access icon free Robust region-wise colour correction method for stereo matching

© The Institution of Engineering and Technology
Received 22/09/2015, Accepted 16/03/2016, Revised 23/02/2016, Published 18/03/2016

Significant colour discrepancies between stereo images have severe impacts on stereo matching algorithms, which depend on colour similarity. To address this problem, a region-wise colour correction method is proposed in this study. First, the source image, which is to be corrected, is segmented into a set of regions using the mean-shift method. Scale invariant feature transform (SIFT) features are extracted from both the source image and the reference image, and then matched. The matched SIFT pairs are refined by exploiting epipolar geometry constraint. Based on the segmentation result and the refined SIFT matches, the regional correspondences between two stereo images are estimated. Then, each matched region pair is used to compute a local colour correction function. A set of colour weight maps is calculated for these functions. Finally, to alleviate the colour transformation discontinuities along the region boundaries and facilitate a smooth colour correction globally, the corrected colour is obtained by combining the colour correction functions using the colour weighting maps. The authors apply the proposed local colour correction method to stereoscopic images before conducting stereo matching. The results indicate that the proposed algorithm can effectively and robustly alleviate the colour discrepancies, and improve the accuracy of stereo matching.

Inspec keywords: image segmentation; feature extraction; transforms; stereo image processing; image matching; geometry; smoothing methods; image colour analysis

Other keywords: source image; stereo images; stereo matching algorithms; smooth colour correction; epipolar geometry; region-wise colour correction method; scale invariant feature transform; stereoscopic image; mean shift method; reference image; SIFT

Subjects: Integral transforms; Integral transforms; Combinatorial mathematics; Combinatorial mathematics; Computer vision and image processing techniques; Image recognition

