Advancing Roadway Sign Detection with YOLO Models and Transfer Learning

被引:0
|
作者
Nafaa, Selvia [1 ]
Ashour, Karim [1 ]
Mohamed, Rana [1 ]
Essam, Hafsa [1 ]
Emad, Doaa [1 ]
Elhenawy, Mohammed [2 ]
Ashqar, Huthaifa I. [3 ]
Hassan, Abdallah A. [1 ]
Alhadidi, Taqwa I. [4 ]
机构
[1] Minia Univ, Comp & Syst Dept, Al Minya, Egypt
[2] Queensland Univ Technol, CARRS Q, Brisbane, Qld, Australia
[3] Arab Amer Univ, Civil Engn Dept, Jenin, Palestine
[4] Al Ahliyya Amman Univ, Civil Engn Dept, Amman, Jordan
来源
2024 IEEE 3RD INTERNATIONAL CONFERENCE ON COMPUTING AND MACHINE INTELLIGENCE, ICMI 2024 | 2024年
关键词
Deep Learning; Assets Management; Signs Detection;
D O I
10.1109/ICMI60790.2024.10586105
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Roadway signs detection and recognition is an essential element in the Advanced Driving Assistant Systems (ADAS). Several artificial intelligence methods have been used widely among of them YOLOv5 and YOLOv8. In this paper, we used a modified YOLOv5 and YOLOv8 to detect and classify different roadway signs under different illumination conditions. Experimental results indicated that for the YOLOv8 model, varying the number of epochs and batch size yields consistent MAP50 scores, ranging from 94.6% to 97.1% on the testing set. The YOLOv5 model demonstrates competitive performance, with MAP50 scores ranging from 92.4% to 96.9%. These results suggest that both models perform well across different training setups, with YOLOv8 generally achieving slightly higher MAP50 scores. These findings suggest that both models can perform well under different training setups, offering valuable insights for practitioners seeking reliable and adaptable solutions in object detection applications.
引用
收藏
页数:4
相关论文
共 50 条
  • [1] Advancing e-waste classification with customizable YOLO based deep learning models
    P. Akhil Rajeev
    Vivek Dharewa
    D. Lakshmi
    G. Vishnuvarthanan
    Jayant Giri
    T. Sathish
    Mubarak Alrashoud
    Scientific Reports, 15 (1)
  • [2] Sign-YOLO: A Novel Lightweight Detection Model for Chinese Traffic Sign
    Song, Weizhen
    Suandi, Shahrel Azmin
    IEEE ACCESS, 2023, 11 : 113941 - 113951
  • [3] Advancing Phishing Email Detection: A Comparative Study of Deep Learning Models
    Altwaijry, Najwa
    Al-Turaiki, Isra
    Alotaibi, Reem
    Alakeel, Fatimah
    SENSORS, 2024, 24 (07)
  • [4] Sea Mine Detection Framework Using YOLO, SSD and EfficientDet Deep Learning Models
    Munteanu, Dan
    Moina, Diana
    Zamfir, Cristina Gabriela
    Petrea, Stefan Mihai
    Cristea, Dragos Sebastian
    Munteanu, Nicoleta
    SENSORS, 2022, 22 (23)
  • [5] Research of YOLO Architecture Models in Book Detection
    Kalinina, Maria
    Nikolaev, Pavel
    PROCEEDINGS OF THE 8TH SCIENTIFIC CONFERENCE ON INFORMATION TECHNOLOGIES FOR INTELLIGENT DECISION MAKING SUPPORT (ITIDS 2020), 2020, 174 : 218 - 221
  • [6] Early detection and diagnosis of lung cancer using YOLO v7, and transfer learning
    Mammeri, Selma
    Amroune, Mohamed
    Haouam, Mohamed-Yassine
    Bendib, Issam
    Silva, Aristofanes Correa
    MULTIMEDIA TOOLS AND APPLICATIONS, 2024, 83 (10) : 30965 - 30980
  • [7] Eye Recognition by YOLO for Inner Canthus Temperature Detection in the Elderly Using a Transfer Learning Approach
    Ghourabi, Malak
    Mourad-Chehade, Farah
    Chkeir, Aly
    SENSORS, 2023, 23 (04)
  • [8] Early detection and diagnosis of lung cancer using YOLO v7, and transfer learning
    Selma Mammeri
    Mohamed Amroune
    Mohamed-Yassine Haouam
    Issam Bendib
    Aristofanes Corrêa Silva
    Multimedia Tools and Applications, 2024, 83 : 30965 - 30980
  • [9] A Deep Learning Approach to Badminton Player Footwork Detection Based on YOLO Models: A Comparative Study
    Jannet, Kawsin
    Sunar, Mohd Shahrizal
    Molla, Md Monirul Islam
    Bin As'Ari, Muhammad Amir
    2024 IEEE 8TH INTERNATIONAL CONFERENCE ON SIGNAL AND IMAGE PROCESSING APPLICATIONS, ICSIPA, 2024,
  • [10] Sign-YOLO: Traffic Sign Detection Using Attention-Based YOLOv7
    Mahadshetti, Ruturaj
    Kim, Jinsul
    Um, Tai-Won
    IEEE ACCESS, 2024, 12 : 132689 - 132700