Araştırma Makalesi
BibTex RIS Kaynak Göster

Yapay Zeka Destekli Sürücü Uyarı Sistemi

Yıl 2025, Cilt: 9 Sayı: 1, 23 - 29, 31.07.2025

Öz

Yapay zeka destekli sistemler, trafik güvenliği gibi kritik alanlarda insan hatalarını en aza indirerek kazaların önlenmesinde önemli bir rol oynayabilir. Bu çalışma, sürüş sırasında dikkat dağınıklığını önlemek ve trafik kazalarını azaltmak için yapay zeka destekli bir sürücü izleme ve uyarı sistemi geliştirmeyi amaçlamaktadır. Geliştirilen sistem, Nvidia Jetson Nano platformu üzerinde çalışan ve YOLOv4-tiny modeliyle nesne algılama teknolojisini kullanan bir yapıya sahiptir. Sistem, görsel ve işitsel uyarılar aracılığıyla, mobil cihaz kullanımı gibi dikkat dağıtıcı davranışları belirleyerek sürücünün dikkatini yeniden yola odaklamasına yardımcı olur. Yapılan testlerde elde edilen doğruluk oranı kabul edilebilir düzeydedir. Geliştirilen sistem, düşük maliyeti nedeniyle hem filo yöneticilerine hem de bireysel sürücülere hitap edebilir. Kaza olasılığı düşürülerek yol güvenliği, sürücü ve yolcuların güvenliği artırılabilir.

Kaynakça

  • [1] Allianz SE. (2012). Risk Pulse: Ablenkung am Steuer – Unfallursache Nummer 1 [Risk Pulse: Distraction at the wheel – The number one cause of accidents]. [Online]. Available: https://www.allianz.com/content/dam/onemarketing/azcom/Allianz_com/migration/media/press/document/other/risk-pulse-okt-12_de.pdf
  • [2] Allianz Zentrum für Technik. (2023). Ablenkung und moderne Technik. Allianz Deutschland AG. [Online]. Available: https://www.azt-automotive.com/_Resources/Persistent/5a65121e65b7ccd3ef08fb03139ad979eee5862b/Allianz%20Studie%20Ablenkung%20und%20moderne%20Technik%20(2023).pdf
  • [3] S. Büyükbaş, E. Tekin and B. Tekeş, B. “Akıllı telefon bağımlılığı ile sürücü davranışları arasındaki ilişki,” Trafik ve Ulaşım Araştırmaları Dergisi, vol. 2, no. 1, pp. 16-29, 2019.
  • [4] Turkish Statistical Institute, (2023). Road Traffic Accident Statistics, 2023. [Online]. Available: https://data.tuik.gov.tr/Bulten/Index?p=Karayolu-Trafik-Kaza-Istatistikleri-2023-53479
  • [5] A. Khandakar, M. E. H. Chowdhury, R. Ahmed, A. Dhib, M. Mohammed, N. A. M. A. Al-Emadi and D. Michelson, “Portable System for Monitoring and Controlling Driver Behavior and the Use of a Mobile Phone While Driving,” Sensors, vol. 19, no. 7, 1563, 2019.
  • [6] J. He, W. Choi, J. S. McCarley, B. S. Chaparro and C. Wang, “Texting while driving using Google Glass™: Promising but not distraction-free,” Accident Analysis & Prevention, vol. 81, pp. 218-229, 2015.
  • [7] M. Fazeen, B. Gozick, R. Dantu, M. Bhukhiya and M. C. González, "Safe Driving Using Mobile Phones," IEEE Transactions on Intelligent Transportation Systems, vol. 13, no. 3, pp. 1462-1468, Sept. 2012, doi: 10.1109/TITS.2012.2187640.
  • [8] S. H. Ali and R. Hassan, “The effectiveness of RF jamming devices in preventing distracted driving,” Journal of Transportation Safety & Security, vol. 10, no. 2, pp. 123-130, 2018.
  • [9] D. N. Lu, T. T. T. Ngo, D. N. Nguyen, T. H. Nguyen and H. N. Nguyen, “A Novel Mobile Online Vehicle Status Awareness Method Using Smartphone Sensors,” in International Conference on Information Science and Applications, 2017, pp. 30-37.
  • [10] M. L. Brumbelow and D. S. Zuby, “Real-world safety benefits of HUD technologies,” Accident Analysis & Prevention, vol. 60, pp. 60-65, 2013.
  • [11] Y. Çınar and Z. Kılınç, “Görüntü işleme teknikleriyle sürücü davranışlarının izlenmesi,” in Ulusal Otomotiv Teknolojileri Konferansı Bildirileri, 2021, pp. 45-52.
  • [12] H. A. Shabeer, R. W. Banu and H. A. Zubar, “Technology to prevent mobile phone accidents,” International Journal of Enterprise Network Management, vol. 5, no. 2, pp. 144-155, 2012.
  • [13] K. Haberka and R. S. Jurecki, “Drivers' use of different types of multimedia devices while driving – A survey study,” The Archives of Automotive Engineering – Archiwum Motoryzacji, vol. 103, no. 1, 2024.
  • [14] S. A. Al-Ajlouny and K. K. Alzboon, “Effects of mobile phone usage on driving behavior and risk of traffic accidents,” Journal of Radiation Research and Applied Sciences, vol. 16, no. 4, 100662, 2023.
  • [15] L. Gicquel, P. Ordonneau, E. Blot, C. Toillon, P. Ingrand and L. Romo, “Description of various factors contributing to traffic accidents in youth and measures proposed to alleviate recurrence,” Frontiers in Psychiatry, vol. 8, no. 94, 2017.
  • [16] JetpackSDK (2024) Jetpack Dev. [Online] Available: https://developer.nvidia.com/embedded/jetpack
  • [17] A. Bochkovskiy, C. Wang and H. M. Liao, “YOLOv4: Optimal Speed and Accuracy of Object Detection,” ArXiv, abs/2004.10934, 2020.
  • [18] J. Redmon, S. Divvala, R. Girshick and A. Farhadi, “You Only Look Once: Unified, Real-Time Object Detection,” ArXiv, abs/1506.02640, 2016.
  • [19] S. J. Ji, Q. H. Ling and F. Han, “An improved algorithm for small object detection based on YOLO v4 and multi-scale contextual information,” Computers and Electrical Engineering, vol. 105, 108490, 2023.
  • [20] D. Vera-Yanez, A. Pereira, N. Rodrigues, J. P. Molina, A. S. García and A. Fernández-Caballero, “Vision-based flying obstacle detection for avoiding midair collisions: A systematic review,” Journal of Imaging, vol. 9, no. 10, 194, 2023.
  • [21] R. Tian, K. Ruan, L. Li, J. Le, J. Greenberg and S. Barbat, "Standardized evaluation of camera-based driver state monitoring systems," IEEE/CAA Journal of Automatica Sinica, vol. 6, no. 3, pp. 716-732, May 2019, doi: 10.1109/JAS.2019.1911483

