Extended social force model-based mean shift for pedestrian tracking under obstacle avoidance

Extended social force model-based mean shift for pedestrian tracking under obstacle avoidance

For access to this article, please select a purchase option:

Buy article PDF
(plus tax if applicable)
Buy Knowledge Pack
10 articles for $120.00
(plus taxes if applicable)

IET members benefit from discounts to all IET publications and free access to E&T Magazine. If you are an IET member, log in to your account and the discounts will automatically be applied.

Learn more about IET membership 

Recommend Title Publication to library

You must fill out fields marked with: *

Librarian details
Your details
Why are you recommending this title?
Select reason:
IET Computer Vision — Recommend this title to your library

Thank you

Your recommendation has been sent to your librarian.

It has been shown that mean shift tracking algorithm can achieve excellent results in pedestrian tracking task. It empirically estimates the target position of current frame by locating the maximum of a density function from the local neighborhood of the target position of previous frame. However, this method only considers its past trajectory without considering the influence of pedestrian environment when applying to pedestrian tracking. In practical, pedestrians always keep a safe distance away from obstacles when programming their paths. To address the issue of obstacle avoidance, this paper proposes a novel extended social force model-based mean shift tracking algorithm in which pedestrian environment is full taken in consideration. Firstly, an extended social force model is presented to quantify the interaction between pedestrian and obstacle by means of force. Furthermore, directional weights and speed weights are introduced to adjust the strength of the force in terms of the difference of individual perspectives and relative velocities. Finally, the initial target position is predicted by Newton's laws of motion and then the Mean Shift method is integrated to track target position. Experiment results show that this algorithm achieves an encouraging performance when obstacles exist.


