Development of Fall Detection System for Elderly with Computer Vision
Keywords:
Elderly person, Fall detection, Internet of things, Computer visionAbstract
Elderly individuals are particularly susceptible to fall-related accidents, especially those living alone. This study proposes the development of a computer vision-based fall detection system designed to enhance personal safety through real-time monitoring. The system integrates indoor video surveillance using OpenCV and processes the captured frames via Media Pipe to extract and analyze human postures based on 33 skeletal landmark points. Fall detection is achieved by identifying abrupt downward movements toward the ground, measured in terms of both direction and duration.
Experimental simulations covering various fall scenarios—namely forward, backward, leftward, and rightward—demonstrated that the system achieved an average detection accuracy of 90%. These findings underscore the system’s potential to reduce the risk of injury among elderly individuals by enabling timely intervention in the event of a fall. It is anticipated that the outcomes of this research will contribute to the advancement of intelligent fall detection technologies and provide a foundation for future developments in elderly care and health monitoring systems.
References
Alam, M., Ullah, S., Munir, A., Rahman, A., & Kim, D. (2023). Fall detection using IoT-enabled computer vision and edge computing. Sensors, 23(5), 2408. Form https://www.mdpi.com/1424-8220/23/5/2408.
Boonliang, C. (2019). Development of a fall detection device for the elderly using wearable devices combined with embedded systems and IoT technology. Thai-Nichi Institute of Technology Journal of Technology and Innovation, 5(1), 12–22. Form https://ph01.tci-thaijo.org/index.php/TNIJournal/article/view/198035. (in Thai)
Chung, G. C., Naeim, M. K. M., Lee, I. E., Tiang, J. J., & Tan, S. F. (2023). A mobile IoT-based elderly monitoring system for senior safety. International Journal of Technology, 14(6), 1185–1195. Form https://ijtech.eng.ui.ac.id/article/view/6634.
Choonhaphatrakun, T. (2024). Research and development of a web application for elderly fall detection and alerting using the MediaPipe framework. Journal of Science and Technology, Southeast Bangkok University, 4(1), 55–67. Form https://ph02.tci-thaijo.org/index.php/JSCI/article/view/253061. (in Thai)
Delahoz, Y. S., & Labrador, M. A. (2014). Survey on fall detection and fall prevention using wearable and external sensors. Sensors, 14(10), 19806–19842. Form https://www.mdpi.com/1424-8220/14/10/19806.
Department of Health, Ministry of Public Health. (2021). Guidelines for promoting healthy aging and longevity. Bangkok: Department of Health. Form https://hp.anamai.moph.go.th/...493d895eb11327ff493e710419ee454c.pdf.
Department of Older Persons. (2021). [Title of the report, guideline, or document]. Bangkok: Department of Older Persons. Form https://www.dop.go.th/download/knowledge/th1663828576-1747_1.pdf.
Google Developers. (n.d.). Classification: Accuracy, recall, precision, and related metrics. Retrieved June 9, 2025, Form https://developers.google.com/machine-learning/crash-course/classification/accuracy-precision-recall?hl=th.
Leelathian, P., & Phararat, K. (2024). Fall detection according to severity for the elderly using WiFi signals. King Mongkut’s University of Technology North Bangkok Academic Journal, 34(1). Form https://ojs.kmutnb.ac.th/index.php/kjournal/article/view/5732. (in Thai)
Lenovo. (2025). How does a webcam work? Retrieved From https://www.lenovo.com.
National Statistical Office. (2023). Report on the number and proportion of the elderly population in Thailand, 2023. Form https://www.nso.go.th. (in Thai)
Nilsukhum, N., & Yawai, W. (2023). Intelligent fall alert system for person recognition and fall detection. Journal of Applied Informatics and Technology, 6(1), 65–83. Form https://ph01.tci-thaijo.org/index.php/jait/article/view/251838. (in Thai)
Nualtim, W., Piulalong, T., Wongsri, N., & Khambu, A. (2023). Walking aid using face detection and fall alert system through LINE application for the elderly. Journal of Science and Technology, Udon Thani Rajabhat University, 11(1), 65–83. Form https://ph01.tci-thaijo.org/index.php/scudru/article/view/251495. (in Thai)
Rahman, A., Ahmad, A., Ismail, M. M., Shukor, S. A. A., & Mohamed, A. (2023). Fall detection device design for elderly people using quality function deployment (QFD). Journal of Advanced Research in Applied Sciences and Engineering Technology, 32(1), 28–42. Form https://journals.sagepub.com/doi/full/10.1177/23337214221148245.
Rattanapratum, S., Kaena, P., & Hanta, S. (2025). Object monitoring system in smart homes for visually impaired persons. Journal of Academic Innovation for Area-Based Development, 6(2). (in Thai)
Roboflow Inc. (2025). What is OpenCV? Retrieved Form https://roboflow.com/learn/opencv/.
Saenkaew, P., Phumthuean, C., Boonsob, J., Waristhanit, N., Tarathong, T., & Srijiranon, K. (2024). Standing posture monitoring system for the elderly. Journal of Information Science and Technology, 14(2), 54–61. Form https://ph02.tci-thaijo.org/index.php/JIST/article/view/253465. (in Thai)
Sertis Team. (2021). Media Pipe Holistic: Full body tracking for the future. Medium. Form https://sertiscorp.medium.com/mediapipe-holistic-full-body-tracking-for-the-future-278ff7d83ebf.
Thaworawong, N., Akaraseth, A., & Makhasorn, P. (2011). Design of a fall detection suit for the elderly using tilt sensors. Naresuan University Journal, Special Issue, 43. Form https://www.thaiscience.info/journals/Article/NUJ/10896657.pdf. (in Thai)
World Health Organization. (2021). Falls. Retrieved Form https://www.who.int/news-room/fact-sheets/detail/falls.
Yacchirema, D., Suárez de Puga, J., Palau, C., & Esteve, M. (2018). Fall detection system for elderly people using IoT and Big Data. Procedia Computer Science, 130, 603–610. Form https://www.sciencedirect.com/science/article/pii/S1877050918304721.
Zereen, A. N., Gurung, A., Rajak, A., Moonrinta, J., Dailey, M. N., Ekpanyapong, M., Vachalathiti, R., & Bovonsunthonchai, S. (2021). Automatic elderly fall and unstable movement detection system using frame wise and LSTM based video analytics on an embedded device. NBTC Journal, 5(5), 117–134. Form https://so04.tci-thaijo.org/index.php/NBTC_Journal/article/view/253616.
Zhang, Z., Zhu, C., Wu, H., Wang, W., & Wang, Z. (2022). Fall detection system based on wearable sensors and Internet of Things. IEEE Access, 10, 40215–40228. Form https://ieeexplore.ieee.org/abstract/document/9792277.
