Object detection of steel surface defect based on multi-scale enhanced feature fusion

被引：0
|
作者：
Lin S. [1 ,2 ]
Peng X. [1 ,2 ]
Wang D. [1 ,2 ]
Lin Z. [1 ,2 ,3 ]
Lin J. [1 ,2 ]
Guo T. [2 ,3 ]
机构：
[1] School of Advanced Manufacturing, Fuzhou University, Quanzhou
[2] China Fujian Photoelectric Information Science and Technology Innovation Laboratory, Fuzhou
[3] School of Physics and Information Engineering, Fuzhou University, Fuzhou
来源：
Guangxue Jingmi Gongcheng/Optics and Precision Engineering | 2024年 / 32卷 / 07期
关键词：
adaptive weighted fusion; defect detection; enhanced feature fusion; Single Shot multibox Detector（SSD）; spatial feature enhancement;
D O I：
10.37188/OPE.20243207.1075
中图分类号：
学科分类号：
摘要：
To address the issue of low recognition accuracy in lightweight algorithms for steel surface defect detection, this paper introduces a Multi-scale Enhanced Feature Fusion (EFF) technique. Initially, an Adaptive Weighted Fusion (AWF) module calculates fusion weights adaptively for different feature levels. This allows shallow features to enrich with deep semantics without compromising detail. Subsequently, the Spatial Feature Enhancement (SFE) module boosts the fused features from three distinct directions and improves network stability by integrating residual pathways, enabling the convolution process to extract more critical information. The model then selects better training samples based on the overlap between the prior box and the ground truth. Experimental outcomes show that the proposed method achieves a detection accuracy of 80.47%, marking a 6.81% increase over the baseline algorithm. Moreover, with 2.36 M parameters and 952.67 MFLOPs, this algorithm efficiently and accurately identifies steel surface defects, demonstrating significant practical utility. © 2024 Chinese Academy of Sciences. All rights reserved.
引用
收藏
页码：1075 / 1086
页数：11
相关论文
共 27 条
  • [1] LI Y, LI Y J, LIU J CH, Et al., Research on segmentation of steel surface defect images based on improved res-UNet network［J］, Journal of Electronics & Information Technology, 44, 5, pp. 1513-1520, (2022)
  • [2] LI Z G，, WEI X M，, HASSABALLAH M，, Et al., A deep learning model for steel surface defect detection ［J］, Complex & Intelligent Systems, 10, 1, pp. 885-897, (2024)
  • [3] KHAN S，, GUPTA G，, Et al., A study of CNN and transfer learning in medical imaging：advantages，challenges，future scope［J］, Sustainability, 15, 7, pp. 5930-5958, (2023)
  • [4] WANG Z, Et al., Automatic detection of individual trees in forests based on airborne LiDAR data with a tree region-based convolutional neural network （RCNN）［J］, Remote Sensing, 15, 4, pp. 1024-1044, (2023)
  • [5] DENG SH SH, MA Y., A small object detection algorithm based on improved Faster RCNN［J］, Computer Engineering & Science, 45, 5, pp. 869-877, (2023)
  • [6] DENG Y P, LI Y J., A review of YOLO algorithm and research on target detection in autonomous driving scenarios［J］, computer application, pp. 1-12, (2023)
  • [7] WANG S, Research and improvement of SSD（single shot MultiBox detector）target detection algorithm［J］, Industrial Control Computer, 32, 4, pp. 103-105, (2019)
  • [8] Convolutional Neural Network featuring VGG-16 Model for Glioma Classification［J］, JOIV：International Journal on Informatics Visualization, 6, 3, pp. 660-666, (2022)
  • [9] SANDLER M, ZHU M L, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 4510-4520, (2018)
  • [10] DENG C F, WANG M M，, LIU L, Et al., Extended feature pyramid network for small object detection ［J］, IEEE Transactions on Multimedia, 24, pp. 1968-1979, (2022)
123