The aim of this paper is to enhance the performance of the target detection model in the insulator defect detection task. The YOLO v8 detection model is first improved by designing the Backbone-DCNv3 module, which is significantly enhanced in feature extraction and target localization capabilities. Meanwhile, the introduction of MPDIoU loss function further improves the detection accuracy of the model. Tests on the same dataset show that compared with the original model and other models in the YOLO series this paper's model exhibits superior performance in key evaluation metrics such as precision rate, recall rate and average precision. They for precision was 91.45%, recall was 89.47%, and mAP was 91.89%, respectively. Compared with the original model, the improvement was 2.13%, 2.02%, and 2.62%, respectively. Therefore, the research in this paper not only provides new ideas and methods in the field of target detection, but also provides strong technical support for the practical engineering application of insulator defect detection.

Sun Xia, Qi Shuo. A Study on Defect Detection of YOLOV8 Insulators Based on Improvements. Academic Journal of Computing & Information Science (2024), Vol. 7, Issue 5: 37-43. https://doi.org/10.25236/AJCIS.2024.070505.

[1] Tang Lu, Wang Shuqing, Wang Niantao, et al. Defect detection of insulators in foggy weather based on improved YOLOX network [J]. High Voltage Electrical Apparatus, 2024, 60(03):223-228. 

[2] Wen Bin, Hu Yiming, Peng Shun, et al. A lightweight network for multi-defect detection of transmission line insulators [J/OL]. Radio Engineering, 2024, 55(05): 1-9. 

[3] Zhang Changle, Jin Jun. Simulation study of insulator fault detection based on YOLOv5s[J]. Electronic Design Engineering, 2024, 32(05):178-182. 

[4] Pan Wei, Wei Chao, Qian Chunyu, et al. An improved model of YOLOv8s for small target detection in UAV view [J/OL]. Computer Engineering and Applications, 2024,1-10. 

[5] Luo Lei, Xie Zhukui. Traffic sign detection algorithm based on improved YOLOv8[J]. Electromechanical Engineering Technology, 2024, 53(03):205-210. 

[6] Li Z, Zhu Y, Sui S, et al. Real-time detection and counting of wheat ears based on improved YOLOv7[J]. Computers and Electronics in Agriculture, 2024, 218108670. 

[7] Xiaoqiang D, Hongchao C, Zenghong M, et al. DSW-YOLO: A detection method for ground-planted strawberry fruits under different occlusion levels[J]. Computers and Electronics in Agriculture, 2023, 214. 

[8] Yang Z, Shen Y, Shen Y . Football referee gesture recognition algorithm based on YOLOv8s[J]. Frontiers in Computational Neuroscience, 2024, 18: 1341234. 

[9] He J, Zhang S, Yang C, et al. Pest recognition in microstates state: an improvement of YOLOv7 based on Spatial and Channel Reconstruction Convolution for feature redundancy and vision transformer with Bi-Level Routing Attention. [J]. Frontiers in plant science, 2024, 15: 1327237. 

[10] Wang Guofa, Pang Yihui, Ren Huaiwei, et al. Research and practice of intelligent mine system engineering and key technology [J]. Coal Journal, 2024, 49(01):181-202.