Artificial Intelligence-Assisted Driver Alert System

Yıl 2025, Cilt: 9 Sayı: 1, 23 - 29, 31.07.2025

Öz

Artificial intelligence-supported systems can play a key role in preventing accidents by minimizing human errors in critical areas such as traffic safety. This study aims to develop an artificial intelligence-supported driver monitoring and alert system to prevent distraction while driving and reduce traffic accidents. The developed system has a structure that works on the Nvidia Jetson Nano platform and uses object detection technology with the YOLOv4-tiny model. Through visual and aural alerts, the system helps the driver refocus his attention on the road by identifying distracting behaviors like using mobile devices. The accuracy rate obtained in the tests performed is at an acceptable level. The developed system can appeal to both fleet managers and individual drivers due to its low cost. Road safety, as well as the safety of drivers and passengers, can be improved by lowering the likelihood of accidents.

Etik Beyan

Çalışma insan ya da hayvanlarla ilgili bir deneysel çalışma içermemektedir.

Destekleyen Kurum

None

Teşekkür

-

Kaynakça

  • [1] Allianz SE. (2012). Risk Pulse: Ablenkung am Steuer – Unfallursache Nummer 1 [Risk Pulse: Distraction at the wheel – The number one cause of accidents]. [Online]. Available: https://www.allianz.com/content/dam/onemarketing/azcom/Allianz_com/migration/media/press/document/other/risk-pulse-okt-12_de.pdf
  • [2] Allianz Zentrum für Technik. (2023). Ablenkung und moderne Technik. Allianz Deutschland AG. [Online]. Available: https://www.azt-automotive.com/_Resources/Persistent/5a65121e65b7ccd3ef08fb03139ad979eee5862b/Allianz%20Studie%20Ablenkung%20und%20moderne%20Technik%20(2023).pdf
  • [3] S. Büyükbaş, E. Tekin and B. Tekeş, B. “Akıllı telefon bağımlılığı ile sürücü davranışları arasındaki ilişki,” Trafik ve Ulaşım Araştırmaları Dergisi, vol. 2, no. 1, pp. 16-29, 2019.
  • [4] Turkish Statistical Institute, (2023). Road Traffic Accident Statistics, 2023. [Online]. Available: https://data.tuik.gov.tr/Bulten/Index?p=Karayolu-Trafik-Kaza-Istatistikleri-2023-53479
  • [5] A. Khandakar, M. E. H. Chowdhury, R. Ahmed, A. Dhib, M. Mohammed, N. A. M. A. Al-Emadi and D. Michelson, “Portable System for Monitoring and Controlling Driver Behavior and the Use of a Mobile Phone While Driving,” Sensors, vol. 19, no. 7, 1563, 2019.
  • [6] J. He, W. Choi, J. S. McCarley, B. S. Chaparro and C. Wang, “Texting while driving using Google Glass™: Promising but not distraction-free,” Accident Analysis & Prevention, vol. 81, pp. 218-229, 2015.
  • [7] M. Fazeen, B. Gozick, R. Dantu, M. Bhukhiya and M. C. González, "Safe Driving Using Mobile Phones," IEEE Transactions on Intelligent Transportation Systems, vol. 13, no. 3, pp. 1462-1468, Sept. 2012, doi: 10.1109/TITS.2012.2187640.
  • [8] S. H. Ali and R. Hassan, “The effectiveness of RF jamming devices in preventing distracted driving,” Journal of Transportation Safety & Security, vol. 10, no. 2, pp. 123-130, 2018.
