發(fā)布時(shí)間：2018-06-27 23:20

  本文選題：由運(yùn)動(dòng)恢復(fù)結(jié)構(gòu) + 無(wú)結(jié)構(gòu)影像��； 參考：《中國(guó)測(cè)繪科學(xué)研究院》2017年碩士論文

【摘要】：由運(yùn)動(dòng)恢復(fù)結(jié)構(gòu),即structure from motion是計(jì)算機(jī)視覺(jué)和攝影測(cè)量中的核心問(wèn)題,它是僅僅通過(guò)一組具有重疊度的影像或視頻來(lái)恢復(fù)相機(jī)拍攝瞬間的位置和姿態(tài)同時(shí)獲得場(chǎng)景的稀疏三維結(jié)構(gòu)信息的處理過(guò)程,此過(guò)程的準(zhǔn)確性和有效性將直接影響后續(xù)的密集重建。雖然這個(gè)問(wèn)題在2000年左右整個(gè)流程就基本確定下來(lái),多視圖幾何重建也已被研究多年,但是由于重建過(guò)程中設(shè)置的參數(shù)較多流程較為復(fù)雜,很難找到全局最優(yōu)解,大規(guī)模影像的重建速度依然存在瓶頸,至今國(guó)內(nèi)外依然有較多研究者關(guān)注此問(wèn)題。目前,國(guó)內(nèi)還沒(méi)有一款較為成熟的通用的基于多源影像建模的商業(yè)軟件,國(guó)外商用軟件依然占據(jù)主導(dǎo)地位,基于這些背景,有必要在此基礎(chǔ)上開展基于任意拍攝的無(wú)結(jié)構(gòu)影像的稀疏三維重建算法研究。傳統(tǒng)的攝影測(cè)量中空中三角測(cè)量過(guò)程,相當(dāng)于計(jì)算機(jī)視覺(jué)中的structure from motion需要嚴(yán)格的相機(jī)標(biāo)定參數(shù)和規(guī)則的航帶信息,其過(guò)程是先做單個(gè)模型的相對(duì)定向再進(jìn)行模型間的連接,而且定向都是沿著攝影測(cè)量坐標(biāo)系中的X方向進(jìn)行。然而在計(jì)算機(jī)視覺(jué)領(lǐng)域,拍照的過(guò)程較為隨意,一般也不需要影像的任何先驗(yàn)信息,絕大多數(shù)情況下可以從影像的EXIF信息中估計(jì)相機(jī)的參數(shù),然后再bundle adjustment中進(jìn)行參數(shù)的進(jìn)一步優(yōu)化,此方法對(duì)獲取影像設(shè)備的要求降低,處理過(guò)程中的人工干預(yù)少自動(dòng)化程度較高。所以,針對(duì)當(dāng)前多數(shù)影像,如手機(jī)影像、數(shù)碼相機(jī)影像、甚至互聯(lián)網(wǎng)影像,同時(shí)也包括無(wú)人機(jī)影像和航空影像,有時(shí)存在很難獲取相機(jī)檢校參數(shù)或航帶信息不規(guī)則的情況,采用計(jì)算機(jī)視覺(jué)中的這種方法可以很好的解決這一問(wèn)題�；诖�,本文主要研究?jī)?nèi)容包括:1.系統(tǒng)總結(jié)基于影像重建的基礎(chǔ)理論和算法原理:介紹計(jì)算機(jī)視覺(jué)中經(jīng)典的三種基于影像的重建算法并比較每種算法的優(yōu)缺點(diǎn)和適用條件,歸納出基于影像重建的一般方法和流程,并全面地總結(jié)當(dāng)前國(guó)內(nèi)外最先進(jìn)的幾大商業(yè)軟件和開源軟件的功能和特點(diǎn),在此基礎(chǔ)上概括出基于影像重建的兩大關(guān)鍵問(wèn)題:一是面對(duì)大數(shù)據(jù)量的影像,如何找到這些影像的對(duì)應(yīng)關(guān)聯(lián)信息,即data association,二是采取何種策略來(lái)重建這些影像,不同的策略可能導(dǎo)致不同的結(jié)果。2.詳細(xì)分析了兩張影像到三張影像的重建算法:此過(guò)程對(duì)應(yīng)于攝影測(cè)量中的相對(duì)定向和絕對(duì)定向,分別研究了基于8點(diǎn)法和5點(diǎn)法相對(duì)定向并比較其特點(diǎn),在已知相機(jī)參數(shù)和未知相機(jī)參數(shù)的情況下采取不同的相對(duì)定向算法,并將該算法與RANSAC算法相結(jié)合,獲得魯棒解;并且引入了計(jì)算機(jī)視覺(jué)中一種新型的在已知相機(jī)參數(shù)情況下3點(diǎn)絕對(duì)定向算法,實(shí)驗(yàn)證明此算法簡(jiǎn)便有效,可利用在序列影像重建過(guò)程中。研究一種在匹配幾何約束階段通過(guò)多模型約束來(lái)選取影像對(duì)的最優(yōu)幾何模型,為后續(xù)的重建過(guò)程奠定基礎(chǔ)。3.對(duì)比了三種不同的特征提取算法(SIFT、SURF、ORB)對(duì)像對(duì)運(yùn)動(dòng)恢復(fù)的影響:傳統(tǒng)的基于影像重建大多仍然采用SIFT,由于其穩(wěn)定性和魯棒性,但是SIFT的速度較慢,在影像數(shù)據(jù)量較大和實(shí)時(shí)性方面有所欠缺。本文將另外兩種特征提取算法SURF和ORB應(yīng)用到影像重建中,并在文中詳細(xì)比較了三種算法的性能和對(duì)重建的影響,給出了在保持其重建穩(wěn)定性的情況下提高速度的策略。4.實(shí)現(xiàn)并改進(jìn)了經(jīng)典的漸進(jìn)式序列影像重建算法:利用SIFT和SURF算法分別進(jìn)行特征提取和匹配,在獲得所有影像的匹配信息后,作為整體輸入生成track信息,用指定和自動(dòng)搜索兩種方法找到初始像對(duì),在確定初始像對(duì)之后,用剩余影像和之前像對(duì)有最多2D-3D對(duì)應(yīng)點(diǎn)來(lái)確定下一張影像,每確定一張影像再對(duì)該影像的位姿,即旋轉(zhuǎn)和平移做一次bundle adjustment,然后再根據(jù)設(shè)定的參數(shù)來(lái)確定是否做整體的bundle adjustment,結(jié)果證明此方案可行并達(dá)到預(yù)期效果。提出一種基于特征點(diǎn)分布的影像選取策略,與傳統(tǒng)的基于最多2D-3D特征點(diǎn)數(shù)量的方法相比,可以一定程度上提高重建的精確性和魯棒程度。
