Keeping an Eye on Safety: How Safe-Drive Detects Driver Distractions and Unsafe Behaviors

• Ângela Brigida Albarello UnB http://orcid.org/0009-0002-9455-0144
• Edna Dias Canedo UnB https://orcid.org/0000-0002-2159-339X
• Vinícius P. Gonçalves UnB https://orcid.org/0000-0002-3771-2605
• Fábio L. L. Mendonça UnB https://orcid.org/0000-0001-7100-7304
• Francisco Airton Silva UFPI https://orcid.org/0000-0002-8211-6060
• Rodolfo I. Meneguette USP https://orcid.org/0000-0003-2982-4006
• Geraldo P. Rocha Filho UESB https://orcid.org/0000-0001-6795-2768

DOI: https://doi.org/10.5753/courb.2025.8262

Abstract

Urban traffic safety is one of the main challenges faced by smart cities, especially given the increasing number of accidents caused by driver distractions. Identifying and mitigating distracted and unsafe driving behaviors in real time remains an open problem due to scene complexity and the limitations of existing solutions. To address this scenario, this work proposes Safe-Drive, a hybrid computer vision solution based on two YOLO convolutional architectures: one dedicated to detecting distracted behaviors and another focused on segmenting seat belt usage. When compared to other approaches in the literature, Safe-Drive achieved a high accuracy rate and a 52% reduction in inference time in the worst-case scenario. These results highlight Safe-Drive as an effective and scalable solution for real-time detection of distracted and unsafe driver behaviors.

Keywords: urban traffic safety, distracted behaviors, unsafe behaviors, real-time detection, YOLO

References

Abbass, M. A. B. and Ban, Y. (2024). Mobilenet-based architecture for distracted human driver detection of autonomous cars. Electronics, 13(2):365.

Abouelnaga, Y., Eraqi, H. M., and Moustafa, M. N. (2017). Real-time distracted driver posture classification. arXiv preprint arXiv:1706.09498.

Al-Mahbashi, M., Li, G., Peng, Y., Al-Soswa, M., and Debsi, A. (2025). Real-time distracted driving detection based on gm-yolov8 on embedded systems. Journal of Transportation Engineering, Part A: Systems, 151(3):04024126.

Bouhsissin, S., Sael, N., and Benabbou, F. (2023). Driver behavior classification: a systematic literature review. IEEE Access, 11:14128–14153.

Debsi, A., Ling, G., Al-Mahbashi, M., Al-Soswa, M., and Abdullah, A. (2024). Driver distraction and fatigue detection in images using me-yolov8 algorithm. IET Intelligent Transport Systems, 18(10):1910–1930.

Du, Y., Liu, X., Yi, Y., and Wei, K. (2023). Optimizing road safety: advancements in lightweight yolov8 models and ghostc2f design for real-time distracted driving detection. Sensors, 23(21):8844.

Elshamy, M. R., Emara, H. M., Shoaib, M. R., and Badawy, A.-H. A. (2024). P-yolov8: Efficient and accurate real-time detection of distracted driving. arXiv preprint arXiv:2410.15602.

Ferrante, G. S., Vasconcelos Nakamura, L. H., Sampaio, S., Filho, G. P. R., and Meneguette, R. I. (2024). Evaluating yolo architectures for detecting road killed endangered brazilian animals. Scientific Reports, 14(1):1353.

Fresta, M., Bellotti, F., Bochenko, I., Lazzaroni, L., Merlhiot, G., Tango, F., and Berta, R. (2025). Deep learning-based real-time driver cognitive distraction detection. IEEE Access.

Kshatri, S. S. and Rathore, Y. K. (2025). Real-time driver distraction detection using fast r-cnn algorithm.

Kumar, K. S. and Raja, S. P. (2025). A comprehensive review of computer vision technology in driver monitoring system. Data Science & Exploration in Artificial Intelligence, 519–525.

Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.-Y., and Berg, A. C. (2016). SSD: Single shot multibox detector. In Computer Vision–ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11–14, 2016, Proceedings, Part I 14, 21–37. Springer.

Qu, F., Dang, N., Furht, B., and Nojoumian, M. (2024). Comprehensive study of driver behavior monitoring systems using computer vision and machine learning techniques. Journal of Big Data, 11(1):32.

Redmon, J., Divvala, S., Girshick, R., and Farhadi, A. (2016). You only look once: Unified, real-time object detection. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 779–788.

Ren, S., He, K., Girshick, R., and Sun, J. (2015). Faster R-CNN: Towards real-time object detection with region proposal networks. Advances in Neural Information Processing Systems, 28.

Ribeiro Jr, A., da Costa, J. B., Rocha Filho, G. P., Villas, L. A., Guidoni, D. L., Sampaio, S., and Meneguette, R. I. (2023). Harmonic: Shapley values in market games for resource allocation in vehicular clouds. Ad Hoc Networks, 149:103224.

Rocha Filho, G. P., Meneguette, R. I., Neto, J. R. T., Valejo, A., Weigang, L., Ueyama, J., Pessin, G., and Villas, L. A. (2020). Enhancing intelligence in traffic management systems to aid in vehicle traffic congestion problems in smart cities. Ad Hoc Networks, 107:102265.

Sajid, F., Javed, A. R., Basharat, A., Kryvinska, N., Afzal, A., and Rizwan, M. (2021). An efficient deep learning framework for distracted driver detection. IEEE Access, 9:169270–169280.

Shen, Q., Zhang, L., Zhang, Y., Li, Y., Liu, S., and Xu, Y. (2024). Distracted driving behavior detection algorithm based on lightweight stardl-yolo. Electronics, 13(16):3216.

Shirole, V., Shahade, A. K., and Deshmukh, P. V. (2025). A comprehensive review on data-driven driver behaviour scoring in vehicles: technologies, challenges and future directions. Discover Artificial Intelligence, 5(1):26.

StateFarm (2016). State farm distracted driver detection. [link]. Acessado em 28 de outubro de 2024.

Wang, R., Wang, W., Gao, J., Lin, D., Yap, K.-H., and Li, B. (2024). Multifuser: Multimodal fusion transformer for enhanced driver action recognition. arXiv preprint arXiv:2408.01766.

World Health Organization (2022). Distracted driving. [link]. Acesso em: 22 mar. 2025.

Zhao, C., Zhang, B., Lian, J., He, J., Lin, T., and Zhang, X. (2011). Classification of driving postures by support vector machines. In 2011 Sixth International Conference on Image and Graphics, 926–930. IEEE.