    1. 1)
      • 1. Torabi, A., Massé, G., Bilodeau, G.A.: ‘An iterative integrated framework for thermal–visible image registration, sensor fusion, and people tracking for video surveillance applications’, Comput. Vis. Image Underst., 2012, 116, (2), pp. 210221.
    2. 2)
      • 2. Rao, Y.B.: ‘Automatic vehicle recognition in multiple cameras for video surveillance’, Vis. Comput., 2015, 31, (3), pp. 271280.
    3. 3)
      • 3. Mekonnena, A.A., Leraslea, F., Herbulota, A.: ‘Cooperative passers-by tracking with a mobile robot and external cameras’, Comput. Vis. Image Underst., 2013, 117, (10), pp. 12291244.
    4. 4)
      • 4. Zhou, W., Fei, Z., Hu, H.S., et al: ‘Real-time object subspace searching based on discrete searching paths and local energy’, Int. J. Autom. Comput., 2016, 13, (2), pp. 99107.
    5. 5)
      • 5. Lee, D., Kim, G., Kim, D., et al: ‘Vision-based object detection and tracking for autonomous navigation of underwater robots’, Ocean Eng., 2012, 48, pp. 5968.
    6. 6)
      • 6. Pai, C.J., Tyan, H.R., Liang, Y.M.: ‘Pedestrian detection and tracking at crossroads’, Pattern Recogn., 2004, 37, (5), pp. 10251034.
    7. 7)
      • 7. Yan, X., Kakadiaris, I.A., Shah, S.K.: ‘Modeling local behavior for predicting social interactions towards human tracking’, Pattern Recogn., 2014, 47, (4), pp. 16261641.
    8. 8)
      • 8. Beyan, C., Temizel, A.: ‘Adaptive mean-shift for automated multi object tracking’, IET Comput. Vis., 2012, 6, (1), pp. 112doi: 10.1049/iet-cvi.2011.0054.
    9. 9)
      • 9. An, X., Kim, J., Han, Y.: ‘Optimal colour-based mean shift algorithm for tracking objects’, IET Comput. Vis., 2012, 8, (3), pp. 235244doi: 10.1049/iet-cvi.2013.0004.
    10. 10)
      • 10. Zheng, Y.Z., Wang, H.Y., Guo, Q.X.: ‘A novel mean shift algorithm combined with least square approach and its application in target tracking’. Proc. of IEEE Int. Conf. on Signal Processing, 2012, pp. 11021105.
    11. 11)
      • 11. Pellegrini, S., Ess, A., Schindler, K.: ‘You'll never walk alone: modeling social behavior for multi-target tracking’. Proc. of IEEE Int. Conf. on Computer Vision, 2009, pp. 261268.
    12. 12)
      • 12. Zeng, W.L., Nakamura, H., Chen, P.: ‘A modified social force model for pedestrian behavior simulation at signalized crosswalks’, Procedia, Soc. Behav. Sci., 2014, 138, pp. 521530.
    13. 13)
      • 13. Saboia, P., Goldenstein, S.: ‘Crowd simulation: applying mobile grids to the social force model’, Vis. Comput., 2012, 28, (10), pp. 10391048.
    14. 14)
      • 14. Jian, X.X., Wong, S.C., Zhang, P., et al: ‘Perceived cost potential field cellular automata model with an aggregated force for pedestrian dynamics’, Transp. Res. C, Emerg. Technol., 2014, 42, pp. 200210.
    15. 15)
      • 15. Henein, C.M., White, T.: ‘Microscopic information processing and communication in crowd dynamics’, Phys. A, Stat. Mech. Appl., 2010, 389, (21), pp. 46364653.
    16. 16)
      • 16. Kuwano, M., Zhang, J.Y., Fujiwara, A.: ‘Dynamic discrete choice model for multiple social interactions’, Transp. Res. Board, 2011, 2231, pp. 6875.
    17. 17)
      • 17. Robin, T., Antonini, G., Bierlaire, M., et al: ‘Specification, estimation and validation of a pedestrian walking behavior model’, Transp. Res. B, Methodol., 2009, 43, (1), pp. 3656.
    18. 18)
      • 18. Roy, D., Krishnamurthy, A., Heragu, S., et al: ‘Queuing models to analyze dwell-point and cross-aisle location in autonomous vehicle-based warehouse systems’, Eur. J. Oper. Res., 2015, 242, (1), pp. 7287.
    19. 19)
      • 19. Helbing, D., Farkas, I., Vicsek, T.: ‘Simulating dynamical features of escape panic’, Nature, 2000, 407, (6803), pp. 487490.
    20. 20)
      • 20. Helbing, D., Buzna, L., Johansson, A., et al: ‘Self-organized pedestrian crowd dynamics: experiments, simulations, and design solutions’, Transp. Sci., 2005, 39, (1), pp. 124.
    21. 21)
      • 21. Bousetouane, F., Dib, L., Snoussi, H.: ‘Improved mean shift integrating texture and color features for robust real time object tracking’, Vis. Comput., 2013, 29, (3), pp. 155170.
    22. 22)
      • 22. Siyit, R., Ding, Y.G.: ‘Research and realization of mean shift tracking algorithm’, J. Comput. Inf. Syst., 2014, 10, (7), pp. 30573064.
    23. 23)
      • 23. Maalouf, A., Larabi, M.C., Nicholson, D.: ‘Offline quality monitoring for legal evidence images in video-surveillance applications’, Multimedia Tools Appl., 2014, 73, (1), pp. 189218.
    24. 24)
      • 24. Li, Y., Liang, S., Bai, B.D., et al: ‘Detecting and tracking dim small targets in infrared image sequences under complex backgrounds’, Multimedia Tools Appl., 2014, 71, (3), pp. 11791199.
    25. 25)
      • 25. Johansson, F., Peterson, A., Tapani, A.: ‘Waiting pedestrians in the social force model’, Phys. A, Stat. Mech. Appl., 2015, 419, pp. 95107.
    26. 26)
      • 26. Seer, S., Rudloff, C., Matyus, T., et al: ‘Validating social force based models with comprehensive real world motion data’, Transp. Res. Procedia, 2014, 2, pp. 724732.
    27. 27)
      • 27. Stoudt, H.W., Damon, A., McFarland, R., et al: ‘Weight, height, and selected body dimensions of adults’. Vital and health statistics series 11 (DHEW Publication (PHS) 8, National Center for Health Statistics, Rockville, MD, 1969).
    28. 28)
      • 28. Mehran, R., Oyama, A., Shah, M.: ‘Abnormal crowd behavior detection using social force model’. Proc. of IEEE Int. Conf. on Computer Vision and Pattern Recognition, 2009, pp. 935942.
    29. 29)
      • 29. Curtis, S., Zafar, B., Gutub, A., et al: ‘Right of way’, Vis. Comput., 2013, 29, (12), pp. 12771292.
    30. 30)
      • 30. Löhner, R.: ‘On the modeling of pedestrian motion’, Appl. Math. Model., 2010, 34, (2), pp. 366382.
    31. 31)
      • 31. Kim, S., Guy, S.J., Hillesland, K., et al: ‘Velocity-based modeling of physical interactions in dense crowds’, Vis. Comput., 2014, 31, (5), pp.541555doi: 10.1007/s00371-014-0946-1.
    32. 32)
      • 32. Johansson, A., Helbing, D., Shukla, P.K.: ‘Specification of a microscopic pedestrian model by evolutionary adjustment to video tracking data’, Adv. Complex Syst., 2008, 10, (4), pp. 271288.
    33. 33)
      • 33. Gao, Y., Luh, P.B., Zhang, H., et al: ‘A modified social force model considering relative velocity of pedestrians’. IEEE Int. Conf. on Automation Science and Engineering, 2013, pp. 747751.
    34. 34)
      • 34. Pellegrini, S., Ess, A., Schindler, K., et al: ‘You'll never walk alone: modeling social behavior for multi-target tracking’. 2009 IEEE 12th Int. Conf. on Computer Vision, September 2009, pp. 261268.
    35. 35)
      • 35. ‘Ethz – computer vision lab: datasets’. Available at
    36. 36)
      • 36. Parisi, D.R., Gilman, M., Moldovan, H.: ‘A modification of the social force model can reproduce experimental data of pedestrian flows in normal conditions’, Phys. A, Stat. Mech. Appl., 2009, 338, (17), pp. 36003608.
    37. 37)
      • 37. Yin, F., Dimitrios, M., Sergio, A.V.: ‘Performance evaluation of object tracking algorithms’. IEEE Int. Workshop on Performance Evaluation of Tracking and Surveillance, 2007.
    38. 38)
      • 38. Kaysi, I., Alshalalfah, B., Shalaby, A., et al: ‘Users’ evaluation of rail systems in mass events: case study in Mecca, Saudi Arabia’, Transp. Res. Rec., J. Transp. Res. Board, 2013, (2350), pp. 111118.
    39. 39)
      • 39. Abdelgawad, H., Shalaby, A., Abdulhai, B., et al: ‘Microscopic modeling of large-scale pedestrian–vehicle conflicts in the city of Madinah, Saudi Arabia’, J. Adv. Transp., 2014, 48, (6), pp. 507525.

Related content

This is a required field
Please enter a valid email address