Advancements in Deep Learning-Based Approaches for Enhancing Accuracy in Traffic Sign Recognition

DOI

10.2991/978-94-6463-540-9_74How to use a DOI?

Keywords

Object Detection; Traffic Sign Recognition; Deep Learning

Abstract

With the increasing complexity and diversity of traffic environments, accurate identification of traffic signs becomes a necessary aspect for the development of assisted driving and autonomous driving technologies. Traffic sign recognition approaches exploiting deep learning have demonstrated significant advantages and higher accuracy. This paper provides a literature review in the field, summarizing the current research status, development trends, and challenges of image recognition methods based on deep learning. It also compares two approaches based on the bottom-up and top-down concepts. Among the former approaches, algorithms like You Only Look Once (YOLOv3), YOLOv4, and YOLOv5 have gained attention for their fast processing speed but relatively lower accuracy. On the other hand, in the latter approaches, algorithms like Region Convolutional Neural Network (R-CNN) demonstrate higher accuracy but slower processing speed. Depending on specific requirements, the appropriate method can be chosen. Additionally, methods that combine bottom-up and top-down concepts, such as YOLOv4 and YOLOv5, can achieve a balance between accuracy and processing speed.

Copyright

© 2024 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  - Dazhi Qin
AU  - Junxiang Tang
AU  - Sicheng Yu
PY  - 2024
DA  - 2024/10/16
TI  - Advancements in Deep Learning-Based Approaches for Enhancing Accuracy in Traffic Sign Recognition
BT  - Proceedings of the 2024 2nd International Conference on Image, Algorithms and Artificial Intelligence (ICIAAI 2024)
PB  - Atlantis Press
SP  - 723
EP  - 729
SN  - 2352-538X
UR  - https://doi.org/10.2991/978-94-6463-540-9_74
DO  - 10.2991/978-94-6463-540-9_74
ID  - Qin2024
ER  -