ABSTRACT
Bangladesh is rapidly getting urbanized. Recently traffic jams are caused mainly because of the growing number of motorcycles and cars and it implies the violation of traffic in Dhaka City. It causes severe destruction of property and more accidents that may endanger the living of the people. Due to recent incidents, it is very risky for pedestrians and drivers to consider full safety on the road. In this research, we present the construction of a system that makes the traffic sector easier than for the traffic police to operate the system, monitor traffic violations, and take action against the violations of traffic rules. Usually, traffic rules and signal violations are monitored via traffic camera by traffic police, or sometimes it is monitored manually. However, if motor vehicle users engage in any unethical behavior, the traffic police will have a difficult time detecting it. As a result, it would be highly beneficial if machine intelligence could assist traffic police in maintaining Dhaka City's traffic integrity. The system can classify traffic violations at a street intersection and investigate effective engagement strategies to identify traffic rule violations. We are using the transfer learning technique which is a surveillance system that uses two types of pre-trained CNN keras application models which names VGG16 and ResNet50 on images to read and detect the vehicles, helmet identification, no helmet identification, and bike triple riding. Our dataset is available online and presented in the paper. The Kaggle repository name is “traffic-violation-dataset-v3”. [21]
- Charde, S., Baddalwar, V., Dekate, P., Chawda, P., Wagh, U. and Chitriv, Y.U., 2020. Automated Gate for Vehicular Entry Using Image Processing.Google Scholar
- Vishnu, C., Singh, D., Mohan, C.K. and Babu, S., 2017, May. Detection of motorcyclists without helmet in videos using convolutional neural network. In 2017 International Joint Conference on Neural Networks (IJCNN) (pp. 3036-3041). IEEE.Google Scholar
- Saha, Sumit. “A Comprehensive Guide to Convolutional Neural Networks-the eli5 Way.” Medium, Towards Data Science, 17 Dec. 2018, https://towardsdatascience.com/a-comprehensive-guide-to-convolutional-neural-networks-the-eli5-way-3bd2b1164a53.Google Scholar
- Author: James McDermott Data Science Consultant, and James McDermott Data Science ConsultantJames is a data science consultant and technical writer. He has spent four years working on data-driven projects and delivering machine learning solutions in the research industry. “Hands-on Transfer Learning with Keras and the VGG16 Model.” Learn Data Science - Tutorials, Books, Courses, and More, https://www.learndatasci.com/tutorials/hands-on-transfer-learning-keras/.Google Scholar
- “Classification in Machine Learning: Classification Algorithms.” Edureka, 29 July 2021, https://www.edureka.co/blog/classification-in-machine-learning/.Google Scholar
- Simonyan, K. and Zisserman, A., 2014. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556.Google Scholar
- Snippets, Great Learning. “Traffic Violation Detection and Monitoring System Using Deep Learning.” Medium, Medium, 8 July 2020, https://medium.com/@blogsupport/traffic-violation-detection-and-monitoring-system-using-deep-learning-8e7401f321fb.Google Scholar
- Krizhevsky, A., Sutskever, I. and Hinton, G.E., 2012. Imagenet classification with deep convolutional neural networks. Advances in neural information processing systems, 25, pp.1097-1105.Google Scholar
- Goodfellow, I., Bengio, Y. and Courville, A., 2016. Deep learning. MIT press.Google Scholar
- K. He, X. Zhang, S. Ren, and J. Sun, "Deep Residual Learning for Image Recognition," 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016, pp. 770-778, doi: 10.1109/CVPR.2016.90.Google Scholar
- Deng, J., Dong, W., Socher, R., Li, L.J., Li, K. and Fei-Fei, L., 2009, June. Imagenet: A large-scale hierarchical image database. In 2009 IEEE conference on computer vision and pattern recognition (pp. 248-255). Ieee.Google Scholar
- Yu, J., Yang, L., Xu, N., Yang, J. and Huang, T., 2018. Slimmable neural networks. arXiv preprint arXiv:1812.08928.Google Scholar
- Swapna. “Convolutional Neural Network: Deep Learning.” Developers Breach,23 July, 2021 https://developersbreach.com/convolution-neural-network-deep-learning/.Google Scholar
- Satheeshbabu, D. and Govardhana, B., INTERNATIONAL JOURNAL OF ENGINEERING SCIENCES & RESEARCH TECHNOLOGY.Google Scholar
- Asadianfam, S., Shamsi, M. and Kenari, A.R., 2020. Big data platform of traffic violation detection system: identifying the risky behaviors of vehicle drivers. Multimedia Tools and Applications, 79(33), pp.24645-24684.Google ScholarDigital Library
- Traffic Rules Violation Detection System. https://www.irjet.net/archives/V7/i4/IRJET-V7I4324.pdf.Google Scholar
- Shreyas, R., Kumar, B.P., Adithya, H.B., Padmaja, B. and Sunil, M.P., 2017, August. Dynamic traffic rule violation monitoring system using automatic number plate recognition with SMS feedback. In 2017 2nd International Conference on Telecommunication and Networks (TEL-NET) (pp. 1-5). IEEE.Google Scholar
- Ara, J., Hasan, M.T., Al Omar, A. and Bhuiyan, H., 2020, June. Understanding Customer Sentiment: Lexical Analysis of Restaurant Reviews. In 2020 IEEE Region 10 Symposium (TENSYMP) (pp. 295-299). IEEE.Google Scholar
- e Silva, R.R.V., Aires, K.R.T. and Veras, R.D.M.S., 2014, August. Helmet detection on motorcyclists using image descriptors and classifiers. In 2014 27th SIBGRAPI Conference on Graphics, Patterns, and Images (pp. 141-148). IEEE.Google Scholar
- Masyhur, A.H., Nurprasetio, I.P., Budiman, B.A. and Utomo, T.P.B., 2019, November. Design and Prototyping of Weigh-In-Motion and Overload Detection System for Freight Vehicle. In IOP Conference Series: Materials Science and Engineering (Vol. 694, No. 1, p. 012003). IOP Publishing.Google Scholar
- Sourav Paul. (2021). traffic-violation-dataset-v3(Version 1). [Data file]. Retrieved from https://www.kaggle.com/meliodassourav/traffic-violation-dataset-v3Google Scholar
Index Terms
- Image Analysis using Deep Learning for a Smart Traffic Control System
Recommendations
Combining CNN Deep Learning and SVM for Vehicle Classification
IC3INA '21: Proceedings of the 2021 International Conference on Computer, Control, Informatics and Its ApplicationsVehicle classification plays an important role in an intelligent transportation system. The development of research in image processing, pattern recognition, and deep learning has encouraged more research interest in categorizing vehicles using deep ...
Detection of Driver Dynamics with VGG16 Model
AbstractOne of the most important factors triggering the occurrence of traffic accidents is that drivers continue to drive in a tired and drowsy state. It is a great opportunity to regularly control the dynamics of the driver with transfer learning ...
A smart analysis of driver fatigue and drowsiness detection using convolutional neural networks
AbstractAutomotive industry experiences multiple injuries in our everyday life. The increasing road accident rate is due to driver drowsiness, such as fatigue and insomnia. This research is intended primarily to diagnose exhaustion and drowsiness, ...
Comments