TRAFİK GÜVENLİĞİNİ ARTIRMAK İÇİN DERİN ÖĞRENME TEMELLİ UYKU DURUM TESPİTİ VE UYARI SİSTEMİ

Öz

Bu çalışma, sürücü yorgunluğunu düşük maliyetli NVIDIA Jetson Nano üzerinde gerçek zamanlı olarak saptayabilen tak‑çalıştır bir prototip geliştirmeyi amaçlamaktadır. Gözün açık‑kapalı durumunu tespit etmek için YOLO ailesinin güncel modelleri kullanılmış ve NVIDIA Jetson Nano’ya aktarılmıştır. Geliştirilen prototip 3B yazıcıyla üretilmiş kompakt bir muhafaza kutusuna yerleştirilerek araç çakmak prizinden beslenen, sürücünün gsörüşünü engellemeyen ve sesli ikaz veren tam entegre bir modül hâline getirilmiştir. Böylece çalışma, YOLO serisinin parametre‑verimli sürümlerini sistematik olarak değerlendirerek gömülü donanımda yüksek doğruluk‑hız dengesi sağlayan bir prototip örneği sunmaktadır.

Anahtar Kelimeler

• Güvenli Sürüş
• Uyku Durumu Tespiti
• Derin Öğrenme
• Yapay Zeka
• 3B Yazıcı.

Destekleyen Kurum

Bu projedeki donanım malzemeleri ( NVIDIA jetson nano yapay zeka kiti ve Raspberry Pi Kamera Modül 2) TÜBİTAK Bilim İnsanı Destek Programları Başkanlığı (BİDEB) tarafından yürütülen 2209 A Üniversite Öğrencileri Araştırma Projeleri Destekleme Programı tarafından finanse edilmiştir.

Proje Numarası

1919B012322459

Teşekkür

Bu çalışma, TÜBİTAK Bilim İnsanı Destek Programları Başkanlığı (BİDEB) tarafından yürütülen 2209 A Üniversite Öğrencileri Araştırma Projeleri Destekleme Programı 2023 yılı 2. dönemi kapsamında 1919B012322459 numaralı proje olarak desteklenmiştir. Sağladığı mali ve akademik katkılar için TÜBİTAK’a içten teşekkür ederiz. Ayrıca, bu çalışmanın gerçekleştirilmesinde katkısı olan Tekirdağ Namık Kemal Üniversitesi TBMYO Bilgisayar Teknolojileri Bölümüne de teşekkür ederiz.

DEEP LEARNING‑BASED DROWSINESS DETECTION AND ALERT SYSTEM FOR ENHANCING TRAFFIC SAFETY

Öz

This study presents a plug‑and‑play prototype capable of detecting driver drowsiness in real time on a low‑cost NVIDIA Jetson Nano platform. State‑of‑the‑art (SOTA), parameter‑efficient models from the YOLO family are employed to identify the eye‑open/eye‑closed state and are ported to the Jetson Nano for inference. The trained network is housed in a compact 3D‑printed enclosure that can be powered from the vehicle’s cigarette‑lighter socket, does not obstruct the driver’s view, and issues an audible alert when drowsiness is detected. By systematically evaluating recent YOLO variants, the prototype demonstrates a balanced trade‑off between accuracy and processing speed on resource‑constrained embedded hardware, offering a practical solution for real‑time driver monitoring.

Anahtar Kelimeler

• Safe Driving
• Drowsiness Detection
• Deep Learning
• Artificial Intelligence
• 3D Printing

