A Simple and Effective Surface Defect Detection Method of Power Line Insulators for Difficult Small Objects
Source abstract
Abstract
Insulator defect detection plays a vital role in maintaining the secure operation of power systems. To address the issues of the difficulty of detecting small objects and missing objects due to the small scale, variable scale, and fuzzy edge morphology of insulator defects, we construct an insulator dataset with 1600 samples containing flashovers and breakages. Then a simple and effective surface defect detection method of power line insulators for difficult small objects is proposed. Firstly, a high-resolution feature map is introduced and a small object prediction layer is added so that the model can detect tiny objects. Secondly, a simplified adaptive spatial feature fusion (S-ASFF) module is introduced to perform cross-scale spatial fusion to improve adaptability to variable multi-scale features. Finally, we propose an enhanced deformable attention mechanism (EDAM) module. By integrating a gating activation function, the model is further inspired to learn a small number of critical sampling points near reference points. And the module can improve the perception of object morphology. The experimental results indicate that concerning the dataset of flashover and breakage defects, this method improves the performance of YOLOv5, YOLOv7, and YOLOv8. In practical application, it can simply and effectively improve the precision of power line insulator defect detection and reduce missing detection for difficult small objects.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Advanced Neural Network Applications · Image Enhancement Techniques · Advanced Image and Video Retrieval Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (41)
Show source-provided references
1. Fault detection of insulator based on saliency and adaptive morphology10.1007/s11042-016-3981-2 ↗
2. Insulator surface dirt image detection technology based on improved watershed algorithm
3. Inspection and identification of transmission line insulator breakdown based on deep learning using aerial images10.1016/j.epsr.2022.108199 ↗
4. L. Zhang, B. Q. Li, Y. Cui, Y. S. Lai, and J. Gao, “Research on improved YOLOv8 algorithm for insulator defect detection,” 2023. Accessed: 15 Sep. 2023. [Online]. Available: 10.21203/rs.3.rs-3337929/v110.21203/rs.3.rs-3337929/v1 ↗
5. InsuDet: A fault detection method for insulators of overhead transmission lines using convolutional neural networks10.1109/TIM.2021.3127641 ↗
6. H. Jiang, “Multi-defect detection of transmission line insulators based on YOLOV5 UAV aerial photography,” M.S. dissertation, Guangdong Univ. of Tech., China, 2021.
7. H. Xu, “Research on small target detection and defect identification of transmission lines based on machine vision,” M.S. dissertation, Zhejiang Univ., China, 2022.
8. Nonlinear mechanical model of composite insulator interface and nondestructive testing method for weak bonding defects
9. Real-time detection and spatial localization of insulators for UAV inspection based on binocular stereo vision10.3390/rs13020230 ↗
10. Segmentation of insulator images based on HIS color space
11. The identification and diagnosis of self-blast defects of glass insulators based on multi-feature fusion
12. An active contour model based on texture distribution for extracting inhomogeneous insulators from aerial images10.1109/TGRS.2013.2274101 ↗
13. Target tracking method of transmission line insulator based on multi feature fusion and adaptive scale filter
14. Edge detection of high-voltage porcelain insulators in infrared image using dual parity morphological gradients10.1109/ACCESS.2019.2900658 ↗
15. A method of insulator detection from video sequence
16. Self-shattering defect detection of glass insulators based on spatial features10.3390/en12030543 ↗
17. Rich feature hierarchies for accurate object detection and semantic segmentation
18. Fast R- CNN
19. Faster R-CNN towards real-time object detection with region proposal networks10.1109/TPAMI.2016.2577031 ↗
20. Insulator defect detection based on improved Faster R-CNN
21. You only look once: Unified, real-time object detection
22. A. Bochkovskiy, C. Y. Wang, and H. Y. M. Liao, “YOLOv4: Optimal speed and accuracy of object detection,” arXiv:2004.10934, 2020.
23. ultralytics/yolov5:v6.0-YOLOv5n ‘Nano’ models, Roboflow integration, TensorFlow export, OpenCV DNN support
24. YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors
25. SSD: Single shot multibox detector
26. An Insulator defect detection model in aerial images based on multiscale feature pyramid network
27. An insulator self-blast detection method based on YOLOv4 with aerial images10.1016/j.egyr.2021.11.115 ↗
28. High accuracy real-time insulator string defect detection method based on improved YOLOv510.3389/fenrg.2022.928164 ↗
29. CSPNet: A new backbone that can enhance learning capability of CNN
30. A method for power lines insulator defect detection with attention feedback and double spatial pyramid10.1016/j.epsr.2023.109175 ↗
31. Insulator defect detection based on multi-scale feature coding and dual attention fusion
32. J. Xie, Y. W. Du, Z. J. Liu, H. Liu, T. Y. Wang and M. Mou, “Visible light insulator defect detection algorithm based on lightweight improved YOLOv5s,” 2022. Accessed: 19 Nov. 2022. [Online]. Available: 10.13335/j.10003673.pst.2022.1438
33. Attention is all you need
34. Defect detection model of Angle tower bolts based on Transformer and attention mechanism
35. Foreign body detection in transmission line channel based on the fusion of window self-attention network and YOLOv5
36. X. Z. Zhu, W. J. Su, L. W. Lu, B. Li, X. G. Wang and J. F. Dai, “Deformable DETR: Deformable transformers for end-to-end object detection,” arXiv:2010.04159, 2021.
37. S. Liu, D. Huang, and Y. Wang, “Learning spatial fusion for single-shot object detection,” arXiv:1911.09516, 2019.
38. A DOST based approach for the condition monitoring of 11 kV distribution line insulators10.1109/TDEI.2011.5739465 ↗
39. V. S. Andrel, T. Chaves, and H. Felix, “Unifying Public datasets for insulator detection and fault classification in electrical power lines,” 2020. Accessed: 12 Mar. 2020. [Online]. Available: https://github.com/heitorcfelix/public-insulator-datasets
40. G. Jocher, “Explaining the labels_correlogram.jpg,” 2023. Accessed: 12 Oct. 2021. [Online]. Available: https://github.com/ultralytics/yolov5/issues/5138
41. FINet: An insulator dataset and detection benchmark based on synthetic fog and improved YOLOv5