(49-5) 16 * << * >> * Русский * English * Содержание * Все выпуски

DFW-YOLO: A small insulator target defect detection algorithm based on improved YOLOv8s
S.X. Liu 1,2, L. Zhang 1

School of Electrical Engineering, Shanghai Dianji University,
201306, Shanghai, China, Shuihua Road 300;
The Key Laboratory of Cognitive Computing and Intelligent Information Processing of Fujian Education Institutions, Wuyi University,
354300, Fujian, China, Wuyi Avenue 16

  PDF, 4707 kB

DOI: 10.18287/2412-6179-CO-1600

Страницы: 835-843.

Язык статьи: English.

Аннотация:
With the continuous progress of deep learning technology, UAV aerial photography faces significant challenges for insulator defect detection. Aiming at the problems of low detection accuracy of existing target detection algorithms and difficulty in recognizing small target defects, we propose an improved small target insulator defect detection algorithm based on YOLOv8s, named DFW-YOLO. Firstly, the Detect_Efficient lightweight detection header is proposed using partial convolution (PConv) to lighten the original detection header. Secondly, a FocalModulation focal modulation module is introduced into the backbone network to enhance the model’s extraction and fusion capabilities for features at different scales. Finally, to enhance the model’s focus on poor-quality samples and reduce the harmful gradients they produce, a loss function with a Wise-IoU V3 dynamic non-monotonic focusing mechanism is used instead of the original CIOU loss function. We conducted experiments on a publicly available dataset of UAV aerial photography. According to the experimental data, DFW-YOLO achieves an 86.8% mAP in insulator defect detection, showing a 6.8% improvement compared to the original YOLOv8s model and generally exceeding the performance of other prominent models. Utilizing this method can effectively boost the accuracy of identifying insulator defects in small targets.

Ключевые слова:
Deep learning, YOLOv8, insulator defect detection, focus modulation, pconv, Wise-IoU V3.

Citation:
Liu SX, Zhang L. DFW-YOLO: A small insulator target defect detection algorithm based on improved YOLOv8s. Computer Optics 2025; 49(5): 835-843. DOI: 10.18287/2412-6179-CO-1600.

References:

  1. Liu KP, Li BQ, Qin L, Li Q, Zhao F, Wang QL, Xu ZP, Yu JY. Review of application research of deep learning object detection algorithms in insulator defect detection of overhead transmission lines. High Volt Eng 2023; 49(9): 3584-3595. DOI: 10.13336/j.1003-6520.hve.20220273.
  2. Gouda OE, Darwish MMF, Mahmoud K, Lehtonen M, Elkhodragy TM. Pollution severity monitoring of high voltage transmission line insulators using wireless device based on leakage current bursts. IEEE Access 2022; 10: 53713-53723. DOI: 10.1109/ACCESS.2022.3175515.
  3. Liu J, Hu MM, Dong JY, Lu X. Summary of insulator defect detection based on deep learning. Electr Pow Syst Res 2023; 224: 109688. DOI: 10.1016/j.epsr.2023.109688.
  4. Jin IJ, Lim DY, Bang IC. Development of fault diagnosis for nuclear power plant using deep learning and infrared sensor equipped UAV. Ann Nucl Energy 2023; 181: 109577. DOI: 10.1016/j.anucene.2022.109577.
  5. Al-Qubaydhi N, Alenezi A, Alanazi T, Senyor A, Alanczi N, Alotaibi B, Alotaibi M, Razaque A, Hariri S. Deep learning for unmanned aerial vehicles detection: A review. Comput Sci Rev 2024; 51: 100614. DOI: 10.1016/j.cosrev.2023.100614.
  6. Kamarulzaman AMM, Jaafar WSWM, Said MNM, Saad SNM, Mohan M. UAV implementations in urban planning and related sectors of rapidly developing nations: A review and future perspectives for Malaysia. Remote Sens 2023; 15(11): 2845. DOI: 10.3390/rs15112845.
  7. Deng C. The method of insulator defect recognition based on group theory. IEEE Access 2021; 9: 96380-96389. DOI: 10.1109/ACCESS.2021.3095382.
  8. Tian F, Hao Y, Zou Z, Zheng Y, He W, Yang L, Li L. An ultrasonic pulse-echo method to detect internal defects in epoxy composite insulation. Energies 2019; 12(24): 4804. DOI: 10.3390/en12244804.
  9. Chaou AK, Mekhaldi A, Teguar M. Elaboration of novel image processing algorithm for arcing discharges recognition on hv polluted insulator model. IEEE Trans Dielectr Electr Insul 2015; 22(2): 990-999. DOI: 10.1109/TDEI.2015.7076800.
  10. Liu Y, Guo Y, Fan Y, Zhou J, Li Z, Xiao S, Zhang X, Wu G. Optical imaging technology application in transmission line insulator monitoring: A review. IEEE Trans Dielectr Electr Insul 2024; 31(6): 3120-3132. DOI: 10.1109/TDEI.2024.3351093.
  11. Zheng R, Zhu L, Hu T, Li J. Detection of fault insulator of power transmission line based on region-CNN. 2020 35th Youth Academic Annual Conf of Chinese Association of Automation (YAC) 2020: 73-76. DOI: 10.1109/YAC51587.2020.9337692.
  12. Li J, Niu Y-X. Method of insulator detection based on improved faster R-CNN. 2023 6th International Conf on Electronics Technology (ICET) 2023: 1127-1133. DOI: 10.1109/ICET58434.2023.10211953.
  13. Hao K, Chen G, Zhao L, Li Z, Liu Y, Wang C. An insulator defect detection model in aerial images based on multiscale feature pyramid network. IEEE Trans Instrum Meas 2022; 71: 3522412. DOI: 10.1109/TIM.2022.3200861.
  14. Liu Y, Huang X, Liu D. Weather-domain transfer-based attention YOLO for multi-domain insulator defect detection and classification in UAV images. Entropy 2024; 26(2): 136. DOI: 10.3390/e26020136.
  15. Wang X, Zhang Y. Insulator identification from aerial images using support vector machine with background suppression. 2016 Int Conf on Unmanned Aircraft Systems (ICUAS) 2016: 892-897. DOI: 10.1109/ICUAS.2016.7502544.
  16. Zhao Z-Q, Zheng P, Xu S-t, Wu X. Object detection with deep learning: A review. IEEE Trans Neural Netw Learn Syst 2019; 30(11): 3212-3232. DOI: 10.1109/TNNLS.2018.2876865.
  17. Zhang R, Li W, Mo T. Review of deep learning. arXiv Preprint. 2018. Source: <https://arxiv.org/abs/1804.01653>. DOI: 10.48550/arXiv.1804.01653.
  18. Archana R, Jeevaraj PSE. Deep learning models for digital image processing: a review. Artif Intell Rev 2024; 57: 11. DOI: 10.1007/s10462-023-10631-z.
  19. Zou Z, Chen K, Shi Z, Guo Y, Ye J. Object detection in 20 years: A survey. Proc IEEE 2023; 111(3): 257-276. DOI: 10.1109/JPROC.2023.3238524.