Proje Numarası

1919B012322459

Kaynakça

1. 1. Civik, E., Yüzgeç, U., “Real-time driver fatigue detection system with deep learning on a low-cost embedded system”, Microprocessors and Microsystems, Vol. 99, Issue 1, Pages 1-12, 2023.
2. 2. Türkiye İstatistik Kurumu, “Karayolu Trafik Kaza İstatistikleri, 2024”, https://data.tuik.gov.tr/Bulten/Index?p=Karayolu-Trafik-Kaza-Istatistikleri-2024-54056#:~:text=Karayolu%20trafik%20kazalarında%202024%20yılında bin%20470%20kişi%20ise%20yaralandı, Erişim Tarihi: 07.07.2025.
3. 3. Fletcher, A., McCulloch, K., Baulk, S.D., Dawson, D., “Countermeasures to driver fatigue: a review of public awareness campaigns and legal approaches”, Australian and New Zealand Journal of Public Health, Vol. 29, Issue 5, Pages 471–476, 2005.
4. 4. Ahmed, H.A., Rashid, T.A., Sadiq, A.T., “Face behavior recognition through support vector machines”, International Journal of Advanced Computer Science and Applications, Vol. 7, Issue 1, Pages101-108, 2016.
5. 5. Sikander, G., Anwar, S., “Driver Fatigue Detection Systems: A Review”, IEEE Transactions on Intelligent Transportation Systems, Vol. 20, Issue 6, Pages 2339–2352, 2019.
6. 6. Coetzer, R.C., Hancke, G.P., “Driver fatigue detection: A survey”, AFRICON 2009, IEEE, Pages 1–6, Yaounde, Cameroon, 2009.
7. 7. Wang, Q., Yang, J., Ren, M., Zheng, Y., “Driver Fatigue Detection: A Survey”, 6th World Congress on Intelligent Control and Automation, Pages 8587–8591, IEEE, Jinan, China, 2006.
8. 8. Saini, V., Saini, R., “Driver drowsiness detection system and techniques: a review”, International Journal of Computer Science and Information Technologies, Vol. 5, Issue 3, Pages 4245–4249, 2014.

