Ensuring road safety in this technologically advanced society is critical. This study presents an innovative approach for identifying traffic signs using convolutional neural networks (CNNs). Here, the existing traffic sign detection practices are explored. The proposed method includes data collection, development of robust CNN architecture, and enabling model training optimization. Performance evaluation metrics such as recall, accuracy, and F1-score analyze the proposed model's efficiency. Through experimentation, this study demonstrates CNNs' transformative potential in traffic sign detection, supported by data-driven visualizations and real-world scenarios. Beyond enhancing existing systems, this research findings point to larger applications in traffic management, Advanced Driver Assistance Systems (ADAS), and self-driving cars, paving way for safer and more efficient transportation.
Revolutionizing Road Safety: CNN-based Traffic Sign Recognition
2024-03-11
371082 byte
Conference paper
Electronic Resource
English
REVOLUTIONIZING SPACE TRAFFIC MANAGEMENT
TIBKAT | 2021
|VIRTUALIZED ROAD TRAFFIC SIGN GENERATION FOR ENHANCING ROAD SAFETY
European Patent Office | 2022
|VIRTUALIZED ROAD TRAFFIC SIGN GENERATION FOR ENHANCING ROAD SAFETY
European Patent Office | 2022
|