Skip to main content

Advertisement

Springer Nature Link
Log in

Counting moving people in crowds using motion statistics of feature-points

  • Published:
Multimedia Tools and Applications Aims and scope Submit manuscript

Abstract

Reliable people counting is a crucial task in video surveillances. Among the available techniques, map-based approaches have shown a good performance in estimating the number of people in crowds. These approaches generally subtract the background, and then map the number of people to some features such as foreground area, texture features or edge count. However, in complex scenes, they suffer from inaccurate foreground/background segmentations, erroneous image features, and require large amount of training data to capture the wide variations in crowd distribution. This paper proposes a method using motion statistics of feature-points to estimate the number of moving people in a crowd. Simple feature-points are tracked within the scene. Then moving feature-points are partitioned into clusters corresponding to separate groups of people. For each group, three statistical features are calculated from related feature-points. The amount of moving feature-points is used to provide a rough estimate of group size. Furthermore, motion trajectories of feature-points are utilized to extract two other features related with the amount of occlusions present in groups. The extracted data are used to estimate the number of people in each group, so that the total crowd size is the sum of all group estimates. The experimental results show that the proposed method outperforms the state of the art approaches, e.g., with MSE of 2.357 and MAE of 1.093 for the benchmark video clip “Peds1”. The proposed approach is good for estimating the number of people in public places, such as pedestrian walkways and parks, where people are moving and partial occlusions present in the scene.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14
Fig. 15
Fig. 16
Fig. 17
Fig. 18
Fig. 19
Fig. 20

Notes

  1. To avoid confusion, “feature” will be used when referring to the statistical features extracted from feature-points and “feature-point (FP)” will be used when referring to feature-points detected for tracking.

  2. Available at: http://www.svcl.ucsd.edu/projects/peoplecnt

  3. Available at: http://www.svcl.ucsd.edu/projects/anomaly

  4. Available at: http://www.cs.zju.edu.cn/~gpan/database/crowd.html

References

  1. Albiol A, Silla MJ, Albiol A, Mossi JM (2009) Video analysis using corner motion statistics. In: Proc. of the IEEE Int. workshop on performance evaluation of tracking and surveillance (PETS), pp 31–38

  2. Benfold B, Reid I (2011) Stable multi-target tracking in real-time surveillance video. In: Proc. of int. conf. on computer vision and pattern recognition (CVPR11), pp 3457–3464

  3. Bishop CM. (1995) Neural networks for pattern recognition. New York: Oxford University Press

    Google Scholar 

  4. Brostow GJ, Cipolla R (2006) Unsupervised bayesian detection of independent motion in crowds. In: Proc. of int. conf. on computer vision and pattern recognition (CVPR06), pp 594–601

  5. Celik H, Hanjalic A, Hendriks E (2006) Towards a robust solution to people counting. In: Proc. of the IEEE int. conf. on image processing, pp 2401–2404

  6. Chan AB, Liang Z, Vasconcelos N (2008) Privacy preserving crowd monitoring: counting people without people models or tracking. In: Proc. of Int. conf. on computer vision and pattern recognition (CVPR08)

  7. Cheriyadat AM, Bhaduri BL, Radke RJ (2008) Detecting multiple moving objects in crowded environments with coherent motion regions. In: Proc. of sixth IEEE Workshop on Perceptual Organization in Computer Vision (POCV08), in conjunction with IEEE CVPR08

  8. Cho SY, Chow TWS, Leung CT (1999) A neural-based crowd estimation by hybrid global learning algorithm. IEEE Trans Syst Man Cybern B 29(4):535–541

    Article  Google Scholar 

  9. Davies AC, Yin JH, Velastin SA (1995) Crowd monitoring using image processing. Electron Comm Eng J 7:37–47

    Article  Google Scholar 

  10. Doulamis N (2009) Evacuation planning through cognitive crowd tracking systems. In: Proc. of the 16th int. conf. on signals and image processing, pp 1–4

  11. Doulamis A, Doulamis N, Kollias S (2000) On line retrainable neural networks: improving the performance of neural networks in image analysis problems. IEEE Trans Neural Netw 11(1):137–155

    Article  Google Scholar 

  12. Ellis A, Shahrokni A, Ferryman J (2009) PETS 2009 and Winter-PETS 2009 Results: A Combined Evaluation. In: Proc. of 12th IEEE int. workshop on performance evaluation of tracking and surveillance (PETS)

  13. Haibo W, Hong F (2010) The research of emergency evacuation model based on digital city management platform. In: Proc. of Int. Conf. on Multimedia Technology, pp 1–4

  14. Haritaoglu I, Harwood D, Davis LS (1999) Hydra: multiple people detection and tracking using silhouettes. In: Proc. of second IEEE workshop on visual surveillance, pp 280–285

  15. Harris C, Stephens M (1988) A combined corner and edge detector. In: Proc. of the 4th Alvey vision conference, pp 147–151

  16. Hou YL, Pang GKH (2011) People counting and human detection in a challenging situation. IEEE Trans Syst Man Cybern A, 41(1):24–33

    Article  Google Scholar 

  17. Kilambi P, Ribnick E, Joshi AJ, Masoud O, Papanikolopoulos N (2008) Estimating pedestrian counts in groups. Comput Vis Image Underst 110(1):43–59

    Article  Google Scholar 

  18. Kong D, Gray D, Tao H (2006) A viewpoint invariant approach for crowd counting. In: Proc. of the 18th int. conf. on pattern recognition, vol 3, pp 1187–1190

  19. Kong D, Gray D, Tao H (2005) Counting pedestrians in crowds using viewpoint invariant training. In: Proc. of British Machine Vision Conf

