您当前的位置:
首页 >
文章列表页 >
Object detection of steel surface defect based on multi-scale enhanced feature fusion
Information Sciences | 更新时间:2024-05-06
    • Object detection of steel surface defect based on multi-scale enhanced feature fusion

    • In response to the problem of low recognition accuracy of lightweight object detection algorithms in steel surface defect detection tasks, researchers have proposed a multi-scale enhanced feature fusion algorithm for steel surface defect object detection. This algorithm innovatively adopts an adaptive weighted fusion module, which achieves weighted fusion of deep semantics and shallow details, effectively improving the feature representation ability. At the same time, the algorithm also introduces a spatial feature enhancement module, which enhances the fusion features from three independent directions, improves the stability of the network structure, and mines more key information. The experimental results show that the detection accuracy of this algorithm reaches 80.47%, which is 6.81% higher than the original algorithm. In addition, the parameter and computational complexity of the algorithm are relatively small, and it can quickly and accurately detect defect information on the surface of steel, which has high application value. This research achievement provides a new solution for detecting surface defects in steel and opens up new directions for research in related fields.
    • Optics and Precision Engineering   Vol. 32, Issue 7, Pages: 1075-1086(2024)
    • DOI:10.37188/OPE.20243207.1075    

      CLC: TP394.1;TH691.9
    • Received:24 October 2023

      Revised:01 December 2023

      Published:10 April 2024

    移动端阅览

  • LIN Shanling,PENG Xueling,WANG Dong,et al.Object detection of steel surface defect based on multi-scale enhanced feature fusion[J].Optics and Precision Engineering,2024,32(07):1075-1086. DOI: 10.37188/OPE.20243207.1075.

  •  
  •  

0

Views

646

下载量

1

CSCD

Alert me when the article has been cited
提交
Tools
Download
Export Citation
Share
Add to favorites
Add to my album

Related Articles

Deflectometric measurement technology for optical surfaces: principles, challenges, and prospects(invited)
Improved phase correlation and clustering ideas for Micro-LED chip microscopic image stitching
YOLOv8 model-based additive manufacturing micro porosity defect detection and its dimension measurement
Solar cell defect detection network combining multiscale feature and attention
Improving the lightweight VTG-YOLOv7-tiny for steel surface defect detection

Related Author

ZHANG Zonghua
LIU Ruiyang
LI Pingfeng
ZHANG Xiangchao
NIU Xingman
HAO Siyuan
LANG Wei
LIN Shanling

Related Institution

College of Mechanical Engineering, Hebei University of Technology
School of Information Science and Technology, Fudan University
China Fujian Photoelectric Information Science and Technology Innovation Laboratory
College of Mechanical Engineering, Dalian University of Technology
School of Artificial Intelligence, Hebei University of Technology
0