Advertisement

Multimedia Tools and Applications

, Volume 77, Issue 15, pp 20227–20246 | Cite as

Granular-based dense crowd density estimation

  • Ven Jyn Kok
  • Chee Seng Chan
Article
  • 203 Downloads

Abstract

Dense crowd density estimation is one of the fundamental tasks in crowd analysis. While tremendous progress has been made to understand crowd scenes along with the rise of Convolutional Neural Networks (CNNs), research work on dense crowd density estimation is still an ongoing process. In this paper, we propose a novel approach to learn discriminative crowd features from granules, that conforms to the outline between crowd and background (i.e. non-crowd) regions, for density estimation. It shows that by studying the inner statistics of granules for density estimation, this approach is adaptive to arbitrary distribution of crowd (i.e. scene independent). Multiple features fusion is proposed to learn discriminative crowd features from granules. This is to be used as description of the crowd where a direct mapping between the features and crowd density is learned. Extensive experiments on public benchmark datasets demonstrate the effectiveness of our novel approach for scene independent dense crowd density estimation.

Keywords

Dense crowd analysis Density estimation Texture features Visual surveillance 

Notes

Acknowledgements

This research is supported by the GGPM grant GGPM-2017-024, from the National University of Malaysia (UKM); and Chee Seng Chan is supported by the Fundamental Research Grant Scheme (FRGS) MoHE Grant FP070-2015A, from the Ministry of Education Malaysia.