[Abstract]:The motion recovery structure, structure from motion, is the core problem in computer vision and photogrammetry. It is the process of recovering the sparse three-dimensional structure information of the scene by only a set of overlapped images or videos to restore the camera's position and posture at the same time. The accuracy and effectiveness of this process will be There is a direct impact on subsequent intensive reconstruction. Although the whole process is basically determined around 2000, multi view geometric reconstruction has been studied for many years. However, it is difficult to find the global optimal solution because of the more complex parameters set in the reconstruction process. The reconstruction speed of the large pattern image still has a bottleneck. There are still many researchers at home and abroad concerned about this problem. At present, there is no more mature commercial software based on multi source image modeling in China. Foreign commercial software still occupies the dominant position. Based on these background, it is necessary to carry out a sparse three-dimensional reconstruction algorithm based on unstructured images based on arbitrary photographing. In the traditional aerial photogrammetry, the process of aerial triangulation is equivalent to the structure from motion in computer vision, which requires strict camera calibration parameters and rules. The process is to make the relative orientation of a single model first and then to connect the model between the models, and the orientation is carried out along the X direction in the photogrammetric coordinate system. However, in the field of computer vision, the process of taking pictures is more random and generally does not need any prior information of the image. In the vast majority of cases, the parameters of the camera can be estimated from the EXIF information of the image, and then the parameters are further optimized in the bundle adjustment. This method reduces the requirements for the acquisition of the image equipment and the process of processing. Therefore, for most of the current images, such as mobile phone images, digital camera images, and even Internet images, including UAV images and aerial images, sometimes it is difficult to obtain camera calibration parameters or aerial information irregularities. This method can be used in computer vision. Based on this, the main contents of this paper include: 1. systematically summarize the basic theory and algorithm principle based on image reconstruction: introduce three classic image based reconstruction algorithms in computer vision and compare the advantages and disadvantages and applicable conditions of each algorithm, and generalize the general methods and processes based on image reconstruction. And summarize the functions and characteristics of the most advanced commercial and open source software at home and abroad. On this basis, we summarize the two key problems based on image reconstruction: first, how to find the corresponding correlation information of these images, that is, data association, and what kind of strategy to reconstruct the image based on the image of large amount of data. Some images, different