Insulator Detection Method Using YOLO Combining Feature Reuse and Reconstruction

doi:10.19678/j.issn.1000-3428.0068244

Abstract

Abstract:

To overcome challenges such as low generalization performance and difficulty in identifying insulators amidst complex backgrounds in deep learning-based insulator defect detection methods, this study introduces a novel method based on the You Only Look Once (YOLO) with feature Reuse and Reconstruction (YOLO-RR) model, focusing on feature extraction and fusion. Firstly, in the feature extraction stage, a dense35 network is constructed based on DenseNet as the backbone network. By reusing features, the model enhances its perception of feature details, thereby improving detection accuracy under low saturation and low contrast imaging while reducing the number of network parameters. Secondly, in the feature fusion stage, an Hourglass-based Bidirectional Feature Pyramid Network (H-BiFPN) structure is introduced for bidirectional fusion of features at different scales. Through feature reconstruction and fusion, this method enriches feature information of varying scales, addressing the issue of information loss of small targets under continuous convolution and enhancing small target detection accuracy. Finally, the Wise Intersection of Union (WIoU) loss function is employed to optimize the model, enhancing prediction accuracy by focusing on common anchor boxes. Experimental results on the expanded Chinese Power Line Insulator Dataset (CPLID) demonstrate that the YOLO-RR model achieves a recognition rate of 93.6% with network parameters compressed to 5.16×10⁶, outperforming comparative models. The proposed model meets the requirements of accurate localization and real-time performance for insulator defect detection, exhibiting robust detection performance even in scenarios with significant background interference and lighting effects.

Key words: insulator detection, YOLO model, feature reuse, feature reconstruction, lightweight, intelligent inspection

摘要：

针对基于深度学习的绝缘子缺陷检测方法存在泛化性能低、难以识别复杂背景下的绝缘子等问题,从特征提取和融合角度出发,提出一种结合特征重用与重建的YOLO(YOLO-RR)模型的绝缘子缺陷检测方法。首先,在特征提取阶段,以DenseNet为基础构建dense35网络作为主干网络,通过特征的重用增加对特征细节的感知能力,提升了模型在低饱和度和低对比度成像情况下的检测精度,并降低了网络参数量。其次,在特征融合阶段,提出基于沙漏模块的双向特征金字塔网络(H-BiFPN)结构进行不同尺度特征间的双向融合,通过特征重建和融合丰富了不同尺度的特征信息,解决了连续卷积下小目标信息丢失的问题,提升了对小目标的检测精度。最后,使用Wise-交并比(WIoU)损失函数优化模型,通过重点关注普通锚框使预测更加精准。在扩充后的中国输电线路绝缘子数据集(CPLID)上的实验结果表明,YOLO-RR模型识别率达到93.6%,网络参数量压缩至5.16×10⁶,优于对比模型,能够满足绝缘子缺陷定位的准确性和实时性要求,同时在背景干扰较大、受光照影响的成像上也有很好的检测效果。

关键词: 绝缘子检测, YOLO模型, 特征重用, 特征重建, 轻量化, 智能巡检

Lulu YANG, Ping MA, Cong WANG, Xinkai LI, Yue MENG, Hongli ZHANG. Insulator Detection Method Using YOLO Combining Feature Reuse and Reconstruction[J]. Computer Engineering, 2024, 50(7): 303-313.

杨露露, 马萍, 王聪, 李新凯, 孟月, 张宏立. 结合特征重用与重建的YOLO绝缘子检测方法[J]. 计算机工程, 2024, 50(7): 303-313.