  20. Krahnstoever N, Mendona PRS (2005) Bayesian autocalibration for surveillance. In: Proc. of int. conf. on computer vision (ICCV05), vol 2, pp 1858–1865

  21. Krausz B, Bauckhage C (2011) Loveparade 2010: automatic video analysis of a crowd disaster. Comput Vis Image Underst 116(3):307–319

    Article  Google Scholar 

  22. Leibe B, Seemann E, Schiele B (2005) Pedestrian detection in crowded scenes. In: Proc. of int. conf. on computer vision and pattern recognition (CVPR05), vol 1, pp 878–885

  23. Lempitsky V, Zisserman A (2010) Learning to count objects in images. In: Advances in neural information processing systems (NIPS), pp 1324–1332

  24. Lim J, Kim W (2012) Detecting and tracking of multiple pedestrians using motion, color information and the AdaBoost algorithm. Multimedia Tools Appl J. doi:10.1007/s11042-012-1156-3. Springer

    Google Scholar 

  25. Lin Z, Davis L (2010) Shape-based human detection and segmentation via hierarchical part-template matching. IEEE Trans Pattern Anal Mach Intel 32(4):604–618

    Article  Google Scholar 

  26. Lin Z, Liu L, Yan Z, Li Z (2011) Multi-agent modeling of city emergency evacuation. In: Proc. of int. conf. on multimedia technology, pp 3570–3574

  27. Lucas BD, Kanade T (1981) An iterative image registration technique with an application to stereo vision. Proc. of 7th int. joint conf. on artificial intelligence (IJCAI81), pp 674–679

  28. Ma H, Zeng C, Ling CX (2012) A reliable people counting system via multiple cameras. ACM Trans Intel Syst Technol 3(2):1–22

    Article  Google Scholar 

  29. Mahadevan V, Li W, Bhalodia V, Vasconcelos N (2010) Anomaly detection in crowded scenes. In: Proc. of int. conf. on computer vision and pattern recognition (CVPR10), pp 1975–1981

  30. Marana AN, da Fontoura Costa L, Lotufo RA, Velastin SA (1999) Estimating crowd density with Minkoski fractal dimension. In: Proc. of int. conf. acoust, speech, signal processing, pp 3521–3524

  31. Marana AN, Velastin SA, Costa LF, Lotufo RA (1997) Estimation of crowd density using image processing. In: IEE colloquium on image processing for security applications, vol 11, pp 1–8

  32. Paragios N, Ramesh V (2001) A mrf-based approach for real-time subway monitoring. In: Proc. of int. conf. on computer vision and pattern recognition (CVPR01), vol 1, pp 1034–1040

  33. PETS: performance evaluation of tracking and surveillance workshop at CVPR 2009. Miami, Florida (2009) http://www.cvg.rdg.ac.uk/PETS2009/

  34. Rabaud V, Belongie SJ (2006) Counting crowded moving objects. In: Proc. of Int. conf. on computer vision and pattern recognition (CVPR06), pp 705–711

  35. Rahmalan H, Nixon MS, Carter JN (2006) On crowd density estimation for surveillance. In: The institution of engineering and technology conference on crime and security, pp 540–545

  36. Rittscher J, Tu PH, Krahnstoever N (2005) Simultaneous estimation of segmentation and shape. In: Proc. of int. conf. on computer vision and pattern recognition (CVPR05), vol 2, pp 486–493

  37. Ryan D, Denman S, Fookes C, Sridharan S (2009) Crowd counting using multiple local features. In: Proc. of conf. on digital image computing: techniques and applications, pp 81–88

  38. Sugimura D, Kitani K, Okabe T, Sato Y, Sugimoto A (2009) Using individuality to track individuals: clustering individual trajectories in crowds using local appearance and frequency trait. In: Proc. of Int. conf. on computer vision (ICCV09), pp 1467–1474

  39. Tomasi C, Kanade T (1991) Detection and tracking of point features. Carnegie Mellon Univ., Pittsburgh, PA, Tech. Rep. CMU-CS-91-132

    Google Scholar 

  40. Tomasi C, Shi J (1994) G ood features to track. In: Proc. of int. conf. on computer vision and pattern recognition (CVPR94), pp 593–600

  41. Wu B, Nevatia R (2007) Detection and tracking of multiple, partially occluded humans by Bayesian combination of edgelet based part detectors. Int J Comput Vis 75:247–266

    Article  Google Scholar 

  42. Zeng C, Ma H, Ming A (2010) Fast human detection using mi-SVM and a cascade of HOG-LBP features. In: Proc. of IEEE int. conf. on image processing, pp 3845–3848

  43. Zhao T, Nevatia R (2003) Bayesian human segmentation in crowded situations. In: Proc. of int. conf. on computer vision and pattern recognition (CVPR03), pp 459–466

Download references

Acknowledgements

This work was partly supported by the 973 Program (2013CB329504), NSF of China (No. 61070067), and Qianjiang Talent Program of Zhejiang (2011R10078).

Author information

Authors and Affiliations

  1. College of Computer Science and Technology, Zhejiang University, Hangzhou, China

    Mahdi Hashemzadeh, Gang Pan & Min Yao

Authors
  1. Mahdi Hashemzadeh
    View author publications

    You can also search for this author inPubMed Google Scholar

  2. Gang Pan
    View author publications

    You can also search for this author inPubMed Google Scholar

  3. Min Yao
    View author publications

    You can also search for this author inPubMed Google Scholar

Corresponding author

Correspondence to Gang Pan.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Hashemzadeh, M., Pan, G. & Yao, M. Counting moving people in crowds using motion statistics of feature-points. Multimed Tools Appl 72, 453–487 (2014). https://doi.org/10.1007/s11042-013-1367-2

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11042-013-1367-2

Keywords