Gerçek Zamanlı Sürücü Yorgunluk Tespiti ve Uyarı Sistemi

Öz

Sürücü yorgunluğu, sürüş sırasında bilişsel performansın azalmasına ve sürücünün tepki zamanının uzamasına sebep olan trafik güvenliğini tehdit eden hem sürücüyü hem de çevresindeki insanları tehlikeye atan önemli etkenlerden biridir. Sürücü yorgunluğu, uzun süreli araç kullanımı ile sürüş anında sürücünün performansını olumsuz etkileyebilir. Bu çalışma sürücünün yorgunluğunu gerçek zamanlı olarak tespit edebilmek amacıyla, Raspberry Pi 4 mikro bilgisayar tabanlı bir sistem tasarımı sunmaktadır. Sistem araç içi kamera ile yüz ve göz hareketlerinin izlenmesi ve MPU6050 ivmeölçer sensörü ile baş hareketlerinin tespiti, analiz edilmesi esasına dayanmaktadır. OpenCV kütüphanesi kullanılarak sürücünün yüzünün algılanması ve göz hareketlerinin tespiti gerçekleştirilmiştir. Görüntü işleme algoritmaları ile göz en-boy oranı(EAR) ve gözün kapalı kalma süresinin yüzdesi(PERCLOS) hesaplanmaktadır. Aynı zamanda MPU6050 sensöründen gelen verilerle sürücünün baş eğimi, başın anlık düşme hareketi ve başın doğal konumundaki hareketleri analiz edilerek sürücünün yorgunluğunu belirlenmesinde destek sistemi olarak çalışmaktadır.

Anahtar Kelimeler

• Gerçek zamanlı sistemler
• Sürücü yorgunluk tespiti
• Görüntü işleme
• Raspberry Pi 4

Etik Beyan

Bu çalışmada etik kurallara ve gönüllülük esasına uyulmuştur.

Real-Time Driver Fatigue Detection and Alert System

Öz

Driver fatigue is one of the critical factors that threaten traffic safety by impairing cognitive performance and prolonging reaction times during driving, thereby posing risks not only to the driver but also to surrounding individuals. Fatigue can nagatively impact driving performance, particularly during long periods of continuous vehicle operation. This study presents the design of a real-time driver fatigue detection system based on Raspberry Pi 4 microcomputer. The system operates by monitoring facial and ocular movements using an in-vehicle camera and analyzing head movements via an MPU6050 accelerometer sensor. Facial detection and eye tracking are performed using the OpenCV library. Through image processing algorithms, the Eye Aspect Ratio(EAR) and the Percentage of Eye Closure(PERCLOS) are calculated to evaluate visual indicators of fatigue. Simultaneously, data obtained from the MPU6050 sensor is used to analyze head tilt, sudden head drops and deviations from the natural head position. These multimodal data streams work in conjunction to support the detection of driver fatigue, forming the basis of an assistive moniroring system.

Anahtar Kelimeler

• Real-Time system
• Driver drowsiness detection
• Image processing
• Raspberry Pi4

Etik Beyan

Ethical principles and voluntary participation were observed in this study.

Kaynakça

1. [1] Kamran MA, Mannan MMN, Jeong MY. Drowsiness, fatigue and poor sleep’s causes and detection: A Comprehensive Study. IEEE Access. 2019; 7: 167172-167186. doi: 10.1109/ACCESS.2019.2951028.
2. [2] Shaik ME. A systematic review on detection and prediction of driver drowsiness. Transportation Research Interdisciplinary Perspectives. 2023; 21: 100864. https://doi.org/10.1016/j.trip.2023.100864
3. [3] Bergasa LM, Nuevo J, Sotelo MA, Barea R, Lopez ME. Real-time system for monitoring driver vigilance. IEEE Transactions on Intelligent Transportation Systems. 2006; 7: 63-77. doi: 10.1109/TITS.2006.869598.
4. [4] Gottlieb DJ, Ellenbogen JM, Bianchi MT, Czeisler CA. Sleep deficiency and motor vehicle crash risk in the general population: A prospective cohort study. BMC Medicine. 2018; 16: 1-10. https://doi.org/10.1186/s12916-018-1025-7
5. [5] Danisman T, Bilasco IM, Djeraba C, Ihaddadene N. Drowsy driver detection system using eye blink patterns. International Conference on Machine and Web Intelligence. 2010; 230- 33. doi: 10.1109/ICMWI.2010.5648121.
6. [6] Sikander G. Driver fatigue detection systems: A Review. Institute Electrical and Electronic Engineering IEEE. 2019; 20: 2339-2352. doi: 10.1109/TITS.2018.2868499.
7. [7] Davidovits P. Physics in biology and medicine. Elsevier Science. 2013; 191-203.
8. [8] Jung SJ, Shin HS, Chung WY. Driver fatigue and drowsiness monitoring system with embedded electrocardiogram sensor on steering wheel. IET Intelligent Transport Systems. 2014; 8: 43-50. https://doi.org/10.1049/iet-its.2012.0032

