Smart Grid Insulator Detection Network Improved based on YOLOv8
Keywords:
Insulator, Object Detection, Prediction offsetAbstract
Insulators are critical components of power transmission lines. Due to environmental changes, insulators may fail, making timely and effective detection of these failures a pressing issue. However, the detection of inclined insulators faces challenges, such as inadequate fitting of detection frames and excessive background noise within the target frames. To address this, this paper proposes an improved inclined insulator detection network (RCAS-YOLOv8). To resolve issues related to feature sparsity and effectiveness, a non-local module with row and column-level sharing is introduced by considering the correlations between feature points. Finally, the task of locating the four vertices of the insulator is completed by summing the predicted offsets of the target frame’s four vertices. Experimental results show that the proposed RCAS-YOLOv8 algorithm has achieved significant improvement in the detection of tilted targets in the Power Line Insulator Dataset (CPLID), with high detection accuracy, in which the APR index of our method reached 0.891.
Downloads
References
X. Zhang, J. An, and F. Chen, “A simple method of tempered glassinsulator recognition from airborne image,” in Proceedings of the IEEE2010 International Conference on Optoelectronics and Image, pp. 127–130, November 2010. doi:10.1109/ICOIP.2010.23.
Q. Wu and J. An, “An active contour model based on texture distri-bution for extracting inhomogeneous insulators from aerial images,”IEEE Trans. Geosci. Remote Sens., vol. 52, pp. 3613–3626, 2014.doi:10.1109/TGRS.2013.2274101.
P. Tan, X.-F. Li, J.-M. Xu, and Y. Ning, “Catenary insulator defect detec-tion based on contour features and gray similarity matching,” J. ZhejiangUniv.-Sci. A, vol. 21, pp. 64–73, 2020. doi:10.1631/jzus.A1900341.
X. Wang and Y. Zhang, “Insulator identification from aerial images usingsupport vector machine with background suppression,” in Proceedings ofthe IEEE 2014 International Conference on Unmanned Aircraft Systems,pp. 892–897, June 2016. doi:10.1109/ICUAS.2016.7502544.
R. Girshick, J. Donahue, T. Darrell, and J. Malik, “Rich featurehierarchies for accurate object detection and semantic segmentation,” inProceedings of the IEEE Conference on Computer Vision and PatternRecognition, pp. 580–587, June 2014. doi:10.1109/CVPR.2014.81.
R. Girshick, “Fast r-cnn,” in Proceedings of the IEEE Conference onComputer Vision and Pattern Recognition, pp. 1440–1448, June 2015.doi:10.1109/ICCV.2015.169.
S. Ren, K. He, R. Girshick, and J. Sun, “Faster r-cnn: Towardsreal-time object detection with region proposal networks,” IEEETrans. Pattern Anal. Mach. Intell., vol. 39, pp. 1137–1149, 2016.doi:10.1109/TPAMI.2016.2577031.
W. Liu, D. Anguelov, D. Erhan, C. Szegedy, S. Reed, C. Fu, andA. Berg, “Ssd: Single shot multibox detector,” in Proceedings of theEuropean Conference on Computer Vision, pp. 21–37, October 2016.doi:10.1007/978-3-319-46448-0_2.
J. Huang, V. Rathod, C. Sun, M. Zhu, A. Korattikara, A. Fathi, I. Fischer,Z. Wojna, Y. Song, S. Guadarrama, and K. Murphy, “Speed/accuracytrade–offs for modern convolutional object detectors,” in Proceedingsof the IEEE Conference on Computer Vision and Pattern Recognition,pp. 3296–3297, July 2017. doi:10.1109/CVPR.2017.351.
J. Redmon and A. Farhadi, “Yolo9000: Better, faster, stronger,” inProceedings of the IEEE Conference on Computer Vision and PatternRecognition, pp. 6517–6525, July 2017. doi:10.1109/CVPR.2017.690.
H. Li, L. Deng, C. Yang, J. Liu, and Z. Gu, “Enhanced yolo v3 tinynetwork for real-time ship detection from visual image,” Ieee Access,vol. 9, pp. 16692–16706, 2021. doi:10.1109/ACCESS.2021.3053956.
A. Bochkovskiy, C. Wang, and H.-Y. M. Liao, “Yolov4: Op-timal speed and accuracy of object detection,” arXiv, 2020.doi:10.48550/arXiv.2004.10934.
Z. Jiang, L. Zhao, S. Li, and Y. Jia, “Real-time object de-tection method based on improved yolov4-tiny,” arXiv, 2020.doi:10.48550/arXiv.2011.04244.
Z. Zhao, G. Xu, and Y. Qi, “Representation of binary fea-ture pooling for detection of insulator strings in infrared images,”IEEE Trans. Dielectr. Electr. Insul., vol. 23, pp. 2858–2866, 2016.doi:10.1109/TDEI.2016.7736846.
S. Liao and J. An, “A robust insulator detection algorithm based on localfeatures and spatial orders for aerial images,” IEEE Geosci. Remote Sens.Lett., vol. 12, pp. 963–967, 2015. doi:10.1109/LGRS.2014.2369525.
