Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{175213,
        author = {Sanjith s and Joshua thesikar m and Kamales m},
        title = {Automatic video surveillance using computer vision},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {11},
        pages = {2128-2130},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=175213},
        abstract = {Background: Traffic safety is a significant concern worldwide. Helmet usage among motorcyclists is a crucial preventive measure to reduce fatalities in road accidents. However, non-compliance remains an issue. This research proposes an automated system for helmet detection and number plate recognition to identify and penalize violators efficiently.
Materials and Methods: The system utilizes deep learning techniques for helmet detection and Optical Character Recognition (OCR) for number plate recognition. A YOLO-based convolutional neural network (CNN) model is trained for helmet detection, while Tesseract OCR is employed for license plate reading. The dataset comprises images from surveillance cameras. The model is evaluated based on accuracy, precision, recall, and F1-score.
Results: The system achieves an accuracy of 95.2% in helmet detection and 92.8% in number plate recognition. The approach demonstrates real-time processing capability, making it suitable for smart traffic monitoring systems. Conclusion: The proposed system enhances traffic law enforcement by automating helmet detection and vehicle identification. Integrating this technology with police databases can aid in issuing automated penalties to violators.},
        keywords = {Helmet detection, YOLO, OCR, Number Plate Recognition, Traffic Monitoring.},
        month = {April},
        }