OSA's Digital Library

Applied Optics

Applied Optics


  • Editor: Joseph N. Mait
  • Vol. 51, Iss. 7 — Mar. 1, 2012
  • pp: 841–845

Stereo vision calibration based on GMDH neural network

Bingwen Chen, Wenwei Wang, and Qianqing Qin  »View Author Affiliations

Applied Optics, Vol. 51, Issue 7, pp. 841-845 (2012)

View Full Text Article

Enhanced HTML    Acrobat PDF (200 KB)

Browse Journals / Lookup Meetings

Browse by Journal and Year


Lookup Conference Papers

Close Browse Journals / Lookup Meetings

Article Tools



In order to improve the accuracy and stability of stereo vision calibration, a novel stereo vision calibration approach based on the group method of data handling (GMDH) neural network is presented. Three GMDH neural networks are utilized to build a spatial mapping relationship adaptively in individual dimension. In the process of modeling, the Levenberg–Marquardt optimization algorithm is introduced as an interior criterion to train each partial model, and the corrected Akaike’s information criterion is introduced as an exterior criterion to evaluate these models. Experiments demonstrate that the proposed approach is stable and able to calibrate three-dimensional (3D) locations more accurately and learn the stereo mapping models adaptively. It is a convenient way to calibrate the stereo vision without specialized knowledge of stereo vision.

© 2012 Optical Society of America

OCIS Codes
(150.1488) Machine vision : Calibration
(100.4996) Image processing : Pattern recognition, neural networks

ToC Category:
Image Processing

Original Manuscript: August 24, 2011
Revised Manuscript: November 18, 2011
Manuscript Accepted: November 27, 2011
Published: February 27, 2012

Virtual Issues
Vol. 7, Iss. 5 Virtual Journal for Biomedical Optics

Bingwen Chen, Wenwei Wang, and Qianqing Qin, "Stereo vision calibration based on GMDH neural network," Appl. Opt. 51, 841-845 (2012)

Sort:  Author  |  Year  |  Journal  |  Reset  


  1. J. Weng, P. Cohen, and M. Herniou, “Camera calibration with distortion models and accuracy evaluation,” IEEE Trans. Pattern Anal. Machine Intell. 14, 965–980 (1992). [CrossRef]
  2. J. I. González, J. C. Gámez, C. G. Artal, and A. M. N. Cabrera, “Stability study of camera calibration methods,” in Proceedings of CI Workshop en Agentes Fisicos (WAF), Spain, 2005, pp. 1–8.
  3. M. B. Lynch and C. H. Dagli, “Back propagation neural network for stereoscopic vision calibration,” Proc. SPIE 8194, 289–298 (1991).
  4. D. Ge, X. Yao, and W. Chen, “Research of machine vision system based on RBF neural network,” in Proceedings of Computer Science and Information Technology, Singapore, 2008, pp. 218–222.
  5. J. Wen and G. Schweitzer, “Hybrid calibration of CCD cameras using artificial neural nets,” in Proceedings of Neural Networks, Singapore, 1991, pp. 337–342.
  6. A. G. Ivakhnenko, “Polynomial theory of complex systems,” IEEE Trans. Syst. Man Cybernet. 1, 364–378 (1971). [CrossRef]
  7. E.-S. M. El-Alfy, “A hierarchical GMDH-based polynomial neural network for handwritten numeral recognition using topological features,” in Proceedings of Neural Networks, Barcelona, 2010, pp. 1–7.
  8. A. G. Ivakhnenko, “The review of problems solvable by algorithms of the group method of data handling (GMDH),” Pattern Recogn. Image Anal. 5, 527–535 (1995).
  9. M. T. Hagan and M. B. Menhaj, “Training feed forward networks with the Marquardt algorithm,” IEEE Trans. Neural Netw. 5, 989–993 (1994). [CrossRef]
  10. M. Lourakis, “Levmar,” http://www.ics.forth.gr/~lourakis/levmar/ .
  11. G. Jekabsons, “Adaptive basis function construction: an approach for adaptive building of sparse polynomial regression models,” in Machine Learning, Y. Zhang, ed. (InTech, 2010), pp. 127–155.
  12. A. Hirotugu, “A new look at the statistical model identification,” IEEE Trans. Autom. Control 19, 716–723 (1974). [CrossRef]
  13. M. T. Ahmed, E. E. Hemayed, and A. A. Farag, “Neurocalibration: a neural network that can tell camera calibration parameters,” in Proceedings of IEEE Conference on Computer Vision (IEEE, 1999), pp. 463–468.

Cited By

Alert me when this paper is cited

OSA is able to provide readers links to articles that cite this paper by participating in CrossRef's Cited-By Linking service. CrossRef includes content from more than 3000 publishers and societies. In addition to listing OSA journal articles that cite this paper, citing articles from other participating publishers will also be listed.


Fig. 1. Fig. 2.

« Previous Article  |  Next Article »

OSA is a member of CrossRef.

CrossCheck Deposited