Journal of Real-Time Image Processing

, Volume 14, Issue 2, pp 279–291 | Cite as

GPU deformable part model for object recognition

  • Etienne Gadeski
  • Hamidreza Odabai Fard
  • Hervé Le BorgneEmail author
Original Research Paper


We consider the problem of rapidly detecting objects in static images or videos. The task consists in locating and identifying objects of interest. With the progress of affordable high computing hardware, we propose to analyse and evaluate the deformable part model on the Graphics Processing Unit. We do not take any prior assumptions on the scene and location of the objects. We provide a fast implementation and analyse the different modules of the state-of-the-art detector. Our implementation allows to accelerate both training and testing. While maintaining comparable classification performance, we report a speed-up of \(\times\)10.6 using a standard GPU card compared to a baseline implemented in C++ on a single core and \(\times\)5 compared to a multi-core OpenMP (8 threads) implementation.


Deformable part model Object recognition GPU Pascal VOC Classification 


  1. 1.
    Viola, P., Jones, M., Snow, D.: Detecting pedestrians using patterns of motion and appearance. In: International Conference on Computer Vision, IEEE Press (2003)Google Scholar
  2. 2.
    Ess, A., Leibe, B., Schindler, K., van Gool, L.: A mobile vision system for robust multi-person tracking. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR’08), IEEE Press (2008)Google Scholar
  3. 3.
    Gavrila, D.M., Munder, S.: Multi-cue pedestrian detection and tracking from a moving vehicle. Int J Comput Vision 73(1):41–59. doi: 10.1007/s11263-006-9038-7 (2007)
  4. 4.
    Chum, O., Perdoch, M., Matas, J.: Geometric min-hashing: finding a (thick) needle in a haystack. In: Computer Vision and Pattern Recognition, pp. 17–24 (2009)Google Scholar
  5. 5.
    Letessier, P., Buisson, O., Joly, A., Boujemaa, N.: Scalable mining of small visual objects. In: ACM Multimedia (2012)Google Scholar
  6. 6.
    Viola, P.A., Jones, M.J.: Rapid object detection using a boosted cascade of simple features. In: Computer Vision and Pattern Recognition, IEEE Computer Society (2001)Google Scholar
  7. 7.
    Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: Schmid, C., Soatto, S., Tomasi, C. (eds.) International Conference on Computer Vision & Pattern Recognition, vol. 2, pp. 886–893 (2005)Google Scholar
  8. 8.
    Felzenszwalb, P.F., Girshick, R.B., McAllester, D., Ramanan, D.: Object detection with discriminatively trained part based models. IEEE Trans. Pattern Anal. Mach. Intell. 32(9), 1627–1645 (2010a)CrossRefGoogle Scholar
  9. 9.
    Cho, H., Rybski, P.E., Bar-Hillel, A., Zhang, W.: Real-time pedestrian detection with deformable part models. In: Intelligent Vehicles Symposium (2012)Google Scholar
  10. 10.
    Sudowe, P., Leibe, B. Efficient use of geometric constraints for sliding-window object detection in video. In: International Conference on Computer Vision Systems (ICVS’11) (2011)Google Scholar
  11. 11.
    Pedersoli, M., Gonzalez, J., Hu, X., Roca, X.: Towards a real-time pedestrian detection based only on vision. J. Intell. Transp. Syst. (2012)Google Scholar
  12. 12.
    Felzenszwalb, P.F., Girshick, R.B., McAllester, D.A.: Cascade object detection with deformable part models. In: CVPR (2010)Google Scholar
  13. 13.
    Lampert, C.H., Blaschko, M.B., Hofmann, T.: Efficient subwindow search: a branch and bound framework for object localization. IEEE Trans Pattern Anal Mach Intell (2009)Google Scholar
  14. 14.
    Alexe, B., Deselaers, T., Ferrari, V.: What is an object? In: CVPR (2010)Google Scholar
  15. 15.
    Dollár, P., Belongie, S., Perona, P. The fastest pedestrian detector in the west. In: BMVC (2010)Google Scholar
  16. 16.
    Prisacariu, V., Reid, I.: fastHOG—a real-time GPU implementation of HOG. Department of Engineering Science, Oxford University, Tech. rep. (2009)Google Scholar
  17. 17.
    Benenson, R., Mathias, M., Timofte, R., Van Gool, L. Pedestrian detection at 100 frames per second. In: CVPR (2012)Google Scholar
  18. 18.
    Song, H.O., Zickler, S., Althoff, T., Girshick, R., Fritz, M., Geyer, C., Felzenszwalb, P., Darrell, T.: Sparselet models for efficient multiclass object detection. In: European Conference on Computer Vision (ECCV) (2012)Google Scholar
  19. 19.
  20. 20.
  21. 21.
    Opencv home page. (2013)
  22. 22.
    Danielsson, P.E.: Euclidean distance mapping 14(3), 227–248 (1980)Google Scholar
  23. 23.
    Grevera, G.J.: Distance transform algorithms and their implementation and evaluation. In: Deformable Models, pp 33–60 (2007)Google Scholar
  24. 24.
    Everingham, M., Van Gool, L., Williams, C.K.I., Winn, J., Zisserman, A. The PASCAL visual object classes challenge 2007 (VOC2007) Results. (2007)
  25. 25.
    Prisacariu, V., Reid, I. fastHOG—a real-time GPU implementation of HOG. Tech. Rep. 2310/09. Department of Engineering Science, Oxford University (2009)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2014

Authors and Affiliations

  • Etienne Gadeski
    • 1
  • Hamidreza Odabai Fard
    • 1
  • Hervé Le Borgne
    • 1
    Email author
  1. 1.CEA, LIST, Vision and Content Engineering LaboratoryGif-sur-YvetteFrance

Personalised recommendations