本文選題：傾斜影像 + 特征提取　； 參考：《武漢大學(xué)》2014年博士論文

【摘要】：中高空航空攝影由于航飛高度大和固定的空間拍攝姿態(tài)(垂直或者小角度攝影)的原因,僅僅能獲取建筑物的低分辨率紋理和頂部紋理信息,難以滿足城市建筑物三維模型對紋理的要求。而低空無人機(jī)結(jié)合新近發(fā)展的多傳感器集成技術(shù),具有靈活、快速、分辨率高的優(yōu)點(diǎn),將其用來采集城市建筑物三維模型信息,可以滿足城市建筑物三維模型構(gòu)建的需求。但是,從目前市場和科研單位的成果上來看,三維景觀模型生產(chǎn)效率低且粗糙,難以滿足實(shí)際的用戶需求。在低空多傳感器影像上,一個物方點(diǎn)可同時成像于多張影像上,因此,這是一個數(shù)據(jù)“又多又少”的矛盾。一方面,多角度影像重疊度高,冗余信息大；另一方面,影像實(shí)際利用率低,生產(chǎn)的三維模型粗糙,無法滿足用戶需求。本論文從實(shí)際生產(chǎn)出發(fā),設(shè)計出一套利用低空傾斜影像特征信息提取,引導(dǎo)密集匹配生成景觀三維模型的技術(shù)路線。 論文完成的研究內(nèi)容如下： 對傾斜攝影技術(shù)的基本原理進(jìn)行說明,分析了傾斜影像立體匹配存在的難點(diǎn)；然后,對現(xiàn)有匹配模型進(jìn)行系統(tǒng)分析、總結(jié)和分類；總結(jié)了現(xiàn)有的基于像方的特征角點(diǎn)檢測算子、描述子和基于物方的立體匹配算法；對通用的匹配技術(shù)和約束方法進(jìn)行歸納和總結(jié)。 對射影變換群下的射影變換、仿射變換、相似變換幾何特點(diǎn)進(jìn)行系統(tǒng)總結(jié)；總結(jié)了各個變換的不變量和變換之間的自由度；從理論上推導(dǎo)了由仿射性質(zhì)恢復(fù)度量性質(zhì)的條件和將射影變形近似為仿射變形的條件,總結(jié)和歸納了常用的仿射不變量。針對城市地區(qū)低空傾斜影像幾何變形大、視差斷裂、高程不平滑的特點(diǎn),提出了一種基于三階矩陣的仿射不變特征提取算法,用于克服仿射變形提取影像中的不變特征,通過3組不同的影像類型進(jìn)行實(shí)驗(yàn),驗(yàn)證了算法的效果。 針對低空傾斜影像重疊度大、冗余信息多的特點(diǎn),從理論上分析了在匹配中篩選影像的必要性和可行性。針對多視影像,提出了一種多通道二進(jìn)制評價模型用于在匹配的過程中實(shí)時的篩選影像,對局部影像的質(zhì)量進(jìn)行分析和排序,尋找最佳匹配像對,優(yōu)化多片匹配模型的性能,篩選出“少而精”的影像對完成匹配的流程。 針對城市地區(qū)建筑物影像存在視差斷裂的特點(diǎn),提出了一種由特征信息引導(dǎo)的自適應(yīng)物方面元傳播密集匹配算法,算法根據(jù)窗口范圍內(nèi)特征的視差邊界自適應(yīng)的調(diào)整面元大小,使面元在傳播的過程中不越過視差邊界,并且在平滑的表面面元面積擴(kuò)大,在地勢起伏變化的表面,面元變小,提高了算法的匹配效率。生成精確、可靠的三維點(diǎn)云模型。 總結(jié)了地形場景海量點(diǎn)云數(shù)據(jù)下Delaunay構(gòu)網(wǎng)算法的思路,基于目前大數(shù)據(jù)量構(gòu)網(wǎng)普遍遇到的內(nèi)存不足、CPU核心利用率低的情況,提出了一種基于并行多核心平臺的算法,算法將OpenMP多線程編程技術(shù),與流數(shù)據(jù)的并行構(gòu)網(wǎng)相結(jié)合,并實(shí)時的釋放運(yùn)行內(nèi)存,取得了不錯的效果。 實(shí)驗(yàn)基于標(biāo)準(zhǔn)航空影像和1+4傾斜影像兩組數(shù)據(jù),從視覺檢測和定量評價兩個方面來驗(yàn)證本文方案的實(shí)際效果。
[Abstract]:The high altitude aerial photography can only obtain the low resolution texture and the top texture information of the building because of the high flying altitude and the fixed space shooting attitude (vertical or small angle photography). It is difficult to meet the requirement of the three-dimensional model of the city building to the texture. The low altitude unmanned aerial vehicle combined with the newly developed multi-sensor integration technology. With the advantages of flexible, rapid and high resolution, it can be used to collect three-dimensional model information of urban buildings, which can meet the needs of building three-dimensional model of urban buildings. However, from the results of current market and scientific research units, the production efficiency of 3D landscape model is low and rough, and it is difficult to meet the needs of actual users. On the image of the sensor, one object point can be simultaneously imaging on multiple image images. Therefore, this is a contradiction of "more and less" data. On the one hand, the multi angle image overlaps high and the redundant information is large; on the other hand, the actual utilization rate of the image is low and the production of the 3D model is rough, which can not meet the needs of the users. A technical route of extracting low altitude tilted image feature information and guiding dense matching to generate 3D landscape model is worked out.
The contents of the thesis are as follows:
