Real-Time Vehicle Accident Recognition from Traffic Video Surveillance using YOLOV8 and OpenCV
Article Sidebar
Main Article Content
Abstract
The automatic detection of traffic accidents is a significant topic in traffic monitoring systems. It can reduce irresponsible driving behavior, improve emergency response, improve traffic management, and encourage safer driving practices. Computer vision can be a promising technique for automatic accident detection because it provides a reliable, automated, and speedy accident detection system that can improve emergency response times and ultimately save lives. This paper proposed an ensemble model that uses the YOLOv8 approach for efficient and precise event detection. The model framework's robustness is evaluated using YouTube video sequences with various lighting circumstances. The proposed model has been trained using the open-source dataset Crash Car Detection Dataset, and its produced precision, recall, and mAP are 93.8% and 98%, 96.1%, respectively, which is a significant improvement above the prior precision, recall, and mAP figures of 91.3%, 87.6%, and 93.8%. The effectiveness of the proposed approach in real-time traffic surveillance applications is proved by experimental results using actual traffic video data.
Article Details
References
Wang, Y., Huang, Y., Li, X., & Liu, Z. (2020). A Review of Machine Learning Approaches for Traffic Incident Detection and Management. IEEE Access, 8, 202359-202372.
doi: 10.1109/ACCESS.2020.3035549.
Suriya, N. C., Immanuel, J., & Balaji, R. (2020). An overview of the YOLO algorithm for traffic accident detection and analysis. International Journal of Advanced Science and Technology, 29(9), 5597-5605. doi: 10.1007/978-3-030-58805-2_22.
Taha, M. I., & Almohaimeed, A. (2014). Real-time traffic accident detection and management system. 2014 IEEE International Conference on Industrial Engineering and Engineering Management, 1191-1195.
doi: 10.1109/IEEM.2014.7058805.
Lu, K., Lin, D. D., & Loo, C. K. (2014). Real-time automatic detection of traffic accidents in surveillance video. 2014 IEEE International Conference on Multimedia and Expo Workshops (ICMEW), 1-6.
doi: 10.1109/ICMEW.2014.6890511.
Nogueira, A. L., & Oliveira, M. M. (2014). Automatic detection of traffic accidents from closed-circuit television footage. 2014 IEEE International Conference on Image Processing (ICIP), 3477-3481.
doi: 10.1109/ICIP.2014.7025609.
Mathur, A., Agrawal, R., & Khanna, A. (2015). Real-time vehicle accident detection system using surveillance video analysis. Procedia Computer Science, 70, 641-647.
doi: 10.1016/j.procs.2015.10.076.
M. Rizwan et al. (2016). Real-Time Vehicle Accident Detection System based on Image Processing Techniques. In 2016 International Conference on Frontiers of Information Technology (FIT), Islamabad, 2016, pp. 250-255,
doi: 10.1109/FIT.2016.53.
M. Rizwan et al. (2019). Real-time Vehicle Accident Detection System using Machine Learning Techniques. In 2019 IEEE International Conference on Advanced Information Technology, Services, and Systems (AITSS), Marrakesh, Morocco, 2019, pp. 1-6.doi: 10.1109/AITSS.2019.8777166.
Sabrin, S. M., Rahman, M. A., Hassan, M. R., & Hossain, M. S. (2019, September). Real-Time Detection of Road Accidents using Deep Learning Techniques. In 2019 International Conference on Robotics, Electrical, and Signal Processing Techniques (ICREST) (pp. 250-255). IEEE.
doi: 10.1109/ICREST45688.2019.9079712.
Wang, J., Lai, L., & Guo, Y. (2019). A Real-Time Vehicle Detection and Crash Detection Algorithm for Intelligent Transportation Systems. IEEE Access, 7, 24932-24941. doi: 10.1109/access.2019.2907535.
Lee, J., Kim, M., and Kim, C. "Real-Time Traffic Accident Detection using Deep Convolutional Neural Networks." 2019 16th International Conference on Control, Automation, Robotics and Vision (ICARCV), 2019, pp. 878-883. IEEE. doi: 10.1109/ICARCV.2018.8581111.
Zhang, L., Ren, Y., Li, X., & Wu, Y. (2020). A Real-Time Object Detection Method for Traffic Surveillance System Based on YOLOv3. Applied Sciences, 10(20), 7293.
doi: 10.3390/app10207293.
M. Saleem, et al. (2021) .Traffic Sign Detection and Classification using YOLOv3 and Machine Learning. Processes, vol. 9, no. 4, p. 446, Mar. 2021.
doi: 10.3390/pr9040446.
Yang, Z., Feng, Y., Li, J., & Li, W. (2021). An Intelligent Vehicle Monitoring System Based on YOLOv4 and Cloud Computing. Applied Sciences, 11(11), 5184.
doi: 10.3390/app11115184.
Sun, J., Wang, S., & Wei, P. (2021). Traffic Sign Detection and Recognition using YOLOv3 and Convolutional Neural Networks. Electronics, 10(7), 826.
doi: 10.3390/electronics10070826.
Nguyen, T. D., Nguyen, D. T., and Vo, N. L. (2021). A Real-time Traffic Surveillance System based on YOLOv3 and EfficientNet. 11th International Conference on Communi- cations and Electronics (ICCE), 2021, pp. 423-428. IEEE. doi: 10.1109/ICCE51597.2021.9522188.
The dataset is publicly available at:
https://universe.roboflow.com/mada-study/crash-car-detection.
Mane, D.T., Sangve, S.M., Upadhye, G.D., Kandhare, S., Mohole, S., Sonar, S., & Tupare, S. (2022). Detection of Anomaly using Machine Learning: A Comprehensive Survey. International Journal of Emerging Technology and Advanced Engineering. Vol. 12, issue 11, pp. 134-152. DOI: 10.46338/ ijetae1122_15