本文選題：車載移動(dòng)測(cè)量系統(tǒng) + 數(shù)據(jù)配準(zhǔn)��； 參考：《武漢大學(xué)》2014年博士論文

【摘要】：車載移動(dòng)測(cè)量系統(tǒng)集成了激光掃描儀、數(shù)碼相機(jī)、GPS、里程計(jì)、慣性測(cè)量單元等多種傳感器,不僅能快速獲取包含物體空間坐標(biāo)信息的激光掃描數(shù)據(jù),還能獲取包含豐富紋理信息的光學(xué)影像,具有數(shù)據(jù)獲取速度快、場(chǎng)景目標(biāo)豐富的特點(diǎn),已成為一種新型、集成、高效的空間信息獲取的技術(shù)手段,廣泛應(yīng)用于地理國(guó)情監(jiān)測(cè)和智慧城市的各項(xiàng)建設(shè)。由于光學(xué)影像和激光掃描數(shù)據(jù)對(duì)目標(biāo)物的描述存在諸多互補(bǔ)性,為了提高城市場(chǎng)景三維可視化效果,需要發(fā)展高效的光學(xué)影像與激光點(diǎn)云的配準(zhǔn)方法。另外,車載移動(dòng)測(cè)量系統(tǒng)獲取的點(diǎn)云數(shù)據(jù)具有海量特性,點(diǎn)云數(shù)據(jù)處理耗時(shí)長(zhǎng)、計(jì)算量大,再加上場(chǎng)景復(fù)雜,不同目標(biāo)分類的自動(dòng)化和智能化程度低,這些問(wèn)題限制了車載移動(dòng)測(cè)量系統(tǒng)在移動(dòng)測(cè)圖、基礎(chǔ)測(cè)繪等應(yīng)用的實(shí)際功效。 本文針對(duì)上述存在的問(wèn)題,重點(diǎn)研究和探討車載激光點(diǎn)云和全景影像的精確配準(zhǔn)方法,以及激光點(diǎn)云的高效分類識(shí)別技術(shù),主要進(jìn)行了以下幾方面的工作： 1.總結(jié)了當(dāng)前國(guó)內(nèi)外車載移動(dòng)測(cè)量系統(tǒng)在光學(xué)影像與激光點(diǎn)云數(shù)據(jù)配準(zhǔn)、車載激光點(diǎn)云分類方面的研究進(jìn)展。對(duì)現(xiàn)有的相關(guān)技術(shù)和研究方法進(jìn)行歸納并分析其優(yōu)缺點(diǎn),針對(duì)現(xiàn)有數(shù)據(jù)配準(zhǔn)及分類中的不足和難點(diǎn),確定了本文的研究目標(biāo)與內(nèi)容。 2.闡述了車載移動(dòng)測(cè)量中的相關(guān)基本原理。包括系統(tǒng)的組成及工作原理,分析了各傳感器間數(shù)據(jù)的流轉(zhuǎn)關(guān)系；介紹了全景影像的成像原理,對(duì)魚(yú)眼鏡頭成像的光學(xué)基礎(chǔ)、成像過(guò)程、魚(yú)眼圖像變形特征及糾正算法進(jìn)行分析；闡述了車載激光掃描儀測(cè)距的原理、方式及其對(duì)三維空間的表征方式。 3.提出了一種基于投影回歸的全景影像采集和激光掃描配準(zhǔn)方法。根據(jù)光路傳播的可逆原理,把魚(yú)眼鏡頭成像理解為一個(gè)以投影中心為光源點(diǎn)的光線發(fā)射過(guò)程,提出通過(guò)把魚(yú)眼鏡頭的光源和激光掃描儀的光源進(jìn)行歸一重合,實(shí)現(xiàn)魚(yú)眼圖像與激光點(diǎn)云配準(zhǔn)的思想,對(duì)投影回歸方法的正確性進(jìn)行了理論證明。結(jié)合具體的實(shí)驗(yàn)數(shù)據(jù),對(duì)魚(yú)眼圖像糾正、配準(zhǔn)、拼接、分割并最終紋理映射成球形全景,對(duì)激光點(diǎn)云數(shù)據(jù)進(jìn)行了配準(zhǔn)、除噪和簡(jiǎn)化處理,并把處理好的點(diǎn)云投影到與球形全景圖共球心的虛擬投影球面上,實(shí)現(xiàn)了全景影像與激光點(diǎn)云的配準(zhǔn)。該配準(zhǔn)方法不受區(qū)域灰度及幾何特征信息的制約。 4.配準(zhǔn)量測(cè)精度的驗(yàn)證研究。在全景影像與激光點(diǎn)云配準(zhǔn)的基礎(chǔ)上,提出了一種采用角度逼近法來(lái)獲取球面投影中距離待測(cè)點(diǎn)最近鄰的激光點(diǎn)的方法,把對(duì)影像上的量測(cè)轉(zhuǎn)換為對(duì)最近鄰激光掃描點(diǎn)坐標(biāo)的查詢與計(jì)算,對(duì)角度逼近法的正確性進(jìn)行了數(shù)學(xué)證明,并針對(duì)不同角度分辨率下激光點(diǎn)云與全景影像的配準(zhǔn)精度進(jìn)行了驗(yàn)證與分析,結(jié)果表明采用投影回歸原理的配準(zhǔn)方法具有較好的精確度。 5.基于知識(shí)與特征圖像的點(diǎn)云分類研究。采用橫軸圓柱投影和正射投影分別生成了點(diǎn)云的空間特征圖像、回波強(qiáng)度圖像和顏色特征圖像,基于知識(shí)和特征圖像對(duì)行道樹(shù)點(diǎn)云提出了分層投影、疊加分析的分類方法,即通過(guò)高程閾值對(duì)樹(shù)干點(diǎn)云和樹(shù)冠點(diǎn)云分別投影,得到相應(yīng)的特征圖像,再根據(jù)灰度值把特征圖像轉(zhuǎn)換成二值圖像,并對(duì)二值圖像進(jìn)行疊加與分析,最后通過(guò)知識(shí)濾波來(lái)提取行道樹(shù)點(diǎn)云數(shù)據(jù)。論文結(jié)合具體數(shù)據(jù)進(jìn)行了分類實(shí)驗(yàn),實(shí)驗(yàn)結(jié)果表明,該方法對(duì)一些混雜在行道樹(shù)的噪聲信息處理的比較好,且該方法把三維點(diǎn)云轉(zhuǎn)化為二值圖像進(jìn)行處理,有效避免了大量的幾何運(yùn)算,顯著降低了分類算法的復(fù)雜度。說(shuō)明采用分層投影、疊加分析的方法對(duì)行道樹(shù)點(diǎn)云提取是行之有效的。 6.基于機(jī)器學(xué)習(xí)的點(diǎn)云分類研究。以激光點(diǎn)云對(duì)象的原始特征為基礎(chǔ),通過(guò)對(duì)其周邊點(diǎn)群的上下文語(yǔ)義環(huán)境進(jìn)行分析,充分利用點(diǎn)云的空間分布特征及其局部幾何特征,歸納計(jì)算了點(diǎn)云對(duì)象的新特征,最終構(gòu)建了由17個(gè)特征組成的點(diǎn)云特征向量。采用支持向量機(jī)和人工神經(jīng)網(wǎng)絡(luò)模型對(duì)行道樹(shù)分類識(shí)別進(jìn)行實(shí)驗(yàn),在支持向量機(jī)分類過(guò)程中,為了提高模型的泛化能力,分別采用粒子群優(yōu)化算法和遺傳算法對(duì)模型參數(shù)進(jìn)行尋優(yōu),分析了不同算法的學(xué)習(xí)曲線特征,最終采用粒子群優(yōu)化算法,針對(duì)不同訓(xùn)練樣本、不同特征向量進(jìn)行了點(diǎn)云分類識(shí)別的系列實(shí)驗(yàn)。論文選取支持向量機(jī)最優(yōu)分類結(jié)果所對(duì)應(yīng)的實(shí)驗(yàn)條件,采用人工神經(jīng)網(wǎng)絡(luò)的方法對(duì)點(diǎn)云分類進(jìn)行實(shí)驗(yàn)對(duì)比驗(yàn)證,兩種方法均取得整體較為滿意的實(shí)驗(yàn)結(jié)果,表明了機(jī)器學(xué)習(xí)方法在車載激光點(diǎn)云自動(dòng)分類中的適用性,為提高車載激光點(diǎn)云分類自動(dòng)化程度和智能化水平提供了新的思路。
