An attempt at fall detection on an embedded device based on YOLOv8n-pose
,
,
,
and
*
Article Sidebar
Full Text: 
PDF
Main Article Content
Abstract
Human-action recognition aims to identify the actions performed by individuals. Due to the broad spectrum of human activities, action recognition covers a wide range. Among all, fall detection is a critical aspect of surveillance, particularly in environments where individuals are at risk. Throughout the years, several sensors, data types, and classification techniques have been investigated to address this issue. This paper proposes a lightweight fall detection designed to process sequences of images in real-time. This system is deployed on an embedded device, specifically the Jetson nano. Our goal is to construct a comprehensive dataset that accurately detects falls in various lighting conditions. The proposed system is constructed using YOLOv8n-pose, which have been trained to identify people using widely recognized dataset. Our methodology includes the design and implementation of the YOLOv8n-pose, data collection, and rigorous testing to ensure the accuracy of fall detection in real-time using surveillance camera. The experimental results show that high detection accuracy and acceptable timing capabilities are achieved.
Article Details
Conflict of Interest
© 2026 The authors. This is an open access article distributed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License.
References
Arulalan, V., Muralidharan, C., Sahayaraj, K. K. A., & Garg, P. (2024). Vision based fall detection model using Raspberry Pi, In International Conference on Innovations and Advances in Cognitive Systems, pp. 369-382.
Buckland, M, & Gey, F. (1994). The relationship between recall and precision, Journal of the American society for information science, 45(1), 12-19.
Dorsey, E. R., & Bloem, B. R (2024). Parkinson’s disease is predominantly and enviromental disease, Journal of Parkinson’s Disease, 14(3), 451-465.
Dong, C., & Du, G. (2024). An enhanced real-time human pose estimation method based on modified YOLOv8 framwork, Scientific Reports, 14(1), 8012.
Herbers, C., Zhang, R., Erdman, A., & Johnson, M. D (2024). Distinguishing features of Parkinson’s disease fallers based on wireless insole plantar pressure monitoring, npj Parkinson's Disease, 10(1), 67.
Paul, S. S., Harvey, L., Canning, C. G., Boufous, S., Lord, S. R., Close, J. C. T., & Sherrington, C. (2017). Fall-related hospitalization in people with Parkinson’s disease, European journal of neurology, 24(3), 523-529.
Sohan, M., Sai Ram, T., Reddy, R., & Venkata, C. (2024). A review on YOLOv8 and its advancements, In International Conference on Data Intelligence and Cognitive Informatics, 529-545.
Selcuk, B., & Serif, T. (2023).A comparison of YOLOv5 and YOLOv8 in the context of mobile UI detection, In International Conference on Mobile Web and Intelligent Information Systems, pp. 161-174.
Wang, Y., Chi, Z., Liu, M., Li, G., & Ding, S.. (2023). High performance lightweight fall detection with an improved YOLOv5s algorithm, Machines, 11(8), 818.
De Miguel, K., Brunete, A., Hernando, M., & Gambao, E. (2017). Home camera-based fall detection system for the elderly, Sensors, 17(12), 2864.
Yadav, A., Chaturvedi, P. K., Rani, S., Tripathi, A. K., & Shrivastava, V. (2023). Object detection and tracking using YOLOv8 and DeepSORT, Advancements in Communication and Systems, 81-90.
Lima, D. P., de-Almeida, S. B., Bonfadini, J. D. C., Carneiro, A. H. S., Luna, J. R. G. D., Alencar, M. S. D., & Braga-Neto, P. (2022). Falls in Parkinson's disease: the impact of disease progression, treatment, and motor complications. Dementia & Neuropsychologia, 16(2), 153-161.
Sara, B., What doctors wish patients knew about Parkinson’s disease, 2025 (accessed 17 March 2025).
Fitriawan, H., Purwiyanti, S., Faturrohman, E. A., Santoso, M. R. F., Darajat, A. U., & Gunawan, T. S. (2024). Development of a Low-Cost Fall Detection System for the Elderly with Accurate Detection and Real-Time Alerts. In 2024 IEEE 10th International Conference on Smart Instrumentation, Measurement and Applications (ICSIMA), pp. 309-314.
Alexandrova, S., Tatlock, Z., & Cakmak, M. (2015). RoboFlow: A flow-based visual programming language for mobile manipulation tasks. In 2015 IEEE international conference on robotics and automation (ICRA), pp. 5537-5544.
Bisong, E. (2019). Google colaboratory. In Building machine learning and deep learning models on google cloud platform: a comprehensive guide for beginners, pp. 59-64. Berkeley, CA: Apress.
Chang, L., & Zhang, Z. (2024). Drowning Detection Based on YOLOv8-Pose and Human Pose Estimation. In 2024 10th International Conference on Systems and Informatics (ICSAI), pp. 1-6.