Skip to main content
SpringerLink
Log in

GPU deformable part model for object recognition

  • Original Research Paper
  • Published:
Journal of Real-Time Image Processing Aims and scope Submit manuscript

Abstract

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.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5

Similar content being viewed by others

References

  1. Viola, P., Jones, M., Snow, D.: Detecting pedestrians using patterns of motion and appearance. In: International Conference on Computer Vision, IEEE Press (2003)

  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)

  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. 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)

  5. Letessier, P., Buisson, O., Joly, A., Boujemaa, N.: Scalable mining of small visual objects. In: ACM Multimedia (2012)

  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)

  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)

  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)

    Article  Google Scholar 

  9. Cho, H., Rybski, P.E., Bar-Hillel, A., Zhang, W.: Real-time pedestrian detection with deformable part models. In: Intelligent Vehicles Symposium (2012)

  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)

  11. Pedersoli, M., Gonzalez, J., Hu, X., Roca, X.: Towards a real-time pedestrian detection based only on vision. J. Intell. Transp. Syst. (2012)

  12. Felzenszwalb, P.F., Girshick, R.B., McAllester, D.A.: Cascade object detection with deformable part models. In: CVPR (2010)

  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)

  14. Alexe, B., Deselaers, T., Ferrari, V.: What is an object? In: CVPR (2010)

  15. Dollár, P., Belongie, S., Perona, P. The fastest pedestrian detector in the west. In: BMVC (2010)

  16. Prisacariu, V., Reid, I.: fastHOG—a real-time GPU implementation of HOG. Department of Engineering Science, Oxford University, Tech. rep. (2009)

  17. Benenson, R., Mathias, M., Timofte, R., Van Gool, L. Pedestrian detection at 100 frames per second. In: CVPR (2012)

  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)

  19. Cuda, C.: Best practices guide. http://docs.nvidia.com/cuda/cuda-c-best-practices-guide/index.html (2013)

  20. Nvidia cuda home page. http://www.nvidia.com/object/cuda_home_new.html (2013)

  21. Opencv home page. http://opencv.org/ (2013)

  22. Danielsson, P.E.: Euclidean distance mapping 14(3), 227–248 (1980)

    Google Scholar 

  23. Grevera, G.J.: Distance transform algorithms and their implementation and evaluation. In: Deformable Models, pp 33–60 (2007)

  24. Everingham, M., Van Gool, L., Williams, C.K.I., Winn, J., Zisserman, A. The PASCAL visual object classes challenge 2007 (VOC2007) Results. http://www.pascal-network.org/challenges/VOC/voc2007/workshop/index.html (2007)

  25. Prisacariu, V., Reid, I. fastHOG—a real-time GPU implementation of HOG. Tech. Rep. 2310/09. Department of Engineering Science, Oxford University (2009)

Download references

Author information

Authors and Affiliations

  1. CEA, LIST, Vision and Content Engineering Laboratory, Gif-sur-Yvette, France

    Etienne Gadeski, Hamidreza Odabai Fard & Hervé Le Borgne

Authors
  1. Etienne Gadeski
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Hamidreza Odabai Fard
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Hervé Le Borgne
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Hervé Le Borgne.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Gadeski, E., Fard, H.O. & Le Borgne, H. GPU deformable part model for object recognition. J Real-Time Image Proc 14, 279–291 (2018). https://doi.org/10.1007/s11554-014-0447-5

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11554-014-0447-5

Keywords

Search

Navigation