Aiming at the problems of insulator detection such as low recognition accuracy for small targets and the algorithm model is too large and difficult to be deployed to the edge devices. In this paper, a lightweight YOLOv8-ASF-P2 insulator defect detection model is designed. The model introduces the ASF and P2 detection layer, and at the same time according to the idea of ASF to add the P2 detection layer, the new network structure is trained and then pruned. After pruning, the mAP of this algorithm is 89.5%, the model size is 2.1 MB, and the detection speed is 144.9FPS. 1.7% improvement in mAP, 64.7% reduction in model size, and 40% improvement in detection speed compared with the YOLOv8 algorithm, which verifies the effectiveness of the improved method.
Antwi-BekoeELiuGSAinamJP, et al.A deep learning approach for insulator instance segmentation and defect detection. Neural Comput Appl2022; 34(9): 7253–7269.
2.
GaoZSYangGDLiE, et al.Novel feature fusion module-based detector for small insulator defect detection. IEEE Sens J2021; 21(15): 16807–16814.
3.
QiuZBZhuXLiaoCB, et al.Detection of transmission line insulator defects based on an improved lightweight YOLOv4 model. Appl Sci2022; 12(3): 1207.
4.
LiXFSuHSLiuGH. Insulator defect recognition based on global detection and local segmentation. IEEE Access2020; 8: 59934–59946.
5.
ZouZXChenKYShiZW, et al.Object detection in 20 Years: a survey. Proc IEEE2023; 111(3): 257–276.
6.
ZhaoZBZhenZZhangL, et al.Insulator detection method in inspection image based on improved faster R-CNN. Energies2019; 12(7): 1204.
7.
LiaoG-PYangG-JTongW-T, et al. (eds) Study on power line insulator defect detection via improved faster region-based convolutional neural network. In: 2019 IEEE 7th international conference on computer science and network technology (ICCSNT), Dalian, China, 19–20 October 2019. IEEE.
8.
ShuangFWeiSDLiY, et al.Detail R-CNN: insulator detection based on detail feature enhancement and metric learning. IEEE Trans Instrum Meas2023; 72: 1–14.
9.
LingZZhangDQiuRC, 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. CSEE Journal of Power and Energy Systems2019; 5(4): 474–482.
10.
NazirAWaniMA (eds) You only Look once - object detection models: a review. In: 17th INDIACom; 2023 10th International Conference on Computing for Sustainable Global Development, INDIACom 2023, New Delhi, India, 15–17 March 2023. Institute of Electrical and Electronics Engineers Inc.
11.
YanCZhangHLiX, et al.R-SSD: refined single shot multibox detector for pedestrian detection. Appl Intell2022; 52(9): 10430–10447.
12.
YangZSXuZWangYH. Bidirection-Fusion-YOLOv3: an improved method for insulator defect detection using UAV image. IEEE Trans Instrum Meas2022; 71: 1–8.
13.
ZhaMQianWYiW, et al.A lightweight YOLOv4-Based forestry pest detection method using coordinate attention and feature fusion. Entropy2021; 23(12): 1587.
14.
HuangSDongXWangY, et al. (eds) Detection of insulator burst position of lightweight YOLOv5. In: Proceedings of the 8th International Conference on Computing and Artificial Intelligence, 2022.
15.
ZhengJFWuHZhangH, et al.Insulator-defect detection algorithm based on improved YOLOv7. Sensors2022; 22(22): 8801.
16.
MaFWangBDongX, et al.Power vision edge intelligence: power depth vision acceleration technology driven by edge computing. Dianwang Jishu/Power System Technology2020; 44(6): 2020–2029.
17.
HuDAYuMWuXY, et al.DGW-YOLOv8: a small insulator target detection algorithm based on deformable attention backbone and WIoU loss function. IET Image Process2024; 18(4): 1096–1108.
18.
HeMQinLDengXL, et al.MFI-YOLO: multi-fault insulator detection based on an improved YOLOv8. IEEE Trans Power Deliv2024; 39(1): 168–179.
19.
ZhangLLiBQCuiY, et al.Research on improved YOLOv8 algorithm for insulator defect detection. J Real Time Image Process2024; 21(1): 22.
20.
GeZLiuSWangF, et al.YOLOX: exceeding YOLO series in 2021. 2021.
21.
YangKZhangYZhangX, et al.YOLOX with CBAM for insulator detection in transmission lines. Multimed Tool Appl2023; 83(14): 1–19.
22.
KangMTingC-MTingFF, et al.ASF-YOLO: a novel YOLO model with attentional scale sequence fusion for cell instance segmentation. 2023.
23.
LeeJParkSMoS, et al. (eds) Layer-adaptive sparsity for the magnitude-based pruning. In: 9th International Conference on Learning Representations, ICLR2021, 3–7May 2021.Virtual, Online: International Conference on Learning Representations, ICLR.
