Algorithm for determining the location and dimensions of objects based on analysis of image objects
P.S. Geidarov

Full text of article: Russian language.

Abstract:
The paper presents an algorithm for determining the distance to the object based on analysis images obtained by optical systems. To this end, it consider curves black and white color palette for the vertical and horizontal components, an algorithm for segmentation of curves and determination coefficients blurs the boundaries of image objects. The proposed algorithm is considered as an example one and two-lens optical systems. It also consider the possibility of determining the size and displacement of objects relative to the optical axis of the system.

Key words:
distance to an object, a visual estimate of the distance, radar systems, range finders, image sharpness, optical systems, optical formula, biological eyes

References:

  1. The principle of laser ranging. – http://www.optics4you.ru/article5.html. – (in Russian).
  2. Churilovsky, V.N. The theory of optical devices / V.N. Churilovsky. – Moscow: “Mashinostroenie” Publisher, 1966. – P. 47-49. – (in Russian).
  3. Golovko, V.L. Neural networks: training, organization and application / V.L. Golovko. – Moscow: IPRZHR, 2001. – 256 p. – (in Russian).
  4. Geidarov, P.S. Neuron networks on the basis of the metric methods of recognition in application to tasks with fuzzy inference / P.S. Geidarov // Artificial intelligence and decision making. – 2010. – N 2. – P. 77-88. – (in Russian).
  5. Kozin, N.E. Gradual learning the radial neural networks / N.E. Kozin, V.A. Fursov // Computer Optics. – 2004. – N 26. – P. 138-141. – (in Russian).
  6. Kruglov, V.V. Fuzzy logic and artificial neural networks / V.V. Kruglov, M.I. Dli, R.Y. Golunov. – Moscow: “Fizmalit” Publisher, 2001. – 224 p. – (in Russian).
  7. Wasserman, F. Neural Computing. Theory and Practice / F. Wasserman. – Moscow: “Mir” Publisher, 1992. – 184 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) 332-56-20