本文選題：標(biāo)定 + 稠密匹配�。� 參考：《南京理工大學(xué)》2017年碩士論文

【摘要】：立體視覺(jué)的實(shí)現(xiàn)可分為攝像機(jī)標(biāo)定、特征點(diǎn)提取、立體匹配、三維信息的恢復(fù)及后處理五個(gè)步驟。本文圍繞計(jì)算機(jī)立體視覺(jué)系統(tǒng),針對(duì)攝像機(jī)標(biāo)定和立體匹配技術(shù)展開(kāi)深入研究,為實(shí)現(xiàn)從二維圖像中提取三維信息打下基礎(chǔ)。在攝像機(jī)標(biāo)定部分,本文采用了綜合傳統(tǒng)標(biāo)定和自標(biāo)定優(yōu)點(diǎn)的張正友平面模板標(biāo)定法獲得了雙目攝像頭的內(nèi)外參數(shù)。同時(shí)對(duì)雙目圖像進(jìn)行了畸變校正和極線校正,改善了圖像質(zhì)量并使雙目攝像頭拍攝的左右成像平面對(duì)極線行對(duì)齊,為后續(xù)圖像立體匹配提供了方便。在特征點(diǎn)初匹配中,本文對(duì)幾種常用的特征提取算子性能進(jìn)行對(duì)比并選擇了抗噪性和穩(wěn)定性較好的SIFT算法進(jìn)行特征提取和匹配,同時(shí)采用RANSAC算法去除誤匹配點(diǎn),從而達(dá)到了精匹配效果。在特征點(diǎn)稠密匹配中,本文首先研究了基于區(qū)域增長(zhǎng)的稠密匹配方法,詳細(xì)闡述了具體實(shí)現(xiàn)過(guò)程。同時(shí)本文提出了一種基于單應(yīng)性的稠密匹配方法,該方法通過(guò)不斷地假設(shè)當(dāng)前的配準(zhǔn)結(jié)果中相互毗鄰的三對(duì)特征點(diǎn)形成的三角面片滿足單應(yīng)性關(guān)系,并利用互相關(guān)函數(shù)對(duì)單應(yīng)性假設(shè)進(jìn)行校驗(yàn)。將符合校驗(yàn)原則的三角面片記為配準(zhǔn)面片,將不滿足校驗(yàn)原則的三角面片進(jìn)行細(xì)分后重新判斷,既而從圖像上檢測(cè)更多的稠密匹配點(diǎn),且匹配準(zhǔn)確度較高。最后本文對(duì)兩種稠密匹配方法的實(shí)驗(yàn)結(jié)果進(jìn)行對(duì)比,驗(yàn)證了該方法的有效性。
[Abstract]:The realization of stereo vision can be divided into five steps: camera calibration, feature point extraction, stereo matching, 3D information recovery and postprocessing.In this paper, the camera calibration and stereo matching technology are deeply studied around the computer stereo vision system, which lays the foundation for extracting 3D information from two-dimensional images.In the camera calibration part, the internal and external parameters of the binocular camera are obtained by using the Zhang Zhengyou plane template calibration method, which combines the advantages of traditional calibration and self-calibration.At the same time, the distortion correction and pole line correction of binocular image are carried out to improve the image quality and align the left and right imaging plane of binocular camera, which provides convenience for stereo matching of subsequent images.In the initial matching of feature points, this paper compares the performance of several commonly used feature extraction operators, and selects the SIFT algorithm with good noise resistance and stability for feature extraction and matching. At the same time, RANSAC algorithm is used to remove the mismatch points.Thus, the precision matching effect is achieved.In the dense matching of feature points, this paper first studies the dense matching method based on regional growth, and describes the implementation process in detail.At the same time, a dense matching method based on homotropy is proposed. This method continuously assumes that the triangular patches formed by the three pairs of feature points adjacent to each other in the current registration results satisfy the monotropic relationship.The hypothesis of homotropy is verified by cross-correlation function.After subdividing the triangulated face which does not meet the checkout principle, more dense matching points are detected from the image, and the matching accuracy is high.Finally, the experimental results of two dense matching methods are compared to verify the effectiveness of the proposed method.
【學(xué)位授予單位】：南京理工大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類(lèi)號(hào)】：TP391.41

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 高晶;陳莉;蘭小艷;靳立燕;楊洲;;基于FAST特征點(diǎn)提取的圖像拼接算法[J];西北大學(xué)學(xué)報(bào)(自然科學(xué)版);2016年03期

2 賀一楠;耿娟;秦軍;劉晨;楊輝;;結(jié)合Forstner與NCC約束的UAV圖像配準(zhǔn)研究[J];國(guó)土資源遙感;2015年01期

3 羅元;楊明珠;張毅;;基于改進(jìn)去偽匹配SURF算法的靜態(tài)手語(yǔ)字母識(shí)別[J];激光雜志;2014年07期

4 張梁;徐錦法;夏青元;;雙目立體視覺(jué)的無(wú)人機(jī)位姿估計(jì)算法及驗(yàn)證[J];哈爾濱工業(yè)大學(xué)學(xué)報(bào);2014年05期

5 劉亞強(qiáng);陳文藝;;桶形畸變圖像的一種校正方法[J];西安郵電學(xué)院學(xué)報(bào);2012年02期

6 周曉敏;趙力彬;張新利;;低空無(wú)人機(jī)影像處理技術(shù)及方法探討[J];測(cè)繪與空間地理信息;2012年02期

7 狄穎辰;陳云坪;陳瑩瑩;陳彥;;無(wú)人機(jī)圖像拼接算法綜述[J];計(jì)算機(jī)應(yīng)用;2011年01期

8 林宗堅(jiān);劉正坤;支曉棟;;一種基于統(tǒng)計(jì)模型的自適應(yīng)窗口匹配方法[J];測(cè)繪科學(xué);2010年06期

9 張峰;許振輝;史利民;孫鳳梅;胡占義;;基于寬基線圖像遠(yuǎn)距離場(chǎng)景的自動(dòng)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);2010年02期

10 谷雨;李平;韓波;;一種適用于局部特征的混合視覺(jué)伺服方法[J];控制與決策;2010年01期

，

本文編號(hào)：1745076