Distracted Driving Detection with Machine Learning Methods by CNN Based Feature Extraction

Year 2021, Volume: 9 Issue: 4, 116 - 121, 31.12.2021

Shafeeq Kanaan Shakir Al-doorı , Yavuz Selim Taspınar , Murat Koklu

https://doi.org/10.18100/ijamec.1035749

Cited By: 8

Abstract

Millions of people lose their lives due to accidents caused by various reasons. As the number of vehicles increases, the number of accidents also increases. When driver errors caused by technological devices are added to this, the rate of accidents is increasing more and more. Generally, the vast majority of accidents occur as a result of distractions from drivers. For this reason, there is a need for a system based on the detection of driver errors and warning the driver in modern vehicles. For this purpose, the analysis of the convolutional neural network (CNN) feature extraction based classification models was carried out in this study. The SequeezeNet CNN architecture is trained with the transfer learning method and the image features are taken before the classification layer. The images were classified by giving the obtained features as input to k-nearest neighbor (k-NN), support vector machine (SVM) and random forest (RF) machine learning algorithms. A 10-class dataset containing 22,424 driver error images was used in the training of the models. Classification successes of k-NN, SVM, RF models trained with images are 98.1%, 95.8%, and 88.7%, respectively. The highest classification success was obtained from the k-NN model. Other performance measurement metrics were also used for the detailed analysis of the classification models. It is aimed to find the most suitable model by comparing the training and testing times of the models. It is aimed that the obtained models can be used to detect driver errors over the image.

Keywords

Classification, Deep learning, Driver distracted, Feature ectraction, Machine learning

References

• Arnold, P. K., Hartley, L. R., Corry, A., Hochstadt, D., Penna, F., & Feyer, A. M., Hours of work, and perceptions of fatigue among truck drivers. Accident Analysis & Prevention, 1997. 29(4): p. 471-477.
• Philip, P., Sagaspe, P., Moore, N., Taillard, J., Charles, A., Guilleminault, C., & Bioulac, B., Fatigue, sleep restriction and driving performance. Accident Analysis & Prevention, 2005. 37(3): p. 473-478.
• Beirness, D.J., H.M. Simpson, and A. Pak, The road safety monitor: Driver distraction. 2002.
• Wahlstrom, E., O. Masoud, and N. Papanikolopoulos. Vision-based methods for driver monitoring. in Proceedings of the 2003 IEEE International Conference on Intelligent Transportation Systems. 2003. IEEE.
• Sagberg, F., Jackson, P., Krüger, H. P., Muzet, A., & Williams, A. J., Fatigue, sleepiness and reduced alertness as risk factors in driving. 2004: Institute of Transport Economics Oslo.
• Lal, S.K. and A. Craig, A critical review of the psychophysiology of driver fatigue. Biological psychology, 2001. 55(3): p. 173-194.
• Bayly, M., Fildes, B., Regan, M., & Young, K., Review of crash effectiveness of intelligent transport systems. Emergency, 2007. 3: p. 14.
• Dinges, D. and M. Mallis. Managing fatigue by drowsiness detection: Can technological promises be realized? in International Conference on Fatigue and Transportation, 3rd, 1998, Fremantle, Western Australia. 1998.
• Ranney, T.A., W.R. Garrott, and M.J. Goodman, NHTSA driver distraction research: Past, present, and future. 2001, Citeseer.
• Stutts, J. C., Reinfurt, D. W., Staplin, L., & Rodgman, E., The role of driver distraction in traffic crashes. 2001.
• Škrjanc, I., Andonovski, G., Ledezma, A., Sipele, O., Iglesias, J. A., & Sanchis, A., Evolving cloud-based system for the recognition of drivers’ actions. Expert Systems with Applications, 2018. 99: p. 231-238.
• Wang, X., Liu, Y., Wang, F., Wang, J., Liu, L., & Wang, J., Feature extraction and dynamic identification of drivers’ emotions. Transportation research part F: traffic psychology and behaviour, 2019. 62: p. 175-191.
• Olabiyi, O., Martinson, E., Chintalapudi, V., & Guo, R., Driver action prediction using deep (bidirectional) recurrent neural network. arXiv preprint arXiv:1706.02257, 2017.
• Braunagel, C., Kasneci, E., Stolzmann, W., & Rosenstiel, W., Driver-activity recognition in the context of conditionally autonomous driving. in 2015 IEEE 18th International Conference on Intelligent Transportation Systems. 2015. IEEE.
• Yan, S., Teng, Y., Smith, J. S., & Zhang, B. Driver behavior recognition based on deep convolutional neural networks. in 2016 12th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD). 2016. IEEE.
• Huang, C., Wang, X., Cao, J., Wang, S., & Zhang, Y., HCF: a hybrid CNN framework for behavior detection of distracted drivers. IEEE Access, 2020. 8: p. 109335-109349.
• Baheti, B., S. Talbar, and S. Gajre, Towards computationally efficient and realtime distracted driver detection with mobilevgg network. IEEE Transactions on Intelligent Vehicles, 2020. 5(4): p. 565-574.
• Mase, J. M., Chapman, P., Figueredo, G. P., & Torres, M. T., A hybrid deep learning approach for driver distraction detection. in 2020 International Conference on Information and Communication Technology Convergence (ICTC). 2020. IEEE.
• State Farm. Distracted Driver Detection Competition. [cited 2021 9 December]; Available from: https://www.kaggle.com/c/state-farm-distracted-driver-detection.
• Koklu, M., I. Cinar, and Y.S. Taspinar, Classification of rice varieties with deep learning methods. Computers and Electronics in Agriculture, 2021. 187: p. 106285.
• Koklu, M., I. Cinar, and Y.S. Taspinar, CNN-based bi-directional and directional long-short term memory network for determination of face mask. Biomedical Signal Processing and Control, 2022. 71: p. 103216.
• Taspinar, Y.S., I. Cinar, and M. Koklu, Classification by a stacking model using CNN features for COVID-19 infection diagnosis. Journal of X-Ray Science and Technology, 2021(Preprint): p. 1-16.
• Ali, M., Jung, L. T., Abdel-Aty, A. H., Abubakar, M. Y., Elhoseny, M., & Ali, I., Semantic-k-NN algorithm: an enhanced version of traditional k-NN algorithm. Expert Systems with Applications, 2020. 151: p. 113374.
• Yan, X. and M. Jia, A novel optimized SVM classification algorithm with multi-domain feature and its application to fault diagnosis of rolling bearing. Neurocomputing, 2018. 313: p. 47-64.
• Speiser, J. L., Miller, M. E., Tooze, J., & Ip, E., A comparison of random forest variable selection methods for classification prediction modeling. Expert systems with applications, 2019. 134: p. 93-101.
• Yurttakal, A. H., Erbay, H., İkizceli, T., Karacavus, S., & Çinarer, G., A comparative study on segmentation and classification in breast mri imaging. IIOAB journal, 2018. 9(5): p. 23-33.
• Yasar, A., E. Kaya, and I. Saritas, Classification of Wheat Types by Artificial Neural Network. International Journal of Intelligent Systems and Applications in Engineering, 2016. 4(1): p. 12-15.