Login Register Cart 0
Generic placeholder image

Recent Advances in Electrical & Electronic Engineering

Editor-in-Chief

ISSN (Print): 2352-0965
ISSN (Online): 2352-0973

Back
Journal Home About Journal Editorial Board Journal Insight Current Issue Volumes/Issues
Subscribe
Research Article

Contrasting YOLOv7, SSD, and DETR on Insulator Identification under Small-sample Learning

Author(s): Yanli Yang*, Xinlin Wang and Weisheng Pan

Volume 17, Issue 8, 2024

Published on: 13 October, 2023

Page: [787 - 796] Pages: 10

DOI: 10.2174/0123520965248875231004060818

Price: $65

conference banner
Abstract

Background: Daily inspections of insulators are necessary because they are indispensable components for power transmission lines. Using deep learning to monitor insulators is a newly developed method. However, most deep learning-based detection methods rely on a large training sample set, which consumes computing resources and increases the workload of sample labeling. The selection of learning models to monitor insulators becomes problematic.

Objective: Through comparative analysis, a model suitable for small-sample insulator learning is found to provide a reference for the research and application of insulator detection.

Methods: This paper compares some of the latest deep learning models, YOLOv7, SSD, and DETR, for insulator detection based on small-sample learning. The small sample here means that the number of samples and their proportion to the total sample are relatively small. Two public insulator image sets, InsulatorDataSet with 600 insulator images and Transmission-line-pictures (TLP) with 1230 insulator images in the natural background are selected to test the performance of these models.

Results: Tests on two public insulator image sets, InsulatorDataSet and TLP, show that the recognition rates of YOLOv7, DETR, and SSD are arranged from high to low. The DETR and the YOLOv7 have stable performance, while the SSD lacks stable performance in terms of the learning time and recognition rate.

Conclusion: The in-domain and cross-domain scenario tests show that YOLOv7 is more suitable for insulator detection under small-sample conditions among the three models.

