Advertisement

Real-Time Driver Fatigue Monitoring with a Dynamic Bayesian Network Model

  • Issam Bani
  • Belhassan Akrout
  • Walid Mahdi
Conference paper
Part of the Advances in Predictive, Preventive and Personalised Medicine book series (APPPM, volume 10)

Abstract

In this chapter, our objective is to detect the driver fatigue state. To this end, we have integrated the most relevant causes and effects of fatigue in a dynamic Bayesian network. We used the following as the main causes of drowsiness: sleep quality, road environment, and driving duration. On the other hand, we added as consequences real-time facial expressions, such as blinking, yawning, gaze, and head position. The result obtained changes over time and it is repeatedly included in the model to calculate fatigue level. In comparison with a realistic simulation, this model is very effective at detecting driver fatigue.

Keywords

Driver fatigue Hypovigilance Facial expressions Dynamic Bayesian network 

References

  1. 1.
    Ji Q, Lan P, Looney C (2006) A probabilistic framework for modeling and real-time monitoring human fatigue. IEEE Trans Syst Man Cybern-Part A Syst Hum 36(5):862–875CrossRefGoogle Scholar
  2. 2.
    Yang G, Lin Y, Bhattacharya P (2010) A driver fatigue recognition model based on information fusion and dynamic Bayesian network. Inf Sci 180(10):1942–1954CrossRefGoogle Scholar
  3. 3.
    Gang L, Song X, Zhang M, Yao B, Zhou L (2017) Analysis of driver fatigue causations based on the Bayesian network model. Simulation 93(7):553–565CrossRefGoogle Scholar
  4. 4.
    He Q, Li W, Fan X, Fei Z (2014) Driver fatigue evaluation model with integration of multi-indicators based on dynamic Bayesian network. IET Intell Transp Syst 9(5):547–554CrossRefGoogle Scholar
  5. 5.
    Li X, Ji Q (2005) Active affective state detection and user assistance with dynamic Bayesian networks. IEEE Trans Syst Man Cybern-Part A Syst Hum 35(1):93–105CrossRefGoogle Scholar
  6. 6.
    Guo W, Zhang B, Xia L, Shi S, Zhang X, She J (2016) Driver drowsiness detection model identification with Bayesian network structure learning method. In: Control and Decision Conference (CCDC), 2016 Chinese. IEEE, pp 131–136Google Scholar
  7. 7.
    Safety Board (1999) Evaluation of US department of transportation efforts in the 1990s to address operator fatigue. Safety Report NTSB/SR-99/01, Washington, DCGoogle Scholar
  8. 8.
    Charlton SG, Ashton ME (1998) Review of fatigue management strategies in the transport industry. Land transport safety authority, Wellington, New Zealand, Technical Report, pp 97–91Google Scholar
  9. 9.
    Lan P, Ji Q, Looney CG (2002) Information fusion with Bayesian networks for monitoring human fatigue. In: Proceedings of the Fifth International Conference on Information Fusion, 2002, vol 1. IEEE, pp 535–542Google Scholar
  10. 10.
    Philip P, Sagaspe P, Moore N, Taillard J, Charles A, Guilleminault C, Bioulac B (2005) Fatigue, sleep restriction and driving performance. Accid Anal Prev 37(3):473–478CrossRefGoogle Scholar
  11. 11.
    Cabon P (1992) Maintien de la vigilance et gestion du sommeil dans les systemes automatises: recherche de laboratoire applications aux transports ferroviaires et aeriens. PhD thesis, Paris 5Google Scholar
  12. 12.
    Akerstedt T, Czeisler CA, Dinges DF, Horne JA (1994) Accidents and sleepiness: a consensus statement from the International Conference on Work Hours, Sleepiness and Accidents, Stockholm. J Sleep Res 3(4):195CrossRefGoogle Scholar
  13. 13.
    Trutschel U, Sirois B, Sommer D, Golz M, Edwards D (2011) PERCLOS: an alertness measure of the past. In: Proceedings of the sixth international driving symposium on human factors in driver assessment, training and vehicle design. University of Iowa, pp 172–79Google Scholar
  14. 14.
    Akrout B, Mahdi W (2013) A blinking measurement method for driver drowsiness detection. In: Proceedings of the 8th International Conference on Computer Recognition Systems CORES. Springer, pp 651–660Google Scholar
  15. 15.
    Momin BF, Abhyankar PP (2012) Current status and future research directions in monitoring vigilance of individual or mass audience in monotonous working environment. Int J Soft Comput 3(2):45CrossRefGoogle Scholar
  16. 16.
    Akrout B, Mahdi W (2015) Spatio-temporal features for the automatic control of driver drowsiness state and lack of concentration. Mach Vis Appl 26(1):1–13CrossRefGoogle Scholar
  17. 17.
    Dean T, Kanazawa K (1989) A model for reasoning about persistence and causation. Comput Intell 5(2):142–150CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Issam Bani
    • 1
  • Belhassan Akrout
    • 1
    • 2
  • Walid Mahdi
    • 1
    • 3
  1. 1.Laboratory MIRACL, Institute of Computer Science and Multimedia of SfaxSfax UniversitySfaxTunisia
  2. 2.College of Computer Engineering and SciencesPrince Sattam bin Abdulaziz UniversityAl-KharjSaudi Arabia
  3. 3.Department of Computer ScienceTaif UniversityTaifSaudi Arabia

Personalised recommendations