• Bhanu Sunka
• Dr Jaychand Upadhyay
• Sarvesh Chavan
• Osama Shaikh
• Harsh Dalvi

Our research centres on creating a user-friendly Traffic Signboard Recognition System to boost road safety by swiftly identifying signs in real time and informing drivers, reducing accidents, and ensuring smoother traffic flow. Designed for ordinary drivers, the system prioritizes simplicity, avoiding technical complexities. Emphasizing practicality, it addresses existing system issues, making it beneficial for all drivers. Advancements in computer vision and deep learning, including techniques like Convolutional Neural Networks (CNN), Mask R-CNN, and YOLO, showcase high accuracy rates. Real-time applications, such as YOLO operating at 30 frames per second, prioritize driver convenience. The integration of RANSAC and ICP algorithms for point cloud data registration aids in detecting vehicle queue lengths. Integrated alert systems, incorporating traffic signs, lights, and pedestrian detection, demonstrate high accuracy rates (e.g., 95.71) and swift computation times. Despite challenges like adversarial attacks and obscured signs, our system aligns with broader advancements, offering practical solutions for road safety through a comprehensive and accessible approach

Traffic Signboard Recognition, Road Safety, Intelligent System, Real-time Detection, Driver Alerts, Accident Prevention, Traffic Flow Optimization, User-Friendly Design, Simple Technology, and Practical Solutions.

"Traffic Signboard Recognition Using Deep Learning", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 4, page no.p630-p635, April-2024, Available :http://www.jetir.org/papers/JETIR2404G83.pdf

"Traffic Signboard Recognition Using Deep Learning", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 4, page no. ppp630-p635, April-2024, Available at : http://www.jetir.org/papers/JETIR2404G83.pdf