Driver Fatigue Detection by Fusing Multiple Cues

  • Rajinda Senaratne
  • David Hardy
  • Bill Vanderaa
  • Saman Halgamuge
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4492)


A video-based driver fatigue detection system is presented. The system automatically locates the face in the first frame, and then tracks the eyes in subsequent frames. Four cues which characterises fatigue are used to determine the fatigue level. We used Support Vector Machines to estimate the percentage eye closure, which is the strongest cue. Improved results were achieved by using Support Vector Machines in comparison to Naive Bayes classifier. The performance was further improved by fusing all four cues using fuzzy rules.


Support Vector Machine Particle Swarm Optimization Fuzzy Rule Particle Swarm Optimization Algorithm Polynomial Kernel 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Lal, S.K.L., Craig, A.: Driver Fatigue: Electroencephalography and Psychological Assessment. Psychophysiology 39(3), 313–321 (2002)CrossRefGoogle Scholar
  2. 2.
    Ji, Q., Zhu, Z.W., Lan, P.L.: Real-time Nonintrusive Monitoring and Prediction of Driver Fatigue. IEEE Trans. on Vehicular Technology 53(4), 1052–1068 (2004)CrossRefGoogle Scholar
  3. 3.
    Smith, P., Shah, M., Lobo, N.D.: Determining Driver Visual Attention with One Camera. IEEE Trans. on Intelligent Transportation Systems 4(4), 205–218 (2003)CrossRefGoogle Scholar
  4. 4.
    Bergasa, L.M., Nuevo, J., Sotelo, M.A., Barea, R., Lopez, M.E.: Real-time System for Monitoring Driver Vigilance. IEEE Trans. on Intelligent Transportation Systems 7(1), 63–77 (2006)CrossRefGoogle Scholar
  5. 5.
    Hartley, L., Horberry, T., Mabbott, N., Krueger, G.P.: Review of Fatigue Detection and Prediction Technologies. National Road Transport Commision, Melbourne (2000)Google Scholar
  6. 6.
    Senaratne, R., Halgamuge, S.: Optimised Landmark Model Matching for Face Recognition. In: 7th International Conference on Automatic Face and Gesture Recognition, pp. 120–125 (2006)Google Scholar
  7. 7.
    Senaratne, R., Halgamuge, S.: Optimal Weighting of Landmarks for Face Recognition. Journal of Multimedia 1(3), 31–41 (2006)CrossRefGoogle Scholar
  8. 8.
    Kennedy, J., Eberhart, R.C.: Particle Swarm Optimization. In: IEEE International Conference on Neural Networks, vol. 4, pp. 1942–1948 (1995)Google Scholar
  9. 9.
    Shi, Y., Eberhart, R.C.: Empirical Study of Particle Swarm Optimization. In: Proc. of the IEEE Congress on Evolutionary Computation, pp. 1945–1950 (1999)Google Scholar
  10. 10.
    Ratnaweera, A., Halgamuge, S.K., Watson, H.C.: Self-organizing Hierarchical Particle Swarm Optimizer with Time-varying Acceleration Coefficients. IEEE Trans. on Evolutionary Computation 8(3), 240–255 (2004)CrossRefGoogle Scholar
  11. 11.
    Stringa, L.: Eyes Detection for Face Recognition. Applied Artificial Intelligence 7(4), 365–382 (1993)CrossRefGoogle Scholar
  12. 12.
    Baluja, S.: Using Labeled and Unlabeled Data for Probabilistic Modeling of Face Orientation. International Journal of Pattern Recognition and Artificial Intelligence 14(8), 1097–1107 (2000)CrossRefGoogle Scholar
  13. 13.
    Cortes, C., Vapnik, V.: Support-vector Networks. Machine Learning 20(3), 273–297 (1995)zbMATHGoogle Scholar
  14. 14.
    Chang, C.C., Lin, C.J.: LIBSVM: A Library for Support Vector Machines (2001), Software available at
  15. 15.
    Popieul, J.C., Simon, P., Loslever, P.: Using Driver’s Head Movements Evolution as A Drowsiness Indicator. In: IEEE Intelligent Vehicles Symposium, pp. 616–621 (2003)Google Scholar
  16. 16.
    Roge, J., Pebayle, T., Muzet, A.: Variations of the Level of Vigilance and of Behavioural Activities during Simulated Automobile Driving. Accident Analysis and Prevention 33(2), 181–186 (2001)CrossRefGoogle Scholar
  17. 17.
    Halgamuge, S.K.: Self-evolving Neural Networks for Rule-based Data Processing. IEEE Trans. on Signal Processing 45(11), 2766–2773 (1997)CrossRefGoogle Scholar
  18. 18.
    Halgamuge, S.K., Poechmueller, W., Glesner, M.: An Alternative Approach for Generation of Membership Functions and Fuzzy Rules based on Radial and Cubic Basis Function Networks. International Journal of Approximate Reasoning 12(3-4), 279–298 (1995)zbMATHCrossRefMathSciNetGoogle Scholar
  19. 19.
    Halgamuge, S.K., Glesner, M.: Fuzzy Neural Networks - Between Functional Equivalence and Applicability. International Journal of Neural Systems 6(2), 185–196 (1995)CrossRefGoogle Scholar
  20. 20.
    Halgamuge, S.K.: A Trainable Transparent Universal Approximator for Defuzzification in Mamdani-type Neuro-fuzzy Controllers. IEEE Trans. on Fuzzy Systems 6(2), 304–314 (1998)CrossRefGoogle Scholar

Copyright information

© Springer Berlin Heidelberg 2007

Authors and Affiliations

  • Rajinda Senaratne
    • 1
  • David Hardy
    • 1
  • Bill Vanderaa
    • 1
  • Saman Halgamuge
    • 1
  1. 1.Dynamic Systems and Control Research Group, Department of Mechanical and Manufacturing Engineering, The University of MelbourneAustralia

Personalised recommendations