Research Article

An Intelligent Driver Tracking and Driving Analysis Reporting System

Volume: 15 Number: 1 March 15, 2025
EN TR

An Intelligent Driver Tracking and Driving Analysis Reporting System

Abstract

As the number of vehicles on the roads increases day by day, the number of traffic accidents also increases. According to Turkish Statistical Institute (TÜİK) 2023 data, 88.9% of these accidents are caused by driver errors. These mistakes of drivers usually occur because they are careless, tired, sleepy, or busy with a different task while driving. At this point, the need for the use of smart systems in vehicles has begun. Intelligent vehicle systems have been developed to warn drivers during these behaviors. These systems aim to provide the driver with a safer driving experience. Looking at the literature, studies have been done on this subject and embedded systems have been developed. The general purpose of these studies is to ensure safe driving by warning the driver while driving. The proposed intelligent driver tracking and driving analysis reporting system in this study is designed mostly for companies in the freight and passenger transportation sector. In order to prevent traffic accidents caused by driver error, the aim is to conduct a driving analysis of commercial vehicle drivers and report them to the transportation company, thus minimizing traffic accidents by choosing more careful drivers or ensuring that the drivers are more careful. The proposed system consists of two cameras placed inside the vehicle, facing with the driver and traffic, recording video throughout the drive. The video recording is uploaded to the driving analysis reporting software, two separate videos are passed through two separate models and the results are displayed in a meaningful format. While carrying out the project, two different models are created. While the first of these models detects the driver's behavior such as sleepiness, making a phone call, or smoking, the second analyzes whether the vehicle complies with the speed limits and traffic lights. These analyses are presented in the form of reports with a user-friendly interface. In this way, it is aimed to ensure a safer traffic flow by preventing accidents caused by drivers.

Keywords

Driver Behavior Tracking, Machine Learning, Driving Analysis

Project Number

1919B012305483

References

  1. Acar Vural, R., Sert, M. Y., & Karaköse, B. (2018). Gerçek Zamanlı Sürücü Yorgunluk Tespit Sistemi. Marmara Fen Bilimleri Dergisi, 30(3), 249-259. https://doi.org/10.7240/marufbd.417915
  2. Aki, M. O. (2017). Sürücü uykululuğunun gerçek zamanlı görüntü işleme ve makine öğrenmesi teknikleri ile tespitine yönelik bir sistem tasarımı ve uygulaması, Doktora Tezi, Trakya Üniversitesi, Fen Bilimleri Enstitüsü.
  3. Çivik, E. (2020). Gömülü sistem üzerinde derin öğrenme bazlı sürücü yorgunluk tespiti, Master's thesis, Bilecik Şeyh Edebali Üniversitesi, Fen Bilimleri Enstitüsü.
  4. Django (Version 5.1) (2024). [Computer Software]. https://www.djangoproject.com (Last Access Date: 04.03.2025)
  5. Grover, P. (2018). Evolution of object detection and localization algorithms. Towards Data Science. https://medium.com/towards-data-science/evolution-of-object-detection-and-localization-algorithms-e241021d8bad (Last Access Date: 04.03.2025)
  6. Golgiyaz, S., Kocamaz, A. F., & Okumuş, F. (2017). Video Tabanlı Uykulu Sürücü Algılama Sistemi. Journal of Safety Research, 7(1), 1-12.
  7. Güney, E. (2021). Sürücü asistan sistemleri için mobil GPU tabanlı gerçek zamanlı durum analizi ve tespit uygulamaları, Master's thesis, Sakarya Üniversitesi, Fen Bilimleri Enstitüsü.
  8. Jocher, G., Chaurasia, A., & Qiu, J. (2023). Ultralytics YOLO (Version 8.0.0) [Computer software]. https://github.com/ultralytics/ultralytics (Last Access Date: 04.03.2025)
  9. Ma, B., Fu, Z., Rakheja, S., Zhao, D., He, W., Ming, W., & Zhang, Z. (2024). Distracted Driving Behavior and Driver’s Emotion Detection Based on Improved YOLOv8 with Attention Mechanism. IEEE Access. https://doi.org/10.1109/ACCESS.2024.3374726
  10. Redmon, J., Divvala, S., Girshick, R., & Farhadi, A. (2016). You Only Look Once: Unified, Real-Time Object Detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 779-788. https://doi.org/10.1109/CVPR.2016.91.
APA
Akalan, F., Mumcu, B., & Şahin, E. (2025). An Intelligent Driver Tracking and Driving Analysis Reporting System. Karadeniz Fen Bilimleri Dergisi, 15(1), 319-340. https://doi.org/10.31466/kfbd.1548673
AMA
1.Akalan F, Mumcu B, Şahin E. An Intelligent Driver Tracking and Driving Analysis Reporting System. KFBD. 2025;15(1):319-340. doi:10.31466/kfbd.1548673
Chicago
Akalan, Ferhat, Betül Mumcu, and Erdinç Şahin. 2025. “An Intelligent Driver Tracking and Driving Analysis Reporting System”. Karadeniz Fen Bilimleri Dergisi 15 (1): 319-40. https://doi.org/10.31466/kfbd.1548673.
EndNote
Akalan F, Mumcu B, Şahin E (March 1, 2025) An Intelligent Driver Tracking and Driving Analysis Reporting System. Karadeniz Fen Bilimleri Dergisi 15 1 319–340.
IEEE
[1]F. Akalan, B. Mumcu, and E. Şahin, “An Intelligent Driver Tracking and Driving Analysis Reporting System”, KFBD, vol. 15, no. 1, pp. 319–340, Mar. 2025, doi: 10.31466/kfbd.1548673.
ISNAD
Akalan, Ferhat - Mumcu, Betül - Şahin, Erdinç. “An Intelligent Driver Tracking and Driving Analysis Reporting System”. Karadeniz Fen Bilimleri Dergisi 15/1 (March 1, 2025): 319-340. https://doi.org/10.31466/kfbd.1548673.
JAMA
1.Akalan F, Mumcu B, Şahin E. An Intelligent Driver Tracking and Driving Analysis Reporting System. KFBD. 2025;15:319–340.
MLA
Akalan, Ferhat, et al. “An Intelligent Driver Tracking and Driving Analysis Reporting System”. Karadeniz Fen Bilimleri Dergisi, vol. 15, no. 1, Mar. 2025, pp. 319-40, doi:10.31466/kfbd.1548673.
Vancouver
1.Ferhat Akalan, Betül Mumcu, Erdinç Şahin. An Intelligent Driver Tracking and Driving Analysis Reporting System. KFBD. 2025 Mar. 1;15(1):319-40. doi:10.31466/kfbd.1548673