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{202246,
        author = {M. Sivakumar},
        title = {Smart Traffic Violation Detection with Edge AI Optimization},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {12},
        pages = {5877-5884},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=202246},
        abstract = {This paper presents an intelligent Edge AI-based traffic violation detection system that automates vehicle speed monitoring, violation evidence captures, and real-time alert generation using computer vision and deep learning techniques. The proposed system processes uploaded video footage through a sequential pipeline of eight integrated modules: video input processing, vehicle detection using TensorFlow-based YOLO architecture, vehicle tracking with unique ID assignment, speed prediction through frame-by-frame displacement analysis, configurable threshold management, automated evidence image capture, email notification generation, and violation record database management. By leveraging OpenCV for video frame extraction and TensorFlow for deep learning-based object detection, the system accurately identifies vehicles and calculates their real-world speed using pixel-to-distance calibration techniques. When a vehicle exceeds the predefined speed threshold, the system automatically captures a timestamped image of the violating vehicle, overlays violation data including vehicle ID, speed, time, and sends an immediate email alert with attached evidence to the designated traffic in-charge. The Edge AI optimization ensures low-latency processing by performing computation locally without cloud dependency, making it suitable for real-time traffic enforcement applications. Experimental results demonstrate that the system achieves reliable vehicle detection accuracy, precise speed estimation, and instantaneous violation notification, thereby addressing the limitations of existing manual monitoring systems that lack automated evidence capture and real-time alert mechanisms. This solution provides traffic authorities with an efficient, scalable, and legally-valid tool for automated traffic law enforcement and improved road safety.},
        keywords = {Edge AI, Traffic Violation Detection, Vehicle Speed Estimation, Deep Learning, OpenCV, Real-Time Alert System},
        month = {May},
        }