Journal of KIISE:Software and Applications (한국정보과학회논문지:소프트웨어및응용)

Korean Institute of Information Scientists and Engineers (한국정보과학회)
권호 표지

An Illumination-Robust Driver Monitoring System Based on Eyelid Movement Measurement

조명에 강인한 눈꺼풀 움직임 측정기반 운전자 감시 시스템

  • 박일권 (연세대학교 컴퓨터과학과) ;
  • 김광수 (삼성전자 정보통신총괄통신연구소) ;
  • 박상철 (특허청컴퓨터시스템) ;
  • 변혜란 (연세대학교 컴퓨터과학과)
  • Published : 2007.04.15
Download PDF
⟨ Previous Next ⟩

Abstract

In this paper, we propose a new illumination-robust drowsy driver monitoring system with single CCD(Charge Coupled Device) camera for intelligent vehicle in the day and night. For this system that is monitoring driver's eyes during a driving, the eye detection and the measure of eyelid movement are the important preprocesses. Therefore, we propose efficient illumination compensation algorithm to improve the performance of eye detection and also eyelid movement measuring method for efficient drowsy detection in various illumination. For real-time application, Cascaded SVM (Cascaded Support Vector Machine) is applied as an efficient eye verification method in this system. Furthermore, in order to estimate the performance of the proposed algorithm, we collect video data about drivers under various illuminations in the day and night. Finally, we acquired average eye detection rate of over 98% about these own data, and PERCLOS(The percentage of eye-closed time during a period) are represented as drowsy detection results of the proposed system for the collected video data.

본 논문은 지능형 자동차 개발을 위한 주간 및 야간 환경에서 차량 운전 시 발생할 수 있는 다양한 조명을 극복하고 운전자 졸음 상태를 단일 CCD(Charge Coupled Device) 카메라를 통해 감시하는 시스템을 제안한다. 운전 중 운전자 눈을 감시하여 졸음 상태를 판단하는 시스템에서 눈 검출 및 눈꺼풀 움직임 측정은 선행되어야 할 중요한 과정이다. 따라서 비전기반 시스템의 가장 큰 단점인 조명변화를 극복하며 눈 검출 성능을 높이고 실시간 처리가 가능한 간단한 조명 보정 알고리즘을 제안하였으며 또한 신뢰성 있는 졸음 판단을 위해 효율적인 눈꺼풀 움직임 측정 방법을 제안한다. 이러한 시스템은 실시간으로 처리되어야 하며 이를 위해 제안한 방법과 더불어 효율적인 눈 검증 방법으로 단계적 SVM(Cascaded Support Vector Machine)을 적용하였다. 한편, 제안한 알고리즘의 성능 측정을 위해 주간 및 야간의 다 양한 조명 변화 속에서 주행 중 수집된 운전자 동영상을 사용하였으며 자체 수집된 동영상에 대해 98% 이상의 눈 검출 성능 및 신뢰성 있는 눈꺼풀 움직임을 측정하였다. 최종 졸음판단 결과는 수집된 각각의 동 영상에 대한 PERCLOS(The percentage of eye-closed time during a period)를 비교함으로써 제안한 시스템의 성능 및 우수성을 보였다.

Keywords

References

  1. Qoamg Ji and Xiaojie Yang, 'Real-time eye, gaze, and face pose tracking for monitoring driver vigilance,' Real-Time Imaging, Vol. 8, Issue 5, Pages : 357-377, 2002 https://doi.org/10.1006/rtim.2002.0279
  2. Mimuro, T, Miichi, Y, Maemura, T and Hayafune, K, 'Mitsubishi Advanced Safety Vehicle(ASV),' Proceedings of the 4th World Congress on Intelligent Transport Systems. 1997
  3. Toshiaki Matsumoto and Yoshihito Hori, 'Toyota Advanced Safety Vehicle(Toyoto ASV),' Proceedings of the 4th World Congress on Ingelligent Transport Systems, 1997
  4. Hayami, T. Matsunaga, K. Shidoji, K. and Matsuki, Y. 'Detecting drowsiness while driveing by measuring eye movement - a pilot study,' Proceedings of the IEEE 5th International Conference on Intelligent Transportation Systems, Page(s): 156-161, 2002 https://doi.org/10.1109/ITSC.2002.1041206
  5. Ueno, H., Kaneda, M. and Tsukino, M., 'Development of drowsiness detection system,' Proceedings of Vehicle Navigation and Information Systems, Page(s):15-20, 1994 https://doi.org/10.1109/VNIS.1994.396873
  6. Van Winsum, W and DE waard, D and Brookhuis, KA, 'Lane Change Manoeuveres and Safety Margins,' Transportation Research Park F, Vol. 2, Page(s):139-149, 1999 https://doi.org/10.1016/S1369-8478(99)00011-X
  7. Renner, G and Mehring, S, 'Lane Departure and Drowsiness-Two Major Accident Causes-One Safety System,' Transport Research Laboratory, TRL Report 220., 1997
  8. Hamada, T., Ito, T., Adachi, K., Nakano, T. and Yamamoto, S., 'Detecting method for drivers' drowsiness applicable to individual features,' Proceedings of IEEE Ingelligent Transportation Systems, Vol. 2, Page(s):1405-0410, 2003
  9. FHWA, 'Crash problem Size Assessment: Large truck crashes related primarily to driver fatigue,' Federal Highway Administration, Office of Motor Carriers, September 1998
  10. Horne, J. and Reyner, L, 'Vehicle accidents related to sleep-a review,' Occupational and Environmental Medicine, Vol. 56, Page(s):289-294, 1999 https://doi.org/10.1136/oem.56.5.289
  11. Vuckovic, A., Popovic, D. and Redivejevic, V., 'Artificial neural network for detecting drowsiness from EEG recordings,' 6th Seminar on Neural Network Applications in Electrical Engineering, Page(s):155-158, 2002
  12. Ito, T., Mita, S., Kozuka, K., Nakano, T. and Yamamoto, S., 'Driver blink measurement by the motion picture processing and its application to drowsiness detection,' Proceedings of The IEEE 5th International Conference on Intelligent Transportation Systems, Page(s):168-173, 2002
  13. Ji, Q. and Yang, Z., 'Real time visual cues extraction for monitoring driver vigilance.' In Proceeding of International Workshop on Computer Vision Systems, Vancouver, Canada, 2001
  14. Dinges, D. and Grace, R, 'PERCLOS: A Valid Psycho-physiological Measure of Alertness as Assessed by Psychomotor Vigilance.' TechBrief FHWA-MCRT-98-006, 1998
  15. Xia Liu, Fengliang Xu and Fujimara, K., 'Real-time eye detection and tracking for driver observation under various light conditions,' IEEE Intelligent Vehicle Symopsium, Vol, 2 Page(s): 278-281, 2004
  16. D'Orazio, T., Leo, M., Cicirelli, G. and Distante, A., 'An algorithm for real time eye detection in face images,' Proceedings of the 17th International Conference on Pattern Recognition, Vol. 3, Page(s):278-281, 2004 https://doi.org/10.1109/ICPR.2004.1334521
  17. Jie Zhu and Jie Yang, 'Subpixel eye gaze tracking,' Automatic Face and Gesture Recognition, 2002, Proceedings, Fifth IEEE International Conference, Page(s): 124-129, 2002
  18. Romdhani, S., Torr, P., Scholkopf, B. and Blake, A. 'Computationally efficient face detection' ICCV 2001