A Differential Evolution Stereo Matching Method in Digital Image Correlation

Abstract:

Stereo matching is widely used in three-dimensional (3D) reconstruction, stereo machine vision and digital image correlation. The aim of stereo matching process is to solve the well-known correspondence problem, which tries to match points or features from one image with the same points or features in another image from the same 3D scene. There are two basic ways, correlation-based and feature-based, are used to find the correspondences between two images. The correlation-based way is to determine if one location in one image looks/seems like another in another image, and the feature-based way to find if a subset of features in one image is similar in the another image. In stereo matching, a simple algorithm is to compare small patches between two rectified images by correlation search. For the pair images acquired from two cameras inevitably exists some rotation transformation, the algorithm first runs a preprocessing step to rectify the images with the epipolar rectification to simplify the problem of finding matching points between images. The epipolar rectification is to determine a transformation of each image plane such that pairs of conjugate epipolar lines become collinear and parallel to one of the image axes. It will lead the loss of gray information of images. The effect is dependent on the amount of angle. When the angle is big enough, the correlation search may yield error results because of retrograded correlation effect. In order to solve the problem, the paper presents an improved stereo matching algorithm with differential evolution to solve the correspondence problem. Our method doesn’t need to runs the preprocessing step to rectify the images with the epipolar rectification. It uses a differential evolution algorithm to minimize the correlation function which contains the angle information after acquiring the epipoar geometry constraint of two image pairs. Then it utilizes a flood-fill algorithm to search correspondence sub-region in the area around the epipolar line. The flood-fill algorithm can overcome the problem of the traditional row-column scanning search method, which will encounter boundary barrier where exists concave polygons or cavities. The Experimental results show that the proposed method can be easily implemented in stereo matching without loss of information of image features with large rotation angle transformation. In the paper, we will introduce the stereo matching principle and its algorithms, including the differential evolution algorithm for finding the correspondences with large rotation transformation between stereo image pairs and the flood-fill traversal strategy for matching large area with complex concave polygons or cavities. In the end of the paper, some experimental results will be given to illustrate the method effectiveness. Keywords: digital image correlation, stereo matching algorithm, epipolar geometry, flood fill algorithm, differential evolution, rotation angle

• Periodical: Key Engineering Materials (Volume 625)
• Pages: 297-304
• DOI: https://doi.org/10.4028/www.scientific.net/KEM.625.297
• Online since: August 2014
• Authors: Lin Chen*, Rong Sheng Lu, Yan Qiong Shi, Jian Sheng Tian
• Keywords: Differential Evolution, Digital Image Correlation (DIC), Epipolar Geometry, Flood Fill Algorithm, Rotation Angle, Stereo Matching Algorithm

References

[1] I. Yamaguchi, laser-speckle strain gauge[J]. Scientific Instruments, 1981, 14(11): 1270- 1273.

DOI: 10.1088/0022-3735/14/11/012

[2] W. H. Peters, W. F. Ranson, Digital imaging techniques in experimental stress analysis[J]. Opt. Eng, 1982, 21(3): 427-431.

[3] M. A. Sutton, W. J, W. H. Peters, et al., Determination of displacements using an improved digital rrelationmethod[J]. Image and Vision Computing, 1983, 1(3): 133-139.

DOI: 10.1016/0262-8856(83)90064-1

[4] T. C. Chu, W. F. Ranson, et al., Application of digital image correlation technique to experimental mechanics[J]. Exp. Mech., 1985, 25(3): 232-244.

[5] S. R. Russel, M .A. Sutton, Image correlation quantitative NDE of impact and fabrication damage in a glass fiber reinforced composite system [J]. Mater. Eval., 1989, 47(5): 550-558.

[6] W. Zhang, X. Cao, E Sung et al. A feature-based matching scheme: MPCD and robust matching strategy[J]. Pattern Recognition Letters, 2007, 7(28): 1222-1231.

DOI: 10.1016/j.patrec.2007.02.004

[7] Zai Xiaotao, Zhao Yuming. A stereo matching algorithm based on SIFT feature descriptor[J]. Microcomputer Information, 2007, 20(8): 285-287.

[8] Daniel Scharstein, Richard Szeliski. A taxonomy and evaluation of dense two-frame stereo correspondence lgorithms[J]. International J. Computer Vision, 2002, 7(1/2/3): 7-42.

DOI: 10.1109/smbv.2001.988771

[9] O D Faugeras. Three-Dimensional Computer Vision A Geometric View point[M]. The MIT Press, Cambridge, MA, (1993).

[10] Hartley R. Theory and practice of projective rectification[J]. International Journal of Computer Vision, 1999, 35(2): 115-127.

[11] HUNG Pe-chin, Voloshin A S. In-plane strain measurement by digital image correlation[J]. Journal of the Brazilian Society of Mechanical Sciences and Engineering, 2003, 25(3): 215-221.

DOI: 10.1590/s1678-58782003000300001

[12] WANG Jing, LI Hong-qi, LIU Mei-hua, et al. A new digital image correlation method combining circular window and moment character[J]. Journal of Experimental Mechanics, 2004, 19(4): 500-506. (in Chinese).

[13] Cumpson P J, Hedley J, Zhdsn P. Accurate force measurement in the atomic force microscope: A micro fabricated array of reference aprings for easy cantilever calibration[J]. Nanotechnology, 2003, 14(8): 918-924.

DOI: 10.1088/0957-4484/14/8/314

[14] Cibson C T, Johnson D J, Anderson C, et al. Method to determine the spring constant of atomic force microscope cantilevers[J]. Review of Scientific Instruments, 2004, 75(2): 565-567.

DOI: 10.1063/1.1642750

[15] C. A. Hall. Natural Cubic and Bicubic Spline Interpolation[J]. SIAM J. Numer. Anal., 10(6), 1055–1060.

DOI: 10.1137/0710088

[16] STORN R, PRICE K. Differential Evolution-a Simple and Efficient Adaptive Scheme for Global Optimization over Continuous Spaces[J]. Technical Report International Compute Science Institute, 1995(8): 22-25.

[17] YANG Xue-feng, YU Juan, QIAN Feng et al. Kinetic Parameter Estimation of Oxidation in Supercritical Water Based on Modified Differential Evolution[J]. Journal of East China University of Science and Technology(Natural Science Edition), 2006, 32(1): 94-97.

[18] Jayong Lee, Hoon Kang. Flood Fill Mean Shift: A Robust Segmentation Algorithm[J]. International Journal of Control, Automation, and Systems (2010) 8(6): 1313-1319.

DOI: 10.1007/s12555-010-0617-6