Real-Time Recognition of Dangerous Human Actions Using Lightweight Pose Estimation and Spatio-Temporal Graph Networks

Tiantian Miao

doi:10.54254/2755-2721/2025.LD26338

Applied and Computational EngineeringOpen access

Real-Time Recognition of Dangerous Human Actions Using Lightweight Pose Estimation and Spatio-Temporal Graph Networks

Research Article

Open Access

Real-Time Recognition of Dangerous Human Actions Using Lightweight Pose Estimation and Spatio-Temporal Graph Networks

Tiantian Miao ^1*

¹ Liangjiang International College, Chongqing University of Technology, 201100

^*Corresponding author: 19112170654@163.com

Published on 26 August 2025

ACE Vol.179

ISSN (Print): 2755-273X

ISSN (Online): 2755-2721

ISBN (Print): 978-1-80590-184-6

ISBN (Online): 978-1-80590-129-7

Download Cover

Abstract

Identification of dangerous human actions is of vital importance for safety monitoring. In response to the limitations of traditional methods, this study has developed an efficient pedestrian dangerous behavior recognition system, aiming to enhance monitoring capabilities and having practical application value. The study adopts a modular design, consisting of four core modules: human detection, posture estimation, behavior recognition, and result output. It can detect and warn of five dangerous behaviors such as throwing objects and climbing obstacles in real time. Among them, the posture estimation module addresses the shortcomings of the classic HRNet by adopting the improved SCite-HRNet model. This model optimizes computational efficiency and feature expression ability, ensuring accuracy (COCOval2017 dataset AP value of 65.9) while significantly reducing computational load (parameter quantity is only 18% of MobileNetV2), significantly improving its applicability on mobile devices. Experimental verification has demonstrated the effectiveness of the model improvement. The system is developed using PyTorch on the Ubuntu system, utilizing CUDA acceleration and multi-threading processing. It achieves a real-time processing speed of at least 25 frames per second on the RTX 2080Ti graphics card. Tests based on 15,000 multi-scenario labeled images show that the system has good robustness in complex environments. The system provides an intuitive visual monitoring interface, and the final classification accuracy reaches 99%.

Keywords:

Action recognition, Pose estimation, Graph neural networks, Lightweight models, Real-time systems

View PDF

References

[1]. YUSHAN LI. Research on Human Action Recognition Method Based on Machine Learning [J]. Highlights in Science, Engineering and Technology, 2024.

[2]. QUNYING HE, LAN SHAN. Action Recognition Method Based on Graph Neural Network [C]. //2023 2nd International Conference on Machine Learning, Cloud Computing and Intelligent Mining (MLCCIM), 2023, : 144-148.

[3]. ZHENGYI MA, HAO ZHANG, YINGSHUO FENG, et al. Hazardous action recognition system based on blazepose and ST-recurrent neural network [C]. //Artificial Intelligence and Big Data Forum, 2023, : 1259311 - 1259311-6.

[4]. DI WANG, ZHONGLIN YANG, GAOTIAN LIU. Research on Human Action Recognition Based on Edge Intelligence [C]. //2024 4th International Conference on Artificial Intelligence, Robotics, and Communication (ICAIRC), 2024, : 1058-1064.

[5]. SAIFUDDIN SAIF, EBISA D WOLLEGA, SYLVESTER A KALEVELA. Spatio-Temporal Features based Human Action Recognition using Convolutional Long Short-Term Deep Neural Network [J]. International Journal of Advanced Computer Science and Applications, 2023.

[6]. XINGTAO BAI, NINGGUO WANG, YONGLIANG LI, et al. Research on Power Safety Monitoring Action Recognition Algorithm Through Neural Network and Deep Learning [C]. //2024 IEEE 4th International Conference on Power, Electronics and Computer Applications (ICPECA), 2024, : 990-994.

[7]. TAO WANG. Research on deep learning-based action recognition and quantitative assessment method for sports skills [J]. Applied Mathematics and Nonlinear Sciences, 2024.

[8]. HAONAN LIU, WENZHEN KUANG. Research on deep learning-based instruction action recognition method for assistant duty officers [C]. //Other Conferences, 2023, : 127901P - 127901P-5.

References

[1]. YUSHAN LI. Research on Human Action Recognition Method Based on Machine Learning [J]. Highlights in Science, Engineering and Technology, 2024.

[7]. TAO WANG. Research on deep learning-based action recognition and quantitative assessment method for sports skills [J]. Applied Mathematics and Nonlinear Sciences, 2024.

[8]. HAONAN LIU, WENZHEN KUANG. Research on deep learning-based instruction action recognition method for assistant duty officers [C]. //Other Conferences, 2023, : 127901P - 127901P-5.

Cite this article

Miao,T. (2025). Real-Time Recognition of Dangerous Human Actions Using Lightweight Pose Estimation and Spatio-Temporal Graph Networks. Applied and Computational Engineering,179,37-43.

Data availability

The datasets used and/or analyzed during the current study will be available from the authors upon reasonable request.

About volume

Volume title: Proceedings of CONF-MLA 2025 Symposium: Intelligent Systems and Automation: AI Models, IoT, and Robotic Algorithms

ISBN: 978-1-80590-184-6(Print) / 978-1-80590-129-7(Online)

Editor: Hisham AbouGrad

Conference website: https://www.confmla.org/london.html

Conference date: 17 November 2025

Series: Applied and Computational Engineering

Volume number: Vol.179

ISSN: 2755-2721(Print) / 2755-273X(Online)

© 2024 by the author(s). Licensee EWA Publishing, Oxford, UK. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license. Authors who publish this series agree to the following terms:

1. Authors retain copyright and grant the series right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this series.

2. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the series's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this series.

3. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See Open access policy for details).