本文關(guān)鍵詞：基于雙目視覺(jué)的大場(chǎng)景三維重建研究與實(shí)現(xiàn)　出處：《吉林大學(xué)》2017年碩士論文　論文類型：學(xué)位論文

  更多相關(guān)文章： 三維重建 雙目視覺(jué) 大場(chǎng)景 立體匹配 Open CV

【摘要】：隨著人們的認(rèn)知水平和物質(zhì)文化追求的提高,越來(lái)越多的3D技術(shù)相關(guān)的產(chǎn)品開(kāi)始在人群中普及,為了獲得更好的產(chǎn)品體驗(yàn),虛擬現(xiàn)實(shí)三維重建技術(shù)開(kāi)始重新回到人們的視野之中,也越發(fā)受到人們的重視。本文研究并實(shí)現(xiàn)了一個(gè)完整的大場(chǎng)景三維重建系統(tǒng),包括立體標(biāo)定,立體校正,立體匹配和場(chǎng)景表面三維點(diǎn)云重建等過(guò)程。在立體匹配階段,針對(duì)原NLCA算法考慮因素過(guò)于單一,無(wú)法適應(yīng)大場(chǎng)景圖形規(guī)模大,多尺度,場(chǎng)景物體豐富,深度變化頻繁等特點(diǎn),本文對(duì)原算法進(jìn)行了進(jìn)一步的改進(jìn)。首先,我們對(duì)初始代價(jià)函數(shù)進(jìn)行優(yōu)化,使用ADCensus代價(jià)計(jì)算方法融合像素點(diǎn)的梯度信息,強(qiáng)化像素點(diǎn)的邊緣特征。另外,在代價(jià)聚合階段,在構(gòu)建最小生成樹(shù)時(shí),本文定義了一種同時(shí)包含了邊緣和顏色權(quán)值分量的新的權(quán)值函數(shù)為相鄰點(diǎn)對(duì)之間的邊賦值。另外根據(jù)圖像邊緣成因,我們?cè)谑褂胹obel算子對(duì)圖像進(jìn)行邊緣檢測(cè)的同時(shí),使用SLIC超像素分割塊對(duì)邊緣權(quán)值分量進(jìn)行二次約束,極大地減少了由于除深度變化外的其他原因產(chǎn)生的邊緣像素點(diǎn)在最小生成樹(shù)構(gòu)建過(guò)程中產(chǎn)生的影響。此外,在視差求精階段,本文提出了一種基于超像素塊的視差優(yōu)化算法,利用同一超像素塊中的像素點(diǎn)具有較高的相似度的特點(diǎn),對(duì)視差數(shù)據(jù)進(jìn)行修復(fù),有效提高穩(wěn)定點(diǎn)的比重,在此基礎(chǔ)上,結(jié)合原算法中使用的基于最小生成樹(shù)代價(jià)聚合的優(yōu)化方案,有效提高了優(yōu)化質(zhì)量。在算法的最后階段,為了提高三維重建的完整性,本文加入了一系列視差優(yōu)化過(guò)程,包括前文所述的基于超像素塊的視差優(yōu)化過(guò)程,并對(duì)該算法無(wú)法優(yōu)化的區(qū)域進(jìn)行再次填充并使用改進(jìn)了的中值濾波算法對(duì)不穩(wěn)定像素點(diǎn)區(qū)域進(jìn)行優(yōu)化,有效減少了視差圖像上的不連續(xù)塊和空洞,有效解決了視差圖像與參考圖像所反映的場(chǎng)景的實(shí)際信息不一致的問(wèn)題,提高三維重建過(guò)程的準(zhǔn)確性和完整性。實(shí)驗(yàn)數(shù)據(jù)表明,本文較原算法而言具有明顯的優(yōu)勢(shì),不僅在低分率圖像上取得較好的效果,對(duì)于本文所使用的高分辨率大場(chǎng)景圖像素材同樣適用,證明了本研究構(gòu)建的大場(chǎng)景三維重建系統(tǒng)可靠性、準(zhǔn)確性以及穩(wěn)定性。
[Abstract]:With the improvement of people's cognitive level and material and cultural pursuit, more and more 3D technology-related products began to be popularized in the crowd, in order to obtain a better product experience. Virtual reality 3D reconstruction technology has begun to return to people's vision, and has been paid more and more attention. This paper studies and implements a complete 3D reconstruction system of large scene, including stereo calibration and stereo correction. Stereo matching and 3D point cloud reconstruction on the scene surface. In the stereo matching stage, the original NLCA algorithm is too single to adapt to large scale, multi-scale and rich scene objects. Because of the frequent change of depth, the original algorithm is further improved. First, we optimize the initial cost function and use the ADCensus cost calculation method to fuse the gradient information of pixels. Enhance the edge feature of the pixel. In addition, in the cost aggregation phase, when building the minimum spanning tree. In this paper, we define a new weight function which includes both edge and color weight components to assign the edges between adjacent points. We use the sobel operator to detect the edge of the image, and we use the SLIC hyperpixel segmentation block to perform the quadratic constraint on the edge weight component. The effect of edge pixels due to other reasons other than depth changes in the construction of the minimum spanning tree is greatly reduced.; in addition, in the parallax refinement stage. In this paper, a parallax optimization algorithm based on super-pixel block is proposed. The parallax data is repaired by using the feature of high similarity of pixels in the same super-pixel block, and the proportion of stable points is improved effectively. On this basis, the optimization scheme based on minimum spanning tree cost aggregation used in the original algorithm is used to improve the optimization quality effectively. In the last stage of the algorithm, in order to improve the integrity of 3D reconstruction. In this paper, a series of parallax optimization processes are added, including the parallax optimization process based on super-pixel blocks mentioned above. The region which can not be optimized by this algorithm is filled again and the unstable pixel area is optimized by using the improved median filter algorithm, which can effectively reduce the discontinuous blocks and holes in parallax images. It effectively solves the problem that the actual information of the scene reflected by the parallax image and the reference image is inconsistent, and improves the accuracy and integrity of the 3D reconstruction process. Compared with the original algorithm, this paper has obvious advantages, not only in the low score image achieved better results, for the use of high-resolution large scene image material is also applicable. The reliability, accuracy and stability of the system are proved.
【學(xué)位授予單位】：吉林大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：TP391.41

