Skip to main navigation Skip to search Skip to main content

Real-Time Traffic Sign Detection and Recognition for Enhanced Road Safety in Autonomous Driving: A Deep CNN-Based Approach

  • H. D. Nataraj Urs*
  • , B. N. Aravind
  • , N. Yashwanth
  • , Moumita Ruj
  • *Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Traffic sign detection and recognition are critical tasks in autonomous driving systems and video-based methods are becoming increasingly popular due to the availability of high-resolution cameras. In this work, we propose a deep CNN-based approach that can detect and recognize traffic signs from video feeds in real-time. Our proposed approach consists of a multi-stage process that includes video pre-processing, object detection, and sign recognition using a deep CNN architecture. The model is trained on a large dataset of annotated video frames and evaluated its performance on a test set. The results indicate that the proposed method achieves high accuracy in detecting and recognizing traffic signs. This method has potential applications in autonomous driving systems and can contribute to improving road safety.

Original languageEnglish
Title of host publicationProceedings of the 4th IEEE International Conference on Smart Technologies in Computing, Electrical and Electronics, ICSTCEE 2023
EditorsVishwanath R. Hulipalled, S. Senthil, Devanathan M, Hemanth K.S
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9798350384628
DOIs
Publication statusPublished - 2023
Event4th IEEE International Conference on Smart Technologies in Computing, Electrical and Electronics, ICSTCEE 2023 - Bengaluru, India
Duration: 08-12-202309-12-2023

Publication series

NameProceedings of the 4th IEEE International Conference on Smart Technologies in Computing, Electrical and Electronics, ICSTCEE 2023

Conference

Conference4th IEEE International Conference on Smart Technologies in Computing, Electrical and Electronics, ICSTCEE 2023
Country/TerritoryIndia
CityBengaluru
Period08-12-2309-12-23

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence
  • Computer Networks and Communications
  • Computer Science Applications
  • Control and Systems Engineering
  • Electrical and Electronic Engineering
  • Control and Optimization

Fingerprint

Dive into the research topics of 'Real-Time Traffic Sign Detection and Recognition for Enhanced Road Safety in Autonomous Driving: A Deep CNN-Based Approach'. Together they form a unique fingerprint.

Cite this