Boosted Algorithms for Visual Object Detection on Graphics Processing Units

  • Hicham Ghorayeb
  • Bruno Steux
  • Claude Laurgeau
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3852)

Abstract

Nowadays, the use of machine learning methods for visual object detection has become widespread. Those methods are robust. They require an important processing power and a high memory bandwidth which becomes a handicap for real-time applications. The recent evolution of commodity PC computer graphics boards (GPU) has the potential to accelerate those algorithms.

In this paper, we present a novel use of graphics hardware for object detection in advanced computer vision applications. We implement a system for object-detection based on AdaBoost [1]. This system can be tuned to run partially or totally on the GPU. This system is evaluated with two face-detection applications. Those applications are based on the boosted cascade of classifiers: Multiple Layers Face Detection (MLFD), and Single Layer Face Detection (SLFD). We show that the SLFD implementation on GPU performs up to nine times faster than its CPU counterpart. The MLFD, in the other hand, can be accelerated using the (GPU) and performs up to three times faster than the CPU.

To the best of our knowledge, this is the first attempt to implement a sliding window technique for visual object-detection on GPU, with promessing performance.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Freund, Y., Schapire, R.E.: A decision-theoretic generalization of on-line learning and an application to boosting. In: European Conference on Computational Learning Theory, pp. 23–37 (1995)Google Scholar
  2. 2.
    Rowley, H.A., Baluja, S., Kanade, T.: Neural network-based face detection. IEEE Transactions on Pattern Analysis and Machine Intelligence 20, 23–38 (1998)CrossRefGoogle Scholar
  3. 3.
    Vapnik, V.N.: The nature of statistical learning theory. Springer, New York (1995)MATHGoogle Scholar
  4. 4.
    Viola, P., Jones, M.: Robust real-time object detection. International Journal of Computer Vision (2002)Google Scholar
  5. 5.
    Abramson, Y., Steux, B., Ghorayeb, H.: Yef real-time object detection. In: ALART 2005:International workshop on Automatic Learning and Real-Time, pp. 5–13 (2005)Google Scholar
  6. 6.
    Viola, P.A., Jones, M.J., Snow, D.: Detecting pedestrians using patterns of motion and appearance. International Journal of Computer Vision 63, 153–161 (2005)CrossRefGoogle Scholar
  7. 7.
    Lienhart, R., Maydt, J.: An extended set of haar-like features for rapid object detection. In: Proc. IEEE International Conf. Image Processing, vol. 1, pp. 900–903 (2002)Google Scholar
  8. 8.
    Abramson, Y., Steux, B.: Hardware-friendly pedestrian detection and impact prediction. In: IVS 2004, pp. 590–595 (2004)Google Scholar
  9. 9.
    Fung, J., Mann, S.: Using multiple graphics cards as a general purpose parallel computer: applications to computer vision. In: ICPR 2004. Proceedings of the 17th International Conference on Pattern Recognition, vol. 1, pp. 805–808 (2004)Google Scholar
  10. 10.
    Fernando, R., Kilgard, M.J.: The Cg Tutorial, 1st edn. (2003)Google Scholar
  11. 11.
    Buck, I., Hanrahan, P.: Data parallel computation on graphics hardware. Graphics Hardware (2003)Google Scholar
  12. 12.
    Venkatasubramanian, S.: The graphics card as a stream computer. In: Workshop on the Management and Processing of Data Streams AT&T Labs – Research (2003)Google Scholar
  13. 13.
    Buck, I., Foley, T., Horn, D., Sugerman, J., Mike, K., Pat, H.: Brook for gpus: Stream computing on graphics hardware. ACM Transactions on Graphics (2004)Google Scholar
  14. 14.
    Segal, M., Akeley, K.: The OpenGL graphics System: A specification Version 2.0 (2004)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Hicham Ghorayeb
    • 1
  • Bruno Steux
    • 1
  • Claude Laurgeau
    • 1
  1. 1.Robotics CenterEcole des Mines de ParisParisFrance

Personalised recommendations