【參考文獻(xiàn)】

相關(guān)期刊論文 前5條

1 周瑜;李戈;張學(xué)賀;趙杰;;基于雙目視覺(jué)的地形三維重建[J];機(jī)械與電子;2016年07期

2 麥春艷;鄭立華;李民贊;;基于點(diǎn)云配準(zhǔn)的果樹(shù)快速三維重建（英文）[J];農(nóng)業(yè)工程學(xué)報(bào);2015年S2期

3 劉怡光;易守林;吳鵬飛;崔鵬;;一種新的大場(chǎng)景3維重建算法[J];四川大學(xué)學(xué)報(bào)(工程科學(xué)版);2015年06期

4 姜翰青;趙長(zhǎng)飛;章國(guó)鋒;王慧燕;鮑虎軍;;基于多視圖深度采樣的自然場(chǎng)景三維重建[J];計(jì)算機(jī)輔助設(shè)計(jì)與圖形學(xué)學(xué)報(bào);2015年10期

5 朱遵尚;苑云;李由;尚洋;于起峰;;嫦娥一號(hào)月面成像的高精度匹配及月貌三維重建[J];光學(xué)學(xué)報(bào);2014年02期

相關(guān)博士學(xué)位論文 前1條

1 田豐;煤礦探測(cè)機(jī)器人導(dǎo)航關(guān)鍵技術(shù)研究[D];中國(guó)礦業(yè)大學(xué);2014年

相關(guān)碩士學(xué)位論文 前2條

1 白鵬;基于卷級(jí)神經(jīng)網(wǎng)絡(luò)的雙目立體視覺(jué)研究[D];浙江大學(xué);2016年

2 陳海波;高分辨率雙目視覺(jué)三維重建技術(shù)研究[D];浙江大學(xué);2013年

，

本文編號(hào)：1383707