Abnormal Object Detection of the Transmission Lines with YOLOv5 and Federated Learning

Kaihong Zhang1; Yimin Zhou2

10.1109/ICDL55364.2023.10364445

2023

IEEE International Conference on Development and Learning (ICDL)

978-1-6654-7076-6

2023 IEEE International Conference on Development and Learning (ICDL)

512-517

9-11 Nov. 2023

Macau, China

345 E 47TH ST, NEW YORK, NY 10017 USA

IEEE

Detecting abnormal object intrusions of the transmission lines in a timely and effective manner is of great significance for the safe operation of the electrical power grid. However, due to the particularity and privacy policy of the power grid companies, there is a lack of available and effective dataset with open source. Besides, individuals tend to gather data in their commonly own regions, which would lead to data silos. In this paper, a dataset of the abnormal object intrusions of the transmission lines is first configured to meet the model training requirements. An improved abnormal object detection (AOD) method is proposed utilizing the federated learning. The FasterNet backbone and partial convolution are incorporated to improve the YOLOv5 based model detection speed. Further, the loss function Wise-IoU (WIoU) and Squeeze & Excitation Networks (SE) are applied to enhance the detection precision. Finally, the distributed training strategy of the federated learning is applied to overcome the data silos. Through the ablation experiments, practicality together with merits of the suggested approach are validated on the federated learning platform, achieving a delicate balance between the detection accuracy and speed with comparison analysis for the abnormal object detection in the transmission lines.

Abnormal object detection YOLOv5 Federated learning Transmission lines

第一

英语

EI ; CPCI-S

National Natural Science Foundation of China["61973296","U1913201"] ; Shenzhen Science and Technology Innovation Commission Project["JSGG20210802154535003","JCYJ20220818101206015"] ; Guangdong Basic and Applied Basic Research Foundation[2021B1515120038]

Behavioral Sciences ; Computer Science ; Robotics

Behavioral Sciences ; Computer Science, Artificial Intelligence ; Robotics

WOS:001172928700080

20240415433287

Deep learning ; Electric power transmission ; Electric power transmission networks ; Object detection ; Object recognition

Ergonomics and Human Factors Engineering:461.4 ; Electric Power Transmission:706.1.1 ; Electric Power Lines and Equipment:706.2 ; Data Processing and Image Processing:723.2

IEEE

1.Southern University of Science and Technology, Shenzhen, China
2.Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China

Kaihong Zhang,Yimin Zhou. Abnormal Object Detection of the Transmission Lines with YOLOv5 and Federated Learning[C]. 345 E 47TH ST, NEW YORK, NY 10017 USA:IEEE,2023:512-517.