Efficient GPU Implementation of Informed-Filters for Fast Computation

Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10749)

Abstract

Human detection is an important task for several practical applications that require high-speed processing with good detection accuracy. This paper proposes a high-speed implementation of Informed-Filtersthat shows excellent accuracy in human detection. Our implementation reduces memory access during feature calculation and realizes efficient computation on an NVIDIA GPU where a thread is allocated to a detection sub-window. Experimental results using top-view images considering surveillance from UAVs showed that the processing speed was about 100 fps for \(2560 \times 1352\) images on an NVIDIA 980Ti GPU, whereas it was 5.4 fps on an Intel Xeon 2.30 GHz CPU.

Notes

Acknowledgment

The research results have been achieved thanks to “Research and development of Innovative Network Technologies to Create the Future”, the Commissioned Research of National Institute of Information and Communications Technology (NICT), JAPAN.

References

  1. 1.
    Hara, S., Yomo, H., Miyamoto, R., Kawamoto, Y., Okuhata, H., Kawabata, T., Nakamura, H.: Challenges in real-time vital signs monitoring for persons during exercises. Int. J. Wirel. Inf. Netw. 24(2), 91–108 (2017)CrossRefGoogle Scholar
  2. 2.
    Oro, D., Fernández, C., Rodríguez, S.J., Martorell, X., Hernando, J.: Real-time GPU-based face detection in HD video sequences. In: Proceedings of IEEE International Conference on Computer Vision, pp. 530–537 (2011)Google Scholar
  3. 3.
    Benenson, R., Mathias, M., Timofte, R., Van Gool, L.J.: Pedestrian detection at 100 frames per second. In: Proceedings of IEEE Conference on Computer Vision Pattern Recognition, pp. 2903–2910 (2012)Google Scholar
  4. 4.
    Miyamoto, R., Oki, T.: Soccer player detection with only color features selected using informed Haar-like features. In: Blanc-Talon, J., Distante, C., Philips, W., Popescu, D., Scheunders, P. (eds.) ACIVS 2016. LNCS, vol. 10016, pp. 238–249. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-48680-2_22 CrossRefGoogle Scholar
  5. 5.
    Hiromoto, M., Sugano, H., Miyamoto, R.: Partially parallel architecture for AdaBoost-based detection with Haar-like features. Proc. IEEE Trans. Circ. Syst. Video Technol. 19, 41–52 (2009)CrossRefGoogle Scholar
  6. 6.
    Hiromoto, M., Miyamoto, R.: Hardware architecture for high-accuracy real-time pedestrian detection with CoHOG features. In: Proceedings of IEEE International Conference on Computer Vision Workshops, pp. 894–899 (2009)Google Scholar
  7. 7.
    Hiromoto, M., Miyamoto, R.: Cascade classifier using divided CoHOG features for rapid Pedestrian detection. In: Fritz, M., Schiele, B., Piater, J.H. (eds.) ICVS 2009. LNCS, vol. 5815, pp. 53–62. Springer, Heidelberg (2009).  https://doi.org/10.1007/978-3-642-04667-4_6 CrossRefGoogle Scholar
  8. 8.
    Yu, J., Miyamoto, R., Onoye, T.: Fast pedestrian detection using a soft-cascade of the CoHOG-based classier: how to speed-up SVM classiers based on multiple-instance pruning. IEEE Trans. Image Process. 22, 4752–4761 (2013)MathSciNetCrossRefMATHGoogle Scholar
  9. 9.
    Zhang, S., Benenson, R., Schiele, B.: Filtered channel features for Pedestrian detection. In: Proceedings of IEEE Conference on Computer Vision Pattern Recognition, pp. 1751–1760 (2015)Google Scholar
  10. 10.
    Redmon, J., Divvala, S.K., Girshick, R.B., Farhadi, A.: You only look once: unified, real-time object detection. In: Proceedings of IEEE Conference on Computer Vision Pattern Recognition, pp. 779–788 (2016)Google Scholar
  11. 11.
    Redmon, J., Farhadi, A.: YOLO9000: better, faster, stronger. In: Proceedings of IEEE Conference on Computer Vision Pattern Recognition, pp. 6517–6525 (2017)Google Scholar
  12. 12.
    Dollár, P., Tu, Z., Perona, P., Belongie, S.J.: Integral channel features. In: Proceedings of British Machine Vision Conference, pp. 1–11 (2009)Google Scholar
  13. 13.
    Nam, W., Dollár, P., Joon, H.H.: Local decorrelation for improved pedestrian detection. In: Proceedings of Advances in Neural Information Processing Systems, pp. 424–432 (2014)Google Scholar
  14. 14.
    Ohtsuki, T., Sato, M., Tachibana, M., Torii, S.: Minimum partitioning of rectilinear regions. IPSJ J. 24, 647–653 (1983)Google Scholar
  15. 15.
    NVIDIA Corporation: nVidia CUDA Programming Guide. http://docs.nvidia.com/cuda/

Copyright information

© Springer International Publishing AG, part of Springer Nature 2018

Authors and Affiliations

  1. 1.Department of Computer Science, Graduate School of Science and TechnologyMeiji UniversityTokyoJapan
  2. 2.Department of Computer Science, School of Science and TechnologyMeiji UniversityTokyoJapan

Personalised recommendations