Your browser does not support JavaScript!
http://iet.metastore.ingenta.com
1887

access icon free Crowd counting considering network flow constraints in videos

© The Institution of Engineering and Technology
Received 22/11/2016, Accepted 13/09/2017, Revised 04/09/2017, Published 18/09/2017

The growth of the number of people in the monitoring scene may increase the probability of security threat, which makes crowd counting more and more important. Most of the existing approaches estimate the number of pedestrians within one frame, which results in inconsistent predictions in terms of time. This study, for the first time, introduces a quadratic programming (QP) model with the network flow constraints to improve the accuracy of crowd counting. Firstly, the foreground of each frame is segmented into groups, each of which contains several pedestrians. Then, a regression-based map is developed in accordance with the relationship between low-level features of each group and the number of people in it. Secondly, a directed graph is constructed to simulate constraints on people's flow, whose vertices represent groups of each frame and arcs represent people moving from one group to another. Finally, by solving a QP problem with network flow constraints in the directed graph, the authors obtain consistency in people counting. The experimental results show that the proposed method can reduce the crowd counting errors and improve the accuracy. Moreover, this method can also be applied to any ultramodern group-based regression counting approach to get improvements.

Inspec keywords: directed graphs; pedestrians; video surveillance; image segmentation; regression analysis; quadratic programming

Other keywords: frame foreground segmentation; integer flow; QP problem; ultramodern group-based regression counting approach; regression-based map; intelligent video surveillance systems; digraph; network flow constraint; directed graph; people counting; quadratic programming model; low-level features; pedestrians; security threat probability; crowd counting accuracy improvement

Subjects: Other topics in statistics; Combinatorial mathematics; Other topics in statistics; Video signal processing; Optimisation techniques; Combinatorial mathematics; Image recognition; Optimisation techniques

