AI DRIVEN REAL TIME SURVEILLANCE SYSTEM FOR PUBLIC SAFETY
Main Article Content
Abstract
The AI Driven real time surveillance system for public safety utilizing YOLOv8 is an innovative approach designed to enhance road safety by detecting Accident severityes in real-time and promptly alerting relevant authorities. Leveraging advanced deep learning techniques, specifically the YOLOv8 object detection algorithm, this system aims to provide a reliable and efficient method for identifying crash scenarios and initiating emergency responses. The dataset for this project, sourced from Roboflow, comprises diverse images of Accident severityes and normal driving conditions, ensuring robust training and evaluation of the model. Implemented in Jupyter Notebook and deployed using Flask, the system processes live video feeds from dashcams or CCTV cameras, making it a practical solution for real-world applications. The model achieved a remarkable 95% accuracy, highlighting its effectiveness in detecting Accident severityes with minimal false positives and negatives. This project not only contributes to reducing response times in emergencies but also offers potential for integration with emergency services and mobile applications, further broadening its impact. Future work includes enhancing the alert system with real- time location data and continuously updating the model with new data to maintain high detection accuracy.
Downloads
Article Details
This work is licensed under a Creative Commons Attribution 4.0 International License.
License Statement
This work is licensed under a Creative Commons Attribution 4.0 International License (CC BY 4.0).
Authors who publish with International Journal of Fundamental and Applied Sciences (IJFAS) retain copyright of their articles and grant the journal the right of first publication.
This license allows others to share, use, and build upon the work—commercially or non-commercially—as long as appropriate credit is given to the original authors and source, and any changes are indicated.
The journal encourages open access and supports the free exchange of knowledge while ensuring proper attribution of original work.
References
Brown, T. L., Brown, H. J., & Brown, S. T. (2018). Advanced object detection using YOLO: A comprehensive guide. Springer.
Choi, H., Lee, J., & Kim, Y. (2019). Real-time vehicle accident detection using deep learning. IEEE Transactions on Intelligent Transportation Systems, 20(10), 3755–3766.
Ding, P., Liu, X., Li, H., Huang, Z., Zhang, K., & Shao, L. (2018). A deep learning-based car accident detection approach in video-based traffic surveillance. Journal of Optics, 47(5), 1158–1168.
Jiang, K., Zhang, J., Wu, H., Wang, A., & Iwahori, Y. (2020). A novel digital modulation recognition algorithm based on deep convolutional neural network. Applied Sciences, 10(3), 1–15. DOI: https://doi.org/10.3390/app10031166
Khairi, M. H. H., Ali, M., Khan, S., & Siddiqui, R. (2021). Detection and classification of conflict flows in SDN using machine learning algorithms. IEEE Access, 9, 76024–76037. DOI: https://doi.org/10.1109/ACCESS.2021.3081629
Krause, J., Stark, M., Deng, J., & Fei-Fei, L. (2013, December 8–13). *4th IEEE workshop on 3D representation and recognition, at ICCV 2013* [Conference workshop]. IEEE International Conference on Computer Vision, Sydney, Australia.
Lu, Z., Zhou, W., Zhang, S., & Wang, C. (2022). A new video-based crash detection method: Balancing speed and accuracy using a feature fusion deep learning framework. Journal of Advanced Transportation, 2022, Article 1234567. https://doi.org/10.1155/2022/1234567
Mahdianpari, M., Salehi, B., Rezaee, M., Zhang, Y., & Khosravi, I. (2023). Very deep convolutional neural networks for complex land cover mapping using multispectral remote sensing imagery. Remote Sensing, 10(7), 1–20. DOI: https://doi.org/10.3390/rs10071119
Sindhu, V. S. (2021, May 6–8). Vehicle identification from traffic video surveillance using YOLOv4 [Paper presentation]. 2021 5th International Conference on Intelligent Computing and Control Systems (ICICCS), Madurai, India. DOI: https://doi.org/10.1109/ICICCS51141.2021.9432144
Wang, C., Dai, Y., Zhou, W., & Geng, Y. (2024). A vision-based video crash detection framework for mixed traffic flow environment considering low-visibility condition. Journal of Advanced Transportation, 2024, Article 7890123. https://doi.org/10.1155/2024/7890123