Improved YOLOv5s model for key components detection of power transmission lines

Chen Chen; Guowu Yuan; Hao Zhou; Yi Ma; Chen Chen; Guowu Yuan; Hao Zhou; Yi Ma

doi:10.3934/mbe.2023334

Mathematical Biosciences and Engineering

2023, Volume 20, Issue 5: 7738-7760. doi: 10.3934/mbe.2023334

Previous Article Next Article

Research article Special Issues

Improved YOLOv5s model for key components detection of power transmission lines

1.
School of Information Science and Engineering, Yunnan University, Kunming 650504, Yunnan, China
2.
Electric Power Research Institute, Yunnan Power Grid Co., Ltd, Kunming 650214, Yunnan, China

Academic Editor: Yiu-ming Cheung

Received: 04 January 2023 Revised: 09 February 2023 Accepted: 14 February 2023 Published: 20 February 2023

High-voltage transmission lines are located far from the road, resulting in inconvenient inspection work and rising maintenance costs. Intelligent inspection of power transmission lines has become increasingly important. However, subsequent intelligent inspection relies on accurately detecting various key components. Due to the low detection accuracy of key components in transmission line image inspection, this paper proposed an improved object detection model based on the YOLOv5s (You Only Look Once Version 5 Small) model to improve the detection accuracy of key components of transmission lines. According to the characteristics of the power grid inspection image, we first modify the distance measurement in the k-means clustering to improve the anchor matching of the YOLOv5s model. Then, we add the convolutional block attention module (CBAM) attention mechanism to the backbone network to improve accuracy. Finally, we apply the focal loss function to reduce the impact of class imbalance. Our improved method's mAP (mean average precision) reached 98.1%, the precision reached 97.5%, the recall reached 94.4% and the detection rate reached 84.8 FPS (frames per second). The experimental results show that our improved model improves the detection accuracy and has advantages over other models in performance.
- transmission line,
- object detection,
- YOLO,
- attention mechanism,
- deep learning
Citation: Chen Chen, Guowu Yuan, Hao Zhou, Yi Ma. Improved YOLOv5s model for key components detection of power transmission lines[J]. Mathematical Biosciences and Engineering, 2023, 20(5): 7738-7760. doi: 10.3934/mbe.2023334

Related Papers:

Abstract

High-voltage transmission lines are located far from the road, resulting in inconvenient inspection work and rising maintenance costs. Intelligent inspection of power transmission lines has become increasingly important. However, subsequent intelligent inspection relies on accurately detecting various key components. Due to the low detection accuracy of key components in transmission line image inspection, this paper proposed an improved object detection model based on the YOLOv5s (You Only Look Once Version 5 Small) model to improve the detection accuracy of key components of transmission lines. According to the characteristics of the power grid inspection image, we first modify the distance measurement in the k-means clustering to improve the anchor matching of the YOLOv5s model. Then, we add the convolutional block attention module (CBAM) attention mechanism to the backbone network to improve accuracy. Finally, we apply the focal loss function to reduce the impact of class imbalance. Our improved method's mAP (mean average precision) reached 98.1%, the precision reached 97.5%, the recall reached 94.4% and the detection rate reached 84.8 FPS (frames per second). The experimental results show that our improved model improves the detection accuracy and has advantages over other models in performance.

