Abstract
To address object occlusion resulting from the density of multiple fittings in transmission lines, a novel graph convolution detection method based on orientation reasoning is proposed. Firstly, the spatial relationship between different categories of fittings was analyzed through a UAV inspection shooting standard. The relative category orientation concept was introduced to express the orientation relationship between the structures of fittings in a data-driven manner. To incorporate spatial orientation information into the deep learning model, the visual features of ROI (region of interest) results were treated as nodes of a spatial connection graph. The regional orientation adjacency matrix obtained by adaptive learning was integrated as relations of the graph. Subsequently, a graph convolutional network was employed to establish the orientation reasoning model. Experimental results were conducted on a dataset(14 categories of fittings). The proposed model outperformed other advanced object detection models in terms of overall detection effect. Compared to the baseline model, the proposed model increased mean average precision by 6.3%. Ablation experiments further confirmed that each module contributes to the improved detection effect. This proposed approach combines advantages of orientation reasoning and graph convolutional networks to enhance average detection accuracy and effectively overcome object occlusion issue.
Similar content being viewed by others
Data availability
The author is not authorized to share this dataset.
References
Ahmed, M., Mohanta, J., Sanyal, A.: Inspection and identification of transmission line insulator breakdown based on deep learning using aerial images. Electr. Power Syst. Res. 211, 108199 (2022). https://doi.org/10.1016/j.epsr.2022.108199
Bochkovskiy, A., Wang, C.-Y., Liao, H.-Y. M.: Yolov4: Optimal speed and accuracy of object detection. arXiv:2004.10934, (2020)
Carolina, G., Andrew, R., Serge, B.: (0). Object categorization using co-occurrence, location and appearance, . (pp. 3552–3559)
Guo, Y.: Study on the extraction method of high-speed railway contact insulator based on contour fluctuation law. Electr. Eng. Technol. 43, 66-71+78 (2016)
Hu, W., Jing, Y.: Recommendation algorithm based on fusion of kl divergence and js divergence similarity. J. Harbin Univ. Commerce (Natl. Sci. Ed.) 36, 48–53 (2020)
Jiang, C., Xu, H., Liang, X., Lin, L.: Hybrid knowledge routed modules for large-scale object detection. arXiv:1810.12681, (2018)
Jing, Y., Liu, J., Liu, Z., Li, S.: Application Research on Split Bregman Algorithm in Edge Detection of Remote Sensing Image. Ph.D. thesis (2017)
Kipf, T.-N., Welling, M.: Semi-supervised classification with graph convolutional networks. arXiv:1609.02907, 2016 (2016)
Li, T., Tian, W., Lei, L., Bing, L., Li, T.: Simulation and experiment research of fittings power loss in high voltage transmission line. In: 2017 1st International Conference on Electrical Materials and Power Equipment (ICEMPE) (2017)
Li, X., Lei, L.: Causes and preventive measures of galloping of overhead transmission lines. Instrumentation Technology (pp. 41–43) (2019)
Lin, T.-Y., Goyal, P., Girshick, R., He, K., Dollár, P.: Focal loss for dense object detection. In Proceedings of the IEEE International Conference on Computer Vision (pp. 2980–2988) (2017)
Liu, C., Ma, X., Zheng, Y., Su, J., Yang, X., Wang, D.: Application of uav in power transmission line inspection based on 5g technology. Electric Power Inf. Commun. Technol. 19, 44–49 (2021)
Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.-Y., Berg, A. C.: Ssd: Single shot multibox detector. In European Conference on Computer Vision (pp. 21–37). Springer (2016)
Liu, Y., Lu, Y., Gao, S.: Edge Detection on Infrared Image of High Voltage Porcelain Disc Type Suspension Insulator Strings. Ph.D. thesis (2020)
