Abstract
Traffic Sign Recognition (TSR) is one of the most sought-after topics in computer vision, mostly due to the increasing scope and advancements in self-driving cars. In our study, we attempt to implement a TSR system that helps a driver stay alert during driving by providing information about the various traffic signs encountered. We will be looking at a working model that classifies the traffic signs and gives output in the form of an audio message. Our study will be focused on traffic sign detection and recognition on Indian roads. A dataset of Indian road traffic signs was created, based upon which our deep learning model will work. The developed model was deployed on NVIDIA Jetson Nano using YOLOv4 architecture, giving an accuracy in the range of 54.68–76.55% on YOLOv4 architecture. The YOLOv4-Tiny model with DeepStream implementation achieved an FPS of 32.5, which is on par with real-time detection requirements.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