References

    1. 1)
      • 20. Yu-Wing, T., Jiaya, J., Chi-Keung, T.: ‘Soft color segmentation and its applications’, IEEE Trans. Pattern Anal. Mach. Intell., 2007, 29, (9), pp. 1520–1537.
    2. 2)
      • 28. Jianbo, S., Jitendra, M.: ‘Normalized cuts and image segmentation’, IEEE Trans. Pattern Anal. Mach. Intell., 2000, 22, (8), pp. 888–905.
    3. 3)
      • 23. Hasan, S.F., Tania, P., Christel, C., et al: ‘A survey of colour mapping and its applications’. Eurographics State of the Art Report, Strasbourg, 2014.
    4. 4)
      • 3. Heiko, H., Daniel, S.: ‘Evaluation of cost functions for stereo matching’. Proc. IEEE Conf. on Computer Vision and Pattern Recognition, 2007, pp. 1–8.
    5. 5)
      • 5. Sylvie, C., Alain, C.: ‘Colour correlation-based matching’, Int. J. Robot. Autom., 2005, 20, (2), pp. 78–85.
    6. 6)
      • 27. Pedro, F.F., Daniel, P.H.: ‘Efficient graph-based image segmentation’, Int. J. Comput. Vis., 2004, 59, (2), pp. 167–181.
    7. 7)
      • 11. Adrian, I., Greg, W.: ‘Ensuring colour consistency across multiple cameras’. Proc. IEEE Conf. on Computer Vision, 2005, no. 2, pp. 1268–1275.
    8. 8)
      • 8. Yong, S.H., Kyoung, M.L., Sang, U.L.: ‘Robust stereo matching using adaptive normalized cross-correlation’, IEEE Trans. Pattern Anal. Mach. Intell., 2011, 33, (4), pp. 807–822.
    9. 9)
      • 26. Dorin, C., Peter, M.: ‘Mean shift: A robust approach toward feature space analysis’, IEEE Trans. Pattern Anal. Mach. Intell., 2002, 24, (5), pp. 603–619.
    10. 10)
      • 13. Wei, X., Jane, M.: ‘Performance evaluation of color correction approaches for automatic multi-view image and video stitching’. Proc. IEEE Conf. on Computer Vision and Pattern Recognition, 2010, pp. 263–270.
    11. 11)
      • 21. Seon, J.K., Marc, P.: ‘Robust radiometric calibration and vignetting correction’, IEEE Trans. Pattern Anal. Mach. Intell., 2008, 30, (4), pp. 562–576.
    12. 12)
      • 7. Zitnick, C.L., Kang, S.B., Uyttendaele, M., et al: ‘High-quality video view interpolation using a layered representation’, ACM Trans. Graph., 2004, 23, (5), pp. 600–608.
    13. 13)
      • 31. Dorin, C., Peter, M.: ‘Mean shift analysis and applications’. Proc. IEEE Conf. on Computer Vision, 1999, pp. 1197–1203.
    14. 14)
      • 1. Daniel, S., Richard, S.: ‘A taxonomy and evaluation of dense two-frame stereo correspondence algorithms’, Int. J. Comput. Vis., 2002, 47, (1–3), pp. 7–42.
    15. 15)
      • 17. Kenji, Y., Tomohiro, Y., Toshiaki, F., et al: ‘Colour correction for multi-camera system by using correspondences’. ACM SIGGRAPH Research posters, 2006, p. 73.
    16. 16)
      • 10. Graham, D.F., Michal, M., Anya, H.: ‘Colour correction using root-polynomial regression’, IEEE Trans. Image Process., 2015, 24, (5), pp. 1460–1470.
    17. 17)
      • 25. Simon, B., Daniel, S., JP, L., et al: ‘A database and evaluation methodology for optical flow’, Int. J. Comput. Vis., 2011, 92, (1), pp. 1–31.
    18. 18)
      • 24. Qi, W., Xi, S., Zengfu, W.: ‘A robust algorithm for color correction between two stereo images’. Proc. Asian Conf. on Computer Vision, 2009, pp. 405–416.
    19. 19)
      • 22. Jia, Y.J., Chi-Keung, T.: ‘Tensor voting for image correction by global and local intensity alignment’, IEEE Trans. Pattern Anal. Mach. Intell., 2005, 27, (1), pp. 36–50.
    20. 20)
      • 18. Erik, R., Michael, A., Bruce, G., et al: ‘Colour transfer between images’, IEEE Comput. Graph. Appl., 2001, 21, (5), pp. 34–41.
    21. 21)
      • 14. Yu-Wing, T., Jiaya, J., Chi-Keung, T.: ‘Local color transfer via probabilistic segmentation by expectation-maximization’. Proc. IEEE Conf. on Computer Vision and Pattern Recognition, 2005, pp. 747–754.
    22. 22)
      • 29. Richard, H., Andrew, Z.: ‘Multiple view geometry in computer vision’ (Cambridge university press, 2003).
    23. 23)
      • 30. ‘Middlebury stereo vision page’, available at http://www.middlebury.edu/stereo, accessed 4 February 2016.
    24. 24)
      • 32. Zeng-Fu, W., Zhi-Gang, Z.: ‘A region based stereo matching algorithm using cooperative optimization’. Proc. IEEE Conf. on Computer Vision and Pattern Recognition, 2008, pp. 1–8.
    25. 25)
      • 2. Steven, M.S., Brian, C., James, D., et al: ‘A comparison and evaluation of multi-view stereo reconstruction algorithms’. Proc. IEEE Conf. on Computer vision and pattern recognition, 2006, no. 1, pp. 519–528.
    26. 26)
      • 12. Yasutaka, F., Brian, C., Steven, M.S., et al: ‘Towards internet-scale multi-view stereo’. Proc. IEEE Conf. Computer Vision and Pattern Recognition (CVPR), 2010, pp. 1434–1441.
    27. 27)
      • 15. Haoxing, W., Longquan, D., Xiaopeng, Z.: ‘Consistent segmentation based colour correction for coarsely registered images’. IEEE Proc. Asian Conf. on Pattern Recognition, 2013, pp. 319–324.
    28. 28)
      • 9. Xing, M., Xun, S., Ming, C.Z., et al: ‘On building an accurate stereo matching system on graphics hardware’. Proc. IEEE Int. Conf. on Computer Vision Workshops (ICCV Workshops), 2011, pp. 467–474.
    29. 29)
      • 16. Mehrdad, P.T., Akio, I., Shigeyuki, S., et al: ‘Iterative colour correction of multicamera systems using corresponding feature points’, J. Vis. Commun. Image Represent., 2010, 21, (5), pp. 377–391.
    30. 30)
      • 4. Micheal, B., Sylvie, C., Uta, P., et al: ‘Evaluation of different method for using colour information in global stereo matching approaches’. Proc. Int. Society for Photogrammetry and Remote Sensing, 2008, pp. 63–68.
    31. 31)
      • 19. Miguel, O., Angel, D.S., Vitor, S.: ‘Unsupervised local colour correction for coarsely registered images’. Proc. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), 2011, pp. 201–208.
    32. 32)
      • 6. Ramin, Z., John, W.: ‘Non-parametric local transforms for computing visual correspondence’. Proc. European Conf. on Computer Vision, 1994, pp. 151–158.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-cvi.2015.0361
Loading

Related content

content/journals/10.1049/iet-cvi.2015.0361
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading