Soft Computing

, Volume 12, Issue 8, pp 751–764 | Cite as

Fuzzy-genetic optimization of the parameters of a low cost system for the optical measurement of several dimensions of vehicles

Original Paper


When designing optical measurement systems, it is common to use cameras, lenses and frame grabbers specially designed for metrology applications. These devices are expensive, therefore optical metrology is not the technology of choice in low cost applications. On the contrary to this, surveillance video cameras and home oriented frame grabbers are cheap, but imprecise. Their use introduces inaccuracies in the measurements, that sometimes can be compensated by software. Following this last approach, in this paper it is proposed to use fuzzy techniques to exploit the tolerance for imprecision of a practical metrology application (to automate the measurement of vehicle dimensions in Technical Inspection of Vehicles in Spain, the equivalent of the Ministry Of Transport Test or MOT Test in UK) and to find an economic solution. It will be shown that a genetic algorithm (GA), guided by a fuzzy characterization of the sources of error, can optimize the placement of the video cameras in a station so that these mentioned sensors can be used to take measurements within the required tolerance.


Fuzzy uncertainty Genetic algorithms Random sets Stereoscopic vision Metrology 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. Abdel-Aziz Y, Karara H (1971) Direct linear transformation from comparator coordinates into object space coordinates in close-range photogrammetry. In: Proceedings of the ASP Symposium on Close Range Photogrammetry. Fall Church, VA: American Society of Photogrammetry, pp 1–18Google Scholar
  2. Bhat DN and Nayar SK (1998). Ordinal measures for image correspondence. IEEE Trans Pattern Anal Mach Intell 20: 415–423 CrossRefGoogle Scholar
  3. Blostein SD and Huang TS (1987). Error analysis in stereo determination of 3D point positions. IEEE Trans Pattern Anal Mach Intell 9: 752–765 Google Scholar
  4. Brown MZ, Burschka D and Hager GD (2003). Advances in computational stereo. IEEE Trans Pattern Anal Mach Intell 25: 993–1008 CrossRefGoogle Scholar
  5. Chen L, Armstrong CW and Raftopoulos DD (1994). An investigation on the accuracy of three-dimensional space reconstruction using the direct linear transformation technique. J Biomech 27: 493–500 CrossRefGoogle Scholar
  6. Couso I, Sánchez L and Gil P (2004). Imprecise distribution functions associated to a random set. Inf Sci 159: 109–123 MATHCrossRefGoogle Scholar
  7. Cressie NAC (1993). Statistics for Spatial Data. Wiley, London Google Scholar
  8. Duda R and Hart P (1973). Pattern classification and scene analysis. Wiley, New York MATHGoogle Scholar
  9. Eshelman LJ, Schaffer JD (1993) Real-coded genetic algorithms and interval schemata. In: Foundations of genetic algorithms.2. Morgan Kaufmann Publishers, Inc., San Mateo, pp 187–202Google Scholar
  10. Faugeras O, Hotz B, Matthieu H, Vieville T, Zhang Z, Fua P, Theron E, Moll L, Berry G, Vuillemin J, Bertin P, Proy C (1993) Real time correlation-based stereo: algorithm, implementations and applications INRIA Technical Report 2013Google Scholar
  11. Faugeras O and Luong QT (2001). The Geometry of Multiple Images. The MIT Press, Cambridge MATHGoogle Scholar
  12. Goodman N (1985). Uncertainty Models for Knowledge-based Systems. North-Holland, Amsterdam MATHGoogle Scholar
  13. Hartley R and Zisserman A (2000). Multiple View Geometry in Computer Vision. Cambridge University Press, Cambridge MATHGoogle Scholar
  14. Hatze H (1988). High-precision three-dimensional photogrammetric calibration and object space reconstruction using a modified DLT-approach. J Biomech 21: 533–538 CrossRefGoogle Scholar
  15. Herrera F and Lozano M (1998). Tackling real-coded genetic algorithms: Operators and tools for the behavioural analysis. Artif Intell Rev 12: 265–319 MATHCrossRefGoogle Scholar
