A Template-Based Approach for Real-Time Speed-Limit-Sign Recognition on an Embedded System Using GPU Computing

  • Pınar Muyan-Özçelik
  • Vladimir Glavtchev
  • Jeffrey M. Ota
  • John D. Owens
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6376)


We present a template-based pipeline that performs realtime speed-limit-sign recognition using an embedded system with a lowend GPU as the main processing element. Our pipeline operates in the frequency domain, and uses nonlinear composite filters and a contrastenhancing preprocessing step to improve its accuracy. Running at interactive rates, our system achieves 90% accuracy over 120 EU speed-limit signs on 45 minutes of video footage, superior to the 75% accuracy of a non-real-time GPU-based SIFT pipeline.


Graphic Processing Unit Scale Invariant Feature Transform Road Sign Graphic Processing Unit Implementation Scale Invariant Feature Transform Feature 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Owens, J.D., Luebke, D., Govindaraju, N., Harris, M., Krüger, J., Lefohn, A.E., Purcell, T.: A survey of general-purpose computation on graphics hardware. Computer Graphics Forum 26(1), 80–113 (2007)CrossRefGoogle Scholar
  2. 2.
    Fung, J., Mann, S., Aimone, C.: OpenVIDIA: Parallel GPU computer vision. In: ACM Multimedia, pp. 849–852 (2005)Google Scholar
  3. 3.
    Lowe, D.G.: Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vision 60(2), 91–110 (2004)CrossRefGoogle Scholar
  4. 4.
    Piccioli, G., De Micheli, E., Parodi, P., Campani, M.: Robust road sign detection and recognition from image sequences. In: IEEE IV 1994, pp. 278–283 (1994)Google Scholar
  5. 5.
    Miura, J., Tsuyoshi, K., Shirai, Y.: An active vision system for real-time traffic sign recognition. In: IEEE ITSC 2000, pp. 52–57 (2000)Google Scholar
  6. 6.
    Betke, M., Makris, N.C.: Fast object recognition in noisy images using simulated annealing. In: IEEE ICCV 1995, pp. 523–530 (1995)Google Scholar
  7. 7.
    Gavrila, D.: Traffic sign recognition revisited. In: DAGM 1999, pp. 86–93 (1999)Google Scholar
  8. 8.
    Cyganek, B.: Road signs recognition by the scale-space template matching in the log-polar domain. In: Martí, J., Benedí, J.M., Mendonça, A.M., Serrat, J. (eds.) IbPRIA 2007. LNCS, vol. 4477, pp. 330–337. Springer, Heidelberg (2007)CrossRefGoogle Scholar
  9. 9.
    Guibert, L., Keryer, G., Servel, A., Attia, M., MacKenzie, H., Pellat-Finet, P., de Bourgrenet de la Tocnaye, J.: On-board optical joint transform correlator for real-time road sign recognition. Opt. Eng. 34(1), 135–143 (1995)CrossRefGoogle Scholar
  10. 10.
    Taniguchi, M., Mokuno, Y., Kintaka, K., Matsuoka, K.: Correlation filter design for classification of road sign by multiple optical correlators. In: SPIE, vol. 3804, pp. 140–147 (1999)Google Scholar
  11. 11.
    Perez, E., Javidi, B.: Nonlinear distortion-tolerant filters for detection of road signs in background noise. IEEE Transactions on Vehicular Technology 51(3), 567–576 (2002)CrossRefGoogle Scholar
  12. 12.
    Javidi, B., Castro, M.A., Kishk, S., Perez, E.: Automated detection and analysis of speed limit signs. Technical Report JHR 02-285, University of Connecticut (2002)Google Scholar
  13. 13.
    Torresen, J., Bakke, W.J., Sekanina, L.: Efficient recognition of speed limit signs. In: IEEE ITSC 2004, pp. 652–656 (2004)Google Scholar
  14. 14.
    Hsu, S.H., Huang, C.L.: Road sign detection and recognition using matching pursuit method. Image and Vision Computing 19(3), 119–129 (2001)CrossRefMathSciNetGoogle Scholar
  15. 15.
    Casasent, D.: Unified synthetic discriminant function computational formulation. Appl. Opt. 23(10), 1620–1627 (1984)CrossRefGoogle Scholar
  16. 16.
    Mahalanobis, A., Kumar, B.V.K.V., Casasent, D.: Minimum average correlation energy filters. Appl. Opt. 26(17), 3633–3640 (1987)CrossRefGoogle Scholar
  17. 17.
    Javidi, B., Painchaud, D.: Distortion-invariant pattern recognition with fourier-plane nonlinear filters. Appl. Opt. 35(2), 318–331 (1996)CrossRefGoogle Scholar
  18. 18.
    Savvides, M., Kumar, B.V., Khosla, P.: Face verification using correlation filters. In: IEEE AutoID 2002, pp. 56–61 (2002)Google Scholar
  19. 19.
    Zuiderveld, K.: Contrast limited adaptive histogram equalization. In: Graphics Gems IV, pp. 474–485 (1994)Google Scholar
  20. 20.
    Keller, C.G., Sprunk, C., Bahlmann, C., Giebel, J., Baratoff, G.: Real-time recognition of U.S. speed signs. In: IEEE IV 2008, pp. 518–523 (2008)Google Scholar
  21. 21.
    Wu, C.: SiftGPU: A GPU implementation of scale invariant feature transform, SIFT (2007),
  22. 22.
    Kuş, M.C., Gökmen, M., Etaner-Uyar, A.S.: Traffic sign recognition using scale invariant feature transform and color classification. In: ISCIS 2008 (2008)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Pınar Muyan-Özçelik
    • 1
  • Vladimir Glavtchev
    • 1
    • 2
  • Jeffrey M. Ota
    • 2
  • John D. Owens
    • 1
  1. 1.University of CaliforniaDavis
  2. 2.BMW Group Technology OfficePalo Alto

Personalised recommendations