The basic principle of tilt photography is explained, and the difficulties in the stereo matching are analyzed. Then, the existing matching model is systematically analyzed, summarized and classified, and the existing feature corner detection operators based on the image square, the descriptor and the stereo matching algorithm based on the object are summarized. Constraint methods are summed up and summarized.
The geometric characteristics of projective transformation, affine transformation and similar transformation under the projective transformation group are systematically summarized, and the degrees of freedom between the invariants of each transformation and the transformation are summarized, and the conditions for restoring the metric properties from the affine properties and the conditions for the approximation of the projective deformation to be similar to the imitating deformation are derived from the theory, and the commonly used ones are summarized and summarized. An affine invariant. In view of the characteristics of the large geometric distortion of the low altitude tilt image in the urban area, the parallax fault and the elevation is not smooth, an affine invariant feature extraction algorithm based on the three order matrix is proposed to overcome the invariant features extracted from the affine deformation, and the experiment is carried out through 3 different types of image types to verify the effectiveness of the algorithm.
In view of the characteristics of low altitude tilt image overlapping and redundant information, the necessity and feasibility of screening images in matching are analyzed theoretically. A multi-channel binary evaluation model is proposed for real-time screening images in the matching process for multi view images, and the quality of local images is analyzed and sorted. The best match image pairs optimize the performance of the multi slice matching model, and select the "less" and "fine" images to complete the matching process.
In view of the characteristics of disparity in the image of buildings in urban areas, an adaptive element propagation dense matching algorithm is proposed, which is guided by feature information. The algorithm adaptively adjusts the size of the surface element according to the parallax boundary of the features within the window range, so that the surface element does not cross the parallax boundary in the propagation path and is smooth in the table. The area of the surface element is enlarged, and the surface element becomes smaller on the fluctuating surface, which improves the matching efficiency of the algorithm, and generates an accurate and reliable three-dimensional point cloud model.
This paper summarizes the idea of Delaunay network algorithm based on massive point cloud data of terrain scene. Based on the lack of memory and low utilization of CPU core, an algorithm based on parallel multi core platform is proposed. The algorithm combines OpenMP multithread programming technique with parallel network of stream data, and real-time The release of running memory has achieved good results.
The experiment is based on two sets of data of standard aerial image and 1+4 tilt image, and verifies the actual effect of the scheme from two aspects: visual inspection and quantitative evaluation.