References

  1. 1.
    Ali S, Shah M (2007) A lagrangian particle dynamics approach for crowd flow segmentation and stability analysis. In: IEEE Conference on Computer Vision and Pattern Recognition. IEEE, pp 1–6Google Scholar
  2. 2.
    Ali S, Nishino K, Manocha D, Shah M (2013) Modeling, simulation and visual analysis of crowds: A multidisciplinary perspective. In: Modeling, Simulation and Visual Analysis of Crowds, The International Series in Video Computing, vol 11. Springer, New York, pp 1–19Google Scholar
  3. 3.
    Chan AB, Dong D (2011) Generalized gaussian process models. In: IEEE Conference on Computer Vision and Pattern Recognition, pp 2681–2688Google Scholar
  4. 4.
    Chan A B, Vasconcelos N (2012) Counting people with low-level features and bayesian regression. IEEE Trans Image Process 21(4):2160–2177MathSciNetCrossRefzbMATHGoogle Scholar
  5. 5.
    Chan AB, Liang ZSJ, Vasconcelos N (2008) Privacy preserving crowd monitoring: Counting people without people models or tracking. In: IEEE Conference on Computer Vision and Pattern Recognition. IEEE, pp 1–7Google Scholar
  6. 6.
    Chen K, Loy CC, Gong S, Xiang T (2012) Feature mining for localised crowd counting. In: Proceedings of the British Machine Vision Association Conference, vol 1, pp 21.1–21.11Google Scholar
  7. 7.
    Chen K, Gong S, Xiang T, Loy CC (2013) Cumulative attribute space for age and crowd density estimation. In: IEEE Conference on Computer Vision and Pattern Recognition. IEEE, pp 2467–2474Google Scholar
  8. 8.
    Davies A C, Yin J H, Velastin S A (1995) Crowd monitoring using image processing. Electron Commun Eng J 7(1):37–47CrossRefGoogle Scholar
  9. 9.
    Everingham M, Van Gool L, Williams C K, Winn J, Zisserman A (2010) The pascal visual object classes (voc) challenge. Int J Comput Vis 88(2):303–338CrossRefGoogle Scholar
  10. 10.
    Field D J (1987) Relations between the statistics of natural images and the response properties of cortical cells. J Opt Soc Amer A 4(12):2379–2394CrossRefGoogle Scholar
  11. 11.
    Fu H, Ma H, Xiao H (2014) Scene-adaptive accurate and fast vertical crowd counting via joint using depth and color information. Multimed Tools Appl 73 (1):273–289CrossRefGoogle Scholar
  12. 12.
    Ge W, Collins RT (2009) Marked point processes for crowd counting. In: IEEE Conference on Computer Vision and Pattern Recognition. IEEE, pp 2913–2920Google Scholar
  13. 13.
    Grant J M, Flynn P J (2017) Crowd scene understanding from video: A survey. ACM Trans Multimed Comput Commun Appl 13(2):19CrossRefGoogle Scholar
  14. 14.
    Helbing D, Mukerji P (2012) Crowd disasters as systemic failures: Analysis of the love parade disaster. EPJ Data Sci 1(1):1–40CrossRefGoogle Scholar
  15. 15.
    Helbing D, Brockmann D, Chadefaux T, Donnay K, Blanke U, Woolley-Meza O, Moussaid M, Johansson A, Krause J, Schutte S, Perc M (2014) Saving human lives: What complexity science and information systems can contribute. J Stat Phys 158(3):735–781MathSciNetCrossRefzbMATHGoogle Scholar
  16. 16.
    Hoerl A E, Kennard R W (1970) Ridge regression: Biased estimation for nonorthogonal problems. Technometrics 12(1):55–67CrossRefzbMATHGoogle Scholar
  17. 17.
    Idrees H, Saleemi I, Seibert C, Shah M (2013) Multi-source multi-scale counting in extremely dense crowd images. In: IEEE Conference on Computer Vision and Pattern Recognition, pp 2547–2554Google Scholar
  18. 18.
    Jon G (2015) Saudi arabia hajj disaster death toll at least 2,110. Business Insider, http://www.businessinsider.com/ap-saudi-arabia-hajj-disaster-death-toll-at-least-2110-2015-10?IR=T&r=US&IR=T
  19. 19.
    Kae A, Sohn K, Lee H, Learned-Miller E (2013) Augmenting crfs with boltzmann machine shape priors for image labeling. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 2019–2026Google Scholar
  20. 20.
    Kaiman J (2015) Shanghai: dozens killed and injured in stampede at new year celebrations. The Guardian, http://www.theguardian.com/world/2014/dec/31/shanghai-35-people-killed-42-injured-new-year-crush
  21. 21.
    Kang K, Wang X (2014) Fully convolutional neural networks for crowd segmentation. arXiv:http://arXiv.org/abs/14114464
  22. 22.
    Kok V J, Chan C S (2017) Grcs: Granular computing-based crowd segmentation. IEEE Trans Cybern 47(5):1157–1168CrossRefGoogle Scholar
  23. 23.
    Kok V J, Lim M K, Chan C S (2016) Crowd behavior analysis: A review where physics meets biology. Neurocomputing 177:342–362CrossRefGoogle Scholar
  24. 24.
    Kovesi P (1999) Image features from phase congruency. Videre: J Comput Vis Res 1(3):1–26Google Scholar
  25. 25.
    Lempitsky V, Zisserman A (2010) Learning to count objects in images. In: Advances in Neural Information Processing Systems, pp 1324–1332Google Scholar
  26. 26.
    Lim MK, Kok V J, Loy CC, Chan CS (2014) Crowd saliency detection via global similarity structure. In: International Conference on Pattern Recognition. lim and Kok contributed equally. IEEE, pp 3957–3962Google Scholar