  20. Bharati P, Pramanik A. Deep learning techniques – R-CNN to mask R-CNN: A survey. In Book: Das AK, Nayak J, Naik B, Pati SK, Pelusi D, eds. Computational Intelligence in Pattern Recognition. Proceedings of CIPR 2019. Singapore: Springer Nature Singapore Pte Ltd; 2020: 657-668. DOI: 10.1007/978-981-13-9042-5_56.
  21. He K, Zhang X, Ren S, Sun J. Spatial pyramid pooling in deep convolutional networks for visual recognition. IEEE Trans Pattern Anal Mach Intell 2015; 37(9): 1904-1916. DOI: 10.1109/TPAMI.2015.2389824.
  22. Girshick R. Fast R-CNN. 2015 IEEE Intl Conf on Computer Vision (ICCV) 2015: 1440-1448. DOI: 10.1109/ICCV.2015.169.
  23. Ren S, He K, Girshick R, Sun J. Faster R-CNN: Towards real-time object detection with region proposal networks. IEEE Trans Pattern Anal Mach Intell 2017; 39(6): 1137-1149. DOI: 10.1109/TPAMI.2016.2577031.
  24. He K, Gkioxari G, Dollar P, Cirshick R. Mask R-CNN. 2017 IEEE Int Conf on Computer Vision (ICCV) 2017: 2980-2988. DOI: 10.1109/ICCV.2017.322.
  25. Zhao W, Xu M, Cheng X, Zhao Z. An insulator in transmission lines recognition and fault detection model based on improved faster RCNN. IEEE Trans Instrum Meas 2021; 70: 5016408. DOI: 10.1109/TIM.2021.3112227.
  26. Ling Z, Zhang D, Qiu RC, Jin Z, Zhang Y, He X, Liu H. An accurate and real-time method of self blast glass insulator location based on faster R-CNN and U-Net with aeria images. CSEE J Power Energy Syst 2019; 5(4): 474-482. DOI: 10.17775/CSEEJPES.2019.00460.
  27. Ming Zhou, Jue Wang, and Bo Li. ARG-mask RCNN: An infrared insulator fault-detection network based on improved mask RCNN. Sensors 2022; 22(13): 4720. DOI: 10.3390/s22134720.
  28. Liu W, Anguelov D, Erhan D, Szegedy C, Reed S, Fu C-Y, Berg AC. SSD: Single shot multibox detector. In Book: Leibe B, Matas J, Sebe N, Welling M, eds. Computer Vision-ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, 0ctober 11-14, 2016, Proceedings, Part I. Cham, Switzerland: Springer International Publishing AG; 2016: 21-37. DOI: 10.1007/978-3-319-46448-0_2.
  29. Wang S, Liu Y, Qing Y, Wang C, Lan T, Yao R. Detection of insulator defects with improved resnest and region proposal network. IEEE Access 2020; 8: 184841-184850. DOI: 10.1109/ACCESS.2020.3029857.
  30. Luan S, Li C, Xu P, Huang Y, Wang X. MI-YOLO: More information based YOLO for insulator defect detection. J Electron Imaging 2023; 32(4): 043014. DOI: 10.1117/1.JEI.32.4.043014.
  31. He M, Qin L, Deng X, Liu K. MFI-YOLO: Multi-fault insulator detection based on an improved YOLOv8. IEEE Trans Power Del 2024; 39(1): 168-179. DOI: 10.1109/TPWRD.2023.3328178.
  32. Zhang Q, Zhang J, Li Y, Zhu C, Wang G. IL-YOLO: An efficient detection algorithm for insulator defects in complex backgrounds of transmission lines. IEEE Access 2024; 12: 14532-14546. DOI: 10.1109/ACCESS.2024.3358205.
  33. Ding L, Rao ZQ, Ding B, Li SJ. Research on defect detection method of railway transmission line insulators based on GC-YOLO. IEEE Access 2023; 11: 102635-102642. DOI: 10.1109/ACCESS.2023.3316266.
  34. Chen J, Kao S-h, He H, Zhuo W, Wen S, Lee CH, Chan S-HG. Run, don’t walk: chasing higher FLOPS for faster neural networks. 2023 IEEE/CVF Conf on Computer Vision and Pattern Recognition (CVPR) 2023: 12021-12031. DOI: 10.1109/CVPR52729.2023.01157.
  35. Yang J, Li C, Dai X, Gao J. Focal modulation networks. NIPS'22: Proc 36th Int Conf on Neural Information Processing Systems 2022: 4203-4217.
  36. Tong Z, Chen Y, Xu Z, Yu R. Wise-IoU: bounding box regression loss with dynamic focusing mechanism. arXiv Preprint. 2023. Source: <https://arxiv.org/abs/2301.10051>. DOI: 10.48550/arXiv.2301.10051.
  37. Zhang Z-D, Zhang B, Lan Z-C, Liu H-C, Li D-Y, Pei L, Yu W-X. FINet: An insulator dataset and detection benchmark based on synthetic fog and improved YOLOv5. IEEE Trans Instrum Meas 2022: 71: 6006508. DOI: 10.1109/TIM.2022.3194909.

© 2009, IPSI RAS
Россия, 443001, Самара, ул. Молодогвардейская, 151; электронная почта: journal@computeroptics.ru; тел: +7 (846) 242-41-24 (ответственный секретарь), +7 (846) 332-56-22 (технический редактор), факс: +7 (846) 332-56-20