  16. Herrera F, Lozano M, Pérez E, Sánchez AM, Villar P (2002) Multiple crossover per couple with selection of the two best offspring: an experimental study with the BLX-α crossover operator for real-coded genetic algorithms. In: Advances in artificial intelligence—IBERAMIA 2002: 8th Ibero–American Conference on AI LNCS 2527/2002, pp 392–401Google Scholar
  17. Hinrichs RN and McLean SP (1995). NLT and extrapolated DLT: 3D cinematography alternatives for enlarging the volume of calibration. J Biomech 28: 1219–1224 CrossRefGoogle Scholar
  18. Hoff W and Ahuja N (1989). Surfaces from stereo: integrating feature matching, disparity estimation and contour detection. IEEE Trans Pattern Anal Mach Intell 11: 121–136 CrossRefGoogle Scholar
  19. Kamgar-Parsi B (1989). Evaluation of quantization error in computer vision. IEEE Trans Pattern Anal Mach Intell 11: 929–940 CrossRefGoogle Scholar
  20. Klir G, Folger T (1988) Fuzzy sets, uncertainty, and information. Prentice HallGoogle Scholar
  21. Kwon YH, Lindley S (2000) Applicability of 4 localized-calibration methods on underwater motion analysis. In: XVIII International Symposium on Biomechanics in SportsGoogle Scholar
  22. Marzan GT, Karara HM (1975) A computer program for direct linear transformation solution of the collinearity condition, and some applications of it. In: Proceedings of the symposium on close-range photogrammetric systems. Falls Church, VA: American Society of Photogrammetry, pp 87:109Google Scholar
  23. Mason SO and Grünt A (1995). Automatic sensor placement for accurate dimensional inspection. Comput Vis Image Underst 61: 454–467 CrossRefGoogle Scholar
  24. McVey ES and Lee JW (1982). Some accuracy and resolution aspects of computer vision distance measurements. IEEE Trans Pattern Anal Mach Intell 4: 646–649 CrossRefGoogle Scholar
  25. Michalewicz Z (1992). Genetic algorithms + data structures = evolution programs. Springer, Heidelberg MATHGoogle Scholar
  26. Olague G and Mohr R (2002). Optimal Camera Placement for Accurate Reconstruction. Pattern Recognit 35: 927–944 MATHCrossRefGoogle Scholar
  27. Olague G (2002). Automated photogrammetric network design using genetic algorithms. Photogramm Eng Remote Sens 68: 423–431 Google Scholar
  28. Olague G and Hernández B (2005). A new accurate and flexible model-based multi-corner detector for measurement and recognition. Patter Recognit Lett 26: 27–41 CrossRefGoogle Scholar
  29. Olague G and Dunn E (2006). Development of a practical photogrammetric network design using evolutionary computing. Photogramm Rec 117: 22–38 Google Scholar
  30. Rodrí guez JJ and Aggarwal JK (1990). Stochastic analysis of stereo quantization error. IEEE Trans Pattern Anal Mach Intell 12: 467–470 CrossRefGoogle Scholar
  31. Sánchez L (1998). A random sets-based method for identifying fuzzy models. Fuzzy Sets Syst 3: 343–354 CrossRefGoogle Scholar
  32. Santamarí a J, Cordón O, Damas S, Alemán I, Botella M (2007) A scatter search-based technique for pair-wise 3D range image registration in forensic anthropology. Soft Comput 9:819–828Google Scholar
  33. Scharstein D and Szeliski R (1998). Stereo matching with non-linear diffusion. Int’l J Comput Vis 28: 155–174 CrossRefGoogle Scholar
  34. Shapiro R (1978). Direct linear transformation method for three-dimensional cinematography. Res Quart 49: 197–205 Google Scholar
  35. Tolt G and Kalaykov I (2006). Measures based on fuzzy similarity for stereo matching of color images. Soft Comput 10: 1117–1126 CrossRefMATHGoogle Scholar
  36. Tomasi C and Manduchi R (1998). Stereo matching as a nearest-neighbor problem. IEEE Trans Pattern Anal Mach Intell 20: 333–340 CrossRefGoogle Scholar
  37. Verri A and Torre V (1986). Absolute depth estimates in stereopsis. J Opt Soc Am 3: 297–299 Google Scholar
  38. Wong PW (1991). On quantization errors in computer vision. IEEE Trans Pattern Anal Mach Intell 13: 951–956 CrossRefGoogle Scholar

Copyright information

© Springer-Verlag 2007

Authors and Affiliations

  1. 1.Department of Computer ScienceUniversity of OviedoGijónSpain
  2. 2.Department of Computer ScienceUniversity of JaénJaénSpain

Personalised recommendations