Proceedings of the International Conference on Computer, Information Technology and Intelligent Computing (CITIC 2022)

<Previous Article In Volume
Next Article In Volume>

Traffic Light Recognition Assistance for Colour Vision Deficiency Using Deep Learning

Authors
Jun Yong Lee1, Hu Ng1, *, Timothy Tzen Vun Yap1, Vik Tor Goh2, Hau Lee Tong1
1Faculty of Computing and Informatics, Multimedia University, Cyberjaya, Malaysia
2Faculty of Engineering, Multimedia University, Cyberjaya, Malaysia
*Corresponding author. Email: nghu@mmu.edu.my
Corresponding Author
Hu Ng
Available Online 27 December 2022.
DOI
10.2991/978-94-6463-094-7_23How to use a DOI?
Keywords
FasterRCNN; Traffic Light; Object Detection; TensorFlow
Abstract

This research intends to train a model to recognize traffic light signals in real-time to allow a person with Colour Vision Deficiency to identify the current signal of traffic lights with a mobile device's camera. First, LISA Traffic Light Dataset is downloaded obtained from Kaggle. Then, two data pre-processing steps are carried out, namely label map generation and TFRecords conversion. A total of six models, SSD MobileNet V2 320 × 320, SSD MobileNet V1 FPN 640 × 640, SSD ResNet50 V1 FPN 1024 × 1024, SSD ResNet101 V1 FPN 1024 × 1024, FasterRCNN ResNet50 V1 FPN1024 × 1024 and FasterRCNN ResNet101 V1 FPN 1024 × 1024 are used from the TensorFlow Model Zoo to perform training and evaluation on the dataset. From the experiment results, the most suitable object detection model is FasterRCNN ResNet101 V1 FPN 1024 × 1024 with the highest recall rate of 52.4% for daytime images and 45.4% for nighttime images.

Copyright
© 2022 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)

<Previous Article In Volume
Next Article In Volume>
Volume Title
Proceedings of the International Conference on Computer, Information Technology and Intelligent Computing (CITIC 2022)
Series
Atlantis Highlights in Computer Sciences
Publication Date
27 December 2022
ISBN
10.2991/978-94-6463-094-7_23
ISSN
2589-4900
DOI
10.2991/978-94-6463-094-7_23How to use a DOI?
Copyright
© 2022 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.

Cite this article

risenwbib
TY  - CONF
AU  - Jun Yong Lee
AU  - Hu Ng
AU  - Timothy Tzen Vun Yap
AU  - Vik Tor Goh
AU  - Hau Lee Tong
PY  - 2022
DA  - 2022/12/27
TI  - Traffic Light Recognition Assistance for Colour Vision Deficiency Using Deep Learning
BT  - Proceedings of the International Conference on Computer, Information Technology and Intelligent Computing (CITIC 2022)
PB  - Atlantis Press
SP  - 289
EP  - 300
SN  - 2589-4900
UR  - https://doi.org/10.2991/978-94-6463-094-7_23
DO  - 10.2991/978-94-6463-094-7_23
ID  - Lee2022
ER  -