building constructed Gibbs model can extract building energy directly from the point cloud data, the spatial information and spatial relationship building is introduced into the Gibbs model in the construction of the new energy, laid the foundation for building the accurate extraction of target.
3, according to the function of the Gibbs energy model constructed belongs to nonlinear function, it is difficult to analyze from the theoretical analysis and obtain the corresponding solution, the global optimal method using RJMCMC method and simulated annealing algorithm for Gibbs energy model solution. Although this method can solve the convergence from the initial state to any the global optimal solution, but the efficiency is relatively low, so this paper optimizes the method, in order to effectively improve the efficiency of the algorithm, save the operation time.
4, to solve the Gibbs energy model can obtain building preliminary. But these boundaries may not be accurate, is not complete, the same building may consist of multiple regions, which may have some error extraction area. So this paper gets preliminary refinement of geometric properties of building area. The building features by combining region growing algorithm to eliminate the errors from the ground point, crown point, noise and other non target crown buildings; then the adjacent regions are merged and obtain the precise outline of each building by using improved convex hull algorithm.
5, the accuracy of benchmark data validation using ISPRS offers and effectiveness of the algorithm proposed. To analyze and discuss the parameters used in the proposed algorithm, and the accuracy evaluation and analysis of the experimental results. Finally, using F1Measure as the measure of building the target extraction accuracy evaluation standards and methods will be presented in this paper and other building extraction methods were compared. The experimental results detailed proved the accuracy of the proposed algorithms and the effectiveness and evaluation of the data.

【學(xué)位授予單位】：武漢大學(xué)
【學(xué)位級(jí)別】：博士
【學(xué)位授予年份】：2013
【分類號(hào)】：TU19;P225.2

【參考文獻(xiàn)】

相關(guān)期刊論文 前8條

1 尤紅建,蘇林;基于機(jī)載激光掃描數(shù)據(jù)提取建筑物的研究現(xiàn)狀[J];測繪科學(xué);2005年05期

2 程亮;龔健雅;李滿春;劉永學(xué);宋小剛;;集成多視航空影像與LiDAR數(shù)據(jù)重建3維建筑物模型[J];測繪學(xué)報(bào);2009年06期

3 劉純平,劉偉強(qiáng),孔玲,夏德深;一種新的基于Dempster-Shafer理論的自適應(yīng)遙感分類融合方法[J];國土資源遙感;2002年03期

4 徐文學(xué);楊必勝;魏征;方莉娜;;多標(biāo)記點(diǎn)過程的LiDAR點(diǎn)云數(shù)據(jù)建筑物和樹冠提取[J];測繪學(xué)報(bào);2013年01期

5 朱萍萍;楊艷飛;許捍衛(wèi);;基于LIDAR數(shù)據(jù)的建筑物提取和三維重建的研究進(jìn)展[J];現(xiàn)代測繪;2007年04期

6 李云帆;馬洪超;;從LiDAR數(shù)據(jù)中提取建筑物平面目標(biāo)的新方法[J];計(jì)算機(jī)工程與應(yīng)用;2011年10期

7 Bradley Efron ,朱鈺,謝愛輝,郭曉燁;貝葉斯學(xué)派統(tǒng)計(jì)學(xué)家,頻率學(xué)派統(tǒng)計(jì)學(xué)家和科學(xué)家[J];統(tǒng)計(jì)與信息論壇;2005年04期

8 沈蔚;李京;陳云浩;鄧?yán)?彭光雄;;基于LIDAR數(shù)據(jù)的建筑輪廓線提取及規(guī)則化算法研究[J];遙感學(xué)報(bào);2008年05期

相關(guān)博士學(xué)位論文 前10條

1 羅伊萍;LIDAR數(shù)據(jù)濾波和影像輔助提取建筑物[D];解放軍信息工程大學(xué);2010年

2 鄭毅;LIDAR數(shù)據(jù)的城區(qū)建筑物提取技術(shù)研究[D];華中科技大學(xué);2011年

3 孫開瓊;血管造影圖像分割[D];華中科技大學(xué);2008年

4 趙凌君;高分辨率SAR圖像建筑物提取方法研究[D];國防科學(xué)技術(shù)大學(xué);2009年

5 曾齊紅;機(jī)載激光雷達(dá)點(diǎn)云數(shù)據(jù)處理與建筑物三維重建[D];上海大學(xué);2009年

6 王刃;機(jī)載LIDAR數(shù)據(jù)濾波與建筑物提取技術(shù)研究[D];解放軍信息工程大學(xué);2008年

7 任自珍;基于等高線特征分析的LiDAR建筑物與道路提取[D];西南交通大學(xué);2009年

8 張志超;融合機(jī)載與地面LIDAR數(shù)據(jù)的建筑物三維重建研究[D];武漢大學(xué);2010年

9 黃銳;圖像線結(jié)構(gòu)提取與區(qū)域分割方法研究[D];華中科技大學(xué);2010年

10 魏征;車載LiDAR點(diǎn)云中建筑物的自動(dòng)識(shí)別與立面幾何重建[D];武漢大學(xué);2012年

，

本文編號(hào)：1693649