Traffic light counter detection comparison using you only look oncev3 and you only look oncev5 for version 3 and 5

Hamzah Abdulmalek Al-Haimi (Universiti Teknikal Malaysia Melaka)
Zamani Md Sani (Universiti Teknikal Malaysia Melaka)
Tarmizi Ahmad Izzudin (Universiti Teknikal Malaysia Melaka)
Hadhrami Abdul Ghani (Universiti Malaysia Kelantan)
Azizul Azizan (Universiti Teknologi)
Samsul Ariffin Abdul Karim (Universiti Malaysia Sabah)

IAES International Journal of Artificial Intelligence (IJ-AI)
Vol 12, No 4: December 2023

This project aims to develop a vision system that can detect traffic lightcounter and to recognise the numbers shown on it. The system used you onlylook once version 3 (YOLOv3) algorithm because of its robust performanceand reliability and able to be implemented in Nvidia Jetson nano kit. A totalof 2204 images consisting of numbers from 0-9 green and 0-9 red. Another80% (1764) from the images are used for training and 20% (440) are used fortesting. The results obtained from the training demonstrated Totalprecision=89%, Recall=99.2%, F1 score=70%, intersection over union(IoU)=70.49%, mean average precision (mAp)=87.89%, Accuracy=99.2%and the estimate total confidence rate for red and green are 98.4% and 99.3%respectively. The results were compared with the previous YOLOv5algorithm, and the results are substantially close to each other as the YOLOv5accuracy and recall at 97.5% and 97.5% respectively.