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

doi:10.1007/s12204-022-2526-2

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

基于人体关键点的室内电力人员安全行为实时检测技术

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 Xingqi^2∗ (方兴其), YU Qian¹ (喻谦), ZHANG Qian¹ (张乾)

(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)
（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

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:

TP29

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 Xingqi^2∗ (方兴其), YU Qian¹ (喻谦), ZHANG Qian¹ (张乾). Real-Time Safety Behavior Detection Technology of Indoors Power Personnel Based on Human Key Points[J]. J Shanghai Jiaotong Univ Sci, 2024, 29(2): 309-315.

References

[1] The National Energy Administration. Accident notification and annual analysis report of December 2020. [EB/OL]. (2021-03-25). http://www.nea.gov.cn/2021-03/25/c 139834495.htm (in Chinese).
[2] NATH N D, BEHZADAN A H, PAAL S G. Deep learning for site safety: Real-time detection of personal protective equipment [J]. Automation in Construction, 2020, 112: 103085.
[3] DONG W T, WANG P, ZOU G W. Application of intelligent safety management and control system in hydropower maintenance industry [J]. Electric Safety Technology, 2021, 23(1): 8-10 (in Chinese). [4] LI P Y. Human action recognition based on Delaunay skeleton model [D]. Changchun: Jilin University, 2011(in Chinese).
[5] LI X S. Abnormal behavior recognition in power generation [D]. Baoding: North China Electric Power University, 2012 (in Chinese).
[6] SIMONYAN K, ZISSERMAN A. Two-stream convolutional networks for action recognition in videos [M]//Advances in neural information processing systems 27. Red Hook: Curran Associates, 2014: 568-576.
[7] NEWELL A, YANG K Y, DENG J. Stacked hourglass networks for human pose estimation [M]//Computer vision–ECCV 2016. Cham: Springer, 2016: 483-499.
[8] AN M, KONG Y H, SHEN H, et al. Action recognition based on deep learning and its application in power system [J]. Electric Power Science and Engineering, 2019, 35(3): 59-65 (in Chinese).
[9] LIN T Y, MAIRE M, BELONGIE S, et al. Microsoft COCO: Common objects in context [M]//Computer vision – ECCV 2014. Cham: Springer, 2014: 740-755.
[10] ANDRILUKA M, PISHCHULIN L, GEHLER P, et al. 2D human pose estimation: New benchmark and state of the art analysis [C]//2014 IEEE Conference on Computer Vision and Pattern Recognition. Columbus: IEEE, 2014: 3686-3693.
[11] CAO Z, HIDALGO G, SIMON T, et al. OpenPose: Realtime multi-person 2D pose estimation using part affinity fields [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021, 43(1): 172-186.
[12] CAO Z, SIMON T, WEI S H, et al. Realtime multiperson 2D pose estimation using part affinity fields [C]//2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu: IEEE, 2017: 1302-1310.
[13] FANG H S, XIE S Q, TAI Y W, et al. RMPE: regional multi-person pose estimation [C]//2017 IEEE International Conference on Computer Vision. Venice: IEEE, 2017: 2353-2362.
[14] SUN K, XIAO B, LIU D, et al. Deep high-resolution representation learning for human pose estimation [C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach: IEEE, 2019: 5686-5696.
[15] ZHAO Y, XIONG Y J, WANG L M, et al. Temporal action detection with structured segment networks [J]. International Journal of Computer Vision, 2020, 128(1): 74-95.
[16] ZHU W T, LAN C L, XING J L, et al. Co-occurrence feature learning for skeleton based action recognition using regularized deep LSTM networks [J]. Proceedings of the AAAI Conference on Artificial Intelligence, 2016, 30(1): 3697-3703.
[17] YAN S J, XIONG Y J, LIN D H. Spatial temporal graph convolutional networks for skeleton-based action recognition [J]. Proceedings of the AAAI Conference on Artificial Intelligence, 2018, 32(1): 7444-7452.
[18] NIEPERT M, AHMED M, KUTZKOV K. Learning convolutional neural networks for graphs [C]//33rd International Conference on Machine Learning. New York: PMLR, 2016: 2014-2023.

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

基于人体关键点的室内电力人员安全行为实时检测技术

PDF (PC)

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 2

Recommended Articles

Metrics

Comments

[1]	GU Wen (顾闻), XU Yi∗ (徐奕). Retinal Vessel Segmentation via Adversarial Learning and Iterative Refinement [J]. J Shanghai Jiaotong Univ Sci, 2024, 29(1): 73-80.
[2]	HAN Yi (韩毅), CAI Jian-hu (蔡建湖), IKOU Kaku, LI Yan-lai (李延来) CHEN Yi-zeng (陈以增), TANG Jia-fu (唐加福). Evolutionary Algorithms for Solving Unconstrained Multilevel Lot-Sizing Problem with Series Structure [J]. Journal of shanghai Jiaotong University (Science), 2012, 17(1): 39-044.