Pacific-Rim Symposium on Image and Video Technology

Image and Video Technology pp 123-135 | Cite as

Logarithmically Improved Property Regression for Crowd Counting

Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9431)


Crowd counting based on video camera recordings faces two major problems, namely inter-occlusion among the people, and perspective scaling. Though the former issue has been adequately addressed using different regression- and model-based schemes, a solution to the later problem remains an open problem so far. This paper proposes a novel scene-independent solution to perspective scaling. We show that it supports promising results. A property matrix, combining both a grey-level co-occurrence matrix and segmentation properties, is first obtained which is subsequently weighted using logarithmic relationships between pixel distances and foreground regions. We apply a Gaussian process regression, using a compounded kernel, to acquire an estimate for the crowd count. We show that results are comparable to those obtained when using more complex and costly techniques.


Crowd counting Perspective scaling Grey-level co-occurrence matrix Gaussian process 


  1. 1.
    Albiol, A., Silla, M.J., Albiol, A., Mossi, V.: Video analysis using corner motion statistics. In: Proceedings of IEEE International Workshop PETS, pp. 31–37 (2009)Google Scholar
  2. 2.
    Barnich, O., Droogenbroeck, M.: ViBe: A universal background subtraction algorithm for video sequences. IEEE Trans. Image Process. 20, 1709–1724 (2011)MathSciNetCrossRefGoogle Scholar
  3. 3.
    Fu, H., Ma, H., Xiao, H.: Real-time accurate crowd counting based on RGB-d information. In: Proceedings of ICIP, pp. 2685–2688 (2012)Google Scholar
  4. 4.
    Beardsley, P., Murray, D.: Camera calibration using vanishing points. Int. J. Comput. Vis. 4, 127–139 (1992)Google Scholar
  5. 5.
    Barnich, O., Droogenbroeck, M.M.V., Paquot, O.: Background subtraction: experiments and improvements for ViBe. In: Proceedings of CVPR Workshop Change Detection, pp. 32–37 (2012)Google Scholar
  6. 6.
    Garcia-Bunster, G., Torres-Torriti, M., Oberli, C.: Crowded pedestrian counting at bus stops from perspective transformations of foreground areas. Comput. Vis. IET 6, 296–305 (2012)MathSciNetCrossRefGoogle Scholar
  7. 7.
    Chan, A., Vasconcelos, N.: Counting people with low-level features and Bayesian regression. IEEE Trans. Image Process. 21, 2160–2177 (2012)MathSciNetCrossRefGoogle Scholar
  8. 8.
    Chan, A.B., Liang, Z.S.J., Vasconcelos, N.: Privacy preserving crowd monitoring: counting people without people models or tracking. In: Proceedings Computer Vision Pattern Recognition, pp. 1–7 (2008)Google Scholar
  9. 9.
    Chan, A.B., Morrow, M., Vasconcelos, N.: Analysis of crowded scenes using holistic properties. In: IEEE International Workshop Performance Evaluation Tracking Surveillance (2009)Google Scholar
  10. 10.
    Conte, D., Foggia, P., Percannella, G., Tufano, F., Vento, M.: A method for counting people in crowded scenes. In: Proceedings of IEEE International Conference Advanced Video Signal Based Surveillance, pp. 225–232 (2010)Google Scholar
  11. 11.
    Dong, L., Parameswaran, V., Ramesh, V., Zoghlami, I.: Fast crowd segmentation using shape indexing. In: Proceedings International Conference Computer Vision, pp. 1–8 (2007)Google Scholar
  12. 12.
    Fradi, H., Dugelay, J.L.: People counting system in crowded scenes based on feature regression. In: Proceedings of European Signal Processing Conference, pp. 27–31 (2012)Google Scholar
  13. 13.
    Fraile, R.: IEEE International Workshop Performance Evaluation Tracking Surveillance (PETS 2009) (2009).
  14. 14.
    Gonzales, R.C., Wintz, P.: Digital Image Processing, 3rd edn. Prentice Hall, Upper Saddle River (2009)Google Scholar
  15. 15.
    Horn, B.K.P., Schunck, B.G.: Determining optical flow. Artif. Intell. 17, 185–203 (1981)CrossRefGoogle Scholar
  16. 16.
    Klette, R.: Concise Computer Vision. Springer, London (2014)CrossRefMATHGoogle Scholar
  17. 17.
    Lalit, G., Thotsapon, S.: A Gaussian-mixture-based image segmentation algorithm. Pattern Recogn. 31(3), 315–325 (1998)CrossRefGoogle Scholar
  18. 18.
    Mousavi, S.M., Shahdi, S.O., Abu-Bakar, S.A.R.: Crowd estimation using histogram model classification based on improved uniform local binary pattern. Int. J. Comput. Electr. Eng. 4, 256–259 (2012)CrossRefGoogle Scholar
  19. 19.
    Rasmussen, C.E., Williams, C.K.I.: Gaussian Processes for Machine Learning. MIT Press, Cambridge (2006)MATHGoogle Scholar
  20. 20.
    Ryan, D., Denman, S., Fookes, C.: Crowed counting using multiple local features. In: Proceedings of Digital Image Computing: Techniques Applications, pp. 81–88 (2009)Google Scholar
  21. 21.
    Shimosaka, M., Masuda, S., Fukui, R., Mori, T., Sato, T.: Counting pedestrians in crowded scenes with efficient sparse learning. In: Proceedings of Asian Conference Pattern Recognition, pp. 27–31 (2011)Google Scholar
  22. 22.
    Subburaman, V.B., Descamps, A., Carincotte, C.: Counting people in the crowd using a generic head detector. In: Proceedings of IEEE International Conference Advanced Video Signal-Based Surveillance, pp. 470–475 (2012)Google Scholar
  23. 23.
    Tuceryan, M., Jain, A.K.: Texture analysis. In: The Handbook of Pattern Recognition and Computer Vision, pp. 207–248 (1998)Google Scholar
  24. 24.
    UCSD: UCSD Anomaly Detection Dataset (2013).
  25. 25.
    Wang, Q.: HMRF-EM-image: implementation of the hidden Markov random field model and its expectation-maximization algorithm, arXiv: 1207.3510 [cs.CV] (2012)

Copyright information

© Springer International Publishing Switzerland 2016

Authors and Affiliations

  1. 1.Centre for Advanced Studies in EngineeringIslamabadPakistan
  2. 2.Auckland University of TechnologyAucklandNew Zealand

Personalised recommendations