Machine Vision and Applications

, Volume 18, Issue 6, pp 343–354 | Cite as

An image-based feature tracking algorithm for real-time measurement of clad height

  • Mehrdad Iravani-Tabrizipour
  • Ehsan ToyserkaniEmail author
Original Paper


This paper presents a novel algorithm for real-time detection of clad height in laser cladding which is known as a layered manufacturing technique. A real-time measurement of clad geometry is based on the use of a developed trinocular optical detector composed of three CCD cameras and the associated interference filters and lenses. The images grabbed by the trinocular optical detector are fed into an algorithm which combines an image-based tracking protocol and a recurrent neural network to extract the clad height in real-time. The image feature tracking strategy is a synergy between a simple image selecting protocol, a fuzzy thresholding technique, a boundary tracing method, a perspective transformation and an extraction of elliptical features of the projected melt pool’s images. The proposed algorithm and the trained network were utilized in the process resulting in excellent detection of the clad height at various working conditions in which SS303L was deposited on mild steel. It was concluded that the developed system can detect the clad height independent from clad paths with about 12% maximum error.


Laser cladding Trinocular CCD-based optical detector Image processing Recurrent neural network Perspective transformation 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Boddu, M.R., Musti, S., Lenards, R.G., Agarwal, S., Liou, F.W.: Empirical modeling and vision based control for laser aided metal deposition process. In: Solid Freeform Fabrication Proceedings, The University of Texas at Austin, pp. 452–459 (2001)Google Scholar
  2. 2.
    Duley, W.W., Kinsman, G.: Method and apparatus for real-time control of laser processing of materials. US Patent Number 5659479 (1997)Google Scholar
  3. 3.
    Elman L.J. (1990). Finding structure in time. Cogn. Sci. 14: 179–211 CrossRefGoogle Scholar
  4. 4.
    Haferkamp H., Gerken J., Stegemann D. and Reichert C. (1997). In-situ Inderschung des Harestofftransportes beim Laserstrahl-Dispergieren mittels Hochgeschwindigkeits-Radioskopie. Metal 3: 185–191 Google Scholar
  5. 5.
    Halir, R., Flusser, J.: Numerically stable direct least squares fitting of ellipses (2000)Google Scholar
  6. 6.
    Hartly R. and Zisserman A. (2003). Multiple view geometry in computer vision. Cambridge Press, Cambridge Google Scholar
  7. 7.
    Hu D., Kovacevic R. Modeling and measuring the thermal behaviour of the molten pool in closed-loop controlled laser-based additive manufacturing. In: Proceedings of the Institution of Mechanical Engineers, Part B. J. Mech. Eng. Sci. 217, 441–452 (2003)Google Scholar
  8. 8.
    Huang L.K. and Wang M.J. (1995). Image thresholding by minimizing the measure of fuzziness. Pattern recogn. 28(1): 41–51 CrossRefGoogle Scholar
  9. 9.
    Koch, J., Mazumder, J.: Apparatus and methods for monitoring and controlling multi-layer laser cladding. US patent number 6122564 (2000)Google Scholar
  10. 10.
    Mazumder J., Dutta D., Kikuchi N. and Ghosh A. (2000). Closed-loop direct metal deposition: art to part. Opt. Lasers Eng. 34: 397–414 CrossRefGoogle Scholar
  11. 11.
    Meriaudeau F. and Truchetet F. (1996). Control and optimization of the laser cladding process using matrix cameras and image processing. J. Laser Appl. 36: 317–324 Google Scholar
  12. 12.
    Nerrand O., Roussel P., Urrbani D., Personnaz L. and Drefus G. (1994). Training recurrent neural networks: Why and how? An illustration in dynamical process modeling. IEEE Trans. Neural Netw. 5(2): 178–184 CrossRefGoogle Scholar
  13. 13.
    Otsu N. (1979). Threshold selection method from gray-level histogram. IEEE Trans. Syst. Man Cybern. 9: 62–66 CrossRefGoogle Scholar
  14. 14.
    Principe J.C., Euliano N.R. and Lefebvre W.C. (2000). Neural and adaptive systems: fundamentals through simulations. Wiley, New York Google Scholar
  15. 15.
    Sonka M., Hlavac V. and Boyle R. (1999). Image processing, analysis and machine vision. Pacific Grove, CA Google Scholar
  16. 16.
    Toyserkani, E., Khajepour, A., Corbin, S.: Vision-based feedback control of laser powder deposition. In: IEEE Mechatronics and Machine Vision in Practice Conference (2003). Billingsley, J. (ed.) ISBN: 0-8638-0290-7Google Scholar
  17. 17.
    Wren, C.R.: (1998) interpolator/Google Scholar

Copyright information

© Springer-Verlag 2007

Authors and Affiliations

  1. 1.Department of Mechanical and Mechatronics EngineeringUniversity of WaterlooWaterlooCanada

Personalised recommendations