Traffic Sign Detection and Navigation System for Visually Impaired Individuals Using Artificial Intelligence

DOI

10.2991/978-94-6463-866-0_32How to use a DOI?

Keywords

Traffic Sign Detection; Navigation System; Visually Impaired; Artificial Intelligence; Deep Learning; Image Classification; Text-to-Speech; Assistive Technology

Abstract

For the sake of protecting lives and property and an efficient traffic management, in the domain of current transportation accurate prediction of the traffic signs is extremely important. We present a novel Traffic Sign Detection and Navigation System for the Visually Impaired using the Artificial Intelligence with the object to improve road safety and make navigation accessible to the visually impaired individuals. Towards the core of our system is RetrievaNet-43, a novel tailored neural network that is optimised for precise segmentation of traffic signs to 43 unique categories. Unlike YOLO v8/v9/v11, the conventional object detection frameworks that are optimized for general purpose detection and localization, RetrievaNet-43 is a traffic sign recognition tailoring based framework which yields better classification accuracy to infer faster processing time in such domain. The RetrievaNet-43 is a modular architecture that consists of two independent convolutional blocks for feature extraction and a robust fully connected classifier as classifier module. The benefit of such a design is that it achieves precise identification of traffic signs at low computational overhead, which is necessary for real-time applications in resource constrained environments.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Kolipaka Sathvik
AU  - Aditya Borse
AU  - Anushka Bandyopadhyay
AU  - R. Radhika
PY  - 2025
DA  - 2025/10/31
TI  - Traffic Sign Detection and Navigation System for Visually Impaired Individuals Using Artificial Intelligence
BT  - Proceedings of the International Conference on Intelligent Systems and Digital Transformation (ICISD 2025)
PB  - Atlantis Press
SP  - 382
EP  - 395
SN  - 2589-4919
UR  - https://doi.org/10.2991/978-94-6463-866-0_32
DO  - 10.2991/978-94-6463-866-0_32
ID  - Sathvik2025
ER  -