Treffer: Advancing Road Safety: A Comprehensive Evaluation of Object Detection Models for Commercial Driver Monitoring Systems.

This paper addresses the critical issue of road safety in the indispensable role of transportation for societal well-being and economic growth. Despite global initiatives like Vision Zero, traffic accidents persist, largely influenced by driver behavior. Advanced driver monitoring systems (ADMSs) utilizing computer vision have emerged to mitigate this issue, but existing systems are often costly and inaccessible, particularly for bus companies. This study introduces a lightweight, deep-learning-based ADMS tailored for real-time driver behavior monitoring, addressing practical barriers to enhance safety measures. A meticulously curated dataset, encompassing diverse demographics and lighting conditions, captures 4966 images depicting five key driver behaviors: eye closure, yawning, smoking, mobile phone usage, and seatbelt compliance. Three object detection models—Faster R-CNN, RetinaNet, and YOLOv5—were evaluated using critical performance metrics. YOLOv5 demonstrated exceptional efficiency, achieving an FPS of 125, a compact model size of 42 MB, and an mAP@IoU 50% of 93.6%. Its performance highlights a favorable trade-off between speed, model size, and prediction accuracy, making it ideal for real-time applications. Faster R-CNN achieved an FPS of 8.56, a model size of 835 MB, and an mAP@IoU 50% of 89.93%, while RetinaNet recorded an FPS of 16.24, a model size of 442 MB, and an mAP@IoU 50% of 87.63%. The practical deployment of the ADMS on a mini CPU demonstrated cost-effectiveness and high performance, enhancing accessibility in real-world settings. By elucidating the strengths and limitations of different object detection models, this research contributes to advancing road safety through affordable, efficient, and reliable technology solutions. [ABSTRACT FROM AUTHOR]

Copyright of Future Transportation is the property of MDPI and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)