International Journal of Computer Vision

, Volume 71, Issue 1, pp 49–69 | Cite as

Centralized and Distributed Multi-view Correspondence

Article

Abstract

A probabilistic algorithm is presented for finding correspondences across multiple images in systems with large numbers of cameras and considerable overlap. The algorithm employs the theory of random graphs to provide an efficient probabilistic algorithm that performs Wide-baseline Stereo (WBS) comparisons on a small number of image pairs, and then propagates correspondence information among the cameras. A concrete mathematical analysis of its performance is given. The algorithm is extended to handle false-positive and false-negative failures of the WBS computations. We characterize the detectability of the existence of such failures, and propose an efficient method for this detection. Based on this, we propose a heuristic method for discarding false matches, and demonstrate its effectiveness in reducing errors.

Since in many multi-camera applications cameras are attached to processors that handle local processing and communication, it is natural to consider distributed solutions that make use of the local processors and do not use a central computer. Our algorithm is especially suited to run in a distributed setting. If the local processors are sufficiently powerful, this allows an order of magnitude increase in computational efficiency. More importantly, a distributed implementation provides strong robustness guarantees, and eliminates the existence of a single point of failure that is inherent when the application is coordinated by a central computer. We show how to efficiently overcome processor crashes and communication failures with a minimal reduction in the quality of the algorithm’s results.