[Abstract]:The vehicle mobile measurement system integrates a variety of sensors, such as laser scanner, digital camera, GPS, odometer, inertial measurement unit and so on. It can not only quickly obtain the laser scanning data containing the space coordinate information of the object, but also obtain the optical image containing rich texture information, which has the characteristics of fast data acquisition and rich scene target. As a new, integrated and efficient technology for obtaining spatial information, it is widely used in geographical conditions monitoring and the construction of intelligent cities. The description of objects in the optical image and laser scanning data has many complementarities. In order to improve the effect of the three-dimensional visualization of the city scene, it is necessary to develop high efficient optical images. In addition, the point cloud data obtained by the vehicle mobile measurement system have massive characteristics, the point cloud data processing is time-consuming, the amount of computation is large, the scene is complex, and the automation and intelligence of different target classification are low. These problems restrict the application of mobile measurement system in mobile mapping and basic surveying and mapping. Practical effect.
Aiming at the above problems, this paper focuses on the research and Discussion on the accurate registration method of the vehicle laser point cloud and panoramic image, as well as the efficient classification and recognition technology of the laser point cloud.
1. summarize the research progress of the vehicle mobile measurement system at home and abroad on the registration of optical image and laser point cloud data and the classification of the on-board laser point cloud. The existing related technologies and research methods are summed up and analyzed their advantages and disadvantages. In view of the shortcomings and difficulties of the existing data registration and classification, the research objectives of this paper are determined. And content.
2. the basic principles of the vehicle mobile measurement are described, including the composition and working principle of the system, the flow relationship between the various sensors is analyzed, the imaging principle of the panoramic image is introduced, the optical foundation of the fish eye lens imaging, the imaging process, the distortion characteristic and the correction algorithm of the fish eye image are analyzed, and the vehicular excitation is expounded. The principle and method of optical scanner ranging and its representation of three-dimensional space are discussed.
3. a method of panoramic image acquisition and laser scanning registration based on projection regression is proposed. According to the reversible principle of optical path propagation, the fish eye lens imaging is understood as a light emitting process with the center of projection as the light source. By combining the light source of the fish eye lens and the light source of the laser scavenger, the fish eye is realized. The idea of registration of image and laser point cloud is used to prove the correctness of the projection regression method. Combined with the specific experimental data, the fish eye image is corrected, registered, spliced, segmented and mapped into a spherical panoramic view, and the laser point cloud data are registered, denoising and simplifying, and projecting the treated point clouds to the ball. The registration of the panoramic image with the laser point cloud is realized on the virtual projection sphere of the central panorama. The registration method is not restricted by the information of the gray and geometric features of the region.