/ Recommend / Download Citations

URL: https://www.ecice06.com/EN/10.19678/j.issn.1000-3428.0068244

https://www.ecice06.com/EN/Y2024/V50/I7/303

Figures/Tables 16

Fig.1 YOLO-RR network

Fig.2 dense35 network

Fig.3 Feature channel concatenation

Fig.4 Hourglass block

Fig.5 H-BiFPN structure

Fig.6 Detection effect of YOLOv3-SPP and YOLO-RR models on complete insulator images

Fig.7 Detection effect of YOLOv3-SPP and YOLO-RR models on defect insulator images

Fig.8 Comparison of model generalization performance

Fig.9 Comparison of effectiveness of model feature extraction and fusion

Fig.10 Training index change curve

References 30

1	刘传洋, 吴一全. 基于深度学习的输电线路视觉检测方法研究进展. 中国电机工程学报, 2023, 43 (19): 7423- 7446. URL
	LIU C Y, WU Y Q. Research progress of vision detection methods based on deep learning for transmission lines. Proceedings of the CSEE, 2023, 43 (19): 7423- 7446. URL
2	刘开培, 李博强, 秦亮, 等. 深度学习目标检测算法在架空输电线路绝缘子缺陷检测中的应用研究综述. 高电压技术, 2023, 49 (9): 3584- 3595. URL
	LIU K P, LI B Q, QIN L, et al. Review of application research of deep learning object detection algorithms in insulator defect detection of overhead transmission lines. High Voltage Engineering, 2023, 49 (9): 3584- 3595. URL
3	方挺, 董冲, 胡兴柳, 等. 航拍图像中绝缘子串的轮廓提取和故障检测. 上海交通大学学报, 2013, 47 (12): 1818- 1822. URL
	FANG T, DONG C, HU X L, et al. Contour extraction and fault detection of insulator strings in aerial images. Journal of Shanghai Jiao Tong University, 2013, 47 (12): 1818- 1822. URL
4	TAN P, LI X F, XU J M, et al. Catenary insulator defect detection based on contour features and gray similarity matching. Journal of Zhejiang University-Science A (Applied Physics & Engineering), 2020, 21 (1): 64- 73.
5	赵振兵, 李延旭, 戚银城, 等. 基于动态焦点损失函数和样本平衡方法的绝缘子缺陷检测方法. 电力自动化设备, 2020, 40 (10): 205- 211. URL
	ZHAO Z B, LI Y X, QI Y C, et al. Insulator defect detection method based on dynamic focus loss function and sample balance method. Electric Power Automation Equipment, 2020, 40 (10): 205- 211. URL
6	王胜, 陈文, 匡小兵, 等. 一种基于多特征显著性融合的绝缘子区域检测与定位算法. 计算机应用研究, 2020, 37 (S2): 351- 353. URL
	WANG S, CHEN W, KUANG X B, et al. An insulator region detection and location algorithm based on multi-feature saliency fusion. Application Research of Computers, 2020, 37 (S2): 351- 353. URL
7	陶显, 侯伟, 徐德. 基于深度学习的表面缺陷检测方法综述. 自动化学报, 2021, 47 (5): 1017- 1034. URL
	TAO X, HOU W, XU D. A survey of surface defect detection methods based on deep learning. Acta Automatica Sinica, 2021, 47 (5): 1017- 1034. URL
8	GIRSHICK R. Fast R-CNN[C]//Proceedings of IEEE International Conference on Computer Vision (ICCV). Washington D. C. , USA: IEEE Press, 2015: 1440-1448.
9	REN S Q, HE K M, GIRSHICK R, et al. Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39 (6): 1137- 1149. doi: 10.1109/TPAMI.2016.2577031
10	REDMON J, DIVVALA S, GIRSHICK R, et al. You only look once: unified, real-time object detection[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Washington D. C. , USA: IEEE Press, 2016: 779-788.
11	LIU W, ANGUELOV D, ERHAN D, et al. SSD: single shot multibox detector[C]//Proceedings of European Conference on Computer Vision. Berlin, Germany: Springer, 2016: 21-37.
12	REDMON J, FARHADI A. YOLOv3: an incremental improvement[EB/OL]. [2023-07-17]. https://arxiv.org/abs/1804.02767.
13	LIN T Y, GOYAL P, GIRSHICK R, et al. Focal loss for dense object detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020, 42 (2): 318- 327. doi: 10.1109/TPAMI.2018.2858826
14	吴涛, 王伟斌, 于力, 等. 轻量级YOLOv3的绝缘子缺陷检测方法. 计算机工程, 2019, 45 (8): 275- 280. URL