  27. 27.
    Liu L, Xing J, Ai H, Lao S (2012) Semantic superpixel based vehicle tracking. In: International Conference on Pattern Recognition. IEEE, pp 2222–2225Google Scholar
  28. 28.
    Lloyd CD (2006) Local Models for Spatial Analysis. CRC Press, https://books.google.com.my/books?id=bIKToJ9en1UC
  29. 29.
    Lowe D G (2004) Distinctive image features from scale-invariant keypoints. Int J Comput Vis 60(2):91–110CrossRefGoogle Scholar
  30. 30.
    Loy C C, Chen K, Gong S, Xiang T (2013) Crowd counting and profiling: Methodology and evaluation. In: Modeling, Simulation and Visual Analysis of Crowds. Springer, pp 347–382Google Scholar
  31. 31.
    Marana A, Velastin S, Costa L, Lotufo R (1997) Estimation of crowd density using image processing. In: IEE Colloquium on Image Processing for Security Applications. IET, pp 11/1–11/8Google Scholar
  32. 32.
    Marana A, Velastin S, Costa L, Lotufo R (1998) Automatic estimation of crowd density using texture. Saf Sci 28(3):165–175CrossRefGoogle Scholar
  33. 33.
    Mikolajczyk K, Schmid C (2004) Scale andamp; affine invariant interest point detectors. Int J Comput Vis 60(1):63–86CrossRefGoogle Scholar
  34. 34.
    Morrone M C, Owens R A (1987) Feature detection from local energy. Pattern Recogn Lett 6(5):303–313CrossRefGoogle Scholar
  35. 35.
    Mousse M A, Motamed C, Ezin E C (2017) People counting via multiple views using a fast information fusion approach. Multimed Tools Appl 76(5):6801–6819CrossRefGoogle Scholar
  36. 36.
    Oppenheim AV, Lim JS (1981) The importance of phase in signals. Proc IEEE 69(5):529–541.  https://doi.org/10.1109/PROC.1981.12022 CrossRefGoogle Scholar
  37. 37.
    Rabaud V, Belongie S (2006) Counting crowded moving objects. In: IEEE Conference on Computer Vision and Pattern Recognition, vol 1. IEEE, pp 705–711Google Scholar
  38. 38.
    Rodriguez M, Laptev I, Sivic J, Audibert JY (2011) Density-aware person detection and tracking in crowds. In: IEEE International Conference on Computer Vision. IEEE, pp 2423–2430Google Scholar
  39. 39.
    Rodriguez M, Sivic J, Laptev I (2013) Analysis of crowded scenes in video, pp 251–272.  https://doi.org/10.1002/9781118577851.ch15
  40. 40.
    Ryan D, Denman S, Sridharan S, Fookes C (2015) An evaluation of crowd counting methods, features and regression models. Comput Vis Image Underst 130:1–17CrossRefGoogle Scholar
  41. 41.
    Shao J, Kang K, Change Loy C, Wang X (2015) Deeply learned attributes for crowded scene understanding. In: IEEE Conference on Computer Vision and Pattern Recognition, pp 4657–4666Google Scholar
  42. 42.
    Shawe-Taylor J, Cristianini N (2004) Kernel methods for pattern analysis. Cambridge University Press, CambridgeCrossRefzbMATHGoogle Scholar
  43. 43.
    Solmaz B, Moore B E, Shah M (2012) Identifying behaviors in crowd scenes using stability analysis for dynamical systems. IEEE Trans Pattern Anal Mach Intell 34(10):2064–2070CrossRefGoogle Scholar
  44. 44.
    Tuytelaars T (2010) Dense interest points. In: IEEE Conference on Computer Vision and Pattern Recognition. IEEE, pp 2281–2288Google Scholar
  45. 45.
    United Nations Department of Economic and Social Affairs, Population Division (2013) World Population Prospects: The 2012 Revision, vol 1. United Nations Publications, New YorkGoogle Scholar
  46. 46.
    United Nations Department of Economic and Social Affairs, Population Division (2014) World Urbanization Prospects: The 2014 Revision. Highlights United Nations Publications, New YorkGoogle Scholar
  47. 47.
    Vedaldi A, Fulkerson B (2010) Vlfeat: An open and portable library of computer vision algorithms. In: Proceedings of the International Conference on Multimedia. ACM, pp 1469–1472Google Scholar
  48. 48.
    Zhan B, Monekosso D N, Remagnino P, Velastin S A, Xu L Q (2008) Crowd analysis: a survey. Mach Vis Appl 19(5-6):345–357CrossRefGoogle Scholar
  49. 49.
    Zhang C, Li H, Wang X, Yang X (2015) Cross-scene crowd counting via deep convolutional neural networks. In: IEEE Conference on Computer Vision and Pattern Recognition, pp 833–841Google Scholar
  50. 50.
    Zhang Y, Zhou D, Chen S, Gao S, Ma Y (2016) Single-image crowd counting via multi-column convolutional neural network. In: IEEE Conference on Computer Vision and Pattern Recognition, pp 589–597Google Scholar
  51. 51.
    Zhou B, Wang X, Tang X (2011) Random field topic model for semantic region analysis in crowded scenes from tracklets. In: IEEE Conference on Computer Vision and Pattern Recognition. IEEE, pp 3441–3448Google Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2017

Authors and Affiliations

  1. 1.Faculty of Information Science and TechnologyNational University of MalaysiaBangiMalaysia
  2. 2.Center of Image and Signal Processing, Faculty of Computer Science and Information TechnologyUniversity of MalayaKuala LumpurMalaysia

Personalised recommendations