⚠ Official Notice: www.ijisrt.com is the official website of the International Journal of Innovative Science and Research Technology (IJISRT) Journal for research paper submission and publication. Please beware of fake or duplicate websites using the IJISRT name.



VisionSafeX: AI-Assisted Traffic Violation Detection Using MERN Stack and Generative AI


Authors : Shourya Yadav; Yusuf Rehan; Shreya Arya; Shreya Jain

Volume/Issue : Volume 11 - 2026, Issue 2 - February


Google Scholar : https://tinyurl.com/4v64ycs3

Scribd : https://tinyurl.com/bdfp3xe5

DOI : https://doi.org/10.38124/ijisrt/26feb1485

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.


Abstract : The rising traffic and the inability to maintain an oversight manually have augmented the issuesin themanagement of traffic in urban areas. Traditional manual monitoring systems, as far as exposing infractions on the fly is concerned, tend to be inefficient and are more susceptible to mistakes. The proposal presented in this paper is for an AI-based traffic violation detection system known as VisionSafeX that utilizes the ability of the artificial intelligence known as Generative AI to improve the resolution of low-resolution surveillance video in addition to the use of the MERN stack to integrate the system. The system automatically detects the violations with the help of CNN-based model, which processes the frames. Generative AI adds more precision to the model since it is able to recreate missing frames. The experiments and research that was undertaken have demonstrated good performance in different real life situations. The dashboard is provided through a MERN based dashboard that is available on-demand. The paper also discusses deployment strategies, security considerations, scalability, and practical im-plementation guidelines for city-wide traffic networks.

Keywords : Traffic Violation Detection, MERN Stack, Gen-erative AI, Deep Learning, Automation, Video Enhancement, Real-Time Monitoring

References :

