Multimedia Tools and Applications

, Volume 74, Issue 19, pp 8703–8721 | Cite as

Evolutionary algorithms for a mixed stereovision uncalibrated 3D reconstruction

  • Alain Koch
  • Claire Bourgeois-République
  • Albert Dipanda


This paper proposes an original 3D shape reconstruction which is a mixture of the passive and active stereovision systems. Similarly to the passive stereovision systems, two cameras are used to acquire the images. As for the active stereovision methods, the detection of the points of interest (POIs) and the matching problem are solved by using a structured-light pattern projected onto the analysed object. An encoding is proposed to ease the matching procedure. Then, Evolutionary Algorithms (EAs) are designed to calculate the depth of the detected POIs. Numerous experiments are conducted to validate the different steps of the proposed method.


3D reconstruction Evolutionary algorithm Uncalibrated system Correspondence problem Encoding 


  1. 1.
    Batenburg KJ (2005) An evolutionary algorithm for discrete tomography. Discret Appl Math 151(1–3):36–54MathSciNetCrossRefzbMATHGoogle Scholar
  2. 2.
    Ben-Hamadou A, Soussen C, Daul C, Blondel W, Wolf D (2013) Flexible calibration of structured-light systems projecting point patterns. Comput Vis Image Underst 117(10):1468–1481CrossRefGoogle Scholar
  3. 3.
    Bensrhair A, Miché P, Debrie R (1996) Fast and automatic stereo vision matching algorithm based on dynamic programming method. Pattern Recogn Lett 17(5):457–466CrossRefGoogle Scholar
  4. 4.
    Bleyer M, Gelautz M (2007) Graph-cut-based stereo matching using image segmentation with symmetrical treatment of occlusions. Signal Process Image Commun 22(2):127–143CrossRefzbMATHGoogle Scholar
  5. 5.
    Brunetti A (2000) A fast and precise genetic algorithm for a non-linear fitting problem. Comput Phys Commun 124:204–211CrossRefGoogle Scholar
  6. 6.
    Chou HL, Chen Z (2004) A novel 3D planar object reconstruction from multiple uncalibrated images using the plane-induced homographies. Pattern Recogn Lett 25(12):1399–1410CrossRefGoogle Scholar
  7. 7.
    Cootes TF, Di Mauro EC, Taylor CJ, Lanitis A (1996) Flexible 3D models from uncalibrated cameras. Image Vis Comput 14(8):581–587CrossRefGoogle Scholar
  8. 8.
    Derrac J, García S, Hui S, Suganthan PN, Herrera F (2014) Analyzing convergence performance of evolutionary algorithms: a statistical approach. Inf Sci 289(24):41–58CrossRefGoogle Scholar
  9. 9.
    Dipanda A, Woo S (2010) Towards a real-time 3D shape reconstruction using a structured light system. Pattern Recogn 38(10):1632–1650CrossRefGoogle Scholar
  10. 10.
    Dipanda A, Woo S, Marzani F, Bilbault JM (2003) 3-D shape reconstruction in an active stereo vision system using genetic algorithms. Pattern Recogn 36:2143–2159CrossRefGoogle Scholar
  11. 11.
    Faugeras O, Toscani G (1987) Camera calibration for 3D computer vision. Proc. International Workshop on Machine Vision and Machine Intelligence, TokyoGoogle Scholar
  12. 12.
    Goldberg DE, Genetic Algorithms in Search (1989) Optimization & machine learning. Addison-Wesley, ReadingGoogle Scholar
  13. 13.
    Guanglong D, Zhang P (2014) Markerless human–robot interface for dual robot manipulators using Kinect sensor. Robot Comput Integr Manuf 30(2):150–159CrossRefGoogle Scholar
  14. 14.
    Han K-P, Song K-W, Chung E-Y, Cho S-J, Ha Y-H (2001) Stereo matching using genetic algorithm with adaptive chromosomes. Pattern Recogn 34(9):1729–1740CrossRefGoogle Scholar
  15. 15.
    Heikkila J (2000) Geometric camera calibration using circular control points. IEEE Trans Pattern Anal 22:1066–1077CrossRefGoogle Scholar
  16. 16.
    Ibañez R, Soria Á, Teyseyre A, Campo M (2014) Easy gesture recognition for Kinect. Adv Eng Softw 76:171–180CrossRefGoogle Scholar
  17. 17.
    Jang W, Je C, Seo Y, Lee SW (2013) Structured-light stereo: comparative analysis and integration of structured-light and active stereo for measuring dynamic shape. Opt Lasers Eng 51(11):1255–1264CrossRefGoogle Scholar
  18. 18.
    Koch A, Dipanda A, Bourgeois-République C (2010) Evolutionary-based 3D reconstruction using an uncalibrated stereovision system: application of building a panoramic object view. Multimed Tools Appl 57(3):565–586CrossRefGoogle Scholar
  19. 19.
    Salvi J, Armangue X, Batlle J (2002) A comparative review of camera calibrating methods with accuracy evaluation. Pattern Recogn 35:1617–1635CrossRefGoogle Scholar
  20. 20.
    Shii F, Zhang X, Liu Y (2004) A new method of camera pose estimation using 2D-3D corner correspondence. Pattern Recogn Lett 25:1155–1163CrossRefGoogle Scholar
  21. 21.
    Wang Y, Li Y, Zhou J, Zhang J, Fang J (2013) A non-encoding structured light approach with infrared illumination for 3D large field shape measurement. Opt Laser Technol 49:28–32CrossRefGoogle Scholar
  22. 22.
    Wei GAO, Liang WANG, Zhan-Yi HU (2008) Flexible calibration of a portable structured light system through surface plane. Acta Autom Sin 34(11):1358–1362CrossRefGoogle Scholar
  23. 23.
    Zhang J, Ge Y, Ong SH, Chui CK, Teoh SH, Yan CH (2008) Rapid surface registration of 3D volumes using a neural network approach. Image Vis Comput 23:201–210CrossRefGoogle Scholar
  24. 24.
    Zhang X, Liu Y. HuangTS (2002) Determining 3D structure and motion of man- made objects from image corners, In: Proceedings of the SSIAI’2 SantaFe, New Mexico, USA, 26–30Google Scholar
  25. 25.
    Zhao Y, Li X, Li W (2012) Binocular vision system calibration based on a one-dimensional target. Appl Opt 51:3338–3345CrossRefGoogle Scholar
  26. 26.
    Zhengyou Z (2000) A flexible new technique for camera calibration. IEEE Trans Pattern Anal Mach Intell 22(11):1330–1334CrossRefzbMATHGoogle Scholar

Copyright information

© Springer Science+Business Media New York 2014

Authors and Affiliations

  • Alain Koch
    • 1
  • Claire Bourgeois-République
    • 1
  • Albert Dipanda
    • 1
  1. 1.LE2I (CNRS-UMR 6306), Faculté des SciencesUniversité de BourgogneDijonFrance

Personalised recommendations