Instance Segmentation Evaluation For Traffic Signs

Authors

  • Shi Heng Siow Faculty of Electrical and Electronic Engineering, Universiti Tun Hussein Onn Malaysia, Batu Pahat, Johor, Malaysia
  • Abu Ubaidah Shamsudin Faculty of Electrical and Electronic Engineering, Universiti Tun Hussein Onn Malaysia, Batu Pahat, Johor, Malaysia
  • Zubair Adil Soomro Faculty of Electrical and Electronic Engineering, Universiti Tun Hussein Onn Malaysia, Batu Pahat, Johor, Malaysia
  • Anita Ahmad School of Electrical Engineering, Faculty of Engineering, Universiti Teknologi Malaysia, Skudai, Johor, Malaysia
  • Ruzairi Abdul Rahim School of Electrical Engineering, Faculty of Engineering, Universiti Teknologi Malaysia, Skudai, Johor, Malaysia
  • Mohd Khairul Ikhwan Ahmad Cybersolution Technologies Sdn Bhd. Johor Bahru, Johor, Malaysia
  • Andi Adriansyah Universitas Mercu Buana, Jakarta, Indonesia

DOI:

https://doi.org/10.37934/araset.34.2.327341

Keywords:

Instance Segmentation, Traffic Sign Recognition, YOLACT, Deep Learning Approach, Image Segmentation

Abstract

This research paper focuses on developing a traffic sign recognition system based on the You Only Look At Coefficients (YOLACT) model, a one-stage instance segmentation model that offers high performance in terms of accuracy and reliability. However, the performance of YOLACT is influenced by various conditions such as day/night and different angles of objects. Therefore, this study aims to evaluate the impact of different angles and environments on the performance of the system. The paper discusses the framework, backbone structure, prototype generation branch, mask coefficient, and mask assembly used in the system. ResNet-101 and ResNet-50 were used as the backbone structure to extract feature maps of objects in the input image. The prototype generation branch generates prototype masks using fully convolutional networks (FCN), and the mask coefficient branch generates the Mask assembly using the sigmoid nonlinearity. Two models, YOLACT and Mask-RCNN, were evaluated in terms of mean precision (mAP) and frames per second (FPS) with the front view dataset. The results show that YOLACT outperforms Mask-RCNN in terms of accuracy and speed. For an image resolution of 550x550, YOLACT with Resnet-101 was considered the best model in this article since it achieves over 80% precision, recall, specificity, and accuracy in various conditions such as day, night, left and right, and forward-looking angles.

Downloads

Download data is not yet available.

Author Biographies

Shi Heng Siow, Faculty of Electrical and Electronic Engineering, Universiti Tun Hussein Onn Malaysia, Batu Pahat, Johor, Malaysia

martinsiow520@gmail.com

Abu Ubaidah Shamsudin, Faculty of Electrical and Electronic Engineering, Universiti Tun Hussein Onn Malaysia, Batu Pahat, Johor, Malaysia

ubaidah@uthm.edu.my

Zubair Adil Soomro, Faculty of Electrical and Electronic Engineering, Universiti Tun Hussein Onn Malaysia, Batu Pahat, Johor, Malaysia

zubairadil4@gmail.com

Anita Ahmad, School of Electrical Engineering, Faculty of Engineering, Universiti Teknologi Malaysia, Skudai, Johor, Malaysia

anita@utm.my

Ruzairi Abdul Rahim, School of Electrical Engineering, Faculty of Engineering, Universiti Teknologi Malaysia, Skudai, Johor, Malaysia

ruzairi@fke.utm.my

Mohd Khairul Ikhwan Ahmad, Cybersolution Technologies Sdn Bhd. Johor Bahru, Johor, Malaysia

mohdkhairulikhwan@gmail.com

Andi Adriansyah, Universitas Mercu Buana, Jakarta, Indonesia

andi@mercubuana.ac.id

Downloads

Published

2023-12-08

How to Cite

Siow, S. H., Shamsudin, A. U. ., Zubair Adil Soomro, Anita Ahmad, Ruzairi Abdul Rahim, Mohd Khairul Ikhwan Ahmad, & Andi Adriansyah. (2023). Instance Segmentation Evaluation For Traffic Signs . Journal of Advanced Research in Applied Sciences and Engineering Technology, 34(2), 327–341. https://doi.org/10.37934/araset.34.2.327341

Issue

Section

Articles

Most read articles by the same author(s)