• Josna O
• SUNIL A
• Rashmi B R

This article explores the enhancement of traffic law enforcement through utilization of augmented reality and deep learning techniques, specifically centering on the implementation of YOLOv3 for detecting violations like signal jumping, speeding, and traffic volume monitoring. The goal is to reduce traffic offenses and enhance road safety by accurately identifying and penalizing offenders. It covers the fundamentals of traffic violation detection, including image representation and the YOLOv3 algorithm, along with concrete instructions for architecture and implementation. The article emphasizes the significance of computer vision technology in overseeing and enforcing traffic regulations, showcasing its ability to detect multiple violations concurrently with great accuracy. Simulation and analysis results illustrate the effectiveness of the architecture in identifying issues such as signal irregularities, offering comprehensive insights into the detection procedure and resulting data. In summary, this piece underscores how AI and deep learning can advance traffic management and promote road safety.

Convolutional neural networks,traffic violation, YOLOV3

"Enhancing Road Safety through Automated Enforcement Systems Using CNN", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 6, page no.h300-h302, June-2024, Available :http://www.jetir.org/papers/JETIR2406733.pdf

"Enhancing Road Safety through Automated Enforcement Systems Using CNN", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 6, page no. pph300-h302, June-2024, Available at : http://www.jetir.org/papers/JETIR2406733.pdf