  1. World Health Organization, “Road traffic injuries,” WHO Fact Sheet, 13 December 2023. [Online]. Available: https://www.who.int/news-room/fact-sheets/detail/road-traffic-injuries/:contentReference[oaicite:0]index=0
  2. “Traffic Violations and Punishments,” BareLaw. [Online]. Available: https://www.barelaw.in/traffic-violations-and-punishments/
  3. K. Balasaranya, C. Chandravathi, M. Balamurugan, K. Logapriyadarshini, S. Babu, and T. Naganathan, “Real-Time Traffic Violation Detection with Automated Enforcement Using Computer Vision,” in Proc. 2025 11th Int. Conf. Communication and Signal Processing (ICCSP), pp. 361–366, 2025, doi: 10.1109/iccsp64183.2025.11089113.
  4. P. Ali, R. Bhattacharyya, D. Kishore, and V. Kumar, “Intelli-gent Traffic Violation Detection and Notification System Using Deep Learning,” Int. J. Adv. Trends Eng. Manage., 2025, doi: 10.59544/tscu2883/ijatemv03i12p3.
  5. “Smart Traffic Management and Detection System Using AI and Com-puter Vision,” Int. J. Sci. Res. Eng. Manage., 2025, doi: 10.55041/ijs-rem47175.
  6. D. U. Oloriegbe and B. Ikharo, “Development of an IoT-based Traffic Signal Violation Detection System,” J. Eng. Res. Reports, 2025, doi: 10.9734/jerr/2025/v27i21389.
  7. C. Banupriya, “AI-Powered Smart Traffic Management System,” Int. J. Sci. Res. Eng. Manage., 2025, doi: 10.55041/ijsrem47454.
  8. M. Gogate, S. Pandey, A. Mishra, and S. Bind, “Detecting Traffic Rules Violations using Computer Vision,” IRJAEM, 2025, doi: 10.47392/ir-jaem.2025.0200.
  9. K. Pujitha, J. Indu, S. Vardhan, S. Kumar, and G. Ramadevi, “Traffic Signal Violation Detection System,” Int. J. Sci. Res. Comput. Sci., Eng. Inf. Technol., 2025, doi: 10.32628/cseit2511141.
  10. Y. A. Raghava, S. Gootham, N. Sharanya, and S. Ahmad, “IoT-Based Autonomous System for Monitoring and Tracking Traffic Rule Viola-tions and Non-Compliance,” Int. J. Innov. Sci. Res. Technol., 2025, doi: 10.38124/ijisrt/25apr1178.
  11. R. Charran and R. Dubey, “Two-Wheeler Vehicle Traffic Violations Detection and Automated Ticketing for Indian Road Scenario,” IEEE Trans. Intell. Transp. Syst., vol. 23, pp. 22002–22007, 2022, doi: 10.1109/tits.2022.3186679.
  12. M. Ashkanani et al., “A Self-Adaptive Traffic Signal System Integrat-ing Real-Time Vehicle Detection and License Plate Recognition for Enhanced Traffic Management,” Inventions, 2025, doi: 10.3390/inven-tions10010014.
  13. M. Rahman and M. R. Islam, “IoT-based automated case generation system for traffic rule violations,” Rev. Inf. Eng. Appl., 2025, doi: 10.18488/79.v12i1.4083.
  14. H. Gehani et al., “Traffic Signal Violation Detection System Using Computer Vision,” J. Electr. Syst., 2024, doi: 10.52783/jes.2037.
  15. V. Meghana, B. Anisha, and R. Kumar, “IoT-based Smart Traffic Signal Violation Monitoring System using Edge Computing,” in Proc. 2021 GCAT, pp. 1–5, 2020, doi: 10.1109/gcat52182.2021.9587585.
  16. S. Kayalvizhi et al., “Intelligent Traffic Management System: An Advanced Solution for Helmet Compliance, Traffic Signal Violation Detection, Number Plate Identification, Cell Phone Usage Tracking, and Proximity-Based Police Station Alerts,” in Proc. 2024 IC4, pp. 1–6, 2024, doi: 10.1109/ic457434.2024.10486721.
  17. Z. Shen, Y. Zhang, X. Wu, and H. Li, “Research on Cross-Regional Traffic Law Enforcement Based on Intelligent Brain,” in Proc. 2025 ECIE, pp. 177–181, 2025, doi: 10.1109/ecie65947.2025.11086861.
  18. Y. Ren, “Intelligent Vehicle Violation Detection System Under Human-Computer Interaction and Computer Vision,” Int. J. Comput. Intell. Syst., vol. 17, pp. 40–, 2024, doi: 10.1007/s44196-024-00427-6.

The rising traffic and the inability to maintain an oversight manually have augmented the issuesin themanagement of traffic in urban areas. Traditional manual monitoring systems, as far as exposing infractions on the fly is concerned, tend to be inefficient and are more susceptible to mistakes. The proposal presented in this paper is for an AI-based traffic violation detection system known as VisionSafeX that utilizes the ability of the artificial intelligence known as Generative AI to improve the resolution of low-resolution surveillance video in addition to the use of the MERN stack to integrate the system. The system automatically detects the violations with the help of CNN-based model, which processes the frames. Generative AI adds more precision to the model since it is able to recreate missing frames. The experiments and research that was undertaken have demonstrated good performance in different real life situations. The dashboard is provided through a MERN based dashboard that is available on-demand. The paper also discusses deployment strategies, security considerations, scalability, and practical im-plementation guidelines for city-wide traffic networks.

Keywords : Traffic Violation Detection, MERN Stack, Gen-erative AI, Deep Learning, Automation, Video Enhancement, Real-Time Monitoring

Paper Submission Last Date
31 - March - 2026

SUBMIT YOUR PAPER CALL FOR PAPERS
Video Explanation for Published paper

Never miss an update from Papermashup

Get notified about the latest tutorials and downloads.

Subscribe by Email

Get alerts directly into your inbox after each post and stay updated.
Subscribe
OR

Subscribe by RSS

Add our RSS to your feedreader to get regular updates from us.
Subscribe