9. 9. Rogado, E., Garcia, J.L., Barea, R., Bergasa, L.M., Lopez, E., “Driver fatigue detection system”, IEEE International Conference on Robotics and Biomimetics, Pages 1105–1110, Xian, China, 2009.
10. 10. Chellappa, Y., Joshi, N.N., Bharadwaj, V., “Driver fatigue detection system”, IEEE International Conference on Signal and Image Processing (ICSIP), Pages 655–660, Beijing, China, 2016.
11. 11. Abbas, Q., Alsheddy, A., “Driver Fatigue Detection Systems Using Multi-Sensors, Smartphone, and Cloud-Based Computing Platforms: A Comparative Analysis”, Sensors, Vol. 21, Issue 1, Pages 2-38, 2020.
12. 12. Ed-Doughmi, Y., Idrissi, N., Hbali, Y., “Real-Time System for Driver Fatigue Detection Based on a Recurrent Neuronal Network”, Journal of Imaging, Vol. 6, Issue 8, Pages 2-15, 2020.
13. 13. Azim, T., Jaffar, M.A., Mirza, A.M., “Fully automated real time fatigue detection of drivers through Fuzzy Expert Systems”, Applied Soft Computing, Vol. 18, Issue 1, Pages 25–38, 2014.
14. 14. Ansari, S., Du, H., Naghdy, F., Stirling, D., “Automatic driver cognitive fatigue detection based on upper body posture variations”, Expert Systems with Applications, Vol. 203, Issue 2, Pages 117568, 2022.
15. 15. Jin, L., Niu, Q., Jiang, Y., Xian, H., Qin, Y., Xu, M., “Driver Sleepiness Detection System Based on Eye Movements Variables”, Advances in Mechanical Engineering, Vol. 5, Issue 1, Pages 1-7, 2013.
16. 16. Dasgupta, A., Rahman, D., Routray, A., “A Smartphone-Based Drowsiness Detection and Warning System for Automotive Drivers”, IEEE Transactions on Intelligent Transportation Systems, Vol. 20, Issue 11, Pages 4045–4054, 2018.
17. 17. Acar Vural, R., Sert, M.Y., Karaköse, B., “Gerçek Zamanlı Sürücü Yorgunluk Tespit Sistemi”, Marmara Fen Bilimleri Dergisi, Cilt 30, Sayı 3, Sayfa 249–259, 2018.
18. 18. Gupta, R., Aman, K., Shiva, N., Singh, Y., “An improved fatigue detection system based on behavioral characteristics of driver”, 2nd IEEE International Conference on Intelligent Transportation Engineering (ICITE), Pages 227–230, Singapore, Singapore, 2017.
19. 19. Khan, M.F., Aadil, F., “Efficient Car Alarming System for Fatigue Detection during Driving”, International Journal of Innovation, Management and Technology, Vol. 3, Issue 4, Pages 480-486, 2012.
20. 20. Hossan, A., Kashem, F. Bin, Hasan, M.M., Naher, S., Rahman, M.I., “A smart system for driver’s fatigue detection, remote notification and semi-automatic parking of vehicles to prevent road accidents”, In 2016 International Conference on Medical Engineering, Health Informatics and Technology (MediTec), Pages 1–6, Dhaka, Bangladesh, 2016.
21. 21. Zhang, Z., Zhang, J., “Driver Fatigue Detection Based Intelligent Vehicle Control”, 18th International Conference on Pattern Recognition (ICPR’06), Pages 1262–1265, Hong Kong, China, 2006.
22. 22. Krishnasree, V., Balaji, N., Rao, P.S., “A real time improved driver fatigue monitoring system”, WSEAS Transactions on Signal Processing, Vol. 10, Issue 1, Page 146-155, 2014.
23. 23. Aboagye, I.A., Owusu-Banahene, W., Amexo, K., Boakye-Yiadom, K.A., Sowah, R.A., Sowah, N.L., “Design and Development of Computer Vision-Based Driver Fatigue Detection and Alert System”, 8th IEEE International Conference on Adaptive Science and Technology (ICAST), Pages 1–6, Accra, Ghana, 2021.
24. 24. Chang, W-J., Chen, L-B., Chiou, Y-Z., “Design and Implementation of a Drowsiness-Fatigue-Detection System Based on Wearable Smart Glasses to Increase Road Safety”, IEEE Transactions on Consumer Electronics, Vol. 64, Issue 4, Pages 461–469, 2018.
25. 25. Patil, P.V., “Drowsiness Detection Dataset”, https://www.kaggle.com/datasets/prasadvpatil/mrl-dataset, Erişim Tarihi: 06.07.2025.
26. 26. Officier Raccoon, “Eye Detection Dataset”, https://www.kaggle.com/datasets/icebearogo/eye-detection-dataset, Erişim Tarihi: 05.07.2025.
27. 27. Frențescu, M., “Age prediction”, https://www.kaggle.com/datasets/mariafrenti/age-prediction, Erişim Tarihi: 05.07.2025.
28. 28. Redmon, J., Divvala, S., Girshick, R., Farhadi, A., “You Only Look Once: Unified, Real-Time Object Detection” Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Pages 779–788, Las Vegas, USA, 2016.
29. 29. Reis, D., Kupec, J., Hong, J., Daoudi, A., “Real‑time flying object detection with YOLOv8”, arXiv preprint, Vol. 2305.09972, Pages. 1–10, 2024.
30. 30. Wang, C-Y., Yeh, I-H., Liao, H-Y.M., “YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information”, In European Conference on Computer Vision (ECCV), Pages 1- 21, Munich, Germany, 2024.
31. 31. Wang, A., Chen, H., Liu, L., Chen, K., Lin, Z., Han, J., et al., “YOLOv10: Real-Time End-to-End Object Detection” In Advances in Neural Information Processing Systems (NeurIPS 2024), Vol. 37, Issue 1, Pages 107984–108011, Vancouver, Canada, 2024.
32. 32. Khanam, R., Hussain, M., “YOLOv11: An Overview of the Key Architectural Enhancements arXiv preprint, Vol. 2410.17725, Pages 1–9, 2024.
33. 33. Mittal, S., “A Survey on optimized implementation of deep learning models on the NVIDIA Jetson platform”, Journal of Systems Architecture, Vol. 97, Issue 1, Pages 428–442, 2019.
34. 34. Saeedi, B., “The Jetson Artificial Intelligence Tool Chain (JAI-TC)”, Yüksek Lisans Tezi, Concordia University, Montreal, 2019.
35. 35. Suzen, A.A., Duman, B., Sen, B., “Benchmark Analysis of Jetson TX2, Jetson Nano and Raspberry PI using Deep-CNN”, International Congress on Human-Computer Interaction, Optimization and Robotic Applications (HORA), Pages 1–5, Ankara, Turkey, 2020.