Skip to main content
SpringerLink
Log in

Directional pedestrian counting with a hybrid map-based model

  • Regular Paper
  • Robotics and Automation
  • Published:
International Journal of Control, Automation and Systems Aims and scope Submit manuscript

Abstract

Detection-based pedestrian counting methods produce results of considerable accuracy in non-crowded scenes. However, the detection-based approach is dependent on the camera viewpoint. On the other hand, map-based pedestrian counting methods are performed by measuring features that do not require separate detection of each pedestrian in the scene. Thus, these methods are more effective especially in high crowd density. In this paper, we propose a hybrid map-based model that is a new directional pedestrian counting model. Our proposed model is composed of direction estimation module with classified foreground motion vectors, and pedestrian counting module with principal component analysis. Our contributions in this paper have two aspects. First, we present a directional moving pedestrian counting system that does not depend on object detection or tracking. Second, the number and major directions of pedestrian movements can be detected, by classifying foreground motion vectors. This representation is more powerful than simple features in terms of handling noise, and can count the moving pedestrians in images more accurately.

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

Similar content being viewed by others

References

  1. B. Wu and R. Nevatia, “Detection of multiple, partially occluded humans in a single image by Bayesian combination of Edgelet part detectors,” Proc. Int’l Conf. on Computer Vision, pp. 90–97, October 2005.

    Google Scholar 

  2. J. Rittscher, P. H. Tu, and N. Krahnstoever, “Simultaneous estimation of segmentation and shape,” Proc. IEEE Conf. Comput. Vis. Pattern Recog., pp. 486–493, 2005.

    Google Scholar 

  3. T. Zhao and R. Nevatia, “Bayesian human segmentation in crowded situations,” Proc. IEEE Conf. Comput. Vis. Pattern Recog., pp. 459–466, 2003.

    Google Scholar 

  4. Y.-L. Hou and G. K. H. Pang, “People counting and human detection in a challenging situation,” IEEE Trans. on Systems, Man, and Cybernetics-Part A: Systems and Humans, vol. 41, no. 1, pp. 24–33, January 2011.

    Article  Google Scholar 

  5. M. Enzweiler and D. M. Gavrila, “Monocular pedestrian detection: survey and experiments,” IEEE Trans. on Pattern Analysis and machine Intelligence, vol. 31, no. 12, pp. 2179–2195, December 2009.

    Article  Google Scholar 

  6. S. Zhang, C. Bauckhageyz, D. A. Klein, and A. B. Cremers, “Moving pedestrian detection based on motion segmentation,” Proc. of IEEE Workshop on Robot Vision, 2013.

    Google Scholar 

  7. D. Goel and T. Chen, “Real-time pedestrian detection using eigenflow,” Proc. IEEE Conf. Image Processing, vol. 3, pp. 229–232, 2007.

    Google Scholar 

  8. C. Hua, Y. Makihara, and Y. Yagi, “Pedestrian detection by using a spatiotemporal histogram of oriented gradients,” IEICE Trans. on Information and Systems, pp. 1376–1386, 2013.

    Google Scholar 

  9. V. Rabaud and S. Belongie, “Counting crowded moving objects,” Proc. IEEE Conf. Comput. Vis. Pattern Recog., pp. 705–711, 2006.

    Google Scholar 

  10. S.-F. Lin, J.-Y. Chen, and H.-X. Chao, “Estimation of number of people in crowded scenes using perspective transformation,” IEEE Trans. Systems, Man, and Cybernetics, vol. 31, no. 6, pp. 645–654, 2001.

    Article  Google Scholar 

  11. S.-Y. Cho, T. W. S. Chow, and C.-T. Leung, “A neural-based crowd estimation by hybrid global learning algorithm,” IEEE Trans. on Systems, Man, and Cybernetics, vol. 29, no. 4, pp. 535–541, 1999.

    Article  Google Scholar 

  12. R. Ma, L. Li, W. Huang, and Q. Tian, “On pixel count based crowd density estimation for visual surveillance,” Proc. IEEE Conf. Cybern. Intell. Syst., pp. 170–173, 2004.

    Google Scholar 

  13. A. Albiol, M. J. Silla, A. Albiol, and J. M. Mossi, “Video analysis using corner motion statistics,” Proc. IEEE Int’l Workshop on Performance Evaluation of Tracking and Surveillance, pp. 31–38, 2009.

    Google Scholar 

  14. A. C. Davies, J. H. Yin, and S. A. Velastin, “Crowd monitoring using image processing,” Electron. Comm. Eng. J., vol. 7, pp. 37–47, 1995.

    Article  Google Scholar 

  15. A. B. Chan, Z.-S. J. Liang, N. Vasconcelos, “Privacy preserving crowd monitoring: Counting people without people models or tracking,” Proc. IEEE Conf. Comput. Vis. Pattern Recog., pp. 1–7, 2008.

    Google Scholar 

  16. A. N. Marana, L. F. Costa, R. A. Lotufo, and S. A. Velastin, “On the efficacy of texture analysis for crowd monitoring,” Proc. Computer Graphics, Image Processing, and Vision, pp. 354–361, 1998.

    Google Scholar 

  17. P. Viola, M. Jones, and D. Snow, “Detecting pedestrians using patterns of motion and appearance,” Proc. IEEE Int’l Conf. Computer Vision, pp. 734–741, 2003.

    Chapter  Google Scholar 

  18. C. Croux, P. Filzmoser, and H. Fritz, “Robust sparse principal component analysis,” Technometrics, pp. 202–214.

  19. H. Ma, L. Gong, and J. Yu, “A moving object detection algorithm based on improved Gaussian mixture model,” Proc. of 20th International Conference on Industrial Engineering and Engineering Management, Berlin, Heidelberg, 2013.

