Estimation of Critical Parameters in Concrete Production Using Multispectral Vision Technology

  • Michael E. Hansen
  • Bjarne K. Ersbøll
  • Jens M. Carstensen
  • Allan A. Nielsen
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3540)


We analyze multispectral reflectance images of concrete aggregate material, and design computational measures of the important and critical parameters used in concrete production. The features extracted from the images are exploited as explanatory variables in regression models and used to predict aggregate type, water content, and size distribution. We analyze and validate the methods on five representative aggregate types, commonly used in concrete production. Using cross validation, the generated models proves to have a high performance in predicting all of the critical parameters.


Light Emit Diode Critical Parameter Multispectral Image Canonical Discriminant Analysis Concrete Production 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


  1. 1.
    Mindess, S., Young, J.F.: Concrete. Prentice-Hall, Inc., Englewood Cliffs (1981)Google Scholar
  2. 2.
    Rixom, M.R., Mailuaganam, N.P.: Chemical Admixtures for Concrete. R. & F.N. Spon, NY (1986)Google Scholar
  3. 3.
    Fisher, R.A.: The use of multiple measurements in taxonomic problems. Annals of Eugenics 7, 179–188 (1936)Google Scholar
  4. 4.
    Bartlett, M.S.: The Statistical Significance of Canonical Correlations. Biometrika 32(1), 29–37 (1941)zbMATHCrossRefMathSciNetGoogle Scholar
  5. 5.
    Wilks, S.S.: Certain Generalizations in the Analysis of Variance. Biometrika 24(3/4), 471–494 (1932)CrossRefGoogle Scholar
  6. 6.
    Lawley, D.N.: Tests of Significance in Canonical Analysis. Biometrika 46(1/2), 59–66 (1959)zbMATHCrossRefMathSciNetGoogle Scholar
  7. 7.
    Lattin, J., Carroll, J.D., Green, P.E.: Analyzing Multivariate Data. Brooks/Cole, Monterey (2003)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2005

Authors and Affiliations

  • Michael E. Hansen
    • 1
  • Bjarne K. Ersbøll
    • 1
  • Jens M. Carstensen
    • 2
  • Allan A. Nielsen
    • 1
  1. 1.Informatics and Mathematical Modelling (IMM)Technical University of Denmark
  2. 2.Videometer A/SHørsholm

Personalised recommendations