Rectification-Free Multibaseline Stereo for Non-ideal Configurations

  • Hongdong Li
  • Richard Hartley
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3617)

Abstract

SSSD-based linear multibaseline stereo is an efficient implementation of multi-camera stereo vision system. This efficiency, however, vitally relies on the ideal configuration of all cameras. For dealing with non-ideal configurations, conventional stereo rectification algorithms can be used, but the performances are often still not satisfactory. This paper proposes a new algorithm to process non-ideally configured multibaseline stereo system, which not only avoids the rectification procedure but also remains the efficiency of SSSD at the same time. This is fulfilled by using the idea of tensor transfer used in image-based-rendering area. In particular, the multibaseline stereo is reformulated as a novel-view-synthesis problem. We propose a new concept of tensor-transfer to generate novel views as well as compute the depth map.

References

  1. 1.
    Okutomi, M., Kanade, T.: A multiple baseline stereo. IEEE-trans on PAMI 15(4), 353–363 (1993)Google Scholar
  2. 2.
    Williamson, T., Thorpe, C.: A Specialized Multibaseline Stereo Technique for Obstacle Detection. In: Proc. IEEE-CVPR 1998, pp. 238–244 (1998)Google Scholar
  3. 3.
    Loop, C., Zhang, Z.Y.: Computing rectifying homographies for stereo vision. In: Proc. IEEE-CVPR 1999, vol. 1, pp. 125–131 (1999)Google Scholar
  4. 4.
    Mulligan, J., Kaniilidis, K.: Trinocular Stereo for Non-parallel Configurations. In: Proc. ICPR 2000, vol. 1, pp. 567–570 (2000)Google Scholar
  5. 5.
    Sato, T., Kanbara, M., Yokoya, N., Takemura, H.: Dense 3-D Reconstruction of an Outdoor Scene by Hundreds-Baseline Stereo Using a Hand-Held Video Camera. Int. J. Comput. Vision 47(1-3), 119–129 (2002)MATHCrossRefGoogle Scholar
  6. 6.
    Seitz, S.M., Dyer, C.R.: Photorealistic scene reconstruction by voxel coloring. In: Proc. IEEE-CVPR, pp. 1067–1073 (1997)Google Scholar
  7. 7.
    Kimura, M., Saito, H., Kanade, T.: Stereo Matching between Three Images by Iterative Refinement in PVS. IEICE Trans. on Information and Systems  E86-D(1), 89–100 (2003)Google Scholar
  8. 8.
    Li, Y., Lin, S., Lu, H., Kang, S.B., Shum, H.Y.: Multibaseline Stereo in the Presence of Specular Reflections. In: Proc. ICPR 2002 (2002)Google Scholar
  9. 9.
    Fusiello, A., Trucco, E., Verri, A.: Rectification with unconstrained stereo geometry. In: Proc BMVC 1997, pp. 400–409 (1997)Google Scholar
  10. 10.
    Gluckman, J.M., Nayar, S.K.: Rectifying Transformations That Minimize Resampling Effects. In: Proc. IEEE-CVPR 2001 (2001)Google Scholar
  11. 11.
    Hartley, R., Zisserman, A.: Multiple View Geometry in Computer Vision, 2nd edn. Cambridge University Press, Cambridge (2004)MATHGoogle Scholar
  12. 12.
    Papadimitriou, D., Dennis, T.: Epipolar line estimation and rectification for stereo image pairs. IEEE trans on Image Processing 5(4), 672–676 (1996)CrossRefGoogle Scholar
  13. 13.
    Pollefeys, M., Koch, R., Gool, L.: A simple and efficient rectification method for general motion. In: Proc. of the 7th ICCV 1999 (1999)Google Scholar
  14. 14.
    Scharstein, D., Szeliski, R.: A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence Algorithms. IJCV 47(1-3), 7–42 (2002)MATHCrossRefGoogle Scholar
  15. 15.
    Li, Y., Lin, S., Lu, H., Kang, S.B., Shum, H.Y.: Multibaseline stereo in the presence of specular reflections. In: ICPR 2002, vol. 3, pp. 573–576 (2002)Google Scholar
  16. 16.
    Lim, M., Paragios, D.: Uncalibrated stereo rectification for automatic 3D surveillance. In: Proc. IEEE-ICIP 2004 (2004)Google Scholar
  17. 17.
    Fitzgibbon, A.W., Wexler, Y., Zisserman, A.: Image-based rendering using image-based priors. In: Proc. ICCV 2003 (2003)Google Scholar
  18. 18.
    Avidan, S., Shashua, A.: Novel View synthesis by Cascading Trilinear Tensors. IEEE-Trans on Visualization and Computer Graphics 4(4) (1998)Google Scholar
  19. 19.
    Mordohai, P., Medioni, G.: Dense Multiple View Stereo with General Camera Placement using Tensor Voting. In: Proc. of 3DPVT 2004 (2004)Google Scholar
  20. 20.
    Xiao, J., Shah, M.: From Images to Video: View Morphing of Three Images. In: Vision, Modeling, and Visualization (VMV2003), pp. 495–502 (2003)Google Scholar
  21. 21.
    Pritchett, P., Zisserman, A.: Wide baseline stereo matching. In: Proc. ICCV 1998, pp. 754–760 (1998)Google Scholar
  22. 22.
    Ferrari, V., Tuytelaars, T., Van Gool, L.: Wide-baseline muliple-view Correspondences. In: IEEE-CVPR 2003, pp. 711–718 (2003)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2005

Authors and Affiliations

  • Hongdong Li
    • 1
  • Richard Hartley
    • 1
  1. 1.Research School of Information Sciences and EngineeringThe Australian National University, ASSeT, Canberra Research Labs, National ICT Australia 

Personalised recommendations