    Google Scholar 

  20. A. Bruhn, J. Weickert, C. Feddern, T. Kohlberger, and C. Schnorr, “Real-time optic flow computation with variational methods,” in Computer Analysis of Images and Patterns, pp. 222–229, 2003.

    Chapter  Google Scholar 

  21. B. D. Lucas and T. Kanade, “An iterative image registration technique with an application in stereo vision,” Proc. Int’l Joint Conference on Artificial Intelligence, pp. 121–130, 1981.

    Google Scholar 

  22. B. K. P. Horn and B. G. Schunk, “Determining optical flow,” Artificial Intelligence, vol. 17, pp. 185–203, 1980.

    Article  Google Scholar 

  23. K. Y. Eom, J. Y. Jung, and M. H. Kim, “A heuristic search-based motion correspondence algorithm using fuzzy clustering,” Int’l Journal of Control, Automation and Systems, vol. 10, no. 3, pp. 594–602, 2012.

    Article  Google Scholar 

  24. R. Xu and D. Wunsch II, “Survey of clustering algorithms,” IEEE Trans. on Neural Networks, vol. 16, no. 3, pp. 645–678, May 2005.

    Article  Google Scholar 

  25. A. Lancichinetti, “Evaluating the performance of clustering algorithms in networks,” Dynamics on and of Complex Networks, vol. 2, pp. 143–158, 2013.

    Article  MathSciNet  Google Scholar 

  26. 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, 2012.

    Article  Google Scholar 

  27. H. Bay, T. Tuytelaars, and L. V. Gool, “SURF: speeded up robust features,” Proc. European Conference on Computer Vision, pp. 404–417, 2006.

    Google Scholar 

  28. D. G. Lowe, “Distinctive image features from scale invariant keypoints,” Proc. Int’l Journal Computer Vision, vol. 60, no. 2, pp. 91–110, 2004.

    Article  Google Scholar 

  29. R. M. Haralick, “Statistical and structural approaches to texture,” Proc. IEEE, vol. 67, no. 5, pp. 786–804, 1979.

    Article  Google Scholar 

  30. G. J. Kim, T. K. An, and M. H. Kim, “Estimation of crowd density in public areas based on neural network,” KSII Trans. on Internet and Information Systems, vol. 6, no. 9, pp. 2170–2190, September 2012.

    Google Scholar 

  31. R. Huang, T. Li, M. Ye, and Y. Dou, “Unconstrained face verification by optimally organizing multiple classifiers,” Int’l Journal of Control, Automation and Systems, vol. 12, no. 4, pp. 833–842, 2014.

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. College of Information and Communication Engineering, Sungkyunkwan University, 2066, Seobu-ro, Jangan-gu, Suwon, 440-746, Korea

    Gyu-Jin Kim, Jin-Pyung Kim, Yun-Gyung Cheong & Moon-Hyun Kim

  2. Metropolitan Transportation Research Center, Korea Railway Research Institute, 176, Cheoldo bangmulgwan-ro, Uiwang, 437-757, Korea

    Tae-Ki An

Authors
  1. Gyu-Jin Kim
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Tae-Ki An
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Jin-Pyung Kim
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Yun-Gyung Cheong
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Moon-Hyun Kim
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Moon-Hyun Kim.

Additional information

Gyu-Jin Kim received his B.S. degree in Applied Mathematics from Sejong University in 2009, and his M.S. degree in Electrical and Computer Engineering from Sungkyunkwan University, Seoul, Korea in 2011. His research interests include pattern recognition, machine learning, computer vision, and artificial intelligence.

Tae-Ki An received his B.S. and M.S. degrees in Electronic Engineering from Kyungpook National University, Daegu, Korea, in 1994 and 1996, respectively. He received his Ph.D. degree in Electrical and Computer Engineering from Sungkyunkwan University, Seoul, Korea in 2011. He is a Chief Researcher in Korea Railroad Research Institute. His research interests are artificial intelligence, pattern recognition, and video analysis.

Jin-Pyung Kim received his M.S. degree from College of Information and Communication Engineering at Sungkyunkwan University, Suwon, Korea in 2006, and his Ph.D. degree in Electrical and Computer Engineering from Sungkyunkwan University, Seoul, Korea in 2014. His research interests include structure learning, pattern recognition, and computer vision.

Yun-Gyung Cheong received her B.S. and M.S. degrees in Information Engineering from Sungkyunkwan University, Korea, in 1996 and 1998, respectively. In 2007, She received her Ph.D. in Computer Science from North Carolina State University. Her research interests lie in Artificial Intelligence with emphasis on its use in interactive media. She is a Research Professor in the School of Information and Communication Engineering, Sungkyunkwan University.

Moon-Hyun Kim received his B.S. degree in Electronic Engineering from Seoul National University in 1978, an M.S. degree in Electrical Engineering from Korea Advanced Institute of Science and Technology, Korea, in 1980, and a Ph.D. degree in Computer Engineering from the University of Southern California in 1988. From 1980 to 1983, he was a Research Engineer at the Daewoo Heavy Industries Co., Seoul. He joined the School of Information and Communication Engineering, Sungkyunkwan University, Seoul, Korea in 1988, where he is currently a Professor. In 1995, he was a Visiting Scientist at the IBM Almaden Research Center, San Jose, California. In 1997, he was a Visiting Professor at the Signal Processing Laboratory of Princeton University, Princeton, New Jersey. His research interests include artificial intelligence, image recognition, and machine learning.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Kim, GJ., An, TK., Kim, JP. et al. Directional pedestrian counting with a hybrid map-based model. Int. J. Control Autom. Syst. 13, 201–211 (2015). https://doi.org/10.1007/s12555-013-0382-4

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s12555-013-0382-4

Keywords

Search

Navigation