摘要
物体表面的三维信息可以通过双目立体视觉来重建,包括摄像机标定,极线校正,对应点匹配,视差计算,亚像素精细化,模型重建等过程。对应点匹配是双目立体视觉的关键。本文采用时空立体匹配,通过人为主动地向空间物体投射一系列光条模式,使得物体表面纹理信息丰富,从而降低匹配难度,提高准确率。利用各种约束条件如对称性匹配约束,视差约束,顺序性约束等可进一步提高匹配效率。时空立体匹配方法较易得到整数级视差,为精细化视差,需要对初步得到的视差进一步亚像素优化。本文还对匹配过程中光条模式的取舍,匹配窗口大小等因素对重建模型的影响进行详细的分析与结果比较。实验结果显示,恰当的光条数目与合适的窗口大小对物体形状重建起着重要的作用。
通过双目立体视觉重建得到的真实物体三维模型一般具有较大的噪声,并可能存在孔洞。针对这一问题,本文提出在规则三维点集下,通过非局部(non-local, NL)方法来滤除三维模型的噪声并填补孔洞。为提高算法效率,对含孔区域和非孔区域的点集,分别做基本NL滤波和基于主成分分析(principal component analysis, PCA)的NL滤波,然后进一步通过NL方法对孔洞做填补。实验结果表明,对于多种真实物体,本文所提出的方法均能有效地重建三维模型,且与其它方法相比具有更高的精度。
3-D surface can be reconstructed based on binocular stereo vision. It always includes camera calibration, image rectification, correspondance pair matching, disparity calculation, sub-pixel refinement, model reconstruction, etc. Correspondance pair matching is the most important step in reconstruction. Space-time stereo matching can effectively improve matching accuracy and reduce matching difficulty, by projecting a series of light patterns for the purpose of enriching surface texture information. At the same time, symmetry restriction, disparity restriction, order restriction and others can also improve matching efficiency. Space-time stereo matching can reach integer disparity easily. Sub-pixel refinement is needed for higher accuracy. This paper analyses and compares the amount of patterns, matching windows'size and other factors'influence in 3D reconstruction. The experimental results show that, right amount of pattern and matching windows'size play an important role in 3-D surface reconstruction.
The 3D models reconstructed from binocular stereo always exhibit noticeable noise, and even contain holes. To deal with this issue, this thesis presents a non-local (NL) method to denoise and hole-fill the original model on regular vertex set. To improve computational efficiency, the proposed method uses the basic NL method and principal component analysis (PCA) based NL method to remove model noise in hole and non-hole regions, respectively. The filled holes are then processed by NL denoising to improve the consistency with the surrounding surfaces. The experimental results show that, when evaluated on different real objects with various sizes, the proposed method can reconstruct 3D models effectively and performs much better than previous methods.
引文
[1]张广军.视觉测量[M].北京：科学出版社,2008：1-22,134-158.
[2]Forsyth DA, Ponce J. Computer vision:a modern approach [M]. New Jersey:Prentice Hall Professional Technical Reference,2002:199-212.
[3]Marr D. Vision:A computational investigation into the human representation and processing of visual information. San Francisco:W. H. Freeman and Company,1982.
[4]吴健康,肖锦玉.计算机视觉基本理论和方法[M].合肥：中国科学技术大学出版社,1993.
[5]Xu G, Zhang Z. Epipolar gemetry in stereo. Motion and Object Recognition. The Netherlands:Kluwer Academic Publishers.1996,79-204.
[6]Robert J. Woodham. Photometric method for determining surface orientation from multiple images[J]. Optical Engineering,1980,19(1):139-144.
[7]Simchony T, Chellappa R. Direct analytical methods for sovling possion equations in computer vision problems[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,1990,12(5):435-446.
[8]Frankot RT, Chellappa R. A method for enforcing integrability in shape from shading algorithms[J]. IEEE Transctions on Pattern analysis and machine intelligence. 1988,10(4):439-451.
[9]Salvi J, Pages J, Battle J. Pattern codification strategies in structured light systems [J]. Pattern Recognition,2004,37(4):827-849.
[10]Davis J, Nehab D, Ramamoorthi R, et al. Spacetime stereo:a unifying framework for depth from triangulation [J]. IEEE Transactions of Pattern Analysis and Machine Intelligence,2005,27(2):296-302.
[11]Zhang L, Curless B, Seitz SM. Spacetime stereo:shape recovery for dynamic scenes [C]//Proceedings-IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Madison, Wisconsin, USA:IEEE Computer Society,2003:367-374.
[12]Bradski G, Kaehler A. Learning OpenCV:computer vision with the OpenCV library [M]. United States of Amearica:O'Reilly Media, Inc,2008.
[13]Zhang Z Y. A flexible new technique for camera calibration. IEEE Trans. On Pattern Analysis and Machine Intelligence,2000,22(11):1330-1334.
