Skip to main content
Springer Nature Link
Log in

Deep Learning and Statistical Models for Time-Critical Pedestrian Behaviour Prediction

  • Conference paper
  • First Online:
Neural Information Processing (ICONIP 2019)

Part of the book series: Communications in Computer and Information Science ((CCIS,volume 1142))

Included in the following conference series:

Abstract

The time it takes for a classifier to make an accurate prediction can be crucial in many behaviour recognition problems. For example, an autonomous vehicle should detect hazardous pedestrian behaviour early enough for it to take appropriate measures. In this context, we compare the switching linear dynamical system (SLDS) and a deep long short-term memory (LSTM) neural network, which are applied to infer pedestrian behaviour from motion tracks. We show that, though the neural network model achieves an accuracy of 80%, it requires long sequences to achieve this (100 samples or more). The SLDS, has a lower accuracy of 74%, but it achieves this result with short sequences (10 samples). To our knowledge, such a comparison on sequence length has not been considered in the literature before. The results provide a key intuition of the suitability of the models in time-critical problems.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

References

  1. Barber, D.: Bayesian Reasoning and Machine Learning. Cambridge University Press, Cambridge (2012)

    MATH  Google Scholar 

  2. Cheng, B., Xu, X., Zeng, Y., Ren, J., Jung, S.: Pedestrian trajectory prediction via the social-grid LSTM model. J. Eng. 2018(16), 1468–1474 (2018). https://doi.org/10.1049/joe.2018.8316

    Article  Google Scholar 

  3. Dabrowski, J.J., Beyers, C., de Villiers, J.P.: Systemic banking crisis early warning systems using dynamic Bayesian networks. Expert Syst. Appl. 62, 225–242 (2016). https://doi.org/10.1016/j.eswa.2016.06.024

    Article  Google Scholar 

  4. Dabrowski, J.J., de Villiers, J.P.: Maritime piracy situation modelling with dynamic Bayesian networks. Inf. Fusion 23, 116–130 (2015). https://doi.org/10.1016/j.inffus.2014.07.001

    Article  Google Scholar 

  5. Dabrowski, J.J., de Villiers, J.P.: A unified model for context-based behavioural modelling and classification. Expert Syst. Appl. 42(19), 6738–6757 (2015). https://doi.org/10.1016/j.eswa.2015.04.061

    Article  Google Scholar 

  6. Dabrowski, J.J., de Villiers, J.P., Beyers, C.: Context-based behaviour modelling and classification of marine vessels in an abalone poaching situation. Eng. Appl. Artif. Intell. 64, 95–111 (2017). https://doi.org/10.1016/j.engappai.2017.06.005

    Article  Google Scholar 

  7. Dabrowski, J.J., de Villiers, J.P., Beyers, C.: Naive Bayes switching linear dynamical system: a model for dynamic system modelling, classification, and information fusion. Inf. Fusion 42, 75–101 (2018). https://doi.org/10.1016/j.inffus.2017.10.002

    Article  Google Scholar 

  8. Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997). https://doi.org/10.1162/neco.1997.9.8.1735

    Article  Google Scholar 

  9. Hoy, M., Tu, Z., Dang, K., Dauwels, J.: Learning to predict pedestrian intention via variational tracking networks. In: 2018 21st International Conference on Intelligent Transportation Systems (ITSC), pp. 3132–3137, November 2018. https://doi.org/10.1109/ITSC.2018.8569641

  10. Hug, R., Becker, S., Hbner, W., Arens, M.: Particle-based pedestrian path prediction using LSTM-MDL models. In: 2018 21st International Conference on Intelligent Transportation Systems (ITSC), pp. 2684–2691, November 2018. https://doi.org/10.1109/ITSC.2018.8569478

  11. Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint: arXiv:1412.6980 (2014)

  12. Kooij, J.F.P., Englebienne, G., Gavrila, D.M.: Mixture of switching linear dynamics to discover behavior patterns in object tracks. IEEE Trans. Pattern Anal. Mach. Intell. 38(2), 322–334 (2016). https://doi.org/10.1109/TPAMI.2015.2443801

    Article  Google Scholar 

  13. Kooij, J.F.P., Schneider, N., Gavrila, D.M.: Analysis of pedestrian dynamics from a vehicle perspective. In: 2014 IEEE Intelligent Vehicles Symposium Proceedings, pp. 1445–1450, June 2014. https://doi.org/10.1109/IVS.2014.6856505

  14. Kooij, J.F.P., Schneider, N., Flohr, F., Gavrila, D.M.: Context-based pedestrian path prediction. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014, Part VI. LNCS, vol. 8694, pp. 618–633. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10599-4_40

