Abstract
Aiming at the problems of slow detection rate and low accuracy of traditional transmission line inspection methods, a transmission line target detection model based on improved YOLOv5 is proposed in this paper. Firstly, the Bottleneck module in the Backbone network is replaced to improve the lightweight of the model; then the coordinate attention (CA) module is introduced to design the Backbone network to improve the performance of model detection; finally, the frame regression loss function is changed to improve the accuracy of detection. After the transmission line images are further expanded, the foreign object data sets of transmission line are constructed. Experiments on the above data sets show that: Compared with YOLOv5, the detection accuracy of the optimized model is improved by 6.7%, the mean average precision (mAP) reaches 87.0%, and the detection speed is improved by 16.0%. The YOLOv5 lightweight model proposed in this paper reduces the power consumption of the platform and improves the model detection speed and accuracy. It is more conducive to the deployment of the target detection model in the mobile terminal.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Tan, P., Li, X.F., Xu, J.M., Ma, J.E., Wang, F.J., Ding, J., et al.: Catenary insulator defect detection based on contour features and gray similarity matching. J. Zhejiang Univ. – Sci. A: Appl. Phys. Eng. 21(1), 64–73 (2020)
Jalil, B., Moroni, D., Pascali, M., Salvetti, O.: Multimodal image analysis for power line inspection. In: International Conference on Pattern Recognition and Artificial Intelligence, Beijing, pp. 13–17 (2018)
Jubayer, F., et al.: Detection of mold on the food surface using YOLOv5. Curr. Res. Food Sci. 4, 724–728 (2021)
Yan, B., Fan, P., Lei, X.Y., Liu, Z.J., Yang, F.Z.: A real-time apple targets detection method for picking robot based on improved YOLOv5. Remote Sens. 13(9), 1619 (2021)
Jalil, B., Leone, G.R., Martinelli, M., Moroni, D., Berton, A.: Fault detection in power equipment via an unmanned aerial system using multi modal data. Sensors 19(13), 3014 (2019)
Tao, X., Zhang, D., Wang, Z., Liu, X., Zhang, H., Xu, D.: Detection of power line insulator defects using aerial images analyzed with convolutional neural networks. Trans. Syst. Man Cybern.: Syst. 5(4), 1486–1498 (2020)
Wang, Y., Wang, J., Gao, F., Hu, P., Li, J.: Detection and recognition for fault insulator based on deep learning. In: 2018 11th International Congress on Image and Signal Processing. Bio Medical Engineering and Informatics, Beijing, pp. 1–6 (2018)
Zhao, J.Q., Zhang, X.H., Yan, J.W., Qiu, X.L., Yao, X., Tian, Y.C., et al.: A wheat spike detection method in UAV images based on improved YOLOv5. Remote Sens. 13(16), 3095 (2021)
Perera, R., Guzzetti, D., Agrawal, V.: Optimized and autonomous machine learning framework for characterizing pores, particles, grains and grain boundaries in microstructural images. Comput. Mater. Sci. 196, 110524 (2021)
Chowdhury, P.N., Shivakumara, P., Nandanwar, L., Samiron, F., Pal, U., Lu, T.: Oil palm tree counting in drone images. J. Pre-proof 153, 1–9 (2021)
Ning, Z.X., Wu, X.J., Yang, J., Yang, Y.Q.: MT-YOLOv5: mobile terminal table detection model based on YOLOv5. Conf. Ser. 1978(1), 012010 (2021)
Jiang, H., Qiu, X.J., Chen, J., Liu, X., Zhuang, S.: Insulator fault detection in aerial images based on ensemble learning with multi-level perception. IEEE Access 7, 61797–61810 (2019)
Wang, J.H., Xiao, T., Gu, Q.Y., Chen, Q.: YOLOv5_CSL_F: YOLOv5’s loss improvement and attention mechanism application for remote sensing image object detection. In: 2021 International Conference on Wireless Communications and Smart Grid, pp. 197–203 (2021)
Liu, J.J., Liu, C.Y., Wu, Y.Q., Xu, H.J., Sun, Z.: An improved method based on deep learning for insulator fault detection in diverse aerial images. Energies 14(14), 4365 (2021)
Han, K., Wang, Y.H., Tian, Q., Guo, J., Xu, C.: Ghost net: more features from cheap operations. In: 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Washington, pp. 1580–1589 (2020)
Zha, M.F., Qian, W.B., Yi, W.L., Hua, J.: A lightweight YOLOv4-based forestry pest detection method using coordinate attention and feature fusion. Entropy 23(12), 1587 (2021)
Zou, Z., Shi, Z., Guo, Y., Ye, J.: Object detection in 20 years: a survey. IEICE Transactions on Fundamentals of Electronics. Communications and Computer Sciences (2019)
Wang, C.Y., Liao, H.Y.M., Wu, Y.H., Chen, P.Y., Yeh, I.H.: CSP net: a new backbone that can enhance learning capability of CNN. In: 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, Washington, pp. 390–391 (2020)
He, K.M., Zhang, X.Y., Ren, S.Q., Sun, J.: Spatial pyramid pooling in deep convolutional networks for visual recognition. IEEE Trans. Pattern Anal. Mach. Intell. 379(9), 1904–1920 (2014)
Liu, S., Qi, L., Qin, H., Shi, J., Jia, J.: Path aggregation network for instance segmentation. In: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Utah, pp. 8759–8761 (2018)
Tang, J.L., Liu, S.B., Zheng, B., Zhang, J., Wang, B., Yang, M.K.: Smoking behavior detection based on improved YOLOv5s algorithm. In: The 9th IEEE International Symposium on Next-Generation Electronics, Changsha, pp. 1–4 (2021)
Rezatofighi, H., Gwak, N., Gwak, J.Y., Sadeghian, A., Savarese, S.: Generalized intersection over union: a metric and a loss for bounding box regression. In: 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition, California, pp. 658–666 (2019)
Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You Only Look Once: unified, real-time object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, New York, pp. 779–788 (2016)
Wang, X.Z., Wei, J.Y., Liu, Y., Li, J.H., Zhang, Z., Chen, J.Y., et al.: Research on morphological detection of FR I and FR II radio galaxies based on improved YOLOv5. Universe 7(7), 211 (2021)
Acknowledgments
We acknowledge funding from the Special Project of Cultivating Scientific and Technological Innovation Ability of University and Middle School Students (Grant No. 2021H011404), the Special Project of Cultivating Scientific and Technological Innovation Ability of University and Middle School Students (Grant No. 2021H010203), the Hebei College and Middle School Students Science and Technology Innovation Ability Cultivation Special Project (Grant No. 22E50075D) and the Sub Project of National Key R&D Plan Covid-19 Patient Rehabilitation Training Posture Monitoring Bracelet Based on 4G Network (Grant No. 2021YFC0863200-6).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Wang, Z., Xie, X., Wang, X., Zhao, Y., Ma, L., Yu, P. (2023). A Robot Foreign Object Inspection Algorithm for Transmission Line Based on Improved YOLOv5. In: Xu, Y., Yan, H., Teng, H., Cai, J., Li, J. (eds) Machine Learning for Cyber Security. ML4CS 2022. Lecture Notes in Computer Science, vol 13657. Springer, Cham. https://doi.org/10.1007/978-3-031-20102-8_11
Download citation
DOI: https://doi.org/10.1007/978-3-031-20102-8_11
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-20101-1
Online ISBN: 978-3-031-20102-8
eBook Packages: Computer ScienceComputer Science (R0)