Improved YOLOv5-Based Lightweight Object Detection Algorithm for People with Visual Impairment to Detect Buses

被引:18
|
作者
Arifando, Rio [1 ]
Eto, Shinji [1 ]
Wada, Chikamune [1 ]
机构
[1] Kyushu Inst Technol, Grad Sch Life Sci & Syst Engn, 2-4 Hibikino,Wakamatsu Ku, Kitakyushu 8080196, Japan
来源
APPLIED SCIENCES-BASEL | 2023年 / 13卷 / 09期
关键词
bus detection; visual impairment; YOLOv5; Ghostnet; SimSPPF; slim scale model; SYSTEM;
D O I
10.3390/app13095802
中图分类号
O6 [化学];
学科分类号
0703 ;
摘要
Object detection is crucial for individuals with visual impairment, especially when waiting for a bus. In this study, we propose a lightweight and highly accurate bus detection model based on an improved version of the YOLOv5 model. We propose integrating the GhostConv and C3Ghost Modules into the YOLOv5 network to reduce the number of parameters and floating-point operations per second (FLOPs), ensuring detection accuracy while reducing the model parameters. Following that, we added the SimSPPF module to replace the SPPF in the YOLOv5 backbone for increased computational efficiency and accurate object detection capabilities. Finally, we developed a Slim scale detection model by modifying the original YOLOv5 structure in order to make the model more efficient and faster, which is critical for real-time object detection applications. According to the experimental results, the Improved-YOLOv5 outperforms the original YOLOv5 in terms of the precision, recall, and mAP@0.5. Further analysis of the model complexity reveals that the Improved-YOLOv5 is more efficient due to fewer FLOPS, with fewer parameters, less memory usage, and faster inference time capabilities. The proposed model is smaller and more feasible to implement in resource-constrained mobile devices and a promising option for bus detection systems.
引用
收藏
页数:19
相关论文
共 50 条
  • [1] An Improved YOLOv5-Based Lightweight Submarine Target Detection Algorithm
    Mei, Likun
    Chen, Zhili
    [J]. SENSORS, 2023, 23 (24)
  • [2] An Improved YOLOv5-Based Underwater Object-Detection Framework
    Zhang, Jian
    Zhang, Jinshuai
    Zhou, Kexin
    Zhang, Yonghui
    Chen, Hongda
    Yan, Xinyue
    [J]. SENSORS, 2023, 23 (07)
  • [3] Lightweight YOLOv5-based Algorithm to Detect Room Nameplates for Autonomous Smart Wheelchair
    Alqadri, Ainandafiq Muhammad
    Utaminingrum, Fitri
    [J]. 2024 21ST INTERNATIONAL JOINT CONFERENCE ON COMPUTER SCIENCE AND SOFTWARE ENGINEERING, JCSSE 2024, 2024, : 463 - 468
  • [4] An improved YOLOv5-based algorithm for small wheat spikes detection
    Lizhao Liu
    Pinrui Li
    [J]. Signal, Image and Video Processing, 2023, 17 : 4485 - 4493
  • [5] An improved YOLOv5-based algorithm for small wheat spikes detection
    Liu, Lizhao
    Li, Pinrui
    [J]. SIGNAL IMAGE AND VIDEO PROCESSING, 2023, 17 (08) : 4485 - 4493
  • [6] Lightweight object detection algorithm for robots with improved YOLOv5
    Liu, Gang
    Hu, Yanxin
    Chen, Zhiyu
    Guo, Jianwei
    Ni, Peng
    [J]. ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE, 2023, 123
  • [7] A lightweight small object detection algorithm based on improved YOLOv5 for driving scenarios
    Wen, Zonghui
    Su, Jia
    Zhang, Yongxiang
    Li, Mingyu
    Gan, Guoxi
    Zhang, Shenmeng
    Fan, Deyu
    [J]. INTERNATIONAL JOURNAL OF MULTIMEDIA INFORMATION RETRIEVAL, 2023, 12 (02)
  • [8] A lightweight small object detection algorithm based on improved YOLOv5 for driving scenarios
    Zonghui Wen
    Jia Su
    Yongxiang Zhang
    Mingyu Li
    Guoxi Gan
    Shenmeng Zhang
    Deyu Fan
    [J]. International Journal of Multimedia Information Retrieval, 2023, 12
  • [9] Lightweight aerial image object detection algorithm based on improved YOLOv5s
    Lixia Deng
    Lingyun Bi
    Hongquan Li
    Haonan Chen
    Xuehu Duan
    Haitong Lou
    Hongyu Zhang
    Jingxue Bi
    Haiying Liu
    [J]. Scientific Reports, 13
  • [10] Lightweight aerial image object detection algorithm based on improved YOLOv5s
    Deng, Lixia
    Bi, Lingyun
    Li, Hongquan
    Chen, Haonan
    Duan, Xuehu
    Lou, Haitong
    Zhang, Hongyu
    Bi, Jingxue
    Liu, Haiying
    [J]. SCIENTIFIC REPORTS, 2023, 13 (01)