References

[1]	Z. B. Zhao, Z. G. Jiang, Y. X. Li, Y. C. Qi, Y. J. Zhai, W. Q. Zhao, et al., Overview of visual defect detection of transmission line components, J. Image Graphics, 26 (2021), 2545–2560. https://doi.org/10.11834/jig.200689 doi: 10.11834/jig.200689
[2]	Z. X. Zou, K. Y. Chen, Z. W. Shi, Y. H. Guo, J. P. Ye, Object detection in 20 years: A survey, Proc. IEEE, 2023. https://doi.org/10.1109/JPROC.2023.3238524 doi: 10.1109/JPROC.2023.3238524
[3]	X. W. Wu, D. Sahoo, S. C. H. Hoi, Recent advances in deep learning for object detection, Neurocomputing, 396 (2020), 39–64. https://doi.org/10.1016/j.neucom.2020.01.085 doi: 10.1016/j.neucom.2020.01.085
[4]	X. Y. Dai, Y. P. Chen, B. Xiao, D. D. Chen, M. C. Liu, L. Yuan, et al., Dynamic head: Unifying object detection heads with attentions, in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, (2021), 7373–7382. https://doi.org/10.48550/arXiv.2106.08322
[5]	Q. Peng, Y. M. Cheung, Automatic video object segmentation based on visual and motion saliency, IEEE Trans. Multimedia, 21 (2019), 3083–3094. https://doi.org/10.1109/TMM.2019.2918730 doi: 10.1109/TMM.2019.2918730
[6]	Z. Y. He, S. Y. Yi, Y. M. Cheung, X. G. You, Y. Y. Tang, Robust object tracking via key patch sparse representation, IEEE Trans. Cybern., 47 (2016), 354–364. https://doi.org/10.1109/TCYB.2016.2514714 doi: 10.1109/TCYB.2016.2514714
[7]	H. Y. Liu, G. W. Yuan, L. Yang, K. X. Liu, H. Zhou, An appearance defect detection method for cigarettes based on C-CenterNet, Electronics, 11 (2022), 2182. https://doi.org/10.3390/electronics11142182 doi: 10.3390/electronics11142182
[8]	L. Yang, G. W. Yuan, H. Zhou, H. Y. Liu, J. Chen, H. Wu, RS-YOLOX: A high-precision detector for object detection in satellite remote sensing images, Appl. Sci., 12 (2022), 8707. https://doi.org/10.3390/app12178707 doi: 10.3390/app12178707
[9]	G. Lin, B. Wang, F. Peng, X. Y. Wang, S. Y. Chen, L. M. Zhang, Multi-objective detection and localization of transmission line inspection images based on improved Faster R-CNN, Electr. Power Syst. Res., 39 (2019), 213–218. https://doi.org/10.16081/j.issn.1006-6047.2019.05.032 doi: 10.16081/j.issn.1006-6047.2019.05.032
[10]	R. S. Li, Y. L. Zhang, D. H. Zhai, D. Xu, Improved SSD-based pin defect detection for transmission lines, High Voltage Eng., 47 (2021), 3795–3802. https://doi.org/10.13336/j.1003-6520.hve.20201650 doi: 10.13336/j.1003-6520.hve.20201650
[11]	H. M. Zhang, H. Zhou, S. Y. Li, P. P. Li, Improved YOLOv3 method for foreign body detection on power transmission lines, Laser J., 43 (2022), 82–87. https://doi.org/10.14016/j.cnki.jgzz.2022.05.082 doi: 10.14016/j.cnki.jgzz.2022.05.082
[12]	T. Guo, F. X. Chen, W. Wang, P. Shen, L. Shi, T. Z. Chen, Electric insulator detection of UAV images based on depth learning, in 2017 2nd International Conference on Power and Renewable Energy (ICPRE), IEEE, (2017), 37–41. https://doi.org/10.1109/ICPRE.2017.8390496
[13]	V. N. Nguyen, R. Jenssen, D. Roverso, Intelligent monitoring and inspection of power line components powered by UAVs and deep learning, IEEE Power Energy Tech. Syst. J., 6 (2019), 11–21. https://doi.org/10.1109/JPETS.2018.2881429 doi: 10.1109/JPETS.2018.2881429
[14]	H. P. Chen, Z. T. He, B. W. Shi, T. Zhong, Research on recognition method of electrical components based on YOLO V3, IEEE Access, 7 (2019), 157818–157829. https://doi.org/10.1109/ACCESS.2019.2950053 doi: 10.1109/ACCESS.2019.2950053
[15]	H. G. Liang, C. Zuo, W. M. Wei, Detection and evaluation method of transmission line defects based on deep learning, IEEE Access, 8 (2020), 38448–38458. https://doi.org/10.1109/ACCESS.2020.2974798 doi: 10.1109/ACCESS.2020.2974798
[16]	H. X. Ni, M. Z. Wang, L. Y. Zhao, An improved faster R-CNN for defect recognition of key components of transmission line, Math. Biosci. Eng., 18 (2021), 4679–4695. https://doi.org/10.3934/mbe.2021237 doi: 10.3934/mbe.2021237
[17]	Y. Q. Chen, H. X. Wang, J. Shen, X. W. Zhang, X. W. Gao, Application of data-driven iterative learning algorithm in transmission line defect detection, Sci. Program., 2021 (2021), 1–9. https://doi.org/10.1155/2021/9976209 doi: 10.1155/2021/9976209
[18]	Z. Y. Liu, G. P. Wu, W. S. He, F. Fan, X. H. Ye, Key target and defect detection of high-voltage power transmission lines with deep learning, Int. J. Electr. Power Energy Syst., 142 (2022), 108277. https://doi.org/10.1016/j.ijepes.2022.108277 doi: 10.1016/j.ijepes.2022.108277
[19]	Z. Q. Feng, L. Guo, D. R. Huang, R. Z. Li, Electrical insulator defects detection method based on YOLOv5, in 2021 IEEE 10th Data Driven Control and Learning Systems Conference (DDCLS), IEEE, (2021), 979–984. https://doi.org/10.1109/DDCLS52934.2021.9455519
[20]	S. Hao, L. Yang, X. Ma, R. Z. Ma, H. Wen, YOLOv5 transmission line fault detection based on attention mechanism and cross-scale feature fusion, in Proceedings of the CSEE, (2022), 1–12.
[21]	Z. B. Zhao, Y. X. Li, Y. C. Qi, Y. H. Kong, L. Q. Nie, Insulator defect detection method based on dynamic focal loss function and sample balancing method, Electr. Power Autom. Equip., 40 (2020), 205–211. https://doi.org/10.16081/j.epae.202010008 doi: 10.16081/j.epae.202010008
[22]	G. H. Yang, W. Feng, J. T. Jin, Q. J. Lei, X. H. Li, G. C. Gui, et al., Face mask recognition system with YOLOV5 based on image recognition, in 2020 IEEE 6th International Conference on Computer and Communications (ICCC), IEEE, (2020), 1398–1404. https://doi.org/10.1109/ICCC51575.2020.9345042
[23]	J. Glenn, YOLOv5, GitHub, https://github.com/ultralytics/YOLOv5, 2020.
[24]	G. Huang, Z. Liu, L. V. D. Maaten, K. Q. Weinberger, Densely connected convolutional networks, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, (2017), 4700–4708. https://doi.org/10.48550/arXiv.1608.06993
[25]	C. Y. Wang, H. Y. M. Liao, Y. H. Wu, P. Y. Chen, J. W. Hsieh, I. H. Yeh, CSPNet: A new backbone that can enhance learning capability of CNN, in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, (2020), 390–391. https://doi.org/10.1109/CVPRW50498.2020.00203
[26]	C. Y. Guo, Z. Xu, Y. K. Ma, M. M. Cao, An improved SMOTE algorithm for fusing Canopy and K-means for unbalanced datasets, Sci. Tech. Eng., 20 (2020), 9069–9074. https://doi.org/10.3969/j.issn.1671-1815.2020.22.032 doi: 10.3969/j.issn.1671-1815.2020.22.032
[27]	U. T. Zhang, Z. Y. Wang, X. Y. Wang, H. D. Fan, Improved K-means clustering algorithm for adaptive Canny operator workpiece edge detection, Mod. Mach. Tool. Autom. Manuf. Tech., 5 (2022), 1–5. https://doi.org/10.13462/j.cnki.mmtamt.2022.05.001 doi: 10.13462/j.cnki.mmtamt.2022.05.001
[28]	Q. Tian, R. Hu, Z. Y. Li, Y. Z. Cai, Z. C. Yu, Insulator detection based on SE-YOLOv5s, Chin. J. Int. Sci., 3 (2021), 312–321. https://doi.org/10.11959/j.issn.2096-6652.202132 doi: 10.11959/j.issn.2096-6652.202132
[29]	T. Y. Lin, P. Goyal, R. Girshick, K. M. He, P. Dollár, Focal loss for dense object detection, in Proceedings of the IEEE International Conference on Computer Vision, (2017), 2980–2988. https://doi.org/10.48550/arXiv.1708.02002
[30]	X. Tao, D. P. Zhang, Z. H. Wang, X. L. Liu, H. Y. Zhang, D. Xu, Detection of power line insulator defects using aerial images analyzed with convolutional neural networks, IEEE Trans. Syst. Man Cybern., 50 (2020), 1486–1498. https://doi.org/10.1109/TSMC.2018.2871750 doi: 10.1109/TSMC.2018.2871750
[31]	W. Q. Zhao, H. H. Cheng, Z. B. Zhao, Y. J. Zhai, Combining attention mechanism and Faster RCNN for insulator recognition, CAAI Trans. Int. Syst., 15 (2020), 7. https://doi.org/10.11992/tis.201907023 doi: 10.11992/tis.201907023
[32]	J. Hu, L. Shen, G. Sun, Squeeze-and-excitation networks, in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, (2018), 7132–7141. https://doi.org/10.48550/arXiv.1709.01507
[33]	Q. L. Wang, B. G. Wu, P. F. Zhu, P. H. Li, W. M. Zuo, Q. H. Hu, ECA-Net: Efficient channel attention for deep convolutional neural networks, in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, (2020), 11531–11539. https://doi.org/10.1109/CVPR42600.2020.01155
[34]	Q. B. Hou, D. Q. Zhou, J. S. Feng, Coordinate attention for efficient mobile network design, in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, (2021), 13708–13717. https://doi.org/10.1109/CVPR46437.2021.01350
[35]	S. WOO, J. PARK, J. Y. LEE, I. S. Kweon, CBAM: convolutional block attention module, in Proceedings of the European Conference on Computer Vision (ECCV), (2018), 3–19. https://doi.org/10.48550/arXiv.1807.06521
[36]	A. M. Roy, R. Bose, J. Bhaduri, A fast accurate fine-grain object detection model based on YOLOv4 deep neural network, Neural Comput. Appl., 34 (2022), 3895–3921. https://doi.org/10.1007/s00521-021-06651-x doi: 10.1007/s00521-021-06651-x
[37]	A. M. Roy, J. Bhaduri, T. Kumar, K. Raj, WilDect-YOLO: An efficient and robust computer vision-based accurate object localization model for automated endangered wildlife detection, Ecol. Inf., (2022), 101919. https://doi.org/10.1016/j.ecoinf.2022.101919 doi: 10.1016/j.ecoinf.2022.101919
[38]	A. M. Roy, J. Bhaduri, Real-time growth stage detection model for high degree of occultation using DenseNet-fused YOLOv4, Comput. Electron. Agric., 193 (2022), 106694. https://doi.org/10.1016/j.compag.2022.106694 doi: 10.1016/j.compag.2022.106694

Reader Comments

Your name:*

Email:*
© 2023 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)