9. [9] Patel M, Lal S, Kavanagh D, Rossiter P. Applying neural network analysis on heart rate variability data to assess driver fatigue. Expert Systems with Applications. 2011; 38: 7235-7242.https://doi.org/10.1016/j.eswa.2010.12.028
10. [10] Awais M, Badruddin N, Drieberg M. A hybrid approach to detect driver drowsiness utilizing physiological signals to improve system performance and wearability. Sensors. 2017; 17: 1-16. https://doi.org/10.3390/s17091991
11. [11] Kaushik P, Yadav K, Gopika SC, Kumar N, Kaushik MM. Deep learning for driver vigilance and road safety. 4th International Conference on Advancement in Electronics & Communication Engineering. 2024; 285-290. doi: 10.1109/AECE62803.2024.10911776.
12. [12] Kumar VP, Aravind P, Pooja SND, Prathyush S, Deborah SA, Chandran KR. Driver assistance system using raspberry pi and haar cascade classifiers. 5th International Conference on Intelligent Computing and Control Systems 2021; 1729-1735. doi: 10.1109/ICICCS51141.2021.9432361.
13. [13] Priadana A, Habibi M. Face detection using haar cascades to filter selfie face image on instagram. International Conference of Artificial Intelligence and Information Technology. 2019; 6-9. doi: 10.1109/ICAIIT.2019.8834526.
14. [14] Schmidt A, Kasiński A. The performance of the haar cascade classifiers applied to the face and eyes detection. Computer Recognition Systems 2. Advances in Soft Computing book series. Heidelberg:Springer, 2007; 45: 816-823. https://doi.org/10.1007/978-3-540-75175-5_101
15. [15] Savaş BK, Becerikli Y. Real time driver fatigue detection system based on multi-task ConNN. IEEE Access. 2020; 8: 12491-12498. doi: 10.1109/ACCESS.2020.2963960.
16. [16] Alshaqaqi B, Baquhaizel AS, Ouis MEA, Boumehed M, Ouamri A, Keche M. Driver drowsiness detection system. 8th International Workshop on Systems Signal Processing and their Applications. 2013; 151-155. DOI: 10.1109/WoSSPA.2013.6602353
17. [17] Hossain MY, George FP. IOT based real-time drowsy driving detection system for the prevention of road accidents. International Conference on Intelligent Informatics and Biomedical Sciences. 2018; 3: 190-195. doi: 10.1109/ICIIBMS.2018.8550026.
18. [18] Constantin L, Cristian, Cristian Z, Petrisor D. Driver monitoring using face detection and facial landmarks. International Conference and Exposition on Electrical And Power Engineering 2018; 385–90. doi: 10.1109/ICEPE.2018.8559898.
19. [19] Shetty AB, Bhoomika D, Rebeiro J, Ramyashree. Facial recognition using Haar cascade and LBP classifiers. Global Transitions Proceedings. 2021; 2: 330-335. https://doi.org/10.1016/j.gltp.2021.08.044
20. [20] Kavsaoğlu AR, Mersinkaya İ, Yıldı ÖF, Güdek H. Computer-Aided interface design for real-time pupil motion detection and an application for physically disabled persons. Gazi Üniversitesi Fen Bilimleri Dergisi Part C: Tasarım ve Teknoloji. 2021; 9: 690-707. https://doi.org/10.29109/gujsc.960546
21. [21] Viola P, Jones MJ. Robust real-time face detection PAUL. International Journal of Computer Vision. 2004; 57: 137-154.
22. [22] Kaur J, Singh W. Tools techniques datasets and application areas for object detection in an image: a review. Multimed Tools. 2022; 81: 38297–38351. https://doi.org/10.1007/s11042-022-13153-y
23. [23] Kazemi V, Sullivan J. One millisecond face alignment with an ensemble of regression trees. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2014; 1867–1874.
24. [24] Cech J, Soukupova T. Real-time eye blink detection using facial landmarks. Cent. Mach. Perception, Dep. Cybern. Fac. Electr. Eng. Czech Tech. Univ. 2016; 1-8.
25. [25] Chang RC-H, Wang C-Y, Chen W-T, Chiu C-D. Drowsiness Detection System Based on PERCLOS and Facial Physiological Signal. Sensors. 2022; 22:5380. https://doi.org/10.3390/s22145380