	WU T, WANG W B, YU L, et al. Insulator defect detection method for lightweight YOLOv3. Computer Engineering, 2019, 45 (8): 275- 280. URL
15	王道累, 张世恒, 袁斌霞, 等. 基于改进YOLOv5的轻量化玻璃绝缘子自爆缺陷检测研究. 高电压技术, 2023, 49 (10): 4382- 4390. URL
	WANG D L, ZHANG S H, YUAN B X, et. al. Research on self-explosion defect detection of lightweight glass insulators based on improved YOLOv5. High Voltage Engineering, 2023, 49 (10): 4382- 4390. URL
16	苟军年, 杜愫愫, 王世铎, 等. 轻量化特征融合的CenterNet输电线路绝缘子自爆检测[J/OL]. 北京航空航天大学学报: 1-13[2023-07-17]. https://doi.org/10.13700/j.bh.1001-5965.2022.0602.
	GOU J N, DU S S, WANG S D, et al. Lightweight feature fusion CenterNet transmission line insulator self-explosion detection[J/OL]. Journal of Beijing University of Aeronautics and Astronautics: 1-13[2023-07-17]. https://doi.org/10.13700/j.bh.1001-5965.2022.0602. (in Chinese)
17	李斌, 屈璐瑶, 朱新山, 等. 基于多尺度特征融合的绝缘子缺陷检测. 电工技术学报, 2023, 38 (1): 60- 70. URL
	LI B, QU L Y, ZHU X S, et al. Insulator defect detection based on multi-scale feature fusion. Transactions of China Electrotechnical Society, 2023, 38 (1): 60- 70. URL
18	HE K M, ZHANG X Y, REN S Q, et al. Spatial pyramid pooling in deep convolutional networks for visual recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 37 (9): 1904- 1916. doi: 10.1109/TPAMI.2015.2389824
19	CHATFIELD K, SIMONYAN K, VEDALDI A, et al. Return of the devil in the details: delving deep into convolutional nets[EB/OL]. [2023-07-17]. https://arxiv.org/abs/1405.3531.
20	HE K M, ZHANG X Y, REN S Q, et al. Deep residual learning for image recognition[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Washington D. C. , USA: IEEE Press, 2016: 770-778.
21	HUANG G, LIU Z, VAN DER MAATEN L, et al. Densely connected convolutional networks[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Washington D. C. , USA: IEEE Press, 2017: 4700-4708.
22	RAMACHANDRAN P, ZOPH B, LE Q V. Swish: a self-gated activation function[EB/OL]. [2023-07-17]. https://arxiv.org/abs/1710.05941v1.
23	LIN T Y, DOLLAR P, GIRSHICK R, et al. Feature pyramid networks for object detection[EB/OL]. [2023-07-17]. https://arxiv.org/abs/1612.03144.
24	LIU S, QI L, QIN H F, et al. Path aggregation network for instance segmentation[C]//Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington D. C. , USA: IEEE Press, 2018: 8759-8768.
25	TAN M X, PANG R M, LE Q V. EfficientDet: scalable and efficient object detection[C]//Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Washington D. C. , USA: IEEE Press, 2020: 10781-10790.
26	NEWELL A, YANG K, DENG J. Stacked hourglass networks for human pose estimation[C//Proceedings of ECCV’16. Berlin, Germany: Springer International Publishing, 2016: 483-499.
27	TONG Z, CHEN Y, XU Z, et al. Wise-IoU: bounding box regression loss with dynamic focusing mechanism[EB/OL]. [2023-07-17]. https://arxiv.org/abs/2301.10051.
28	SELVARAJU R R, COGSWELL M, DAS A, et al. Grad-CAM: visual explanations from deep networks via gradient-based localization[C]//Proceedings of IEEE International Conference on Computer Vision (ICCV). Washington D. C. , USA: IEEE Press, 2017: 336-359.
29	WANG C Y, BOCHKOVSKIY A, LIAO H Y M. YOLOv7: trainable bag-of-freebies sets new state-of-the-art for real-time object detectors[EB/OL]. [2023-07-17]. https://arxiv.org/abs/2207.02696.
30	ZHU X, SU W, LU L, et al. Deformable DETR: deformable transformers for end-to-end object detection[EB/OL]. [2023-07-17]. https://arxiv.org/abs/2010.04159.

