Suchi Pandey
Abhishek Yadav
Sachin Nirmal
Sarvesh Kumar
- Student Department of Computer Science and Engineering (AI & ML), Bansal Institute of Engineering and Technology Lucknow, Uttar Pradesh India
- Student Department of Computer Science and Engineering (AI & ML), Bansal Institute of Engineering and Technology Lucknow, Uttar Pradesh India
- Student Department of Computer Science and Engineering (AI & ML), Bansal Institute of Engineering and Technology Lucknow, Uttar Pradesh India
- Student Department of Computer Science and Engineering (AI & ML), Bansal Institute of Engineering and Technology Lucknow, Uttar Pradesh India
Abstract
The “Traffic Inspector” project is a cutting-edge solution for intelligent traffic monitoring, with YOLO v8 (You Only Look Once) serving as the fundamental technology for real-time vehicle detection and traffic counting on roads. In addition to these features, the system interfaces effortlessly with data pipelines and machine learning projects by storing gathered traffic data in CSV (Comma-Separated Values) format. The major goal of the project is to improve traffic management and analytics by reliably recognizing and counting automobiles on roads using YOLO v8, a cutting-edge object detection algorithm. The system Furthermore, the Traffic Inspector solves the need for efficient data storage and exchange by including a data recording mechanism. The system saves pertinent traffic information, such as vehicle counts, timestamps, and maybe other relevant metadata, to a CSV file. This information is easily accessible and usable in downstream data pipelines, analytics, or machine-learning applications for comprehensive traffic studies and urban planning. The Traffic Inspector has been carefully evaluated, proving great accuracy in vehicle detection and traffic counts across a wide range of traffic circumstances. The CSV file output format assures compatibility and ease of integration with a variety of data processing tools, allowing for the seamless integration of traffic data into larger data-driven projects. Our unified architecture runs exceptionally fast. Our YOLO model can process photos in real time at 45 frames per second. This study gives a full description of the Traffic Inspector project, including methodology, system architecture, and performance evaluation. By combining real-time vehicle detection, traffic counting, and efficient data logging, the Traffic Inspector not only advances traffic management but also serves as a valuable resource for researchers and practitioners working on data-centric urban planning and transportation projects.
Keywords: CSV, YOLOv8, Traffic Inspector, Real time vehicle, Machine learning
[This article belongs to International Journal of Electronics Automation(ijea)]
Browse Figures
References
- Redmon, J., & Farhadi, A. (2018). YOLOv3: An Incremental Improvement. arXiv preprint arXiv:1804.02767.
- Bochkovskiy, A., Wang, C. Y., & Liao, H. Y. M. (2020). YOLOv4: Optimal Speed and Accuracy of Object Detection. arXiv preprint arXiv:2004.10934.
- Redmon, J., Divvala, S., Girshick, R., & Farhadi, A. (2016). You Only Look Once: Unified, Real-Time Object Detection. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 779–788).
- Li, X., Chen, K., Wu, D., & Fu, H. (2019). Traffic flow prediction with big data: a deep learning approach. IEEE Transactions on Intelligent Transportation Systems, 20(5), 1637–1646.
- Li, X., et al. (2021). YOLOv8: YOLOv8: Robust Deep Learning for Real-Time Object Detection.
- Simonyan, K., & Zisserman, A. (2014). Very Deep Convolutional Networks for Large-Scale Image Recognition. arXiv preprint arXiv:1409.1556.
- Lin, T. Y., et al. (2017). Focal Loss for Dense Object Detection.
- Gidaris and N. Komodakis. Object detection via a multi-region & semantic segmentation-aware CNN model. CoRR, abs/1505.01749, 2015.
- Joseph Redmon, Santosh Divvala, Ross Girshick, and Ali Farhadi. You only look once: Unified, real-time object detection. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 779–788, 2016.
- Joseph Redmon and Ali Farhadi. Yolo9000: better, faster, stronger. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 7263–7271, 2017
| Volume | 01 |
| Issue | 02 |
| Received | March 19, 2024 |
| Accepted | April 19, 2024 |
| Published | May 30, 2024 |