access icon free Window-based approach for fast stereo correspondence

In this study, the authors present a new area-based stereo matching algorithm that computes dense disparity maps for a real-time vision system. Although many stereo matching algorithms have been proposed in recent years, correlation-based algorithms still have an edge because of speed and less memory requirements. The selection of appropriate shape and size of the matching window is a difficult problem for correlation-based algorithms. In the proposed approach, two correlation windows are used to improve the performance of the algorithm while maintaining its real-time suitability. The CPU implementation of the proposed algorithm computes more than 10 frame/s. Unlike other area-based stereo matching algorithms, this method works very well at disparity boundaries as well as in low textured image areas and computes a dense and sharp disparity map. Evaluations on the benchmark Middlebury stereo datasets have been performed to demonstrate the qualitative and quantitative performance of the proposed algorithm.

Inspec keywords: stereo image processing; correlation methods; image matching

Other keywords: correlation based algorithms; textured image areas; disparity maps; area based stereo matching; realtime vision system; Middlebury stereo datasets; window based approach; matching window; disparity boundaries; fast stereo correspondence

Subjects: Computer vision and image processing techniques; Image recognition

References

    1. 1)
      • 23. Marr, D., Poggio, T.: ‘A computational theory of human stereo vision’. Proc. Royal Society of London, Series B, 1979, vol. 240, no. 1156, pp. 301328.
    2. 2)
      • 27. Gong, M., Yang, Y.: ‘Near real-time reliable stereo matching using programmable graphics hardware’. IEEE Conf. Computer Vision and Pattern Recognition, 2005, pp. 924931.
    3. 3)
      • 11. Boykov, Y., Veksler, O., Zabih, R.: ‘Fast approximate energy minimization via graph cuts’, IEEE Trans. Pattern Anal. Mach. Intell., 2001, 23, (11), pp. 12221239 (doi: 10.1109/34.969114).
    4. 4)
      • 26. Humenberger, M., Zinner, C., Weber, M., Kubinger, W., Vincze, M.: ‘A fast stereo matching algorithm suitable for embedded real-time systems’, Comput. Vis. Image Underst., 2010, 114, (11), pp. 11801202 (doi: 10.1016/j.cviu.2010.03.012).
    5. 5)
      • 21. Veksler, O.: ‘Stereo matching by compact window via minimum ratio cycle’. IEEE Int. Conf. Comput. Vis., 2001, vol. 1, pp. 540547.
    6. 6)
      • 1. Scharstein, D., Szeliski, R.: ‘A taxonomy and evaluation of dense two-frame stereo correspondence algorithms’, Int. J. Comput. Vis., 2002, 47, (1), pp. 742 (doi: 10.1023/A:1014573219977).
    7. 7)
      • 24. Gupta, R., Cho, S.-Y.: ‘Real-time stereo matching using adaptive binary window’ (3D Data Processing, Visualization and Transmission, 2010).
    8. 8)
      • 25. Zhang, K., Lu, J., Lafruit, G., Lauwereins, R., Gool, L.V.: ‘Real-time accurate stereo with bitwise fast voting on Cuda’. Int. Conf. Computer Vision Workshops, 2009, pp. 540547.
    9. 9)
      • 18. Okutomi, M., Katayama, Y., Oka, S.: ‘A simple stereo algorithm to recover precise object boundaries and smooth surfaces’, Int. J. Comput. Vis., 2002, 47, (1), pp. 261273 (doi: 10.1023/A:1014510328154).
    10. 10)
      • 16. Yoon, K.-J., Kweon, I.S.: ‘Adaptive support-weight approach for correspondence search’, IEEE Trans. Pattern Anal. Mach. Intell., 2006, 28, (4), pp. 650656 (doi: 10.1109/TPAMI.2006.70).
    11. 11)
      • 9. Felzenszwalb, P., Huttenlocher, D.: ‘Efficient belief propagation for early vision’. IEEE Conf. Comput. Vis. Pattern Recognit., 2004, vol. 1, pp. 261268.
