A comparative study of YOLOv5 models performance for image localization and classification

被引：0
|
作者：
Horvat, Marko [1 ]
Jelecevic, Ljudevit [1 ]
Gledec, Gordan [1 ]
机构：
[1] Univ Zagreb, Dept Appl Comp, Fac Elect Engn & Comp, Unska 3, HR-10000 Zagreb, Croatia
来源：
CENTRAL EUROPEAN CONFERENCE ON INFORMATION AND INTELLIGENT SYSTEMS, CECIIS 2022 | 2022年
关键词：
computer vision; image classification; deep learning; deep convolutional neural networks; YOLO; OBJECT DETECTION; TIME;
D O I：
暂无
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
YOLOv5 is one of the latest and often used versions of a very popular deep learning neural network used for various machine learning tasks, mainly in computer vision. The YOLO algorithm has steadily gained acceptance in the data science community due to its superior performance in complex and noisy data environments, availability, and ease of use in combination with widely used programming languages such as Python. This paper aims to compare different versions of the YOLOv5 model using an everyday image dataset and to provide researchers with precise suggestions for selecting the optimal model for a given problem type. The obtained results and the implemented YOLOv5 models are available for non-commercial use at: https://github.com/mhorvat/YOLOv5-models-comparison
引用
收藏
页码：349 / 356
页数：8
相关论文
共 50 条
  • [21] An Aerial Image Detection Algorithm Based on Improved YOLOv5
    Shan, Dan
    Yang, Zhi
    Wang, Xiaofeng
    Meng, Xiangdong
    Zhang, Guangwei
    SENSORS, 2024, 24 (08)
  • [22] Comparative Study of Interpretable Image Classification Models
    Bajcsi, Adel
    Bajcsi, Anna
    Pavel, Szabolcs
    Portik, Abel
    Sandor, Csanad
    Szenkovits, Annamaria
    Vas, Orsolya
    Bodo, Zalan
    Csato, Lehel
    INFOCOMMUNICATIONS JOURNAL, 2023, 15 : 20 - 26
  • [23] The Efficiency of YOLOv5 Models in the Detection of Similar Construction Details
    Kvietkauskas, Tautvydas
    Pavlov, Ernest
    Stefanovic, Pavel
    Pliuskuviene, Birute
    APPLIED SCIENCES-BASEL, 2024, 14 (09):
  • [24] Benchmarking YOLOv5 and YOLOv7 models with DeepSORT for droplet tracking applications
    Durve, Mihir
    Orsini, Sibilla
    Tiribocchi, Adriano
    Montessori, Andrea
    Tucny, Jean-Michel
    Lauricella, Marco
    Camposeo, Andrea
    Pisignano, Dario
    Succi, Sauro
    EUROPEAN PHYSICAL JOURNAL E, 2023, 46 (05):
  • [25] Benchmarking YOLOv5 and YOLOv7 models with DeepSORT for droplet tracking applications
    Mihir Durve
    Sibilla Orsini
    Adriano Tiribocchi
    Andrea Montessori
    Jean-Michel Tucny
    Marco Lauricella
    Andrea Camposeo
    Dario Pisignano
    Sauro Succi
    The European Physical Journal E, 2023, 46
  • [26] Comparison of YOLOv5 and YOLOv6 Models for Plant Leaf Disease Detection
    Iren, Ecem
    ENGINEERING TECHNOLOGY & APPLIED SCIENCE RESEARCH, 2024, 14 (02) : 13714 - 13719
  • [27] Object detection and localization algorithm in agricultural scenes based on YOLOv5
    Yang, Jiachen
    Han, Mengqi
    He, Jingyi
    Wen, Jiabao
    Chen, Desheng
    Wang, Yibo
    JOURNAL OF ELECTRONIC IMAGING, 2023, 32 (05) : 52402
  • [28] Study of Improved Yolov5 Algorithms for Gesture Recognition
    Gaol, Siyuan
    Liu, Zhengyan
    Li, Xu
    2022 IEEE 6TH ADVANCED INFORMATION TECHNOLOGY, ELECTRONIC AND AUTOMATION CONTROL CONFERENCE (IAEAC), 2022, : 378 - 384
  • [29] Object detection and classification of pleurotus ostreatus using improved YOLOv5
    Wang L.
    Wang B.
    Li D.
    Zhao Y.
    Wang C.
    Zhang D.
    Nongye Gongcheng Xuebao/Transactions of the Chinese Society of Agricultural Engineering, 2023, 39 (17): : 163 - 171
  • [30] Underwater image enhancement and detection based on convolutional DCP and YOLOv5
    Liu Guodong
    Feng Lihui
    Lu Jihua
    Yan Lei
    2022 41ST CHINESE CONTROL CONFERENCE (CCC), 2022, : 6765 - 6772
12345