Vision Based Algorithm for People Counting Using Deep Learning

  • Authors

    • M Padmashini
    • R Manjusha
    • Latha Parameswaran
    2018-07-04
    https://doi.org/10.14419/ijet.v7i3.6.14942
  • People counting, deep neural network, HoG, LBP.

  • Abstract

    Estimating the number of people in a particular scene has always been an important topic of research in computer vision and digital image processing. People counting has wide applications in scenario ranging from analyzing the customer's choice and improving the quality of service in retail stores, supermarkets and shopping malls to managing human resources and optimizing the energy usage in office buildings. While there exists algorithms for counting people in a scene, some algorithm have set their benchmark in performance with respect to efficiency, flexibility and accuracy. In this paper, an attempt has been made to perform people counting using Deep Neural Networks (DNN) on comparison with existing image processing based algorithms like Histogram of Oriented Gradients with Support Vector Machine (HoG with SVM), Local Binary Pattern (LBP) based Adaboost classifier and contour based people detection. The proposed DNN based approach has higher accuracy at 90% and less false negatives.

     

     

  • References

    1. [1] Riachi S, Walid K & Hanna G, “An improved real-time method for counting people in crowded scenes based on a statistical approachâ€, IEEE 11th International Conference on Informatics in Control, Automation and Robotics (ICINCO), Vol.2, (2014), pp. 203-212.

      [2] Li B, Jian Z, Zheng Z & Yong X, “A people counting method based on head detection and trackingâ€, IEEE International Conference on Smart Computing (SMARTCOMP), (2014), pp. 136-141.

      [3] Wang Y, Huicheng L, Pei C & Zhenzhen L, “Counting people with support vector regressionâ€, IEEE 10th International Conference on Natural Computation (ICNC), (2014), pp.139-143.

      [4] Baozhu Z, Zhu Q & Xing Y, “People counting system based on improved Gaussian background modelâ€, IET International Conference on Smart and Sustainable City and Big Data (ICSSC), (2015), pp.118-122.

      [5] Pongsakon B & Suteera P, “Robust people counting using a region-based approach for a monocular vision systemâ€, IEEE International Conference on Science and Technology (TICST), (2015), pp.309-312.

      [6] Dimitris S, Evaggelos S, Giorgos S & Theodoros G, “Counting and tracking people in a smart room: An IoT approachâ€, IEEE 10th International Workshop on Semantic and Social Media Adaptation and Personalization (SMAP), (2015), pp.1-5.

      [7] Del PL, Pasquale F, Antonio G, Gennaro P & Mario Vento, “A versatile and effective method for counting people on either RGB or depth overhead camerasâ€, IEEE International Conference on Multimedia & Expo Workshops (ICMEW), (2015), pp.1-6.

      [8] Kuo JY, Guo DF & Tai Yu L, “People counting base on head and shoulder informationâ€, IEEE International Conference on Knowledge Engineering and Applications, (2016), pp.52-55.

      [9] Zhou B, Ming L & Yonggang W, “Counting people using gradient boosted treesâ€, IEEE Information Technology, Networking, Electronic and Automation Control Conference, (2016), pp.391-395.

      [10] Perng JW, Wang TY, Hsu YW & Wu BF, “The design and implementation of a vision-based people counting system in busesâ€, IEEE International Conference on System Science and Engineering (ICSSE), (2016), pp.1-3.

      [11] Cai Z, Yu ZL, Liu H & Zhang K, “Counting people in crowded scenes by video analyzingâ€, IEEE 9th Conference on Industrial Electronics and Applications (ICIEA), (2014), pp.1841-1845.

      [12] Xu J, Wu Q, Zhang J, Silk B, Ngo GT & Tang Z, “Efficient people counting with limited manual interferencesâ€, IEEE International Conference on Digital image Computing: Techniques and Applications (DlCTA), (2014), pp.1-6.

      [13] Howard Andrew G., Menglong Z, Bo C, Dmitry K, Weijun W, Tobias W, Marco A & Hartwig A, “Mobilenets: Efficient convolutional neural networks for mobile vision applicationsâ€, (2017).

      [14] https://opencv.org/

  • Downloads

  • How to Cite

    Padmashini, M., Manjusha, R., & Parameswaran, L. (2018). Vision Based Algorithm for People Counting Using Deep Learning. International Journal of Engineering & Technology, 7(3.6), 74-80. https://doi.org/10.14419/ijet.v7i3.6.14942

    Received date: 2018-07-02

    Accepted date: 2018-07-02

    Published date: 2018-07-04