Keywords

correspondence wide baseline stereo multi-view distributed vision random graphs error correction fault tolerance distributed multi-camera system 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Avidan, S., Moses, Y., and Moses, Y. 2004. Probabilistic multi-view correspondence in a distributed setting with no central server. In Proc. of European Conference of Computer Vision, pp. 428–441.Google Scholar
  2. Baumberg, A. 2000. Reliable feature matching across widely separated views. In Proc. of IEEE Computer Vision and Pattern Recognition, pp. I:774–781.Google Scholar
  3. Blum, A., Bansal, N., and Chawla, S. 2004. Correlation clustering. In Machine Learning 56(1-3):89–113.Google Scholar
  4. Bollobás, B. 2001. Random Graphs, 2nd edition. Cambridge University Press.Google Scholar
  5. Bollobás, B. and Thomason, A.G. 1985. Random graphs of small order. In Random Graphs, Annals of Discrete Mathematics.Google Scholar
  6. Brumitt, B., Krumm, J., Meyers, B., and Shafer, S. 2000. Ubiquitous computing and the role of geometry. IEEE Wireless Communications 7(5):41–43.Google Scholar
  7. Cai, Q. and Aggarwal, J. 1998. Automatic tracking of human motion in indoor scenes across multiple synchronized video streams. In International Conference on Computer Vision, pp. 356–362.Google Scholar
  8. Chetverikov, D. and Matas, J. 2002. Periodic textures as distinguished regions for wide-baseline stereo correspondence. In Texture, pp. 25–30.Google Scholar
  9. Collins, R., Lipton, A., Kanade, T., Fujiyoshi, H., Duggins, D., Tsin, Y., Tolliver, D., Enomoto, N., and Hasegawa, O. 2000. A system for video surveillance and monitoring. CMU-RI-TR-00-12.Google Scholar
  10. Collins, R. and Tsin, Y. 1999. Calibration of an outdoor active camera system. In Proc. of IEEE Computer Vision and Pattern Recognition, pp. 528–534.Google Scholar
  11. Erdös, P. and Rényi, A. 1959. On random graphs Publ. Math. Debrecen, 6:290–297.MATHMathSciNetGoogle Scholar
  12. Ferrari, V., Tuytelaars, T., and Gool, L.V. 2003. Wide-baseline multiple-view correspondences. In Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 718– 725.Google Scholar
  13. Kang, J., Cohen, I., and Medioni, G. 2002. Continuous multi-views tracking using tensor voting. In Motion 02, pp. 181–186.Google Scholar
  14. Karuppiah, D., Zhu, Z. Shenoy, P., and Riseman, E. 2001. A fault-tolerant distributed vision system architecture for object tracking in a smart room. In International Workshop on Computer Vision Systems, pp. 201–219.Google Scholar
  15. Levi, N. and Werman, M. 2003. The viewing graph. In Proc. of IEEE Computer Vision and Pattern Recognition, pp. 518–524.Google Scholar
  16. Lopez de Ipina, D., Mendonca, P.R.S., and Hopper, A. 2002. Trip: A low-cost vision-based location system for ubiquitous computing. In Personal and Ubiquitous Computing Journal, 6(3):206–219.Google Scholar
  17. Lynch, N.A. 1996. Distributed Algorithms. MIT Press.Google Scholar
  18. M.A. Fischler, R. C.B. 1981. Random sample consensus: A paradigm for model fitting with applications to image analysis and automated cartography. In Communication of the ACM, vol. 24, pp. 381– 395.Google Scholar
  19. Matas, J., Chum, O., Urban, M., and Pajdla, T. 2002. Robust wide baseline stereo from maximally stable extremal regions. In The British Machine Vision Conference.Google Scholar
  20. Mikolajczyk, K. and Schmid, C. 2004. Scale & affine invariant interest point detectors. Int. J. Comput. Vision 60, 1: 63–86.Google Scholar
  21. Mittal, A. and Davis, L. 2003. M2tracker: A multi-view approach to segmenting and tracking people in a cluttered scene. IJCV 51, 3: 189–203.CrossRefGoogle Scholar
  22. Mullender, S. 1993. Distributed Systems. Addison Wesley.Google Scholar
  23. Narayanan, P., Kanade, T., and Rander, P. 1995. Virtualized reality: Concepts and early results. In Proc. IEEE Workshop on Representation of Visual Scenes, pp. 69–76.Google Scholar
  24. Pritchett, P. and Zisserman, A. 1998. Wide baseline stereo matching. In Proc. International Conference on Computer Vision, pp. 754–760.Google Scholar
  25. Rahimi, M., Estrin, D., Baer, R., Uyeno, H., and Warrior, J. 2004. Cyclops, image sensing and interpretation in wireless networks. In Proceedings of the 2nd International Conference on Embedded Networked Sensor Systems, pp. 311–311.Google Scholar
  26. Saito, H., Baba, S., Kimura, M., Vedula, S., and Kanade, T. 1999. Appearance-based virtual view generation of temporally-varying events from multi-camera images in the 3d room. In Proc. of Second International Conference on 3-D Digital Imaging and Modeling, pp. 516–525.Google Scholar
  27. Schaffalitzky, F. and Zisserman, A. 2001. Viewpoint invariant texture matching and wide baseline stereo. In Proc. International Conference on Computer Vision, pp. II:636–643.Google Scholar
  28. Schaffalitzky, F. and Zisserman, A. 2002. Multi-view matching for unordered image sets, or how do I organize my holiday snaps? In Proc. of European Conference of Computer Vision, pp. 414–431.Google Scholar
  29. Tanenbaum, A.S. and van Steen, M. 2001. Distributed Systems Principles and Paradigms. Pearson Education Publisher.Google Scholar
  30. Triggs, W., McLauchlan, P., Hartley, R., and Fitzgibbon, A. 1999. Bundle adjustment—a modern synthesis. In Vision Algorithms: Theory and Practice, pp. 298–372.Google Scholar
  31. Tuytelaars, T. and Van Gool, L. 2000. Wide baseline stereo matching based on local, affinely invariant regions. In The British Machine Vision Conference, pp. 412–425.Google Scholar
  32. Wren, C. and Rao, S. 2003. Self-configuring, lightweight sensor networks for ubiquitous computing. In Proc. of International Conference on Ubiquitous Computing (UbiComp.), pp. 205–206.Google Scholar

Copyright information

© Springer Science + Business Media, LLC 2006

Authors and Affiliations

  1. 1.The Efi Arazi School of Computer ScienceThe Interdisciplinary CenterHerzliyaIsrael
  2. 2.National ICTAustralia
  3. 3.Department of Electrical Engineering, TechnionHaifaIsrael

Personalised recommendations