    12. 12)
      • 12. Sun, J., Zheng, N., Shum, H.: ‘Stereo matching using belief propagation’, IEEE Trans. Pattern Anal. Mach. Intell., 2003, 25, (7), pp. 787800 (doi: 10.1109/TPAMI.2003.1206509).
    13. 13)
      • 14. Sara, R.: ‘How to teach stereoscopic matching?ELMAR, 2010, pp. 445453.
    14. 14)
      • 8. Kanade, T., Okutomi, M.: ‘A stereo matching algorithm with an adaptive window: theory and experiments’, IEEE Trans. Pattern Anal. Mach. Intell., 1994, 16, (9), pp. 920932 (doi: 10.1109/34.310690).
    15. 15)
      • 2. Faugeras, O., Hotz, B., Mathieu, M., et al: ‘Real-time correlation-based stereo: algorithm, implementation and applications’. INRIA Technical Report No. 2013, 1993.
    16. 16)
      • 19. Boykov, Y., Veksler, O., Zabih, R.: ‘A variable window approach to early vision’, IEEE Trans. Pattern Anal. Mach. Intell., 1998, 20, (12), pp. 12831294 (doi: 10.1109/34.735802).
    17. 17)
      • 3. Yoon, S., Park, S.-K., Kang, S., Kwak, Y.: ‘Fast correlation-based stereo matching with the reduction of systematic errors’, Pattern Recognit. Lett., 2005, 26, pp. 22212231 (doi: 10.1016/j.patrec.2005.03.037).
    18. 18)
      • 28. Richardt, C., Orr, D., Davies, I., Criminisi, A., Dodgson, N.: ‘Real-time spatiotemporal stereo matching using the dual-cross-bilateral grid’. European Conf. Computer Vision, 2010, vol. 6313, pp. 510523.
    19. 19)
      • 4. Stefano, L., Marchionni, M., Mattoccia, S.: ‘A fast area-based stereo matching algorithm’, Image Vis. Comput., 2004, 22, (12), pp. 9831005 (doi: 10.1016/j.imavis.2004.03.009).
    20. 20)
      • 13. Criminisi, A., Blake, A., Rother, C., Shotton, J., Torr, P.H.: ‘Efficient dense stereo with occlusions for new view-synthesis by four-state dynamic programming’, Int. J. Comput. Vis., 2007, 71, (1), pp. 89110 (doi: 10.1007/s11263-006-8525-1).
    21. 21)
      • 17. Hirschmuller, H., Innocent, P., Garibaldi, J.: ‘Real-time correlation-based stereo vision with reduced border errors’, Int. J. Comput. Vis., 2002, 47, pp. 229246 (doi: 10.1023/A:1014554110407).
    22. 22)
      • 6. Fua, P.: ‘A parallel stereo algorithm that produces dense depth maps and preserves image features’, Mach. Vis. Appl., 1993, 6, (1), pp. 3549 (doi: 10.1007/BF01212430).
    23. 23)
      • 10. Birchfield, S., Tomasi, C.: ‘Depth discontinuities by pixel-to-pixel stereo’, Int. J. Comput. Vis., 1999, 25, pp. 10731080.
    24. 24)
      • 20. Jeon, J., Kim, C., Ho, Y.S.: ‘Sharp and dense disparity maps using multiple windows’. Lecture Notes Computer Science, 2002, pp. 10571064.
    25. 25)
      • 22. Veksler, O.: ‘Fast variable window for stereo correspondence using integral images’. IEEE Conf. Computer Vision and Pattern Recognition, 2003, vol. 1, pp. 556561.
    26. 26)
      • 7. Adhyapak, S., Kehtarnavaz, N., Nadin, M.: ‘Stereo matching via selective multiple windows’, J. Electron. Imag., 2007, 16, (1), pp. 013012 (doi: 10.1117/1.2711817).
    27. 27)
      • 15. http://vision.middlebury.edu/stereo, accessed 16th July 2012.
    28. 28)
      • 5. Fusiello, A., Roberto, V., Trucco, E.: ‘Efficient stereo with multiple windowing’. IEEE Conf. Computer Vision and Pattern Recognition, 1997, pp. 858863.
    29. 29)
      • 29. Ambrosch, K., Kubinger, W.: ‘Accurate hardware-based stereo vision’, Comput. Vis. Image Underst., 2010, 114, (11), pp. 13031316 (doi: 10.1016/j.cviu.2010.07.008).
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-cvi.2011.0077
Loading

Related content

content/journals/10.1049/iet-cvi.2011.0077
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading