Grey Markov Model Prediction Method for Regular Pedestrian Movement Trend

  • Xiaoyu Fang
  • Xiaobin LiEmail author
  • Tianyang Yu
  • Zhen Guo
  • Tao Ma
Conference paper
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 528)


This paper focuses on the problem that mobile vehicles easily collide with regular pedestrians in dangerous area, and the gray prediction algorithm is applied to establish the markov model of regular pedestrian data. Predict their walking trajectory according to the regular pedestrian movement trend, and provide active and safe predictive control for vehicle braking in the region. Taking the coke oven coal transportation area as an example, a set of regular pedestrian trajectory data is selected to verify the model and prediction method. The experimental results show that this method can predict this type of pedestrian trajectory. When it is compared with the results of the traditional gray model prediction, the error is smaller and the accuracy is higher.


Regular pedestrian Trend of movement Grey Markov model Trajectory prediction 


  1. 1.
    S.P. Hoogendoom, W. Daamen, P.H.L. Bovy, Extracting microscopic pedestrian characteristics from video data, in Transportation Research Board Annual Meeting (National Academic Press, Washington, DC, 2003)Google Scholar
  2. 2.
    M. Morzy, Mining frequent trajectories of moving objects for location prediction, in Machine Learning and data Mining in Pattern Recognition (2007), pp. 667–680Google Scholar
  3. 3.
    I.E. Burbey, Predicting Future Locations and Arrival Times of Individuals (Virginia Polytechnic Institute and State University, Virginia, 2011)Google Scholar
  4. 4.
    W. Hongmei, Research on human detection and counting based on video. Sichuan Normal University (2011)Google Scholar
  5. 5.
    W. Li, S. Xia, F. Liu, L. Zhang, G. Yuan, Position prediction of moving objects based on movement trend. J. Commun. 35(02), 46–53 (2014)Google Scholar
  6. 6.
    C. Yang, M. Yang, Q. Wang, Design and implementation of grey Markov chain prediction system. Surv. Sci. 34(06), 182–183 (2009)Google Scholar
  7. 7.
    Q. Fan, W. Li, X. Wang, M. Fan, X. Yang, A memory cutting algorithm of shearer based on grey Markov combination model. J. Central South Univ. (Sci. Technol.) 42(10), 3054–3058 (2011)Google Scholar
  8. 8.
    J. Yang, Z. Hou, A real-time prediction model of large passenger flow based on gray Markov. J. Beijing Jiaotong Univ. 37(02), 119–123 (2013)Google Scholar
  9. 9.
    W. Chen, A. Xu, Prediction of gas flow from boreholes based on grey Markov model. China Saf. Sci. J. 22(03), 79–85 (2012)Google Scholar
  10. 10.
    Z. Xiong, X. Wang, Dynamic unbiased gray Markov prediction of relative gas emission from mine. J. Saf. Environ. 15(03), 15–18 (2015)Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2019

Authors and Affiliations

  • Xiaoyu Fang
    • 1
  • Xiaobin Li
    • 1
    Email author
  • Tianyang Yu
    • 1
  • Zhen Guo
    • 1
  • Tao Ma
    • 1
  1. 1.School of Electrical and Electronic EngineeringShanghai Institute of TechnologyShanghaiChina

Personalised recommendations