Title: Development of Driver Fatigue Detection System By Using Video Images

Abstract: Major reasons for traffic accidents all over the world are mostly because of drivers' fatigue and lack of concentration. In this study, the detection and tracking of the drivers' faces in video based images were realized by using AdaBoost algorithm. The eye area was detected by using Principle Component Analysis (PCA). A predictive system was developed analyzing the eye closure of the drivers'. The system used PERCLOS (Percentage of eye closure) and it was tested on UCLA database.

Keywords: Face detection; eye detection; drivers' fatigue detection; AdaBoost algorithm; PCA algorithm

Başlık: Video Görüntüleri Kullanılarak Sürücü Yorgunluğu Sezme Sistemi Geliştirilmesi

Özet: Değişik sebeplerle sürücülerde meydana gelen yorgunluk, uyuşukluk ve dikkatsizlik tüm dünyada trafik kazalarının başlıca sebeplerindendir. Bu çalışmada video tabanlı görüntülerde sürücü yüz bölgelerinin tespiti ve takibi AdaBoost algoritması kullanılarak yapılmıştır. Elde edilen yüz bölgelerinde Temel Bileşen Analizi (TBA) algoritması kullanılarak göz bölgesi tespit edilmiştir. Göz bölgesinin açıklık/kapalılık durumuna bakılarak sürücülerin yorgun olup olmadıklarını sezen ve yorgunluğa dair tahminde bulunan bir sistem geliştirilmiştir. Gözün kapalılık durumu için PERCLOS'dan yararlanılmıştır. Uygulamayı test etmek için UCLA veritabanı kullanılmıştır.

Anahtar kelimeler: Yüz tespiti; göz tespiti; sürücü yorgunluğu tespiti; Adaboost algoritması; TBA algoritması

• Hsu L, Abdel-Mottaleb M, Jain AK. Face detection in color images. IEEE Transactions on Pattern Analysis and Machine Intelligence 2002; 24(5): 696-706.
• Parmar N. Drowsy Driver Detection System. Engineering Design Project Report, Department of Electrical and Computer Engineering, Ryerson University, 2002.
• Horng WB, Chen CY. A real-time driver fatigue detection system based on eye tracking and dynamic template matching. Tamkang Journal of Science and Engineering 2008; 11(1): 65.
• Devi MS, Bajaj MR. Fuzzy based driver fatigue detection. In 2010 IEEE International Conference on Systems, Man and Cybernetics, October 10-13, 2010, Istanbul, Turkey, pp. 3139-3144.
• Coetzer RC, Hancke GP. Eye detection for a real-time vehicle driver fatigue monitoring system. In 2011 IEEE Intelligent Vehicles Symposium (IV), June 5-9, 2011, Baden-Baden, Germany, pp. 66-71.
• Tayibnapis IR, Koo DY, Choi MK, Kwon S. A novel driver fatigue monitoring using optical imaging of face on safe driving system. In 2016 International Conference on Control, Electronics, Renewable Energy and Communications (ICCEREC), September 13-15, 2016, Bandung, Indonesia, pp. 115-120.
• Zhang F, Su J, Geng L, Xiao Z. Driver fatigue detection based on eye state recognition. In 2017 International Conference on Machine Vision and Information Technology (CMVIT), February 17-19, 2017, Singapore, pp. 105-110.
• Viola P, Jones M. Robust real-time object detection. In Second International Workshop On Statistical And Computational Theories Of Vision–Modeling, Learning, Computing, And Sampling, July 13, 2001, Vancouver, Canada, pp 1-25.
• Vitabile S, De Paola A, Sorbello F. A real-time non-intrusive FPGA-based drowsiness detection system. Journal of Ambient Intelligence and Humanized Computing 2011; 2(4): 251-262.