    Chapter  Google Scholar 

  15. Li, J., Liang, X., Shen, S., Xu, T., Feng, J., Yan, S.: Scale-aware fast R-CNN for pedestrian detection. IEEE Trans. Multimed. 20(4), 985–996 (2018). https://doi.org/10.1109/TMM.2017.2759508

    Article  Google Scholar 

  16. Minguez, R.Q., Alonso, I.P., Fernandez-Llorca, D., Sotelo, M.A.: Pedestrian path, pose, and intention prediction through Gaussian process dynamical models and pedestrian activity recognition. IEEE Trans. Intell. Transp. Syst., 1–12 (2018). https://doi.org/10.1109/TITS.2018.2836305

    Article  Google Scholar 

  17. Murphy, K.P.: Switching Kalman filters. Technical report, Department of Computer Science, UC Berkeley (1998)

    Google Scholar 

  18. Ridel, D., Rehder, E., Lauer, M., Stiller, C., Wolf, D.: A literature review on the prediction of pedestrian behavior in urban scenarios. In: 2018 21st International Conference on Intelligent Transportation Systems (ITSC), pp. 3105–3112, November 2018. https://doi.org/10.1109/ITSC.2018.8569415

  19. Saleh, K., Hossny, M., Nahavandi, S.: Intent prediction of pedestrians via motion trajectories using stacked recurrent neural networks. IEEE Trans. Intell. Veh. 3(4), 414–424 (2018). https://doi.org/10.1109/TIV.2018.2873901

    Article  Google Scholar 

  20. Saleh, K., Hossny, M., Nahavandi, S.: Long-term recurrent predictive model for intent prediction of pedestrians via inverse reinforcement learning. In: 2018 Digital Image Computing: Techniques and Applications (DICTA), pp. 1–8, December 2018. https://doi.org/10.1109/DICTA.2018.8615854

  21. Schneider, N., Gavrila, D.M.: Pedestrian path prediction with recursive Bayesian filters: a comparative study. In: Weickert, J., Hein, M., Schiele, B. (eds.) GCPR 2013. LNCS, vol. 8142, pp. 174–183. Springer, Heidelberg (2013). https://doi.org/10.1007/978-3-642-40602-7_18

    Chapter  Google Scholar 

  22. Schulz, A.T., Stiefelhagen, R.: Pedestrian intention recognition using latent-dynamic conditional random fields. In: 2015 IEEE Intelligent Vehicles Symposium (IV), pp. 622–627, June 2015. https://doi.org/10.1109/IVS.2015.7225754

  23. Volz, B., Behrendt, K., Mielenz, H., Gilitschenski, I., Siegwart, R., Nieto, J.: A data-driven approach for pedestrian intention estimation. In: 2016 IEEE 19th International Conference on Intelligent Transportation Systems (ITSC), pp. 2607–2612, November 2016. https://doi.org/10.1109/ITSC.2016.7795975

Download references

Author information

Authors and Affiliations

  1. Data61, CSIRO, St Lucia, Australia

    Joel Janek Dabrowski & Ashfaqur Rahman

  2. University of Pretoria, Pretoria, South Africa

    Johan Pieter de Villiers & Conrad Beyers

  3. Council for Scientific and Industrial Research (CSIR), Pretoria, South Africa

    Johan Pieter de Villiers

Authors
  1. Joel Janek Dabrowski
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Johan Pieter de Villiers
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Ashfaqur Rahman
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Conrad Beyers
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Joel Janek Dabrowski .

Editor information

Editors and Affiliations

  1. Australian National University, Canberra, ACT, Australia

    Tom Gedeon

  2. Murdoch University, Murdoch, WA, Australia

    Kok Wai Wong

  3. Kyungpook National University, Daegu, Korea (Republic of)

    Minho Lee

Rights and permissions

Reprints and permissions

Copyright information

© 2019 Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Dabrowski, J.J., de Villiers, J.P., Rahman, A., Beyers, C. (2019). Deep Learning and Statistical Models for Time-Critical Pedestrian Behaviour Prediction. In: Gedeon, T., Wong, K., Lee, M. (eds) Neural Information Processing. ICONIP 2019. Communications in Computer and Information Science, vol 1142. Springer, Cham. https://doi.org/10.1007/978-3-030-36808-1_50

Download citation

  • DOI: https://doi.org/10.1007/978-3-030-36808-1_50

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-030-36807-4

  • Online ISBN: 978-3-030-36808-1

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics