J Shanghai Jiaotong Univ Sci ›› 2024, Vol. 29 ›› Issue (2): 309-315.doi: 10.1007/s12204-022-2526-2

• Energy and Power Engineering • Previous Articles     Next Articles

Real-Time Safety Behavior Detection Technology of Indoors Power Personnel Based on Human Key Points


YANG Jian1 (杨坚), LI Congmin2 (李聪敏), HONG Daojian1 (洪道鉴), LU Dongqi1 (卢东祁), LIN Qiujia3 (林秋佳), FANG Xingqi2∗ (方兴其), YU Qian1 (喻谦), ZHANG Qian1 (张乾)   

  1. (1. State Grid Zhejiang Taizhou Power Supply Company, Taizhou 318000, Zhejiang, China; 2. Department of Automation, Shanghai Jiao Tong University, Shanghai 200240, China; 3. Zhejiang Huayun Information Technology Co., Ltd., Hangzhou 310012, China)
  2. (1. 国网浙江省电力有限公司台州供电公司,浙江 台州 318000;2. 上海交通大学 自动化系,上海200240;3. 浙江华云信息技术有限公司,杭州 310012)
  • Received:2021-06-18 Accepted:2021-08-20 Online:2024-03-28 Published:2024-03-28

Abstract: Safety production is of great significance to the development of enterprises and society. Accidents often cause great losses because of the particularity environment of electric power. Therefore, it is important to improve the safety supervision and protection in the electric power environment. In this paper, we simulate the actual electric power operation scenario by monitoring equipment and propose a real-time detection method of illegal actions based on human body key points to ensure safety behavior in real time. In this method, the human body key points in video frames were first extracted by the high-resolution network, and then classified in real time by spatial-temporal graph convolutional network. Experimental results show that this method can effectivel detect illegal actions in the simulated scene.

Key words: real-time behavior recognition, human key points, high-resolution network, spatial-temporal graph convolutional network

摘要: 安全生产对电力企业和社会的发展具有重要意义。由于电力环境的特殊性,发生事故往往造成重大损失,因此加强电力环境中的人员安全管控具有重要意义。本文中,我们模拟实际的电力操作场景视频监控,并提出了一种基于人体关键点的非法行为实时检测方法,以实时确保人员的安全行为。该方法首先通过高分辨率网络提取视频帧中的人体关键点,然后通过时空图卷积网络进行实时分类。实验结果表明,该方法能够有效地检测模拟场景中的人员非法操作行为。

关键词: 实时行为识别,人体关键点,高分辨率网络,时空图卷积网络

CLC Number: