Conformed identification in corresponding points detection problem
Ye.V. Goshin, V.A. Fursov

Full text of article: Russian language.

Abstract:
In this paper is considered a problem of image transformation, which consists in forming lines of corresponding points in images using fundamental matrix formed by a small number given corresponding points. A new approach based on a conformed identification is proposed for this problem.

Key words:
Driver assistance systems, CCTV systems, pattern recognition, artifacts detection, fractal dimension, iterative functions system.

References:

  1. Mallon, J. Projective Rectification from the Fundamental Matrix / John Mallon, Paul F. Whelan // Image and Vision Computing. – 2005. – Vol. 21. – P. 643-650.
  2. Hartley, R.I. Theory and Practice of Projective Rectification / Richard I. Hartley // International Journal of Computer Vision. – 1999. – Vol. 35. – P. 115-127.
  3. Fischler, M.A. Random Sample Consensus: A Paradigm for Model Fitting with Applications to Image Analysis and Automated Cartography / Martin A. Fischler, Robert C. Bolles // Communications of the ACM. – 1981. – Vol. 24. – P. 381-392.
  4. Torr, P.H.S. The Development and Comparison of Robust Methods for Estimating the Fundamental Matrix / P.H.S. Torr, D.W. Murray // International Journal of Computer Vision. – 1997. – Vol. 24. – P. 271-300.
  5. Fursov, V.A. Conformed Identification of the Controlled Object with a Small Number of Observations / V.A. Fursov // Mechatronics, Automation, Control. – 2010. – Vol. 3(108). – P. 2-8. – ISSN 1684-6427. – (In Russian).
  6. Forsyth, D. Computer Vision: A Modern Approach / David Forsyth, Jean Ponce. – Moscow: “Williams” Publishing House, 2004. – 928 p. – (In Russian)
© 2009, IPSI RAS
Institution of Russian Academy of Sciences, Image Processing Systems Institute of RAS, Russia, 443001, Samara, Molodogvardeyskaya Street 151; E-mail: ko@smr.ru; Phones: +7 (846) 332-56-22, Fax: +7 (846) 332-56-2