Foreign-Object Detection in High-Voltage Transmission Line Based on Improved YOLOv8m
Source abstract
Abstract
The safe operation of high-voltage transmission lines ensures the power grid’s security. Various foreign objects attached to the transmission lines, such as balloons, kites and nesting birds, can significantly affect the safe and stable operation of high-voltage transmission lines. With the advancement of computer vision technology, periodic automatic inspection of foreign objects is efficient and necessary. Existing detection methods have low accuracy because foreign objects attached to the transmission lines are complex, including occlusions, diverse object types, significant scale variations, and complex backgrounds. In response to the practical needs of the Yunnan Branch of China Southern Power Grid Co., Ltd., this paper proposes an improved YOLOv8m-based model for detecting foreign objects on transmission lines. Experiments are conducted on a dataset collected from Yunnan Power Grid. The proposed model enhances the original YOLOv8m by incorporating a Global Attention Module (GAM) into the backbone to focus on occluded foreign objects, replacing the SPPF module with the SPPCSPC module to augment the model’s multiscale feature extraction capability, and introducing the Focal-EIoU loss function to address the issue of high- and low-quality sample imbalances. These improvements accelerate model convergence and enhance detection accuracy. The experimental results demonstrate that our proposed model achieves a 2.7% increase in mAP_0.5, a 4% increase in mAP_0.5:0.95, and a 6% increase in recall.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Advanced Neural Network Applications · Power Line Inspection Robots · Industrial Vision Systems and Defect Detection
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Information Science and Engineering, Yunnan University, Kunming 650504, China
Electric Power Research Institute, Yunnan Power Grid Co., Ltd., Kunming 650214, China
Yunnan Key Laboratory of Intelligent Systems and Computing, Kunming 650504, China
Funding
Key R&D Projects of Yunnan Province · Natural Science Foundation of China · Yunnan Provincial Department of Science and Technology-Yunnan University Joint Special Project for Double-Class Construction · Application and Foundation Project of the Yunnan Province
References (45)
Show source-provided references
1. Real-time Rendering Algorithm Optimization for Large-scale Power Transmission Line Scenes Based on LOD
2. A Comprehensive Review on Intelligent Processing of Visible Light Images for Power Overhead Line Inspection
3. Improving YOLOv3’s Foreign Object Detection Method for Transmission Lines
4. A Transmission Line Foreign Object Detection Method Based on Visual Saliency Analysis
5. Research on Foreign Object Detection on Transmission Lines Based on UAV Aerial Images
6. A Comprehensive Review on UAV-based Smart Inspection Technology for Power Transmission Lines
7. Unmanned Aerial Vehicle Intelligent Inspection System for Power Lines Based on Cloud-Fog Edge Heterogeneous Collaboration
8. Girshick, R., Donahue, J., Darrell, T., and Malik, J. (2014, January 23–28). Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Columbus, OH, USA.10.1109/CVPR.2014.81 ↗
9. Girshick, R. (2015, January 7–13). Fast R-CNN. Proceedings of the 2015 IEEE International Conference on Computer Vision and Pattern Recognition, Santiago, Chile.10.1109/ICCV.2015.169 ↗
10. Faster R-CNN: Towards real-time object detection with region proposal networks10.1109/TPAMI.2016.2577031 ↗
11. Redmon, J., Divvala, S., Cirshick, R., and Farhadi, A. (2015, January 7–12). You only look once: Unified, real-time object detection. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Boston, MA, USA.10.1109/CVPR.2016.91 ↗
12. Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C., and Berg, A. (2016, January 10–16). SSD:single shot multibox detector. Proceedings of the European Conference on Computer Vision and Pattern Recognition, Amsterdam, The Netherlands.10.1007/978-3-319-46448-0_2 ↗
13. Lin, T., Goyal, P., Girshick, R., He, K., and Dollar, P. (2017, January 21–26). Focal loss for dense object detection. Proceedings of the IEEE International Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.10.1109/ICCV.2017.324 ↗
14. Redmon, J., and Farhadi, A. (2017, January 21–26). YOLO900:Better, faster, stronger. In Proceeding of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.10.1109/CVPR.2017.690 ↗
15. Redmon, J., and Farhadi, A. (2018, January 18–22). YOLOv3:An incremental improve. In Proceeding of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.
16. Bochkovskiy, A., Wang, C., and Liao, H. (2020). Yolov4: Optimal speed and accuracy of object detection. arXiv.
17. Ultralytics (2020, April 24). YOLOv5 Object Detection. Available online: https://github.com/ultralytics/yolov5.
18. Ge, Z., Liu, S., Wang, F., Li, Z., and Sun, J. (2021). YOLOX: Exceeding YOLO Series in 2021. arXiv.
19. Wang, C., Yeh, I., and Liao, H. (2021). You Only Learn One Representation: Unified Network for Multiple Tasks. arXiv.
