Steel defect detection based on multi-scale lightweight attention

被引：0
|
作者：
Zhou Y. [1 ]
Meng J.-N. [1 ]
Wang D.-L. [1 ]
Tan Y.-Q. [2 ]
机构：
[1] School of Automation and Electronic Information, Xiangtan University, Xiangtan
[2] School of Computer Science · Cyberspace Security, Xiangtan University, Xiangtan
来源：
Kongzhi yu Juece/Control and Decision | 2024年 / 39卷 / 03期
关键词：
attention mechanism; pyramid multi-level attention; steel surface defect detection; YOLOv5;
D O I：
10.13195/j.kzyjc.2022.0997
中图分类号：
学科分类号：
摘要：
Aiming at the problems that the current YOLOv5 algorithm detects steel surface defects with low accuracy and slow speed, a YOLO-Steel steel surface defect detection algorithm is proposed. First, a light-weight channel attention module is proposed, which can effectively focus on important channels with only a small computational cost. Secondly, by using atrous convolution to expand the receptive field, a light-weight spatial attention module is proposed. Finally, a pyramid attention structure is proposed, which uses multi-level pooling to scale feature maps, and uses spatial attention modules on feature maps of different resolutions to learn its spatial dependence information. After splicing in dimensions, the channel attention module is used to reconstruct its channel-related information, which can achieve better detection results for multi-scale detection targets. The experimental results show that the average mean precision (mAP) of YOLO-Steel on the steel surface defect data set can reach 77.2 %, which is 1.8 percentage points higher than that of the YOLOv5s algorithm, and the model time and space complexity are basically the same as those of YOLOv5s. On the basis of ensuring the detection speed, the accuracy is effectively improved. © 2024 Northeast University. All rights reserved.
引用
收藏
页码：901 / 909
页数：8
相关论文
共 26 条
  • [1] Li S B, Yang J, Wang Z, Et al., Review of development and application of defect detection technology, Acta Automatica Sinica, 46, 11, pp. 2319-2336, (2020)
  • [2] Kang S, Chen C Z, Luo Y Q, Et al., Study on infrared detection edge enhancement of wind turbine blade defects based on differential morphology gradient, Acta Energiae Solaris Sinica, 42, 6, pp. 432-437, (2021)
  • [3] Xu P, Geng M, Fang Z, Et al., Study on high-speed rail defect detection method based on combination of EC and MFL testing, Journal of Mechanical Engineering, 57, 18, pp. 57-65, (2021)
  • [4] Zhu Y L, Zhao Y S, Fang Y, Et al., A study on rotating eddy current testing for inspection of cracks at hole edge, China Mechanical Engineering
  • [5] Liu H W, Lan Y Y, Lee H W, Et al., Steel surface in-line inspection using machine vision, First International Workshop on Pattern Recognition, pp. 187-191, (2016)
  • [6] Liang Y, Xu K, Zhou P., Mask gradient response-based threshold segmentation for surface defect detection of milled aluminum ingot, Sensors: Basel, Switzerland, 20, 16, (2020)
  • [7] Liu J H, Fu M R, Tang J H., MFL inner detection based defect recognition method, Chinese Journal of Scientific Instrument, 37, 11, pp. 2572-2581, (2016)
  • [8] Tsai D M, Chen M C, Li W C, Et al., A fast regularity measure for surface defect detection, Machine Vision and Applications, 23, 5, pp. 869-886, (2012)
  • [9] Timm F, Barth E., Non-parametric texture defect detection using Weibull features, Proceedings of SPIE 7877, Image Processing: Machine Vision Applications IV, 7877, pp. 150-161, (2011)
  • [10] Zhou K, Zhang R Z, Ye K, Et al., Electromagnetic ultrasonic SH guided wave detection method for grounded flat steel defects based on synchrosqueezed wavelet transforms, Journal of Tsinghua University: Science and Technology, 62, 12, pp. 2013-2020, (2022)
123