volume | PIER Journals

Abstract

To improve the work efficiency of on-site inspection personnel in diagnosing faults of power transmission lines, in this paper we propose an infrared image segmentation method based on DeepLabV3+ for identifying key components of transmission line. We collected 556 infrared images of transmission lines in our own power supply system, and expanded the original data by data augmentation method. Based on the comparison of the DeepLabV3+ model with three different backbone networks, MobileNetV2 with the best performance is selected as the main backbone network. Compared with FCN, U-Net and SegNet, the test results show that DeepLabV3+ using MobileNetV2 (compared with ResNet50 and Xception) can segment the five types of key components in power transmission lines from infrared images more accurately and faster. The MIoU on the test set is 0.8624, which is better than the performance of FCN, U-Net and SegNet. This lays a foundation for improving the work efficiency of on-site inspection personnel and improving the continuous power supply capacity, stability and safe operation level of the power grid.

1. Zhao, Z., N. Liu, and L. Wang, "Localization of multiple insulators by orientation angle detection and binary shape prior knowledge," IEEE Transactions on Dielectrics and Electrical Insulation, Vol. 22, No. 6, 3421-3428, 2015.
doi:10.1109/TDEI.2015.004741 Google Scholar

2. Tao, X., D. Zhang, Z. Wang, et al. "Detection of power line insulator defects using aerial images analyzed with convolutional neural networks," IEEE Transactions on Systems Man and Cybernetics Systems, Vol. 50, No. 4, 1486-1498, 2020.
doi:10.1109/TSMC.2018.2871750 Google Scholar

3. Lin, T. and X. Liu, "An intelligent recognition system for insulator string defects based on dimension correction and optimized faster R-CNN," Electrical Engineering, Vol. 103, 541-549, 2021.
doi:10.1007/s00202-020-01099-z Google Scholar

4. Gong, D., T. Ma, J. Evans, and S. He, "Deep neural networks for image super-resolution in optical microscopy by using modified hybrid task cascade U-Net," Progress In Electromagnetics Research, Vol. 171, 185-199, 2021.
doi:10.2528/PIER21110904 Google Scholar

5. Shou, Y., Y. Feng, Y. Zhang, H. Chen, and H. Qian, "Deep learning approach based optical edge detection using ENZ layers," Progress In Electromagnetics Research, Vol. 175, 81-89, 2022.
doi:10.2528/PIER22061403 Google Scholar

6. Zhang, S. C., Y. L. Xu, N. Yang, et al. "Insulator image extraction algorithm based on maximum entropy and Hough transform," East China Electric Power, Vol. 40, No. 4, 595-598, 2012. Google Scholar

7. Zhang, Z. J., Y. Zhang, X. L. Jiang, et al. "A model for predicting ice weight on insulators based on regional segmentation method," High Voltage Technology, Vol. 46, No. 2, 406-412, 2020. Google Scholar

8. Liu, Z. T., J. G. Yin, K. D. Li, et al. "Infrared image segmentation method of insulator string based on watershed algorithm," Electric Porcelain Arrester, Vol. 228, No. 2, 216-221, 2020. Google Scholar

9. Li, H. R., J. Gao, T. Wu, et al. "Research on insulator crack detection based on improved Canny operator," Smart Electric Power, Vol. 49, No. 2, 91-98, 2021. Google Scholar

10. Li, W. P., K. Xie, X. Liao, et al. "Intelligent diagnosis method of infrared image for transformer equipment based on improved faster RCNN," Southern Power System Technology, Vol. 13, No. 12, 79-84, 2019. Google Scholar

11. Zhou, K. H., Z. W. Liao, Y. Y. Xiao, et al. "Construction of infrared image classification model for power equipments based on improved CNN," Infrared Technology, Vol. 41, No. 11, 1033-1038, 2019. Google Scholar

12. Jia, X., J. L. Zhang, and X. B. Wen, "Infrared faults recognition for electrical equipments based on dual supervision signals deep learning," Infrared and Laser Engineering, Vol. 47, No. 7, 0703003-1-7, 2018. Google Scholar

13. Long, J., E. Shelhamer, T. Darrell, et al. "Fully convolutional networks for semantic segmentation," Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 3431-3440, 2015. Google Scholar

14. Ronneberger, O., P. Fischer, and T. Brox, "U-Net: Convolutional networks for biomedical image segmentation," Proceedings of International Conference on Medical Image Computing and Computer-Assisted Intervention, 234-241, 2015. Google Scholar

15. Badrinarayanan, V., A. Kendall, and R. Cioplla, "SegNet: A deep convolutional encoder-decoder architecture for image segmentation," IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 39, No. 12, 2481-2495, 2017.
doi:10.1109/TPAMI.2016.2644615 Google Scholar

16. Chen, L. C., G. Papandreou, I. Kokkinos, et al. "DeepLab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs," IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 40, No. 4, 834-848, 2018.
doi:10.1109/TPAMI.2017.2699184 Google Scholar

17. Xiong, F.-G., X. Zhang, X. Han, et al. "Improved semantic segmentation of remote sensing image," Computer Engineering and Applications, Vol. 58, No. 8, 185-190, 2022. Google Scholar

18. Chen, L. C., Y. Zhu, G. Papandreou, et al. "Encoder-decoder with atrous separable convolution for semantic image segmentation," Proceedings of the European Conference on Computer Vision, 801-818, 2018. Google Scholar

19. Wang, C., "Research on infrared image semantic segmentation based on deep learning,", Ph.D. Dissertation of University of Chinese Academy of Sciences (Shanghai Institute of Technical Physics, Chinese Academy of Sciences), Shanghai, 2017. Google Scholar

20. Chollet, F., "Xception: Deep learning with depthwise separable convolutions," Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 1800-1807, 2017. Google Scholar

21. Sandler, M., A. Howarda, M. L. Zhu, et al. "MobileNetV2: Inverted residuals and linear bottlenecks," Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 4510-4520, 2018. Google Scholar

Dr. Donglei Weng

Dr. Shuliang Dou

Dr. Haozhe Wang

Dr. Dawei Gong

Dr. Qun Wang

Prof. Sailing He