4., on the basis of the registration of the panoramic image and the laser point cloud, a method of using angle approximation to obtain the laser point from the nearest neighbor in the spherical projection is proposed, and the measurement of the image is converted to the query and calculation of the coordinates of the nearest neighbor laser scanning point, and the angle approximation method is used. The correctness is proved by mathematics, and the registration accuracy of the laser point cloud and the panoramic image at different angle resolution is verified and analyzed. The results show that the registration method using the projection regression principle has good accuracy.
5. the study of point cloud classification based on knowledge and feature images. Using horizontal cylindrical projection and orthophoto projection, the spatial feature images of point clouds, echo intensity images and color feature images are generated respectively. Based on knowledge and feature images, the hierarchical projection of the road tree point cloud is put forward, and the superposition classification method is used, that is, to the tree trunk through the elevation threshold. The point cloud and the crown point cloud are projected separately, and the corresponding feature images are obtained. Then the feature images are converted into two value images according to the gray value, and the two value images are superimposed and analyzed. Finally, the data of the street tree point clouds are extracted by the knowledge filtering. The paper is classified by the concrete data. The experimental results show that the method is mixed with some of the data. The noise information processing of the miscellaneous tree is better, and this method transforms the three dimensional point cloud into two value images, which effectively avoids a large number of geometric operations and significantly reduces the complexity of the classification algorithm. It is proved that the method of stratified projection and superposition analysis is effective for the extraction of the road tree point cloud.
6. based on the point cloud classification based on machine learning. Based on the original features of the laser point cloud objects, the context semantic environment of the surrounding point groups is analyzed. The spatial distribution features and local geometric features of the point clouds are fully utilized and the new characteristics of the point cloud objects are summed and calculated. Finally, a point cloud consisting of 17 features is constructed. In order to improve the generalization ability of the model, in order to improve the generalization ability of the model, the particle swarm optimization algorithm and genetic algorithm are used to optimize the model parameters, and the characteristics of the learning curve of different algorithms are analyzed. Finally, the characteristics of the learning curve of different algorithms are analyzed. The particle swarm optimization algorithm is used to carry out a series of experiments on the classification of point clouds for different training samples and different eigenvectors. The paper selects the experimental conditions corresponding to the optimal classification results of support vector machines, and uses artificial neural network to test the point cloud classification by experiment. The two methods have obtained the whole more satisfactory experiment. The result shows the applicability of machine learning method in automatic classification of vehicle laser point cloud, which provides a new idea for improving the automation and intelligence level of vehicle laser point cloud classification.
【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】：2014
【分類號(hào)】：P208;P234;TP391.41