F. Gao, J. Wang, Z. Kong, J. Wu, N. Feng, S. Wang, P. Hu,Z. Li, H. Huang, and J. Li, “Recognition of insulator explosionbased on deep learning,” in Proceedings of the IEEE 2017 In-ternational Computer Conference on Wavelet Active Media Tech-nology and Information Processing, pp. 79–82, December 2017.doi:10.1109/ICCWAMTIP.2017.8301453.
Y. Wang, J. Wang, F. Gao, P. Hu, L. Xu, J. Zhang, Y. Yu, J. Xue,and J. Li, “Detection and recognition for fault insulator based on deeplearning,” in Proceedings of the IEEE 2018 International Congress onImage and Signal Processing, BioMedical Engineering and Informatics,October 2018. doi:10.1109/CISP-BMEI.2018.8633245.
X. Li, H. Su, and G. Liu, “Insulator defect recognition based on globaldetection and local segmentation,” IEEE Access, vol. 8, pp. 59934–59946, 2020. doi:10.1109/ACCESS.2020.2982288.
S. Xie, R. Girshick, P. Dollár, Z. Tu, and K. He, “Aggregated residualtransformations for deep neural networks,” in Proceedings of the IEEEConference on Computer Vision and Pattern Recognition, pp. 5987–5995, July 2017. doi:10.1109/CVPR.2017.634.
A. Shrivastava, A. Gupta, and R. Girshick, “Training region-based objectdetectors with online hard example mining,” in Proceedings of the IEEEConference on Computer Vision and Pattern Recognition, pp. 761–769,June 2016. doi:10.1109/CVPR.2016.89.
S. Wang, Y. Liu, Y. Qing, C. Wang, T. Lan, and R. Yao, “De-tection of insulator defects with improved resnest and region pro-posal network,” IEEE Access, vol. 8, pp. 184841–184850, 2020.doi:10.1109/ACCESS.2020.3029857.
Z. Wang, X. Liu, H. Peng, L. Zheng, J. Gao, and Y. Bao, “Rail-way insulator detection based on adaptive cascaded convolutionalneural network,” IEEE Access, vol. 9, pp. 115676–115686, 2021.doi:10.1109/ACCESS.2021.3105419.
L. She, Y. Fan, J. Wang, L. Cai, J. Xue, and M. Xu, “Insula-tor surface breakage recognition based on multiscale residual neu-ral network,” IEEE Trans. Instrum. Meas., vol. 70, pp. 1–9, 2021.doi:10.1109/TIM.2021.3106112.
D. Sadykova, D. Pernebayeva, M. Bagheri, and A. James, “In-yolo:Real-time detection of outdoor high voltage insulators using uavimaging,” IEEE Trans. Power Del., vol. 35, pp. 1599–1601, 2020.doi:10.1109/TPWRD.2019.2944741.
Z. Gao, G. Yang, E. Li, and Z. Liang, “Novel feature fusion module-based detector for small insulator defect detection,” IEEE Sens. J.,vol. 21, pp. 16807–16814, 2021. doi:10.1109/JSEN.2021.3073422.
W. Zhao, M. Xu, X. Cheng, and Z. Zhao, “An insulator in transmis-sion lines recognition and fault detection model based on improvedfaster rcnn,” IEEE Trans. Instrum. Meas., vol. 70, pp. 1–8, 2021.doi:10.1109/TIM.2021.3112227.
D. Zhang, S. Gao, L. Yu, G. Kang, X. Wei, and D. Zhan, “Defgan:Defect detection gans with latent space pitting for high-speed rail-way insulator,” IEEE Trans. Instrum. Meas., vol. 70, pp. 1–10, 2021.doi:10.1109/TIM.2020.3038008.
X. Zhang, Y. Zhang, J. Liu, C. Zhang, X. Xue, H. Zhang, and W. Zhang,“Insudet: A fault detection method for insulators of overhead transmis-sion lines using convolutional neural networks,” IEEE Trans. Instrum.Meas., vol. 70, pp. 1–12, 2021. doi:10.1109/TIM.2021.3120796.
H. Zheng, Y. Sun, X. Liu, C.-L.-T. Djike, J. Li, Y. Liu, J. Ma, K. Xu, andC. Zhang, “Infrared image detection of substation insulators using animproved fusion single shot multibox detector,” IEEE Trans. Power Del.,vol. 36, pp. 3351–3359, 2021. doi:10.1109/TPWRD.2020.3038880.
H. Law and J. Deng, “Cornernet: Detecting objects as paired key-points,” in Proceedings of the European Conference on Computer Vision(ECCV), pp. 734–750, September 2018. doi:10.1007/978-3-030-01264-9_45.
X. Zhou, J. Zhuo, and P. Krähenbühl, “Bottom-up object detectionby grouping extreme and center points,” in Proceedings of the IEEEConference on Computer Vision and Pattern Recognition, pp. 850–859,June 2019. doi:10.1109/CVPR.2019.00094.
X. Zhou, D. Wang, and P. Krähenbühl, “Objects as points,” arXiv, 2019.doi:10.48550/arXiv.1904.07850.
X. Tao, D. Zhang, Z. Wang, X. Liu, H. Zhang, and D. Xu, “Detectionof power line insulator defects using aerial images analyzed withconvolutional neural networks,” IEEE Trans. Syst. Man Cybern.: Syst.,vol. 50, pp. 1486–1498, 2020. doi:10.1109/TSMC.2018.2871750.
