Title: An abnormal identification method for operation and maintenance personnel of intelligent power distribution room based on monitoring video stream

Authors: Wei Huang; Zhigang Wang; Jianying Liu; Yan Li; Litao Han

Addresses: State Grid Jilin Electric Power Co., Ltd., Liaoyuan Power Supply Company, Liaoyuan, Jilin, China ' State Grid Jilin Electric Power Co., Ltd., Liaoyuan Power Supply Company, Liaoyuan, Jilin, China ' State Grid Jilin Electric Power Co., Ltd., Liaoyuan Power Supply Company, Liaoyuan, Jilin, China ' State Grid Jilin Electric Power Co., Ltd., Liaoyuan Power Supply Company, Liaoyuan, Jilin, China ' State Grid Jilin Electric Power Co., Ltd., Liaoyuan Power Supply Company, Liaoyuan, Jilin, China

Abstract: With the rapid development of intelligent distribution rooms, the abnormal detection of safety helmet wearing by operators has gradually shifted from traditional manual monitoring to online recognition of monitoring videos. This paper proposes an abnormal identification method for operation and maintenance personnel of intelligent power distribution room based on monitoring video stream, which aims to solve the problem of insufficient robustness of the detection model due to the limited professional knowledge and practical experience of the design personnel involved in existing safety helmet wearing detection systems. Firstly, based on safety helmet wearing image data in existing distribution room scenes, a multi-operation-based data augmentation algorithm for safety helmet wearing in distribution rooms is designed to generate training data sources for safety helmet wearing in distribution room environments. Secondly, a distribution room operator safety helmet wearing detection model based on improved Yolov5 is constructed to achieve intelligent detection of unmanned distribution room monitoring images. Finally, simulation experimental results show that the proposed method realises intelligent detection of safety helmet wearing by operation and maintenance personnel in various complex environments of distribution rooms, with high robustness and detection rates.

Keywords: intelligent distribution room; safety helmet detection; image recognition; deep learning; Yolov5.

DOI: 10.1504/IJWMC.2024.136583

International Journal of Wireless and Mobile Computing, 2024 Vol.26 No.1, pp.83 - 91

Received: 09 May 2023
Accepted: 24 Jul 2023
Published online: 07 Feb 2024 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article