References

    1. 1)
      • 2. Zini, L., Noceti, N., Odone, F.: ‘Precise people counting in real time’. IEEE Conf. on Image Processing (ICIP), Melbourne, Australia, 2013, pp. 3592–3596.
    2. 2)
      • 11. Dalal, N., Triggs, B.: ‘Histograms of oriented gradients for human detection’. IEEE Conf. Computer Vision and Pattern Recognition (CVPR), San Diego, CA, USA, 2005, pp. 886–893.
    3. 3)
      • 6. Ryan, D., Denman, S., Sridharan, S., et al: ‘An evaluation of crowd counting methods, features and regression models’, Comput. Vis. Image Underst., 2015, 130, pp. 1–17.
    4. 4)
      • 28. ‘PETS’, http://www.cvg.reading.ac.uk/PETS2009/, accessed 2009.
    5. 5)
      • 25. Shitrit, H.B., Berclaz, J., Fleuret, F., et al: ‘Multi-commodity network flow for tracking multiple people’, IEEE Trans. Pattern Anal. Mach. Intell., 2014, 36, (8), pp. 1614–1627.
    6. 6)
      • 21. Li, J., Huang, L., Liu, C.: ‘Robust people counting in video surveillance: dataset and system’. IEEE Conf. Advanced Video and Signal-Based Surveillance (AVSS), Klagenfurt, Austria, 2011, pp. 54–59.
    7. 7)
      • 10. Gao, C., Li, P., Zhang, Y., et al: ‘People counting based on head detection combining adaboost and CNN in crowded surveillance environment’, Neurocomputing, 2016, (208), pp. 108–116.
    8. 8)
      • 13. Chan, A.B., Vasconcelos, N.: ‘Modeling, clustering, and segmenting video with mixtures of dynamic textures’, IEEE Trans. Pattern Anal. Mach. Intell., 2008, 30, (5), pp. 909–926.
    9. 9)
      • 27. Han, Y., Yang, Y., Wu, F., et al: ‘Compact and discriminative descriptor inference using multi-Cues’, IEEE Trans. Image Process., 2015, 24, (12), pp. 5114–5126.
    10. 10)
      • 9. Li, M., Zhang, Z., Huang, K., et al: ‘Estimating the number of people in crowded scenes by mid based foreground segmentation and head-shoulder detection’. IEEE Conf. Pattern Recognition (ICPR), Tampa, Florida, USA, 2008, pp. 1–4.
    11. 11)
      • 1. Chan, A.B., Vasconcelos, N.: ‘Counting people with low-level features and Bayesian regression’, IEEE Trans. Image Process., 2012, 21, (4), pp. 2160–2177.
    12. 12)
      • 15. Conte, D., Foggia, P., Percannella, G., et al: ‘Counting moving people in videos by salient points detection’. IEEE Conf. Pattern Recognition (ICPR), Istanbul, Turkey, 2010, pp. 1743–1746.
    13. 13)
      • 8. Khatoon, R., Saqlain, S.M., Bibi, S.: ‘A robust and enhanced approach for human detection in crowd’. IEEE Conf. Multitopic Conf. (INMIC), 2012, pp. 215–221.
    14. 14)
      • 29. Tan, B., Zhang, J., Wang, L.: ‘Semi-supervised elastic net for pedestrian counting’, Pattern Recognit., 2011, 44, (10), pp. 2297–2304.
    15. 15)
      • 26. Han, Y., Chen, J., Cao, X., et al: ‘Feature selection with spatial path coding for multimedia analysis’, Inf. Sci., 2014, 281, pp. 523–535.
    16. 16)
      • 22. Foroughi, H., Ray, N., Zhang, H.: ‘Robust people counting using sparse representation and random projection’, Pattern Recognit., 2015, 48, (10), pp. 3038–3052.
    17. 17)
      • 14. Chan, A.B., Liang, Z.S.J., Vasconcelos, N.: ‘Privacy preserving crowd monitoring: counting people without people models or tracking’. IEEE Conf. Computer Vision and Pattern Recognition (CVPR), Anchorage, Alaska, USA, 2008, pp. 1–7.
    18. 18)
      • 5. Conte, D., Foggia, P., Percannella, G., et al: ‘Counting moving persons in crowded scenes’, Mach. Vis. Appl., 2013, 24, (5), pp. 1029–1042.
    19. 19)
      • 4. Zhang, X., He, H., Cao, S., et al: ‘Flow field texture representation-based motion segmentation for crowd counting’, Mach. Vis. Appl., 2015, 26, (7-8), pp. 871–883.
    20. 20)
      • 16. Chen, K., Gong, S., Xiang, T., et al: ‘Cumulative attribute space for age and crowd density estimation’. IEEE Conf. Computer Vision and Pattern Recognition (CVPR), Portland, Oregon, 2013, pp. 2467–2474.
    21. 21)
      • 20. Cong, Y., Gong, H., Zhu, S.C., et al: ‘Flow mosaicking: real-time pedestrian counting without scene-specific learning’. IEEE Conf. Computer Vision and Pattern Recognition (CVPR), Miami, Florida, USA, 2009, pp. 1093–1100.
    22. 22)
      • 23. Zhang, C., Li, H., Wang, X., et al: ‘Cross-scene crowd counting via deep convolutional neural networks’. IEEE Conf. Computer Vision and Pattern Recognition (CVPR), Boston, Massachusetts, 2015, pp. 833–841.
    23. 23)
      • 17. Loy, C.C., Gong, S., Xiang, T.: ‘From semi-supervised to transfer counting of crowds’, IEEE Conf. Computer Vision (ICCV), Sydney, Australia, 2013, pp. 2256–2263.
    24. 24)
      • 12. Felzenszwalb, P.F., Girshick, R.B., McAllester, D., et al: ‘Object detection with discriminatively trained part-based models’, IEEE Trans. Pattern Anal. Mach. Intell., 2010, 32, (9), pp. 1627–1645.
    25. 25)
      • 24. Milan, A., Leal-Taixé, L., Schindler, K., et al: ‘Joint tracking and segmentation of multiple targets’, IEEE Conf. Computer Vision and Pattern Recognition (CVPR), Boston, Massachusetts, 2015, pp. 5397–5406.
    26. 26)
      • 3. Al-Zaydi, Z.Q.H., Ndzi, D.L., Yang, Y., et al: ‘An adaptive people counting system with dynamic features selection and occlusion handling’, J. Vis. Commun. Image Represent., 2016, 39, pp. 218–225.
    27. 27)
      • 18. Zhang, Z., Wang, M., Geng, X.: ‘Crowd counting in public video surveillance by label distribution learning’, Neurocomputing, 2015, 166, pp. 151–163.
    28. 28)
      • 7. Saleh, S.A.M., Suandi, S.A., Ibrahim, H.: ‘Recent survey on crowd density estimation and counting for visual surveillance’, Eng. Appl. Artif. Intell., 2015, 41, pp. 103–114.
    29. 29)
      • 19. Kong, D., Gray, D., Tao, H.: ‘A viewpoint invariant approach for crowd counting’. IEEE Conf. Pattern Recognition (ICPR), Hong Kong, China, 2006, pp. 1187–1190.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-ipr.2016.0994
Loading

Related content

content/journals/10.1049/iet-ipr.2016.0994
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading
Print this page
This is a required field
Please enter a valid email address