HOME JOURNALS CONTACT

Journal of Applied Sciences

Year: 2006 | Volume: 6 | Issue: 11 | Page No.: 2461-2465
DOI: 10.3923/jas.2006.2461.2465
A New Method to Resolve the Matching Problem Without Using a Calibration of Camera
S. Ait Kaci Azzou and A. Boukerram

Abstract: In this study, we present a novel approach to match a line segment in the sequence of images obtained by camera in motion. The proposed method is based only on the formalism of the slope of the segment in the sequence of images. We use the definition of the projection of points and the relation which exists between the slopes of the segment in various images. The approach developed not needs the calibration of camera. To resolve the matching problem, two segments in three images are necessary. Experiment showed feasibility as well as robustness of the algorithm.

Fulltext PDF

How to cite this article
S. Ait Kaci Azzou and A. Boukerram, 2006. A New Method to Resolve the Matching Problem Without Using a Calibration of Camera. Journal of Applied Sciences, 6: 2461-2465.

Keywords: projective geometry, the motion, estimation of the structure, tracking, Matching and computer vision

REFERENCES
  • Bartoli, A. and P. Sturm, 2003. Multiple view structure and motion from line correspondances. Proceedings of the 9th IEEE International Conference on Computer Vision, October 13-16, 2003, Nice, France, pp: 207-217.

  • Bazin, P.L. and J.M. Vezien, 2000. Tracking geometric primitives in video streams. Proceedings of the 4th Irish Machine Vision and Image Processing Conference, September 2000, Balfast, pp: 43-50.

  • Dekeyser, F., P.P. Bouthemy, P. Perez and E. Payo, 2000. Super-resolution from noisy image sequence exploiting a 2D parametric model. LAPR Int. Conf. Pattern Recog. ICPR Barcelone, ESP, 3: 354-357.

  • Duda, R. and P. Hart, 1973. Pattern Classification and Scene Analysis. Wiley Interscience Publication, New York

  • Faugeras, O.D., 1988. Quelques pas vers la vision artificielle en trois dimensions. TSI Techniques et Sci. Inform., 7: 547-590.
    Direct Link    

  • Faugeras, O. and B. Mourrain, 1995. On the geometry and algebra of the point and line correspondences between N images. Proceedings of the 5th International Conference on Computer Vision, Cambridge Massachussetts, USA., June 20-23, 1995, IEEE Computer Society, Washington DC, USA., pp: 951-956.

  • Hough, V. and C. Paul, 1962. Method and means for recognizing complex patterns. US Patent, 3069654. http://www.freepatentsonline.com/3069654.html.

  • Huang, T.S. and A.N. Netravali, 1994. Motion and structure from feature correspondances: A review. Proc. IEEE, 82: 252-268.
    CrossRef    Direct Link    

  • Martine, D. and T. Pajdla, 2003. Line reconstruction from many perspective images by factorization. Proceedings of the Conference on Computer Vision and Pattern Recognition, June 18-20, 2003, IEEE Computer Society Press, Madison, Wisconsin, USA., pp: 497-502.

  • Meer, P., D. Mintz, D.Y. Kim and Rosenfeld, 1991. A robust regression methods in computer vision: A review. Int. J. Comput. Vision, 6: 59-70.
    CrossRef    Direct Link    

  • Spetsakis, M. and J. Aloimonos, 1990. Structure from motion using linecorrespondances. Int. J. Comput. Vision, 4: 171-171.

  • Legarreta, G.I., Z. Zakaria and G.M. Hall, 1996. Lactic Fermentation of Prawn Waste: Comparison of Commercial and Isolated Starter Culture. In: Advances in Chitin Science, Domard, A., C. Jeuniaux, R. Muzzarelli and G. Roberts (Eds.). Vol. 1. Jac-Ques Andre, Lyon, France, pp: 399-406

  • Azzou, S.A.K., S. Larab and J.L. Coronado, 1996. Appariement de trajectoires issues d'un systeme de vision stereoscopique en mouvement de convergence. Proceedings of the 12th International Conference on Analysis and Optimization of Systems Images, Wavelets and PDEs Paris, June 26-28, 1996, Springer, Berlin, pp: 323-337.

    • © Science Alert. All Rights Reserved