20. Li, C., Li, L., Jiang, H., Weng, K., Geng, Y., Li, L., Ke, Z., Li, Q., Cheng, M., and Nie, W. (2022). YOLOv6: A Single-Stage Object Detection Framework for Industrial Applications. arXiv.
21. Ding, X., Zhang, X., Ma, N., Han, J., Ding, G., and Sun, J. (2021, January 19–25). RepVGG: Making VGG-style ConvNets Great Again. In Proceeding of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Online.10.1109/CVPR46437.2021.01352 ↗
22. Gevorgyan, Z. (2022). SIoU Loss: More Powerful Learning for Bounding Box Regression. arXiv.
23. Wang, C., Bochkovskiy, A., and Liao, H. (2023, January 15–17). YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. In Proceeding of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Oxford, UK.10.1109/CVPR52729.2023.00721 ↗
24. Wang, C., Liao, H., and Yeh, I. (2022). Designing Network Design Strategies Through Gradient Path Analysis. arXiv.
25. Ultralytics (2023, July 17). YOLOv8 Object Detection. [Online]. Available online: https://ultralytics.com/yolov8.
26. Liu, Y., Shao, Z., and Hoffmann, N. (2021, January 19–25). Global Attention Mechanism: Retain Information to Enhance Channel-Spatial Interactions. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Online.
27. Online Monitoring of Ice Thickness on Transmission Lines using Image Edge Detection
28. Real-Time Image-Identification-Based Anti-Manmade Misoperation System for Substations10.1109/TPWRD.2012.2190428 ↗
29. Recognition of Foreign Objects on Transmission Lines based on Aerial Images
30. Method for Detecting Line Breaks and Foreign Object Defects on Transmission Lines Based on Drone Images
31. Foreign Object Detection on High-voltage Poles based on Deep Learning
32. A Deep Learning Method to Detect Foreign Objects for Inspecting Power Transmission Lines10.1109/ACCESS.2020.2995608 ↗
33. A Method for Monitoring and Identifying Intrusions of Foreign Objects on Transmission Lines based on Deep Learning Networks
34. Yu, Y., Qiu, Z., Zhou, Y., Zhu, X., and Wang, Q. (2022). Transmission Line Foreign Object Detection Based on Convolutional Neural Network and ECOC-SVM. Smart Power, 50.
35. Yu, Y., Qiu, Z., Liao, H., Wei, Z., Zhu, X., and Zhou, Z. (2022). A Method Based on Multi-Network Feature Fusion and Random Forest for Foreign Objects Detection on Transmission Lines. Appl. Sci., 12.10.3390/app12104982 ↗
36. An Improved YOLO Network for Detection of Small Foreign Objects on Transmission Lines
37. A Lightweight YOLOv4-EDAM Model for Accurate and Real-time Detection of Foreign Objects Suspended on Power Lines10.1109/TPWRD.2022.3213598 ↗
38. Improved YOLOX Foreign Object Detection Algorithm for Transmission Lines10.1155/2022/5835693 ↗
39. Foreign Objects Identification of Transmission Line Based on Improved YOLOv710.1109/ACCESS.2023.3277954 ↗
40. Detection of High Voltage Transmission Line Foreign Objects based on Improved YOLOv4 Algorithm
41. Tang, C., Dong, H., Huang, Y., Han, T., Fang, M., and Fu, J. (2023). Foreign object detection for transmission lines based on Swin Transformer V2 and YOLOX. Vis. Comput., 1432–2315.10.1007/s00371-023-03004-8 ↗
42. Improved YOLOv5s model for key components detecion of power transmission lines10.3934/mbe.2023334 ↗
43. Cheng, Q., Yuan, G., Chen, D., Xu, B., Chen, E., and Zhou, H. (2023). Transmission Lines Small-Target Detection Algorithm Research Based on YOLOv5. Appl. Sci., 13.10.20944/preprints202306.1543.v1 ↗
44. Optimized YOLOv7-tiny model for smoke detection in power transmission lines10.3934/mbe.2023853 ↗
45. Woo, S., Park, J., Lee, J.-Y., and Kwoen, I.S. (2018, January 8–14). CBAM: Convolutional Block Attention Module. Proceedings of the Springer Conference on European Conference on Computer Vision, Munich, Germany.10.1007/978-3-030-01234-2_1 ↗