People Counting Based on the Moving Feature of the Mass

Abstract:

In order to improve the accuracy of people counting in video surveillance, the method for people counting based on the moving feature of the mass is proposed. We obtain the orientation and energy density of mass through the optical flow algorithm, and get the information about the size of mass to design the feature of mass. The people counting model is obtained by training a support vector machine (SVM) classifier with the moving feature and shape feature of mass. The experimental results confirm that our approach improves the accuracy of people counting.

• Periodical: Advanced Materials Research (Volumes 989-994)
• Pages: 2540-2542
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.989-994.2540
• Online since: July 2014
• Authors: Peng Zhe Qiao*, Tao Li, Tao Xiang, Xi Zhi Zhang
• Keywords: Moving Feature, Optical Flow Algorithm, People Counting

References

[1] A. Gardel, I. Bravo, P. Jimenez: Real time head detection for embedded vision modules. IEEE International Symposium on Intelligent Signal Processing. (2007).

DOI: 10.1109/wisp.2007.4447515

[2] Y. Benabbas, N. Ihaddadene, T. Yahiaoui: Spatio-temporal optical flow analysis for people counting. Proc. of 7th IEEE International Conference on Advanced Video and Signal Based Surveillance. Boston, USA(2010).

DOI: 10.1109/avss.2010.29

[3] B. Andres, W. Joachim, F. Christian: submitted to Journal of Computer Science(2003).

[4] V. Vapnik: Statistical learning theory(Springer, New York, 1995).

[5] J. Barandiaran, B. Murguia, B. Fernando: Real-time people counting using multiple lines. Proc. of 9th International Workshop on Image Analysis for Multimedia Interactive Services. Klagenfurt, Austria(2008).

DOI: 10.1109/wiamis.2008.27