Vehicle Logo Detection Method Based on Improved YOLOv4

被引:10
|
作者
Jiang, Xiaoli [1 ]
Sun, Kai [1 ,2 ]
Ma, Liqun [1 ]
Qu, Zhijian [1 ]
Ren, Chongguang [1 ]
机构
[1] Shandong Univ Technol, Sch Comp Sci & Technol, Zibo 255000, Peoples R China
[2] Zibo Special Equipment Inspect Inst, Zibo 255000, Peoples R China
关键词
vehicle logo; small object detection; DenseNet; deformable convolution; Vision Transformer; CONVOLUTIONAL NEURAL-NETWORKS; RECOGNITION; IMAGES;
D O I
10.3390/electronics11203400
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
A vehicle logo occupies a small proportion of a car and has different shapes. These characteristics bring difficulties to machine-vision-based vehicle logo detection. To improve the accuracy of vehicle logo detection in complex backgrounds, an improved YOLOv4 model was presented. Firstly, the CSPDenseNet was introduced to improve the backbone feature extraction network, and a shallow output layer was added to replenish the shallow information of small target. Then, the deformable convolution residual block was employed to reconstruct the neck structure to capture the various and irregular shape features. Finally, a new detection head based on a convolutional transformer block was proposed to reduce the influence of complex backgrounds on vehicle logo detection. Experimental results showed that the average accuracy of all categories in the VLD-45 dataset was 62.94%, which was 5.72% higher than the original model. It indicated that the improved model could perform well in vehicle logo detection.
引用
收藏
页数:19
相关论文
共 50 条
  • [21] An Improved Algorithm for Insulator and Defect Detection Based on YOLOv4
    Han, Gujing
    Yuan, Qiwei
    Zhao, Feng
    Wang, Ruijie
    Zhao, Liu
    Li, Saidian
    He, Min
    Yang, Shiqi
    Qin, Liang
    ELECTRONICS, 2023, 12 (04)
  • [22] Detection of cigarette appearance defects based on improved YOLOv4
    Yuan, Guowu
    Liu, Jiancheng
    Liu, Hongyu
    Ma, Yihai
    Wu, Hao
    Zhou, Hao
    ELECTRONIC RESEARCH ARCHIVE, 2023, 31 (03): : 1344 - 1364
  • [23] Video Detection of Helmet Wearing Based on Improved YOLOv4
    Wang, Hongyi
    Yang, Binquan
    2022 41ST CHINESE CONTROL CONFERENCE (CCC), 2022, : 6538 - 6543
  • [24] An Improved Target Detection General Framework Based on Yolov4
    Liu, Hao
    Zhang, Lei
    Xin, Shan
    2021 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND BIOMIMETICS (IEEE-ROBIO 2021), 2021, : 1532 - 1536
  • [25] Wheat Ear Detection Algorithm Based on Improved YOLOv4
    Zhao, Fengkui
    Xu, Lizhang
    Lv, Liya
    Zhang, Yong
    APPLIED SCIENCES-BASEL, 2022, 12 (23):
  • [26] Vehicle door frame positioning method for binocular vision robots based on improved YOLOv4
    Song, Limei
    Wang, Yulin
    Yang, Yangang
    Zhu, Xinjun
    MEASUREMENT SCIENCE AND TECHNOLOGY, 2023, 34 (06)
  • [27] Weld Image Detection and Recognition Based on Improved YOLOv4
    Cheng Song
    Dai Jintao
    Yang Honggang
    Chen Yunxia
    LASER & OPTOELECTRONICS PROGRESS, 2022, 59 (16)
  • [28] An Improved Apple Object Detection Method Based on Lightweight YOLOv4 in Complex Backgrounds
    Zhang, Chenxi
    Kang, Feng
    Wang, Yaxiong
    REMOTE SENSING, 2022, 14 (17)
  • [29] Water Column Detection Method at Impact Point Based on Improved YOLOv4 Algorithm
    Shi, Jiaowei
    Sun, Shiyan
    Shi, Zhangsong
    Zheng, Chaobing
    She, Bo
    SUSTAINABILITY, 2022, 14 (22)
  • [30] Object Detection Method Based on Improved YOLOv4 Network for Remote Sensing Images
    Xiao Zhenjiu
    Yang Yueying
    Kong Xiangxu
    LASER & OPTOELECTRONICS PROGRESS, 2023, 60 (06)