Miao, J., Wang, J., Zhang, H., Miao, Q.: Review of the development of fault diagnosis technology for unmanned aerial vehicle. Chin. J. Sci. Instrum. 41, 56–69 (2020)
Pfeifer, N., Kizilcay, M., Malicki, P.: Analytical and numerical study of an iron-core shunt-compensation reactor on a mixed transmission line. Electr. Power Syst. Res. 220, 109315 (2023). https://doi.org/10.1016/j.epsr.2023.109315
Qi, Y., Wu, X., Zhao, Z., Shi, B., Nie, L.: Bolt defect detection for aerial transmission lines using faster r-cnn with an embedded dual attention mechanism. Chin. J. Image Graph. 26, 2594–2604 (2021)
Qi, Y., Zhao, X., Geng, S.: Transmission line image fitting detection based on occlusion relationship reasoning. J. Intell. Syst. 17, 1154–1162 (2022)
Ren, S., He, K., Girshick, R., Sun, J.: Faster r-cnn: Towards real-time object detection with region proposal networks. arXiv:1506.01497, (2015)
Song, W., Zuo, D.: Corrosion defect detection of earthquake hammer for high voltage transmission line. Proceedings of the 18th Youth Academic Conference of China Instrumentation Society, (pp. 113–117) (2016)
Sun, P., Zhang, R., Jiang, Y., Kong, T., Xu, C., Zhan, W., Luo, P.: Sparse r-cnn: End-to-end object detection with learnable proposals. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 14454–14463) (2021)
Ting, F., Xin, J., Hu, X., Wang, P., Chong, D.: A Fast Insulator-Contour-Detection-Algorithm on Power Transmission Lines Images. Ph.D. thesis Shaoxing, China (2012)
Xu, H., Jiang, C., Liang, X., Lin, L., Li, Z.: Reasoning-rcnn: Unifying adaptive global reasoning into large-scale object detection (2019)
Zhai, Y., Yang, X., Zhao, Z., Wang, Q., Zhao, W.: Faster r-cnn transmission line fitting detection with co-occurrence reasoning. J. Intell. Syst. 16, 237–246 (2021)
Zhang, Y., Wu, G., Liu, Z., Yang, S., Xu, W.: Transfer learning of transmission line damper and clamp detection based on yolov3 network. Comput. Appl. 40, 188–194 (2020)
Zhao, Z., Wang, L.: Aerial insulator string image automatic location method. Chin. J. Sci. Instrum. 35, 558–565 (2014)
Zhao, Z., Xiong, J., Li, B., Wang, Y., Zhang, S.: Typical fittings and its partial defect detection method based on improved cascade r-cnn. High Voltage Technol. 48, 1060–1067 (2022)
Zhao, Z., Xiong, J., Xu, H.: Fusion-structured reasoning deep model for detection of transmission line fittings and their defects. High Voltage Eng. 49, 3346–3353 (2023). https://doi.org/10.13336/j.1003-6520.hve.20230241
Zhu, B., Wang, J., Jiang, Z., Zong, F., Liu, S., Li, Z., Sun, J.: Autoassign: Differentiable label assignment for dense object detection. arXiv:2007.03496 (2020a)
Zhu, H., Han, Z., Liu, C., Zhang, Y., Pan, S., Hou, X., Zhou, S.: Simulation analysis of synthetic electric field of uhv transmission line under mountain fire condition. Electr. Power Syst. Res. 222, 109490 (2023). https://doi.org/10.1016/j.epsr.2023.109490
Zhu, X., Su, W., Lu, L., Li, B., Wang, X., Dai, J.: Deformable detr: Deformable transformers for end-to-end object detection. arXiv:2010.04159 (2020b)
Funding
This work is supported in part by the National Natural Science Foundation of China (NSFC) under Grant Number U21A20486, 61871182, by the Natural Science Foundation of Hebei Province of China under Grant Number F2021502013, F2020502009, F2021502008, by Beijing Natural Science Foundation under Grant Number 4192055.
Author information
Authors and Affiliations
Contributions
We finished the job together.
Corresponding author
Ethics declarations
Conflict of interest
The authors declare no conflicts of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Zhai, Y., Chen, N., Guo, C. et al. Graph convolution detection method of transmission line fitting based on orientation reasoning. SIViP 18, 3603–3614 (2024). https://doi.org/10.1007/s11760-024-03025-3
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11760-024-03025-3