  • [9] D. N. Lu, T. T. T. Ngo, D. N. Nguyen, T. H. Nguyen and H. N. Nguyen, “A Novel Mobile Online Vehicle Status Awareness Method Using Smartphone Sensors,” in International Conference on Information Science and Applications, 2017, pp. 30-37.
  • [10] M. L. Brumbelow and D. S. Zuby, “Real-world safety benefits of HUD technologies,” Accident Analysis & Prevention, vol. 60, pp. 60-65, 2013.
  • [11] Y. Çınar and Z. Kılınç, “Görüntü işleme teknikleriyle sürücü davranışlarının izlenmesi,” in Ulusal Otomotiv Teknolojileri Konferansı Bildirileri, 2021, pp. 45-52.
  • [12] H. A. Shabeer, R. W. Banu and H. A. Zubar, “Technology to prevent mobile phone accidents,” International Journal of Enterprise Network Management, vol. 5, no. 2, pp. 144-155, 2012.
  • [13] K. Haberka and R. S. Jurecki, “Drivers' use of different types of multimedia devices while driving – A survey study,” The Archives of Automotive Engineering – Archiwum Motoryzacji, vol. 103, no. 1, 2024.
  • [14] S. A. Al-Ajlouny and K. K. Alzboon, “Effects of mobile phone usage on driving behavior and risk of traffic accidents,” Journal of Radiation Research and Applied Sciences, vol. 16, no. 4, 100662, 2023.
  • [15] L. Gicquel, P. Ordonneau, E. Blot, C. Toillon, P. Ingrand and L. Romo, “Description of various factors contributing to traffic accidents in youth and measures proposed to alleviate recurrence,” Frontiers in Psychiatry, vol. 8, no. 94, 2017.
  • [16] JetpackSDK (2024) Jetpack Dev. [Online] Available: https://developer.nvidia.com/embedded/jetpack
  • [17] A. Bochkovskiy, C. Wang and H. M. Liao, “YOLOv4: Optimal Speed and Accuracy of Object Detection,” ArXiv, abs/2004.10934, 2020.
  • [18] J. Redmon, S. Divvala, R. Girshick and A. Farhadi, “You Only Look Once: Unified, Real-Time Object Detection,” ArXiv, abs/1506.02640, 2016.
  • [19] S. J. Ji, Q. H. Ling and F. Han, “An improved algorithm for small object detection based on YOLO v4 and multi-scale contextual information,” Computers and Electrical Engineering, vol. 105, 108490, 2023.
  • [20] D. Vera-Yanez, A. Pereira, N. Rodrigues, J. P. Molina, A. S. García and A. Fernández-Caballero, “Vision-based flying obstacle detection for avoiding midair collisions: A systematic review,” Journal of Imaging, vol. 9, no. 10, 194, 2023.
  • [21] R. Tian, K. Ruan, L. Li, J. Le, J. Greenberg and S. Barbat, "Standardized evaluation of camera-based driver state monitoring systems," IEEE/CAA Journal of Automatica Sinica, vol. 6, no. 3, pp. 716-732, May 2019, doi: 10.1109/JAS.2019.1911483
Toplam 21 adet kaynakça vardır.

Ayrıntılar

Birincil Dil İngilizce
Konular Görüntü İşleme
Bölüm Makaleler
Yazarlar

Galip Berk 0009-0001-4382-7900

Gürkan Tuna 0000-0002-6466-4696

Erken Görünüm Tarihi 12 Temmuz 2025
Yayımlanma Tarihi 31 Temmuz 2025
Gönderilme Tarihi 23 Mart 2025
Kabul Tarihi 10 Mayıs 2025
Yayımlandığı Sayı Yıl 2025 Cilt: 9 Sayı: 1

Kaynak Göster

IEEE G. Berk ve G. Tuna, “Artificial Intelligence-Assisted Driver Alert System”, IJMSIT, c. 9, sy. 1, ss. 23–29, 2025.