Road signs are essential for maintaining a safe flow of traffic, yet people frequently ignore or misread them, which leads to accidents. Convolutional neural networks, also known as CNNs, are used in the proposed system to identify and categorize traffic signals, alerting drivers with speech messages upon detection. As a result, travelers, passengers, and pedestrians are all safer. Applications include self-driving cars and driver assistance. Using a processor board and sensor on vehicles, the device can be executed despite the difficulties posed by challenging road settings, accurately detecting traffic signs with a variety of devices and algorithms. The reliability and performance of the system are further enhanced by regular upgrades as well as training on new datasets.
Mask R-CNN for Robust and Accurate Traffic Sign Detection in Dynamic Environments
Lect. Notes in Networks, Syst.
International Conference on Intelligent Computing and Communication ; 2024 ; Hyderabad, India August 30, 2024 - August 31, 2024
29.03.2025
8 pages
Aufsatz/Kapitel (Buch)
Elektronische Ressource
Englisch
Fast and robust traffic sign detection
Tema Archiv | 2005
|Accurate camera-based traffic sign localization
IEEE | 2014
|Traffic Sign Perception in Road Environments
British Library Conference Proceedings | 1994
|Springer Verlag | 2011
|