strategies may lead to different results,.2. detailed analysis of the reconstruction algorithm of two images to three images: this process corresponds to the relative orientation and absolute orientation in photogrammetry, and studies the relative orientation of the 8 point method and the 5 point method, respectively, and compare the characteristics of the camera parameters and the unknown camera parameters. Different relative orientation algorithms are adopted, and the algorithm is combined with the RANSAC algorithm to obtain a robust solution. And a new 3 point absolute orientation algorithm in the case of the known camera parameters in the computer vision is introduced. The experiment proves that the algorithm is simple and effective. In the process of sequence image reconstruction, a kind of matching geometry is studied. In the beam phase, the optimal geometric model of image pair is selected by multiple model constraints, which lays the foundation for the subsequent reconstruction process..3. contrasts the effect of three different feature extraction algorithms (SIFT, SURF, ORB) on motion recovery. The traditional image based reconstruction is still mostly SIFT, because of its stability and robustness, but the speed of SIFT. In this paper, two other feature extraction algorithms, SURF and ORB, are applied to the image reconstruction. In this paper, the performance of the three algorithms and the effect on the reconstruction are compared in detail, and the implementation of the strategy.4. to improve the speed in the condition of maintaining the stability of the reconstruction is also given. The algorithm of the progressive sequence image reconstruction: using SIFT and SURF algorithm for feature extraction and matching respectively. After obtaining the matching information of all the images, the track information is generated as the whole input, and the initial image pairs are found by two methods of designation and automatic search. After the initial image pairs are determined, there are the most 2D-3 with the remaining images and the previous images. The D corresponding point determines the next image, and each image is determined to do a bundle adjustment on the position of the image, that is, rotation and translation, and then determines whether to do the whole bundle adjustment according to the set parameters. The result proves that the scheme is feasible and achieves the expected effect. A image selection based on the distribution of feature points is proposed. Compared with the traditional method based on the number of 2D-3D feature points, the strategy can improve the accuracy and robustness of reconstruction.
【學(xué)位授予單位】：中國(guó)測(cè)繪科學(xué)研究院
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：TP391.41;P23

【相似文獻(xiàn)】

相關(guān)博士學(xué)位論文 前1條

1 陳旺;折反射全向圖像深度信息提取技術(shù)研究[D];國(guó)防科學(xué)技術(shù)大學(xué);2010年

相關(guān)碩士學(xué)位論文 前1條

1 查冰;基于非量測(cè)相機(jī)無(wú)結(jié)構(gòu)影像的運(yùn)動(dòng)估計(jì)算法研究[D];中國(guó)測(cè)繪科學(xué)研究院;2017年

，

本文編號(hào)：2075656