Education, Science, Technology, Innovation and Life
Open Access
Sign In
  1. Home
  2. Journals
  3. Advances in Computer, Signals and Systems
  4. Vol 7, Issue 2, 2023

Lightweight Steel Bar Detection Network Based on YOLOv5

Download as PDF

DOI: 10.23977/acss.2023.070203 | Downloads: 22 | Views: 526

Author(s)

Ren Junsong 1, Wang Yi 1, Peng Xutao 1

Affiliation(s)

1 Department of Computer Science and Engineering, Sichuan University of Science & Engineering, Yibin, Sichuan, China

Corresponding Author

Wang Yi

ABSTRACT

The proposed YOLOv5 model for steel bar detection has been improved with the addition of an ECA-Net attention module and Ghost Conv to reduce model volume. The Neck layer's feature pyramid module has been replaced with a weighted two-way feature pyramid network structure for better feature fusion. Additionally, the loss function and image processing have been improved for better detection efficiency. The experimental results on the reinforced data set show that the volume of the improved YOLO -EB model is reduced by 11 % compared with the original version, and the mAP is increased by 1.6 %, which meets the requirements of actual use.

KEYWORDS

Rebar detection; YOLOv5 algorithm; weighted two-way feature pyramid; attention mechanism

CITE THIS PAPER

Ren Junsong, Wang Yi, Peng Xutao. Lightweight Steel Bar Detection Network Based on YOLOv5. Advances in Computer, Signals and Systems (2023) Vol. 7: 12-25. DOI: http://dx.doi.org/10.23977/acss.2023.070203.

REFERENCES

[1] Ghazali MF, Wong LK, See J. Automatic detection and counting of circular and rectangular steel bars[C]//9th International Conference on Robotic, Vision, Signal Processing and Power Applications. Springer, Singapore, 2017: 199-207. 2017: 199-207.
[2] Niu Caihong. Research and Implementation of Rebar End Image Recognition [D]. Shenyang University of Technology, 2015.
[3] Li Qiang, Chen Zunde. Automatic steel quantity counting system based on fuzzy circular template matching method [J]. Automation Technology and Application, 2004, 23(2): 25-28.
[4] Chen Zhikun, Pan Xiaodi, Wang Fubin, et al. Research on Rebar Counting Method Based on Neural Network [J]. Sensors and Microsystems, 2010(8):4.
[5] Xie Haizhen. Research and application of bar counting algorithm in complex scenes [D]. University of Electronic Science and Technology of China, 2020
[6] Wang Huifang. Research and Application of Object Detection Algorithms for Dense Scenes [D]. University of Electronic Science and Technology of China, 2021.
[7] He K, Zhang X, Ren S, et al. Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2014, 37(9):1904-16.
[8] Lin T Y, Dollár P, Girshick R, et al. Feature pyramid networks for object detection[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2017: 2117-2125.
[9] H  Rezatofighi,  Tsoi N,  JY  Gwak, et al. Generalized Intersection Over Union: A Metric and a Loss for Bounding Box Regression[C]// 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, 2019.
[10] Neubeck A,  Gool L . Efficient Non-Maximum Suppression[C]// International Conference on Pattern Recognition. IEEE Computer Society, 2006.
[11] Wang Q,  Wu B,  Zhu P, et al. ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks[C]// 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, 2020.
[12] Jie H,  Li S,  Gang S, et al. Squeeze-and-Excitation Networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, PP(99).
[13] Han K,  Wang Y,  Tian Q, et al. GhostNet: More Features From Cheap Operations[C]// 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, 2020.
[14] Tan M,  Pang R,  Le Q V . EfficientDet: Scalable and Efficient Object Detection[C]// 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, 2020.
[15] Liu S, Qi L, Qin H, et al. Path aggregation network for instance segmentation[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2018: 8759-8768.
[16] He J, Erfani S, Ma X, et al. $\alpha $- IoU : A Family of Power Intersection over Union Losses for Bounding Box Regression[J]. Advances in Neural Information Processing Systems, 2021, 34: 20230 -20242.
[17] Zheng Z, Wang P, Liu W, et al. Distance- IoU loss: Faster and better learning for bounding box regression [C]// Proceedings of the AAAI Conference on Artificial Intelligence. 2020, 34(07): 12993 -13000. 

Subscription
E-Mail Alert
Most popular papers
Call for Special Issue
Publication Ethics & OA Statement
Plagiarism Policy
Contact Us
Downloads: 13042
Visits: 255032

Sponsors, Associates, and Links

All published work is licensed under a Creative Commons Attribution 4.0 International License.

Copyright © 2016 - 2031 Clausius Scientific Press Inc. All Rights Reserved.