[1]	CAI Junmin, LIANG Zhengyou, SUN Yu, CHEN Ziao. Research on Lightweight Point Cloud Classification Based on Deformable 3D Graph Convolution [J]. Computer Engineering, 2024, 50(9): 255-265.
[2]	Rixin RAO, Yiwen WANG, Lizhi ZENG, Xintian TONG, Haitao ZHAO. Lightweight Network Model for Waste Cable Detection [J]. Computer Engineering, 2024, 50(8): 22-30.
[3]	Zhishu YANG, Jianan LIANG, Yongjun CAO, Zhenyu ZHONG, Yonglun HE. Based on Partial Separation and Multiscale Fusion [J]. Computer Engineering, 2024, 50(7): 314-323.
[4]	Xiangquan GUI, Shiqing LIU, Li LI, Qingsong QIN, Tangyan LI. Pedestrian Detection Algorithm for Scenic Spots Based on Improved YOLOv8 [J]. Computer Engineering, 2024, 50(7): 342-351.
[5]	LI Zhijin, TANG Jiahui, YAN Jinfeng. Lightweight Recognition Method Based on Edge Computing [J]. Computer Engineering, 2024, 50(6): 287-295.
[6]	LIU Ruikang, LIU Weiming, DUAN Mengfei, XIE Wei, DAI Yuan. Metro Platform Foreign Object Detection Based on Dual-channel Transformer [J]. Computer Engineering, 2024, 50(4): 197-207.
[7]	LAN Hong, WANG Huizhao. Combining Lightweight and Multiscale Fusion for Traffic Sign Detection Algorithm [J]. Computer Engineering, 2024, 50(10): 381-392.
[8]	Xinyi ZHANG, Fei ZHANG, Bin HAO, Lu GAO, Xiaoying REN. Mask Wearing Detection Algorithm Based on Improved YOLOv5 [J]. Computer Engineering, 2023, 49(8): 265-274.
[9]	Junhao LIU, Meilin WANG, Xing XIE, Yexing SONG, Lihua XU. Leather Defect Detection Algorithm Based on Improved YOLOv5 [J]. Computer Engineering, 2023, 49(8): 240-249.
[10]	CHEN Wenxuan, ZENG Bi, GUO Zhixing. Fall Detection Method Integrating Multi-Feature and Semantic Graph Convolution Network [J]. Computer Engineering, 2023, 49(5): 277-285,294.
[11]	ZHONG Baorong, WU Xialing. Research on Lightweight Human Pose Estimation Based on High-Resolution Network [J]. Computer Engineering, 2023, 49(4): 226-232,239.
[12]	Qingxiang HU, Wenbi RAO, Shengwu XIONG. Lightweight Small Object Detection Algorithm for UAV Remote Sensing Scene [J]. Computer Engineering, 2023, 49(12): 169-177.
[13]	Tianyu CHEN, Chengqian CHU, Siyuan WAN, Yongjing WAN, Jing SUN. Video Intrusion Detection Algorithm Based on Conditional Lightweight Neural Network [J]. Computer Engineering, 2023, 49(12): 152-160.
[14]	Gang LI, Rui SHAO, Mingle ZHOU, Min LI, Honglin WAN. Lightweight Industrial Products Defect Detection Network Based on Attention [J]. Computer Engineering, 2023, 49(11): 275-283.
[15]	ZENG Leiming, HOU Jin, CHEN Zirui, ZHOU Haoran. Lightweight Traffic Sign Detection Network Based on Weak Semantic Segmentation [J]. Computer Engineering, 2022, 48(9): 269-276,285.

Please choose a citation manager

Content to export