[14]邢德奎.计算机视觉中摄像机标定若干关键技术研究[D].南京：东南大学硕士学位论文,2009.
[15]Marr D C, Hildreth E C. Theory of edge detection [J]. Proceedings of Roy Soc, London, 1980, B207:187-217.
[16]Canny J F. A computational approach to edge detection [J]. IEEE Trans. On PAMI, 1986,8(6):679-698.
[17]Bergholm F. Edge Focusing [J]. IEEE Trans. On PAMI,1987,9(6):726-741.
[18]Saint M P, Chen J S, Medioni G. Adaptive smoothing:A general tool for early vision [J]. IEEE Trans. On PAMI,1991,13(6):514-529.
[19]Harris C. Geometry from visual motion, active motion [M]. Cambridge:MIT Press, 1992,263-284.
[20]Bouguet J-Y. Camera Calibration Toolbox for Matlab [CP/OL]. (2008-06-02) [2009-12-01].http://www.vision.caltech. edu/bouguetj/calib-doc/index.html.
[21]Tsai R Y. An efficient and accurate camera calibration technique for 3D machine vision. Proc. of IEEE Conference of Computer Vision and Pattern Recognition,1986,364-374.
[22]Hartley RI. Theory and practice of projective rectification[J].International Journal of Computer Vision 35.1998:115-127.
[23]Zhang R, Tsi P S, Cryer J E, etc. Shape from shading:A survey [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence.1999(21):690-706.
[24]Psarakis EZ, Evangelidis GD. An enhanced correlation-based method for stereo correspondence with sub-pixel accuracy [C]//10th IEEE International Conference on Computer Vision. Beijing, CHINA:IEEE,2005:907-912.
[25]Yu WR, Xu BG. A sub-pixel stereo matching algorithm and its applications in fabric imaging [J]. Machine Vision and Applications,2009,20(4):261-270.
[26]Scharstein D, Szeliski R. A taxonomy and evaluation of dense two-frame stereo correspondence algorithms [J]. International Journal of Computer Vision,2002,47(1-3): 7-42.
[27]Felzenszwalb PR, Huttenlocher DP. Efficient belief propagation for early vision [J]. IEEE Computer Society Conference on Computer Vision and Pattern Recognition,2004: 261-268.
[28]Stefano Di, Marchionni M, Mattoccia S. A fast area-based stereo matching algorithm [J]. Image and Vision Computing,2004,22(12):983-1005.
[29]Scharctein D, Szeliski R. High-accuracy stereo depth maps using structured light [J]. IEEE Computer Society Conference on Computer Vision and Pattern Recognitionm, 2003:195-202.
[30]Hartley R, Zisserman A. Multiple View Geometry in Computer Vision [M].2nd ed. Cambridge, England:The Press Syndicate of the University of Cambridge,2003: 311-324.
[31]Nehab D, Rusinkiewicz S, Davis J, et al. Efficiently combining positions and normals for precise 3D geometry [J]. ACM Transactions on Graphics,2005,24(3):536-543.
[32]Fleishman S, Drori I, Cohen-Or D. Bilateral mesh denoising[J]. ACM Transactions on Graphics,2003,22(3):950-953.
[33]Buades A, Coll B, Morel JM. A non-local algorithm for image denoising [C] //Proceedings-IEEE Computer Society Conference on Computer Vision and Pattern Recognition. San Diego, CA, USA:IEEE Computer Society,2005:60-65.
[34]Buades A, Coll B, Morel JM. A review of image denoising algorithms, with a new one [J]. Multiscale Modeling & Simulation,2005,4(2):490-530.
[35]Tasdizen T. Principal neighborhood dictionaries for nonlocal means image denoising[J]. IEEE Transactions on Image Processing,2009,18(12):2649-2660.
[36]Lindenbaum M, Fischer M, Bruckstein A. On gabor contribution to image enhancement [J]. Pattern Recognition,1994,27(1):1-8.
[37]Tomasi C, Manduchi R. Bilateral filtering for gray and color images [C]//Sixth International Conference on Computer Vision. Bombay, India:Narosa Publishing House, 1998:839-846.
[38]Mahmoudi M, Sapiro G. Fast image and video denoising via nonlocal means of similar neighborhoods [J]. IEEE Signal Processing Letters,2005,12(12):869-842.
[39]Wang JN, Oliverira MM. A hole-filling strategy for reconstruction of smooth surface in range images [C]//ⅩⅥ Brazilian Symposium on Computer Graphics and Image Processing. Sao Carlos, Brazil:Computer Graphics and Image Processing,2003:11-18.
[40]Paris S, Durand F. A fast approximation of the bilateral filter using a signal processing approach [J]. International Journal of Computer Vision,2009,81(1):24-52.