改进YOLOv5混合样本训练的绝缘子伞盘脱落缺陷检测方法

doi:10.3778/j.issn.1002-8331.2302-0165

摘要/Abstract

摘要： 为了实现输电线路巡检时绝缘子串及伞盘脱落缺陷的精准定位和识别，提出了一种基于改进YOLOv5混合样本训练的绝缘子缺陷检测模型。针对绝缘子缺陷图像稀少问题，提出了一种混合样本数据生成方法，通过将GrabCut算法与图像融合技术相结合实现数据集的扩充。针对绝缘子及缺陷的外形特点，利用长边定义法和环形平滑标签（circular smooth label，CSL）重新定义模型特征提取区域的坐标参数。通过增加角度信息，实现更加精确化的特征提取。通过将主干网络（Backbone）中部分特征层与路径聚合网络（path aggregation network，PAN）提取的特征相融合，对CSPDarkNet主干网络进行优化。改进后的YOLOv5 CSPDarkNet模型相较于改进前绝缘子缺陷检测精度提升了2.8个百分点，检测速率为20.5 FPS。实验结果表明，改进的绝缘子缺陷识别方法基本满足实际应用需求。

关键词: 特征融合, YOLOv5, 旋转框, 伞盘脱落缺陷

Abstract: In order to realize the accurate location and identification of insulator string and umbrella plate falling defects during transmission line inspection, this paper proposes an insulator defect detection model based on improved YOLOv5 mixed sample training. Firstly, aiming at the scarcity of insulator defect images, a hybrid sample data generation method is proposed, which combines GrabCut algorithm with image fusion technology to expand the data set. Then, according to the shape characteristics of insulators and defects, the long edge definition method and CSL (circular smooth label) are used to redefine the coordinate parameters of the model feature extraction area. By adding angle information, more accurate feature extraction is realized. Finally, the CSPDarkNet backbone network is optimized by fusing some feature layers in the Backbone with the features extracted by PAN (path aggregation network). The improved YOLOv5 CSPDarkNet model increases the detection accuracy of insulator defects by 2.8 percentage points compared with the improved model, and the detection rate is 20.5 FPS. The experimental results show that the improved insulator defect identification method basically meets the needs of practical application.

Key words: feature fusion, YOLOv5, rotating frame, umbrella plate falling defect

李洵, 甘润东, 钱俊凤, 张世恒, 赵文彬, 王道累. 改进YOLOv5混合样本训练的绝缘子伞盘脱落缺陷检测方法[J]. 计算机工程与应用, 2024, 60(4): 289-297.

LI Xun, GAN Rundong, QIAN Junfeng, ZHANG Shiheng, ZHAO Wenbin, WANG Daolei. Improved YOLOv5 Mixed Sample Training for Detection of Insulator Umbrella Plate Falling Defects[J]. Computer Engineering and Applications, 2024, 60(4): 289-297.

参考文献

[1] PARK K C, MOTAI Y, YOON J R. Acoustic fault detection technique for high-power insulators[J]. IEEE Transactions on Industrial Electronics, 2017, 64(12): 9699-9708.
[2] LIU X, MIAO X, JIANG H, et al. Box-point detector: a diagnosis method for insulator faults in power lines using aerial images and convolutional neural networks[J]. IEEE Transactions on Power Delivery, 2021, 36(6): 3765-3773.
[3] 翁智, 程曦, 郑志强. 基于改进YOLOv3的高压输电线路关键部件检测方法[J]. 计算机应用, 2020, 40(S2): 183-187．
WENG Z, CHENG X, ZHENG Z Q. Detection method of key components of high-voltage transmission lines based on improved YOLOv3[J]. Journal of Computer Applications, 2020, 40(S2): 183-187．
[4] KIM S, CHO K. Efficient pedestrian detection using multi-scale HOG features with low computational complexity[J]. IEICE Transactions on Information & Systems, 2014, 97(2):366-369．
[5] 方路平, 何杭江, 周国民. 目标检测算法研究综述[J]. 计算机工程与应用, 2018, 54(13): 11-18．
FANG L P, HE H J, ZHOU G M. Research overview of object detection methods[J]. Computer Engineering and Applications, 2018, 54(13): 11-18．
[6] MABROUK O, HLAOUA L, OMRI M N. Exploiting ontology information in fuzzy SVM social media profile classification[J]. Applied Intelligence, 2020(1): 3757-3774．
[7] ZHOU H, YU G. Research on fast pedestrian detection algorithm based on autoencoding neural network and AdaBoost[J]. Complexity, 2021(6): 1-17．
[8] 张少平, 杨忠, 黄宵宁, 等. 航拍图像中玻璃绝缘子自爆缺陷的检测及定位[J]. 太赫兹科学与电子信息学报, 2013, 11(4): 609-613．
ZHANG S P, YANG Z, HUANG X N, et al. Detects detection and positioning for glass insulator from aerial images[J]. Journal of Terahertz Science and Electronic Information Technology, 2013, 11(4): 609-613．
[9] 翟荔婷, 张冰怡, 冯志勇, 等. 基于3D塔架配准的绝缘子自爆缺陷检测[J]. 计算机工程与科学, 2016, 38(8): 1688-1694.
ZHAI L T, ZHANG B Y, FENG Z Y, et al. Insulator blew detection based on match of 3D tower[J]. Computer Engineering & Science, 2016, 38(8): 1688-1694．
[10] 蒲天骄, 乔骥, 韩笑, 等. 人工智能技术在电力设备运维检修中的研究及应用[J]. 高电压技术, 2020, 46(2): 369-383．
PU T J, QIAO J, HAN X, et al. Research and application of artificial intelligence in operation and maintenance for power equipment[J]. High Voltage Engineering, 2020, 46(2): 369-383．
[11] YU J, LIU K, HE M, et al. Insulator defect detection: a detection method of target search and cascade recognition[J].Energy Reports, 2021, 7(7): 750-759．
[12] LING Z, ZHANG D, QIU R C, et al.An accurate and real-time method of self-blast glass insulator location based on Faster R-CNN and U-net with aerial images[J]. CSEE Journal of Power and Energy Systems, 2019, 5(4): 474-482．
[13] 王道累, 孙嘉珺, 张天宇, 等. 基于改进生成对抗网络的玻璃绝缘子自爆缺陷检测方法[J]. 高电压技术, 2022, 48(3):1096-1103．
WANG D L, SUN J J, ZHANG T Y, et al. Self-explosion defect detection method of glass insulator based on improved generative adversarial network[J]. High Voltage Engineering, 2022, 48(3): 1096-1103．
[14] HE H, HUANG X L, SONG Y X, et al. An insulator self-blast detection method based on YOLOv4 with aerial images[J]. Energy Reports, 2022, 8(S1): 448-454．
[15] PAN T, JIANG J, YAO J, et al. A novel multi-focus image fusion network with U-shape structure[J]. Sensors, 2020, 20(14): 3901．
[16] HE K, ZHANG X, REN S, et al. Spatial pyramid pooling in deep convolutional networks for visual recognition[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2014, 37(9): 1904-1916．
[17] WEN P, TONG M, DENG Z, et al. Improved helmet wearing detection method based on YOLOv3[C]//Proceedings of the 6th International Conference on Artificial Intelligence and Security, Hohhot, Jul 17-20, 2020. Cham: Springer, 2020: 670-681．
[18] ROTHER C, KOLMOGOROV V, BLAKE A. GrabCut: interactive foreground extraction using iterated graph cuts[J]. ACM Transactions on Graphics, 2004, 23(3): 309-314.
[19] YANG X，YAN J. Arbitrary-oriented object detection with circular smooth label[C]//Proceedings of the 16th European Conference on Computer Vision, Glasgow, Aug 23-28, 2020. Cham: Springer, 2020: 677-694．
[20] 黄新波, 刘新慧, 张烨, 等. 基于红蓝色差和改进K-means算法的航拍绝缘子分类识别方法[J]. 高电压技术, 2018, 44(5): 1528-1534．
HUANG X B, LIU X H, ZHANG Y, et al. Classification recognition method of insulator in aerial image based on the red-blue difference and developed K-means algorithm[J]. High Voltage Engineering, 2018, 44(5): 1528-1534.
[21] REDMON J, FARHADI A. YOLOv3: an incremental improvement[J]. arXiv:1804.02767, 2018．
[22] LIU W, ANGUELOV D, ERHAN D, et al. SSD: single shot multibox detector[C]//Proceedings of the 14th European Conference on Computer Vision, Amsterdam, Oct 11-14, 2016. Cham: Springer, 2016: 21-37.
[23] TAN M, PANG R, LE Q V. EfficientDet：scalable and efficient object detection[C]//Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020．
[24] REN S, HE K, GIRSHICK R, et al. Faster R-CNN: towards real-time object detection with region proposal networks[C]//Advances in Neural Information Processing Systems 28, 2015.
[25] GE Z, LIU S, WANG F, et al. YOLOX: exceeding YOLO series in 2021[J]. arXiv:2107.08430, 2021.