ABSTRACT
In order to solve the problems of low detection accuracy and high missed detection rate caused by complex background and scale changes in insulator images in aerial photography, this study proposes an improved YOLOv5-CMW algorithm to achieve accurate detection of target insulators. Firstly, utilizing cross local connectivity to achieve multi-scale feature fusion and obtain feature data of the target at different scale levels. In addition, for insulator defects with smaller targets, the backbone network combines a multi-scale adaptive feature attention module to dynamically adjust the importance of feature channels, enhancing the model's ability to represent features. Subsequently, the WIoU loss function was used to train the network, improving the stability of the model and accelerating the convergence process. Experimental data shows that compared with current mainstream single-level detection algorithms, our model can achieve detection accuracy of 94.2%, detection integrity of 93%, and average accuracy of 94.9%. Compared with YOLOv5s, the accuracy has increased by 3.0%, the recall rate has increased by 4.1%, and the average accuracy has increased by 4.5%. This improved technology has shown broad application potential in the field of insulator defect detection in power systems.
- Chen Wenwen, Zhu Ju. 2023. Research on insulator fault detection based on image processing technology [J]. Electrical Technology and Economy., 46-48.Google Scholar
- Wang Yinli, Yan Bin. 2014. Visual based detection and localization of insulator "string drop" defects [J] Computer Engineering and Design, 35 (02): 583-58.Google Scholar
- Shang Junping, Li Chuxin and Chen. 2017. Liang Visual based insulator positioning and self explosion defect detection [J] Journal of Electronic Measurement and Instrumentation, 31 (06): 844-849.Google Scholar
- Li Ji, Liu Le, Niu Yuxiao, etc. 2022. An attention-integrated YOLOv3 insulator string identification method [J]. High Voltage Electronics., 58(11):67-74.Google Scholar
- Lei, Xusheng and Zhehao Sui. 2019. Intelligent fault detection of high voltage line based on the Faster RCNN [J]. Measurement, 138: 379-385.Google ScholarCross Ref
- Wang Suzhen, Zhao Lin, Shao Mingwei, etc. 2022 A transmission line insulator identification method based on improved YOLOv5 [J]. Electronic Measurement Technology., 45(21):181-188.Google Scholar
- Wang He, Wang Gang, Yang Fengyong, etc. 2023. Mask recognition based on improved YOLOv5 target detection algorithm [J]. Automation Technology and Application., 1-5+62.Google Scholar
- Li Menghao and Yuan Sannan. 2023. Improved YOLOv5s traffic sign detection algorithm [J/OL] Journal of Nanjing University of Information Technology (Natural Science Edition), 1-13.Google Scholar
- Üzen, H., Turkoglu, M., Aslan, M. 2023. Depth-wise Squeeze and Excitation Block-based Efficient-Unet model for surface defect detection [J]., Visual Computer, 1745-1764.Google Scholar
- Mohamed M. Farag,Mariam Fouad and Amr T. Abdel-Hamid. 2022. Automatic Severity Classification of Diabetic Retinopathy Based on DenseNet and Convolutional Block Attention Module [J]. IEEE Access, 38299-38308.Google ScholarCross Ref
- Li Wei, Gao Lin. 2023. Improved process flow detection algorithm for RetinaNet [J/OL]. Journal of Electronic Measurement and Instrumentation:1-10.Google Scholar
- Huang Zijie, Ouyang, Jiang Degang, etc. 2023. A lightweight deep learning algorithm for surface quality inspection of traction seat welds[J/OL]. Computer Applications:1-9.Google Scholar
Index Terms
- Research on Defect Detection of Insulators in Transmission Lines Based on Improved YOLOv5
Recommendations
Research on Target Detection Method Based on Improved YOLOv5
Web Information Systems and ApplicationsAbstractAt present, various target detection algorithms are used in detection and classification. It is a problem to improve the accuracy and speed of target detection by using deep learning and neural network model to train the parameters of the data ...
Research on PCB Defect Detection Algorithm Based on Improved YOLOv5
RICAI '22: Proceedings of the 2022 4th International Conference on Robotics, Intelligent Control and Artificial IntelligencePrinted circuit boards (PCB) are defective in industrial manufacturing. To address the current problem of low accuracy of small target defect detection, a YOLOv5 improvement algorithm for more accurate small target detection is proposed to improve the ...
Research on tile surface defect detection by improved YOLOv5
Traditional methods for detecting surface defects on ceramic tiles result in misdetection and missed detection, which makes it difficult to guarantee product stability and consistency within the same batch. Therefore, this article proposes an improved ...
Comments