Three-Steps Uncalibrated Rectification Using Epipolar Distance Transform

Abstract:

A direct, efficient method for the problem of epipolar rectification in the uncalibrated casewas proposed. The method was based on minimizing a measure ofdistortion, by introducing anepipolar distance transform. The transform converted image intensity values to a relative locationinside a planar segment along the epipolar line, so it was robust to noises. The ratio of the distancesbetween two matching points in the epipolar lines was theoretically proved invariant to an affinetransformation for planar surfaces. To calculate the relative rotation between both cameras, thealgorithm was decomposed into three-steps to limit the distortion. Results show that the new measureis more appropriate for image rectification, and the three-step algorithm has obtained an accuracycomparable result both in estimation error and visual effect, especially when the initial epipolar linesare far from horizontal.

• Periodical: Applied Mechanics and Materials (Volumes 411-414)
• Pages: 1341-1347
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.411-414.1341
• Online since: September 2013
• Authors: Li Mei Fu, Guo Hua Peng
• Keywords: Epipolar Distancetransform, Epipolar Rectification, Three-Steps, Uncalibrated

References

[1] Hartley, R., Gupta, R.: Computing matched-epipolar projections. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, p.549–555, New York, NY, June 15–17(1993).

DOI: 10.1109/cvpr.1993.341076

[2] Hartley, R.: Theory and practice of projective rectification. Int. J. Comput. Vis. 35 (2), 1–16 (1999).

[3] Loop, C., Zhang, Z.: Computing rectifying homographies for stereo vision. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. I: 125–131, Fort Collins, CO, June 23–25 (1999).

DOI: 10.1109/cvpr.1999.786928

[4] Isgrò, F., Trucco E.: Projective rectification without epipolar geometry. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. I: 94–99, Fort Collins, CO, June 23–25(1999).

DOI: 10.1109/cvpr.1999.786923

[5] Gluckman, J ., Nayar, S.K.: Rectifying transformations that minimize resampling effects. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, vol. 1, p.111 (2001).

DOI: 10.1109/cvpr.2001.990463

[6] Mallon, J., Whelan, P.F.: Projective rectification from the fundamental matrix. Image Vis. Comput. 23 (7), 643–650 (2005).

DOI: 10.1016/j.imavis.2005.03.002

[7] Pascal Monasse，Jean-Michel Morel, Zhongwei TANG : Three-step image rectification. BMVC, doi: 10. 5244/C. 24. 89(2010).

[8] A. Fusiello and L. Irsara. Quasi-Euclidean uncalibrated epipolar rectification. Machine Vision and Applications. 22: 663–670(2011).

DOI: 10.1007/s00138-010-0270-3

[9] Qingxiong Yang, Narendra Ahuja: Stereo Matching Using Epipolar Distance Transform. IEEE Trans. on image processing, vol. 21, No. 10, October (2012).

DOI: 10.1109/tip.2012.2207393

[10] Hartley, R., Zisserman, A.: Multiple View Geometry in Computer Vision, 2nd edn. Cambridge University Press, Cambridge (2004).

[11] Luong, Q.T., Faugeras, O.D.: The fundamental matrix: theory, algorithms, and stability analysis. Int. J. Comput. Vis. 17 , 43–75 (1996).

DOI: 10.1007/bf00127818

[12] Robert, L ., Buffa, M., Hebert, M.: Weakly-calibrated stereo perception for rover navigation. In: ICCV, p.46–51 (1995).

DOI: 10.1109/iccv.1995.466808