【相似文獻(xiàn)】

相關(guān)期刊論文 前10條

1 高恩陽(yáng);鄭昊鴻;;點(diǎn)云數(shù)據(jù)濾波方法綜述[J];科技資訊;2012年33期

2 龔書(shū)林;;三維激光點(diǎn)云處理軟件的若干關(guān)鍵技術(shù)[J];測(cè)繪通報(bào);2014年06期

3 趙強(qiáng);彭國(guó)華;王鋒;;點(diǎn)云精簡(jiǎn)的一種方法[J];西南民族大學(xué)學(xué)報(bào)(自然科學(xué)版);2006年05期

4 李德江;張延波;于曼竹;姜麗麗;曲雪光;;基于掃描模式的點(diǎn)云修復(fù)技術(shù)研究[J];測(cè)繪與空間地理信息;2011年06期

5 蔡來(lái)良;李儒;;點(diǎn)云數(shù)據(jù)處理算法與實(shí)現(xiàn)初步研究[J];測(cè)繪通報(bào);2012年S1期

6 詹慶明;張海濤;喻亮;;古建筑激光點(diǎn)云-模型多層次一體化數(shù)據(jù)模型[J];地理信息世界;2010年04期

7 曾敬文;朱照榮;丁銳;;基于立方體網(wǎng)格的數(shù)據(jù)點(diǎn)云約簡(jiǎn)和體積計(jì)算方法[J];測(cè)繪科學(xué);2008年06期

8 楊欣;姚海燕;;平面點(diǎn)云邊界參數(shù)識(shí)別[J];中國(guó)西部科技;2009年27期

9 孫瑞;張彩霞;;點(diǎn)云數(shù)據(jù)壓縮算法綜述[J];科技信息;2010年32期

10 張毅;閆利;;地面激光點(diǎn)云強(qiáng)度噪聲的三維擴(kuò)散濾波方法[J];測(cè)繪學(xué)報(bào);2013年04期

相關(guān)會(huì)議論文 前10條

1 李文濤;韋群;楊海龍;;基于圖像的點(diǎn)云生成和預(yù)處理[A];2011年全國(guó)通信安全學(xué)術(shù)會(huì)議論文集[C];2011年

2 蔡來(lái)良;李儒;;點(diǎn)云數(shù)據(jù)處理算法與實(shí)現(xiàn)初步研究[A];第四屆“測(cè)繪科學(xué)前沿技術(shù)論壇”論文精選[C];2012年

3 馬國(guó)慶;陶萍萍;楊周旺;;點(diǎn)云空間曲線的微分信息計(jì)算及匹配方法[A];第四屆全國(guó)幾何設(shè)計(jì)與計(jì)算學(xué)術(shù)會(huì)議論文集[C];2009年

4 江倩殷;劉忠途;李熙瑩;;一種有效的點(diǎn)云精簡(jiǎn)算法[A];第十五屆全國(guó)圖象圖形學(xué)學(xué)術(shù)會(huì)議論文集[C];2010年

5 解輝;張愛(ài)武;孟憲剛;;機(jī)載激光點(diǎn)云快速繪制方法[A];第二十五屆全國(guó)空間探測(cè)學(xué)術(shù)研討會(huì)摘要集[C];2012年

6 李凱;張愛(ài)武;;基于激光點(diǎn)云的糧倉(cāng)儲(chǔ)糧數(shù)量測(cè)量方法[A];第二屆“測(cè)繪科學(xué)前沿技術(shù)論壇”論文精選[C];2010年

7 朱曉強(qiáng);余燁;劉曉平;袁曉輝;Bill P.Buckles;;基于航拍圖像和LiDAR點(diǎn)云的城市道路提取[A];全國(guó)第19屆計(jì)算機(jī)技術(shù)與應(yīng)用（CACIS）學(xué)術(shù)會(huì)議論文集（上冊(cè)）[C];2008年

8 劉虎;;基于線性八叉樹(shù)的點(diǎn)云簡(jiǎn)化與特征提取研究[A];促進(jìn)科技經(jīng)濟(jì)結(jié)合，服務(wù)創(chuàng)新驅(qū)動(dòng)發(fā)展——蚌埠市科協(xié)2012年度學(xué)術(shù)年會(huì)論文集[C];2012年

