Abstract
With the development of smart grids, the use of UAV to inspect power equipment has become one of the hot technologies. However, the current work of troubleshooting is still mainly based on labor. This method is time consuming and laborious, and the accuracy will be affected. Therefore, this paper proposes an infrared image fault identification method based on YOLO target detection algorithm, which is used to detect the state of the power equipment in real time in the video of the inspection, and identify and locate the fault. First, use image enhancement techniques to reduce signal-to-noise ratio, improve fault recognizability, suppress background and other interference. Then, summarize the distribution characteristics of the fault in the image, and select the appropriate candidate box by the method of dimension clustering. And for the problem of high false detection rate caused by environmental impact, the training data sets of different targets and their sizes in various environments are established, which makes the identification of the target more precise. Finally, the feature is extracted by convolutional neural network. Each layer uses the method of batch normalization to standardize the input data, and trains the YOLO network model that can identify infrared faults in many environments. The experimental results show that the model can effectively detect fault targets of different sizes in various environments. The model can be effectively applied in practice.
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
Han, B., Shang, F.: Power tower detection framework model for UAV transmission line inspection. Zhejiang Electr. Power 35(4), 6–11 (2016)
Roverso, D., Nguyenv, N., Jenssen, R.: Automatic autonomous vision-based power line inspection: a review of current status and the potential role of deep learning. Int. J. Electr. Power Energy Syst. 99(7), 107–120 (2018)
Wang, W., Tian, B., Liu, Y., et al.: Research on power component recognition of unmanned aerial vehicle inspection image based on RCNN. Geo-Inf. Sci. 19(2), 256–263 (2017)
Yang, X., Wen, Z.: Research and application of deep learning in fault detection of transmission line insulators. China New Telecommun. 20(10), 208–210 (2018)
Wei, Y., Quan, J., Hou, Y.: Aerial image location of unmanned aerial vehicle based on YOLOv2. Laser Optoelectron. Progr. 5(22), 111002 (2017)
Nordeng, I.E., Hasan, A., Olsen, D., et al.: DEBC detection with deep learning. In: Scandinavian Conference on Image Analysis, Troms, pp. 248–259. Springer, Norway (2017)
Ren, S.Q., He, K.M., Girshick, R., et al.: Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans. Pattern Anal. Mach. Intell. 39(6), 1137–1149 (2017)
Gao, Z., Li, S., Chen, J., et al.: Pedestrian detection method based on YOLO network. Comput. Eng. 44(5), 215–219, 226 (2018)
Liu, W., Anguelov, D., Erhan, D., et al.: SSD: ingle shot multibox detector. In: European Conference on Computer Vision, pp. 21–37. Springer, Amsterdam (2016)
Redmon, J., Divvala, S., Girshick, R., et al.: You only look once: unified, real-time object detection. In: Computer Vision and Pattern Recognition, pp. 779–788. IEEE, Las Vegas (2016)
Redmon, J., Farhadi, A.: YOLO9000: better, faster, stronger. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 6517–6525. IEEE, Hawaii (2017)
Krawczyk, B.: Learning from imbalanced data: open challenges and future directions. Progr. Artif. Intell. 5(4), 1–12 (2016)
Ouyang, W., Wang, X., Zhang, C., et al.: Factors in fine tuning deep model for object detection with long-tail distribution. In: Computer Vision and Pattern Recognition, pp. 864–873. IEEE, Las Vegas (2016)
Zhou, Z., Chen, Q., Ma, B., Qi, D.: An improved YOLO target detection method with its application in cable device abnormal condition recognition. Electr. Meas. Instrum. 12(11), 1–7 (2018)
He, K., Zhang, X., Ren, S., et al.: Spatial pyramid pooling in deep convolutional networks for visual recognition. IEEE Trans. Pattern Anal. Mach. Intell. 37(9), 1904–1916 (2014)
Girshick, R.: Fast R-CNN. In: Proceedings of IEEE International Conference on Computer Vision, pp. 1440–1448. IEEE Press, Washington DC (2015)
Guo, J., Chen, B., Wang, R., Wang, J., Zhong, L.: YOLO-based real-time detection of power line poles from unmanned aerial vehicle Inspection vision. Electr. Power 8(12), 1–7 (2019)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Zhou, F., Ma, Y., Ma, Y., Pan, H. (2020). Infrared Image Fault Identification Method Based on YOLO Target Detection Algorithm. In: Barolli, L., Amato, F., Moscato, F., Enokido, T., Takizawa, M. (eds) Web, Artificial Intelligence and Network Applications. WAINA 2020. Advances in Intelligent Systems and Computing, vol 1150. Springer, Cham. https://doi.org/10.1007/978-3-030-44038-1_42
Download citation
DOI: https://doi.org/10.1007/978-3-030-44038-1_42
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-44037-4
Online ISBN: 978-3-030-44038-1
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)