« Previous Next »
Graphical Abstract

[1]
Y. Yang, L. Wang, Y. Wang, and X. Mei, "Insulator self-shattering detection: A deep convolutional neural network approach", Multimedia Tools Appl., vol. 78, no. 8, pp. 10097-10112, 2019.
[http://dx.doi.org/10.1007/s11042-018-6610-4]
[2]
X. Tao, D. Zhang, Z. Wang, X. Liu, H. Zhang, and D. Xu, "Detection of power line insulator defects using aerial images analyzed with convolutional neural networks", IEEE Trans. Syst. Man Cybern. Syst., vol. 50, no. 4, pp. 1486-1498, 2020.
[http://dx.doi.org/10.1109/TSMC.2018.2871750]
[3]
R. Girshick, J. Donahue, T. Darrell, and J. Malik, "Rich feature hierarchies for accurate object detection and semantic segmentation", In IEEE Conference on Computer Vision and Pattern Recognition, 2014, pp. 580-587
Columbus, Ohio, USA [http://dx.doi.org/10.1109/CVPR.2014.81]
[4]
S. Ren, K. He, R. Girshick, and J. Sun, "Faster R-CNN: Towards real-time object detection with region proposal networks", IEEE Trans. Pattern Anal. Mach. Intell., vol. 39, no. 6, pp. 1137-1149, 2017.
[http://dx.doi.org/10.1109/TPAMI.2016.2577031] [PMID: 27295650]
[5]
Z. Zhao, Z. Zhen, L. Zhang, Y. Qi, Y. Kong, and K. Zhang, "Insulator detection method in inspection image based on improved Faster R-CNN", Energies, vol. 12, no. 7, p. 1204, 2019.
[http://dx.doi.org/10.3390/en12071204]
[6]
Z.N. Ling, R.C. Qiu, Z.J. Jin, Y.H. Zhang, X. He, H.C. Liu, and C. Lei, "An accurate and real-time self-blast glass insulator location method based on Faster R-CNN and U-net with aerial images", arxiv 1801.05143, 2018. http://dx.doi.org/arxiv.org/abs/1801.05143v1
[7]
Q. Wen, Z. Luo, R. Chen, Y. Yang, and G. Li, "Deep learning approaches on defect detection in high resolution aerial images of insulators", Sensors, vol. 21, no. 4, p. 1033, 2021.
[http://dx.doi.org/10.3390/s21041033] [PMID: 33546245]
[8]
T. Lin, and X. Liu, "An intelligent recognition system for insulator string defects based on dimension correction and optimized faster R-CNN", Electr. Eng., vol. 103, no. 1, pp. 541-549, 2021.
[http://dx.doi.org/10.1007/s00202-020-01099-z]
[9]
K. He, G. Gkioxari, P. Dollár, and R. Girshick, "Mask R-CNN", IEEE Trans. Pattern Anal. Mach. Intell., vol. 42, no. 2, pp. 386-397, 2020.
[http://dx.doi.org/10.1109/TPAMI.2018.2844175] [PMID: 29994331]
[10]
Y. Yang, Y. Wang, and H. Jiao, "Insulator identification and self-shattering detection based on mask region with convolutional neural network", J. Electron. Imaging, vol. 28, no. 5, p. 1, 2019.
[http://dx.doi.org/10.1117/1.JEI.28.5.053011]
[11]
J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, "You only look once: Unified, real-time object detection", In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016, pp. 779-788
Las Vegas, Nevada, USA [http://dx.doi.org/10.1109/CVPR.2016.91]
[12]
C.Y. Wang, A. Bochkovskiy, and H.Y.M. Liao, "YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors", arxiv2207.02696v1, 2022. http://dx.doi.org/arxiv.org/abs/2207.02696
[13]
J. Redmon, and A. Farhadi, "YOLO9000: Better, faster, stronger", In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017, pp. 6517-6525 Hawaii, USA
[14]
D. Sadykova, D. Pernebayeva, M. Bagheri, and A. James, "IN-YOLO: Real-time detection of outdoor high voltage insulators using UAV imaging", IEEE Trans. Power Deliv., vol. 35, no. 3, pp. 1599-1601, 2020.
[http://dx.doi.org/10.1109/TPWRD.2019.2944741]
[15]
J. Redmon, and A. Farhadi, "YOLOv3: An incremental improvement", arxiv1506.02640v5, 2018. http://dx.doi.org/arxiv.org/abs/1804.02767
[16]
C. Liu, Y. Wu, J. Liu, and Z. Sun, "Improved YOLOv3 network for insulator detection in aerial images with diverse background interference", Electronics, vol. 10, no. 7, p. 771, 2021.
[http://dx.doi.org/10.3390/electronics10070771]
[17]
S. Chen, C. Su, Z. Kuang, O. Ye, and X. Gong, "Real-time detection of UAV detection image of power line insulator bursting based on YOLOV3", J. Phys. Conf. Ser., vol. 1544, no. 1, p. 012117, 2020.
[http://dx.doi.org/10.1088/1742-6596/1544/1/012117]