9 李濱;王佳;;基于點(diǎn)云的建筑測(cè)繪信息提取[A];第四屆“測(cè)繪科學(xué)前沿技術(shù)論壇”論文精選[C];2012年

10 楊雪春;;反求工程建模中點(diǎn)云切片技術(shù)研究[A];全國(guó)先進(jìn)制造技術(shù)高層論壇暨第八屆制造業(yè)自動(dòng)化與信息化技術(shù)研討會(huì)論文集[C];2009年

相關(guān)重要報(bào)紙文章 前2條

1 曹裕華 高化猛 江鴻賓;激光點(diǎn)云 亦真亦幻[N];解放軍報(bào);2013年

2 中國(guó)工程院院士 劉先林;四維遠(yuǎn)見(jiàn)的裝備創(chuàng)新[N];中國(guó)測(cè)繪報(bào);2012年

相關(guān)博士學(xué)位論文 前10條

1 彭檢貴;融合點(diǎn)云與高分辨率影像的城區(qū)道路提取與表面重建研究[D];武漢大學(xué);2012年

2 劉涌;基于連續(xù)序列自動(dòng)快速拼接的全方位三維測(cè)量技術(shù)研究[D];西南交通大學(xué);2013年

3 賴祖龍;基于LiDAR點(diǎn)云與影像的海岸線提取和地物分類研究[D];武漢大學(xué);2013年

4 王瑞巖;計(jì)算機(jī)視覺(jué)中相機(jī)標(biāo)定及點(diǎn)云配準(zhǔn)技術(shù)研究[D];西安電子科技大學(xué);2015年

5 段敏燕;機(jī)載激光雷達(dá)點(diǎn)云電力線三維重建方法研究[D];武漢大學(xué);2015年

6 李艷紅;車載移動(dòng)測(cè)量系統(tǒng)數(shù)據(jù)配準(zhǔn)與分類識(shí)別關(guān)鍵技術(shù)研究[D];武漢大學(xué);2014年

7 韓峰;基于點(diǎn)云信息的既有鐵路狀態(tài)檢測(cè)與評(píng)估技術(shù)研究[D];西南交通大學(xué);2015年

8 金龍存;3D點(diǎn)云復(fù)雜曲面重構(gòu)關(guān)鍵算法研究[D];上海大學(xué);2012年

9 李揚(yáng)彥;基于點(diǎn)云的三維重建與形變事件分析[D];中國(guó)科學(xué)院深圳先進(jìn)技術(shù)研究院;2013年

10 楊德賀;面向虛擬測(cè)方系統(tǒng)的點(diǎn)云聚類與擬合理論[D];中國(guó)礦業(yè)大學(xué)（北京）;2014年

相關(guān)碩士學(xué)位論文 前10條

1 龔碩然;基于Delaunay三角剖分的點(diǎn)云三維網(wǎng)格重構(gòu)[D];河北大學(xué);2015年

2 楊紅粉;頻域技術(shù)應(yīng)用于點(diǎn)云配準(zhǔn)研究[D];北京建筑大學(xué);2015年

3 段紅娟;點(diǎn)云圖像交互式曲線骨架提取技術(shù)及其應(yīng)用[D];西南交通大學(xué);2015年

4 張永恒;散亂點(diǎn)云數(shù)據(jù)配準(zhǔn)方法研究[D];長(zhǎng)安大學(xué);2015年

5 吳愛(ài);面向特征擬合的點(diǎn)云簡(jiǎn)化方法研究[D];中國(guó)地質(zhì)大學(xué)(北京);2015年

6 薛廣順;基于立體視覺(jué)的牛體點(diǎn)云獲取方法研究與實(shí)現(xiàn)[D];西北農(nóng)林科技大學(xué);2015年

7 胡誠(chéng);精度約束下地表LiDAR點(diǎn)云抽稀方法研究[D];西南交通大學(xué);2015年

8 余明;三維離散點(diǎn)云數(shù)據(jù)處理技術(shù)研究[D];南京理工大學(xué);2015年

9 陳星宇;基于三維彩色點(diǎn)云的地形分類方法研究[D];南京理工大學(xué);2015年

10 朱東方;基于復(fù)雜拓?fù)浣Y(jié)構(gòu)點(diǎn)云的曲線擬合研究與應(yīng)用[D];山東大學(xué);2015年

，

本文編號(hào)：2054805