Infrared Image Segmentation Method of Lightning Arrester Casing Based on Deep Learning and Local Perception Attention Mechanism

doi:10.3969/j.issn.1008-0198.2025.02.017

Abstract

Abstract: Addressing the issues of low accuracy and susceptibility to false detection in the existing instance segmentation methods for lightning arrester casing, a deep learning-based lightning arrester casing segmentation and detection method is proposed to achieve end-to-end segmentation inference through the classic neural network model UNet. Additionally, the designed local perception attention module efficiently aggregates the channel and spatial information of the lightning arrester casing infrared image, overcoming the impact of infrared background noise and achieving clear edge segmentation effect. The performance of the model Unet in infrared image segmentation and detection of lightning arrester casings is validated through qualitative and quantitative experimental comparisons. The results show that this model offers superior detection and segmentation performance for lightning arrester casings, which is significant for subsequent fault detection, reducing labor costs, and ensuring the safe operation of substation equipment.

Key words: lightning arrester casing, infrared image, segmentation detection, computer vision, deep learning, attention mechanism

CLC Number:

WANG Shengqi, CHEN Haibo, YE Jinxiang. Infrared Image Segmentation Method of Lightning Arrester Casing Based on Deep Learning and Local Perception Attention Mechanism[J]. Hunan Electric Power, 2025, 45(2): 122-128.

References

[1] HAN Y F,DAI Y,LIU L,et al.Transformer defects detection method based on visible and infrared fusion images[C]//2021 International Conference on Electrical Materials and Power Equipment(ICEMPE). Chongqing,China. IEEE,2021:1-4.
[2] 卢彬,朱海峰,谷振富,等. 基于红外图像的避雷器故障检测方法[J]. 红外,2018,39(1):19.
[3] 寇鸽子. 携红外相机的无人机架空导线图像识别与显示系统[D]. 西安:西安科技大学,2022.
[4] 胡泰山,刘浩,刘刚,等. 基于改进YOLOv3的避雷器红外图像故障检测方法[J]. 红外技术,2023,45(11):1256-1261.
[5] HAN S,YANG F,JIANG H,et al.A smart thermography camera and application in the diagnosis of electrical equipment[J]. IEEE Transactions on Instrumentation and Measurement,2021,70:5012108.
[6] 李博,刘会斌,王胜辉,等. 基于GANR-UNet的绝缘子红外图像分割及低零值故障诊断研究[J/OL]. 华北电力大学学报(自然科学版),1-11.(2024-01-16)[2025-03-03].http://kns.cnki.net/kcms/detail/13.1212.tm.20240115.1750.002.html.
[7] XU C,LI Q W,JIANG X B,et al.Dual-space graph-based interaction network for RGB-thermal semantic segmentation in electric power scene[J]. IEEE Transactions on Circuits and Systems for Video Technology,2022,33(4):1577-1592.
[8] LI B,WANG T,ZHAI Y J,et al.RFIENet:RGB-thermal feature interactive enhancement network for semantic segmentation of insulator in backlight scenes[J]. Measurement,2022,205:112177.
[9] 郭志刚,朱林林,吴俊敏,等. 基于改进机器视觉算法的电力设备红外检测[J]. 电子设计工程,2023,31(17):178-181,186.
[10] 刘赫,赵天成,刘俊博,等. 基于深度残差UNet网络的电气设备红外图像分割方法[J]. 红外技术,2022,44(12):1351-1357.
[11] MA J L,QIAN K,ZHANG X B,et al.Weakly supervised instance segmentation of electrical equipment based on RGB-T automatic annotation[J]. IEEE Transactions on Instrumentation and Measurement,2020,69(12):9720-9731.
[12] SHELHAMER E,LONG J,DARRELL T.Fully convolutional networks for semantic segmentation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(4): 640-651.
[13] 王蕾,朱芬芬,李金萍,等. 融合注意力门控机制的大场景点云语义分割[J]. 激光与红外,2023,53(11):1785-1792.
[14] 亢洁,王勍,刘文波,等. 融合CAT-BiFPN与注意力机制的航拍绝缘子多缺陷检测网络[J]. 高电压技术,20,49(8):3361-3376.
[15] 刘敏,周国亮,王红旭,等. 基于稀疏重构注意力机制的绝缘子缺陷检测方法[J]. 广东电力,2024,37(5):104-111.
[16] 伍艺佳,华雄,王丽蓉,等. 基于注意力机制学习的变电设备缺陷检测方法[J]. 计算机与现代化,2021(2):7-12,17.
[17] GUO M,XU T,LIU J,et al.Attention mechanisms in computer vision:A survey[J]. Computational Visual Media,2022,8(3):331-368.
[18] ETHEM ALPAYDIN.Multilayer perceptrons[J]. Introduction to Machine Learning,2014:267-316.
[19] RONNEBERGER O,FISCHER P,BROX T.U-Net:convolutional networks for biomedical image segmentation[C]//Medical Image Computing and Computer-Assisted Intervention-MICCAI 2015. Cham:Springer International Publishing,2015:234-241.
[20] ZHOU Z W,SIDDIQUEE M M R,TAJBAKHSH N,et al. UNet++:a nested U-Net architecture for medical image segmentation[J]. Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support,2018,11045:3-11.
[21] 张志超,左雷鹏,邹捷,等. 基于多模态图像信息的变电设备红外分割方法[J]. 红外技术,2023,45(11):1198-1206.
[22] CHEN S H,CHEN Z Z,XU X G,et al.Nv-Net:Efficient infrared image segmentation with convolutional neural networks in the low illumination environment[J]. Infrared Physics & Technology,2020,105:103184.