Improving the lightweight VTG-YOLOv7-tiny for steel surface defect detection

被引：0
|
作者：
Liang L. [1 ]
Long P. [1 ]
Feng Y. [1 ]
Lu B. [1 ]
机构：
[1] School of Electrical Engineering and Automation, Jiangxi University of Science and Technology, Ganzhou
来源：
Guangxue Jingmi Gongcheng/Optics and Precision Engineering | 2024年 / 32卷 / 08期
关键词：
defect detection; Ghost Shuffle Convolution（GSConv）; Lightweight YOLOv7-tiny; Triplet Coordinate Attention(TCA); VoVGA-FPN network;
D O I：
10.37188/OPE.20243208.1227
中图分类号：
学科分类号：
摘要：
To address the problems of diverse and complex shapes of steel surface defects，detection target missing，and large number of algorithm parameters，a lightweight VTG-YOLOv7-tiny steel defect detection algorithm was proposed. The method first designed VoVGA-FPN network to reduce the loss of information during information transmission and enhance the network feature fusion ability；second，it constructed a triple coordinate attention mechanism to improve the model's feature extraction ability of spatial and channel information；third，it introduceed ghost shuffle convolution to reduce the model parameters and computation while improving the accuracy；fourth，it added a large target detection layer to improve the problem that some defects in the feature map occupy a large proportion，resulting in low detection accuracy. The improved algorithm was verified on the NEU-DET and Severstal steel defect datasets. Compared with the original model，the mAP of the improved algorithm is increased by 5. 7% and 8. 5%，re-spectively；the parameters and computation are reduced by 0. 61 M and 4. 2 G，respectively；the accuracy and recall are increased by 7. 1%，1. 8% and 8. 9%，7. 0%，respectively. The experimental results show that the improved algorithm better balances the detection accuracy and lightweight，and provides a reference for edge terminal devices. © 2024 Chinese Academy of Sciences. All rights reserved.
引用
下载
收藏
页码：1227 / 1240
页数：13
相关论文
共 30 条
  • [1] CAO Y Q, XU L., Steel surface defect detection based on improved YOLOv5 algorithm ［J］, Journal of Graphics, 44, 2, pp. 335-345, (2023)
  • [2] ZHOU L S, LIANG L M, SHENG X Q., GA-Net：ghost convolution adaptive fusion skin lesion segmentation network［J］, Computers in Biology and Medicine, 164, (2023)
  • [3] GUO F, ZHU Q B, HUANG M，, Et al., Defect detection in ceramic substrate based on improved YOLOV4［J］, Opt. Precision Eng, 30, 13, pp. 1631-1641, (2022)
  • [4] CHEN Y F, LIAO F, HUANG X Y, Et al., Multi-scale YOLOv5 for solar cell defect detection［J］, Opt. Precision Eng, 31, 12, pp. 1804-1815, (2023)
  • [5] LI S B, YANG J, WANG Z, Et al., Review of development and application of defect detection technology［J］, Acta Automatica Sinica, 46, 11, pp. 2319-2336, (2020)
  • [6] ZHU Y L, ZHAO Y S，, FANG Y，, Et al., Rotating eddy current testing for inspection of cracks at hole edge［J］, China Mechanical Engineering, 34, 8, pp. 883-891, (2023)
  • [7] GIRSHICK R., Fast R-CNN［C］, 2015 IEEE International Conference on Computer Vision（ICCV）, pp. 1440-1448, (2015)
  • [8] 2017 IEEE International Conference on Computer Vision（ICCV）, pp. 2980-2988, (2017)
  • [9] 2016 IEEE Conference on Computer Vision and Pattern Recognition（CVPR）, pp. 779-788, (2016)
  • [10] HUSSAIN M., YOLO-v1 to YOLO-v8，the rise of YOLO and its complementary nature toward digital manufacturing and industrial defect detection ［J］, Machines, 11, 7, (2023)
123