【學(xué)位授予單位】：武漢大學(xué)
【學(xué)位級別】：博士
【學(xué)位授予年份】：2014
【分類號】：P231

【相似文獻(xiàn)】

相關(guān)期刊論文 前10條

1 鐘紹湘;王少新;;用源面元計算任意維物體的勢流場[J];大連大學(xué)學(xué)報;1992年01期

2 楊臣明;;面元細(xì)分技術(shù)淺析[J];科技信息;2013年01期

3 姬金祖;劉戰(zhàn)合;;基于面元分組的電磁遮擋算法及其優(yōu)化[J];北京航空航天大學(xué)學(xué)報;2009年04期

4 于世煥;趙殿棟;李鈺;趙文芳;宋桂橋;;觀測系統(tǒng)面元細(xì)分問題分析[J];石油物探;2010年06期

5 W.R.Cotton;傅岳;呂學(xué)謙;;三維海上測量中道面元劃分的現(xiàn)實(shí)性[J];國外油氣勘探;1985年03期

6 溫建緒;;小面元三維地震勘探技術(shù)在西山屯蘭礦南五采區(qū)的應(yīng)用[J];中國煤炭地質(zhì);2008年06期

7 狄?guī)妥?熊金良;岳英;魏建新;薛廣建;顧培成;;面元大小對地震成像分辨率的影響分析[J];石油地球物理勘探;2006年04期

8 宋長愿;段建華;費(fèi)明澤;溫建緒;;小面元采集三維地震勘探技術(shù)應(yīng)用初探[J];中國煤田地質(zhì);2007年S2期

9 李崇榮，李衍達(dá)，，榮志鵬;自適應(yīng)傾斜面元疊加[J];清華大學(xué)學(xué)報(自然科學(xué)版);1995年04期

10 趙生斌;可分面元三維觀測系統(tǒng)設(shè)計研究[J];石油地球物理勘探;2000年03期

相關(guān)會議論文 前6條

1 陳世軍;劉洪雷;黃雪繼;譚未一;袁紅軍;苑書金;;高精度可變面元三維地震勘探技術(shù)在松南探區(qū)的實(shí)踐[A];中國地球物理·2009[C];2009年

2 李景葉;陳小宏;;時移地震面元重置處理與質(zhì)量監(jiān)控[A];中國地球物理學(xué)會第二十三屆年會論文集[C];2007年

3 李立誠;夏代學(xué);陳振聲;;大面元三維地震勘探技術(shù)在準(zhǔn)噶爾盆地的應(yīng)用[A];1997年中國地球物理學(xué)會第十三屆學(xué)術(shù)年會論文集[C];1997年

4 張軍華;鄭旭剛;單聯(lián)瑜;徐輝;于海鋮;;面元細(xì)分與信噪比關(guān)系定量研究[A];中國地球物理學(xué)會第二十四屆年會論文集[C];2008年

5 鄧小環(huán);應(yīng)秀梅;劉浩宇;田歌;;基于界面元原理的復(fù)合材料拉伸數(shù)值模擬[A];北京力學(xué)會第18屆學(xué)術(shù)年會論文集[C];2012年

6 何光勤;楊蕾;;基于面元模型的PBN程序三維保護(hù)區(qū)算法研究[A];探索 創(chuàng)新 交流——第五屆中國航空學(xué)會青年科技論壇文集(第5集)[C];2012年

相關(guān)博士學(xué)位論文 前3條

1 李堅;基于三階矩和自適應(yīng)物方面元傳播的傾斜影像匹配研究[D];武漢大學(xué);2014年

2 豐彪;面向?qū)ο蟮慕缑嬖椒捌渑c有限元的時域耦合分析模型[D];中國地震局工程力學(xué)研究所;2012年

3 方錫武;一類界面元建模與分析方法及其在裝備設(shè)計中的應(yīng)用研究[D];浙江大學(xué);2013年

相關(guān)碩士學(xué)位論文 前2條

1 鄧晶;基于三角形面元分割法的地球同步衛(wèi)星光學(xué)特性研究[D];杭州電子科技大學(xué);2015年

2 朱煥;高精度地震資料面元細(xì)分方法與評價技術(shù)研究[D];中國石油大學(xué);2009年

本文編號：1818337