[18]
C. Liu, Y. Wu, J. Liu, and J. Han, "MTI-YOLO: A light-weight and real-time deep neural network for insulator detection in complex aerial images", Energies, vol. 14, no. 5, p. 1426, 2021.
[http://dx.doi.org/10.3390/en14051426]
[19]
A. Bochkovskiy, C.Y. Wang, and H. Liao, "YOLOv4: Optimal speed and accuracy of object detection", arxiv2004.10934, 2020. http://dx.doi.org/arxiv.org/abs/2004.10934
[20]
Z. Qiu, X. Zhu, C. Liao, D. Shi, and W. Qu, "Detection of transmission line insulator defects based on an improved lightweight YOLOv4 model", Appl. Sci., vol. 12, no. 3, p. 1207, 2022.
[http://dx.doi.org/10.3390/app12031207]
[21]
G. Han, Q. Yuan, F. Zhao, R. Wang, L. Zhao, S. Li, M. He, S. Yang, and L. Qin, "An improved algorithm for insulator and defect detection based on YOLOv4", Electronics, vol. 12, no. 4, p. 933, 2023.
[http://dx.doi.org/10.3390/electronics12040933]
[22]
"ultralytics/yolov5 Ultralytics", Available from: https://github.com/ultralytics/yolov5
[23]
Y. Yang, and X. Wang, "Insulator self-shattering detection based on YOLOv5 under small sample conditions", J. Phys. Conf. Ser., vol. 2378, no. 1, p. 012073, 2022.
[http://dx.doi.org/10.1088/1742-6596/2378/1/012073]
[24]
Z. Liquan, Z. Mengjun, C. Ying, and J. Yanfei, "Fast detection of defective insulator based on improved YOLOv5s", Comput. Intell. Neurosci., vol. 2022, pp. 1-12, 2022.
[http://dx.doi.org/10.1155/2022/8955292] [PMID: 36097557]
[25]
G. Han, M. He, M. Gao, J. Yu, K. Liu, and L. Qin, "Insulator breakage detection based on improved YOLOv5", Sustainability, vol. 14, no. 10, p. 6066, 2022.
[http://dx.doi.org/10.3390/su14106066]
[26]
J. Gu, J. Hu, L. Jiang, Z. Wang, X. Zhang, Y. Xu, J. Zhu, and L. Fang, "Research on object detection of overhead transmission lines based on optimized YOLOv5s", Energies, vol. 16, no. 6, p. 2706, 2023.
[http://dx.doi.org/10.3390/en16062706]
[27]
Y. Li, M. Ni, and Y. Lu, "Insulator defect detection for power grid based on light correction enhancement and YOLOv5 model", Energy Rep., vol. 8, pp. 807-814, 2022.
[http://dx.doi.org/10.1016/j.egyr.2022.08.027]
[28]
J. Ding, H. Cao, X. Ding, and C. An, "High accuracy real-time insulator string defect detection method based on improved YOLOv5", Front. Energy Res., vol. 10, p. 928164, 2022.
[http://dx.doi.org/10.3389/fenrg.2022.928164]
[29]
J. Zheng, H. Wu, H. Zhang, Z. Wang, and W. Xu, "Insulator-defect detection algorithm based on improved YOLOv7", Sensors, vol. 22, no. 22, p. 8801, 2022.
[http://dx.doi.org/10.3390/s22228801] [PMID: 36433397]
[30]
R. Chang, S. Zhou, Y. Zhang, N. Zhang, C. Zhou, and M. Li, "Research on insulator defect detection based on improved YOLOv7 and multi-UAV cooperative system", Coatings, vol. 13, no. 5, p. 880, 2023.
[http://dx.doi.org/10.3390/coatings13050880]
[31]
W. Liu, D. Anguelov, D. Erhan, C. Szegedy, S. Reed, C.Y. Fu, and A.C. Berg, "SSD: Single shot multiBox detector", European Conference on Computer Vision Springer, pp. 21-37, 2016.
[32]
J. Tan, "Automatic insulator detection for power line using aerial images powered by convolutional neural networks", J. Phys. Conf. Ser., vol. 1748, no. 4, p. 042012-1, 11, 2021.
[http://dx.doi.org/10.1088/1742-6596/1748/4/042012]
[33]
N. Carion, F. Massa, G. Synnaeve, N. Usunier, A. Kirillov, and S. Zagoruyko, "End-to-end object detection with transformers", In European Conference on Computer Vision, 2020, pp. 213-229 Cham, Switzerland
[34]
M.L. Mekhalfi, C. Nicolo, Y. Bazi, M.M.A. Rahhal, N.A. Alsharif, and E.A. Maghayreh, "Contrasting YOLOv5, transformer, and efficientDet detectors for crop circle detection in desert", IEEE Geosci. Remote Sens. Lett., vol. 19, pp. 1-5, 2022.
[http://dx.doi.org/10.1109/LGRS.2021.3085139]
[35]
"Insulator Data/Insulator Data Set", Available from: https://github.com/InsulatorData/InsulatorDataSet
[36]
"chuxizhiyue/Transmission-line-pictures", Available from: https://github.com/chuxizhiyue/Transmission-line-pictures

Rights & Permissions Print Cite
© 2024 Bentham Science Publishers | Privacy Policy