KSII Transactions on Internet and Information Systems (TIIS)

Korean Society for Internet Information (한국인터넷정보학회)
권호 표지
DOI QR코드

DOI QR Code

Estimation of Crowd Density in Public Areas Based on Neural Network

  • Kim, Gyujin (College of Information and Communication Engineering, Sungkyunkwan University) ;
  • An, Taeki (Metropolitan Tranportation Research Center, Korea Railway Research Institute) ;
  • Kim, Moonhyun (College of Information and Communication Engineering, Sungkyunkwan University)
  • Received : 2012.12.07
  • Accepted : 2012.08.23
  • Published : 2012.09.30
Download PDF
⟨ Previous Next ⟩

Abstract

There are nowadays strong demands for intelligent surveillance systems, which can infer or understand more complex behavior. The application of crowd density estimation methods could lead to a better understanding of crowd behavior, improved design of the built environment, and increased pedestrian safety. In this paper, we propose a new crowd density estimation method, which aims at estimating not only a moving crowd, but also a stationary crowd, using images captured from surveillance cameras situated in various public locations. The crowd density of the moving people is measured, based on the moving area during a specified time period. The moving area is defined as the area where the magnitude of the accumulated optical flow exceeds a predefined threshold. In contrast, the stationary crowd density is estimated from the coarseness of textures, under the assumption that each person can be regarded as a textural unit. A multilayer neural network is designed, to classify crowd density levels into 5 classes. Finally, the proposed method is experimented with PETS 2009 and the platform of Gangnam subway station image sequences.

Keywords

References

  1. Sergio A. Velastin, Boghos A. Boghossian and Maria Aclicia Vicencio-Silva, "A motion-based image processing system for detecting potentially dangerous situations in underground railway stations", Transportation Research Part c: Emerging Technologies, vol.14, no.2, pp. 96-113, Apr. 2006. https://doi.org/10.1016/j.trc.2006.05.006
  2. Ruihua Ma, Liyuan Li, Weimin Huang and Qi Tian, "On pixel count based crowd density estimation for visual surveillance", in Proc. of IEEE Conf. on Cybernetics and Intelligent Systems, pp.170-173, Dec.2004.
  3. Dang Kong, Doug Gray and Hai Tao, "A viewpoint invariant approach for crowd counting", in Proc. of 18th Int. Conf. on Pattern Recognition, pp.1187-1190, 2006.
  4. Dang Kong, Doug Gray and Hai Tao, "Counting Pedestrians in crowds using viewpoint invariant training", in Proc. of British Machine Vision Conf., 2005.
  5. Beibei Zhan, Dorothy N. Monekosso, Paolo Remagnino, Sergio A. Velastin and Li-Qun Xu, "Crowd analysis: a survey", Machine Vision and Applications, vol.19, pp.345-357, Apr.2008. https://doi.org/10.1007/s00138-008-0132-4
  6. A. N. Marana, L. F. Costa, R. A. Lotufo and Sergio A. Velastin, "Estimating crowd density with Minkowski fractal dimension", in Proc. of IEEE Int. Conf. on Acoustics, Speech, and Signal Processing, pp.3521-3524, Mar.1999.
  7. A. N. Marana, Sergio A. Velastin, L. F. Costa and R. A. Lotufo, "Automatic estimation of crowd density using texture", Safety Science, vol.28, no.3, pp.165-175, Apr.1998. https://doi.org/10.1016/S0925-7535(97)00081-7
  8. T. K. An and M. H. Kim, "Context-aware Video Surveillance System", Journal of Electrical Engineering and Technology, vol.7, no.1, pp.115-123, Jan.2012. https://doi.org/10.5370/JEET.2012.7.1.115
  9. K. Y. Eom, J. Y. Jung, and M. H. Kim, "A heuristic search-based motion correspondence algorithm using fuzzy clustering", International Journal of Control, Automation and Systems, vol.10, no.3, pp.594-602, 2012. https://doi.org/10.1007/s12555-012-0317-5
  10. Rafael C. Gonzalez and Richard E. Woods, Digital Image Processing, 2nd Edition, Prentice Hall, 2002.
  11. J. Y. Jung and M. H. Kim, "Motion estimation of lips in pronouncing korean vowels based on fuzzy constraint line clustering", in Proc. of IEEE Int. Conf. on Image Processing, pp.507-510, Sep. 1996.
  12. H. J. Kim, H. S. Kang, S. H. Lee and M. H. Kim, "A study on fuzzy constraint line clustering for optical flow estimation", Journal of The Institute of Electronics Engineers of Korea, vol.31, no.9, pp.1403-1411, Sep.1994.
  13. G. J. Kim, T. K. Ahn, K. Y. Eom, J. Y. Jung and M. H. Kim, "Automated Measurement of Crowd Density Based on Edge Detection and Optical Flow", in Proc. 2nd Int. Conf. on Industrial Mechatronics and Automation, pp.553-556, May. 2010.
  14. Andres Bruhn, Joachim Weickert, Christian Feddern, Timo Kohlberger and Christoph Schnorr, "Real-Time optic flow computation with variational methods", in Computer Analysis of Images and Patterns, pp.222-229, 2003.

Cited by

  1. Crowd Activity Recognition using Optical Flow Orientation Distribution vol.9, pp.8, 2015, https://doi.org/10.3837/tiis.2015.08.011
  2. Temporal Search Algorithm for Multiple-Pedestrian Tracking vol.10, pp.5, 2016, https://doi.org/10.3837/tiis.2016.05.019
  3. Instagram image classification with Deep Learning vol.18, pp.5, 2017, https://doi.org/10.7472/jksii.2017.18.5.61