Abstract
Driver distraction is a significant source of road accidents and car crashes. A distracted driver poses a threat to not only himself and the ones in the car but also others in the road, namely nearby pedestrians, bicyclists, and other vehicles. Although distractions while driving may majorly seem to involve cell phone usage and texting, it also comprises of other events such as eating/drinking, communicating with co-passengers, adjusting hair/makeup, or fiddling around the radio or climate controls. Therefore, a system must be built that monitors the driver’s activity and detects any distractions to alert him. Motivated by the advancements of Deep Learning, we propose a Convolutional Neural Network (CNN) model-based system to classify and identify distracted drivers to alert them, thus providing a potential solution to the problem. Our model classifies the driver activity into ten distinct classes, out of which nine are of the driver distracted by other events, and one is of “safe-driving”. If the driver is found in any of the nine said classes, it means he is distracted, and our system will warn him so that any chance of an accident is eliminated.
Similar content being viewed by others
REFERENCES
National Highway Traffic Safety Administration, Traffic Safety Facts Research Notes 2016: Distracted Driving. S. Department of Transportation, Washington, DC: NHTSA; 2015. Available at https://crashstats.nhtsa. dot.gov/Api/Public/ViewPublication/812517external icon. Accessed March 25, 2019.
Knapper, A., Hagenzieker, M., and Brookhuis, K., Do in-car devices affect experienced users’ driving performance?, IATSS Res., 2014. https://doi.org/10.1016/j.iatssr.2014.10.002
Distracted Driving in Fatal Crashes, 2017. https://crashstats.nhtsa.dot.gov.
https://timesofindia.indiatimes.com/india/drivers-using-mobile-four-times-more-likely-to-have-accident-who-report/articleshow/69033785.cms.
Nguyen, Thao, Eun-Ae Park, Jiho Han, Dong-Chul Park, and Soo-Young Min, Object detection using scale invariant feature transform, Genetic and Evolutionary Computing, Cham: Springer, 2014, pp. 65–72.
Abouelnaga, Yehya, Hesham M. Eraqi, and Mohamed N. Moustafa, Real-time distracted driver posture classification, arXiv preprint arXiv:1706.09498, 2017.
Eraqi, Hesham M., Yehya Abouelnaga, Mohamed H. Saad, and Mohamed N. Moustafa, Driver distraction identification with an ensemble of convolutional neural networks, J. Adv. Transp., 2019, vol. 2019.
Sheng, Weihua, Tran, Duy, Do, Ha, Bai, He, Chowdhary, and Girish, Real-time detection of distracted driving based on deep learning, IET Intell. Transp. Syst., 2018, vol. 12. https://doi.org/10.1049/iet-its.2018.5172
Baheti, Bhakti, Gajre, Suhas, and Talbar, Sanjay, Detection of distracted driver using convolutional, Neural Network, 2018, pp. 1145–11456. https://doi.org/10.1109/CVPRW.2018.00150
Tamas, V. and Vistrian Maties, Real-time distracted drivers detection using deep learning, Am. J. Artif. Intell., 2019, vol. 3, no. 1, pp. 1–8. https://doi.org/10.11648/j.ajai.20190301.11
Vasanti Sathe, Neha Prabhune, and Anniruddha Humane, Distracted driver detection using CNN and data augmentation techniques, Int. J. Adv. Res. Comput. Commun. Eng., 2018, vol. 7, no. 4, ISO 3297.
Praveen Hore, Prashant Tiwari, Ashwani Tiwari, Pawan Chauhan, and Ravish Sharma, Autonomous distracted driver detection using machine learning classifiers, Sci. J. Impact Factor (SJIF), 4.72; Int. J. Adv. Eng. Res. Devel., 2017, vol. 4, issue 4.
Torres, R., Ohashi, O., and Pessin, G, A machine-learning approach to distinguish passengers and drivers reading while driving, Sensors (Basel), 2019, vol. 19.
José María Celaya-Padilla, Carlos Eric Galván-Tejada, Joyce Selene Anaid Lozano-Aguilar, Laura Alejandra Zanella-Calzada, Huizilopoztli Luna-García, Jorge Issac Galván-Tejada, Nadia Karina Gamboa-Rosales, Alberto Velez Rodriguez, and Hamurabi Gamboa-Rosales, Texting and driving, detection using deep convolutional Neural Networks, Appl. Sci., 2019, vol. 9, no. 15, p. 2962.
Christopher Streiffer, Ramya Raghavendra, Theophilus Benson, and Mudhakar Srivatsa, DarNet: A deep learning solution for distracted driving detection, in Proceedings of Middleware Industry ’17: Proceedings of the Industrial Track of the 18th International Middleware Conference, LasVegas, NV, USA, December 11–15, 2017 (Middleware Industry ’17). https://doi.org/10.1145/3154448.3154452
State Farm Distracted Driver Detection. https://www.kaggle.com/c/state-farm-distracted-driver-detection.
Sik-Ho Tsang article: Review: Inception-v3-1st Runner Up (Image Classification) in ILSVRC 2015. https://medium.com/@sh.tsang/review-inception-v3-1st-runner-up-image-classification in-ilsvrc-2015-17915421f77c.
Gao Huang, Zhuang Liu, Laurens van der Maaten, and Kilian Q. Weinberger, Densely Connected Convolutional Networks, Cornell University. https://arxiv.org/abs/1608.06993.
ResNets. https://d2l.ai/chapter_convolutional-modern/resnet.html.
Howard, A.G., Menglong Zhu, Bo Chen, Kalenichenko, D., Weijun Wang, Weyand, T., Andreetto, M., Adam, H., MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications. https://arxiv.org/abs/1704.04861.
Author information
Authors and Affiliations
Corresponding authors
About this article
Cite this article
Ankit Pal, Kar, S. & Bharti, M. Algorithm for Distracted Driver Detection and Alert Using Deep Learning. Opt. Mem. Neural Networks 30, 257–265 (2021). https://doi.org/10.3103/S1060992X21030103
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.3103/S1060992X21030103