Analysis of Non-Contact Fall Detection Technologies
DOI:
https://doi.org/10.62051/mydg2s43Keywords:
Fall Detection; Radar; YOLOv8; CSI.Abstract
Against the backdrop of an aging society, the health of middle-aged and elderly individuals has become a growing concern for families. Falls are the leading cause of injury-related deaths, with a significant number of older adults suffering from disabilities or fatalities due to falls each year. Therefore, detecting falls is critically important. Traditional wearable sensors face challenges such as algorithmic limitations and wearability issues, making it difficult to meet the increasing demands of the elderly. Thus, research on non-contact fall detection technologies is essential. To explore various non-contact fall detection methods, this paper examines four types of technologies: those based on WiFi, computer vision, radar, and the multimodal fusion of WiFi and RGB. The paper is divided into three parts: the first introduces the theoretical foundations of each technology, briefly explaining their mechanisms and highlights; the second compares the advantages, disadvantages, and applicable experimental scenarios of each technology; and the third summarizes current technological limitations and offers prospects for future development. By analyzing the principles and characteristics of various technologies, this study presents suitable application scenarios and comparative strengths and weaknesses, providing a theoretical reference and practical guidance for future research on non-contact fall detection, thereby facilitating the optimization and implementation of these technologies.
Downloads
References
[1] Ma, Yongsen, Zhou, Gang, Wang, Shuangquan. WiFi Sensing with Channel State Information: A Survey. ACM COMPUTING SURVEYS, 2019, 52 (03). DOI: https://doi.org/10.1145/3310194
[2] Neena Damodaran, Jorg Schafer. Device Free Human Activity Recognition using WiFi Channel State Information. 2019: 1069–1074. DOI: https://doi.org/10.1109/SmartWorld-UIC-ATC-SCALCOM-IOP-SCI.2019.00205
[3] Yue Zihao. Research on Indoor Fall Detection Technology Based on Wireless Signals. University of Electronic Science and Technology of China, 2022.
[4] Ahn, S., Choi, M., Lee, J., Kim, J., Chung, S. Non-Contact Fall Detection System Using 4D Imaging Radar for Elderly Safety Based on a CNN Model. Sensors, 2025, 25: 3452. DOI: https://doi.org/10.3390/s25113452
[5] Yuan Zhi’an, Zhou Xiaoyu, Liu Xinpu, et al. Millimeter-Wave Radar Human Fall Detection Method Based on RDSNet. Journal of Radars, 2021, 10 (04): 656–664.
[6] Yu, Y.S., Wie, S., Lee, H., Lee, J., Kim, N.H. Long Short-Term Memory-Based Fall Detection by Frequency-Modulated Continuous Wave Millimeter-Wave Radar Sensor for Seniors Living Alone. Appl. Sci., 2025, 15: 8381. DOI: https://doi.org/10.3390/app15158381
[7] Shi, H., Wang, X., Shi, J. Fall Detection Algorithm Using Enhanced HRNet Combined with YOLO. Sensors, 2025, 25: 4128. DOI: https://doi.org/10.3390/s25134128
[8] Liu Dong. Research on Human Fall Detection Based on YOLOv8. Wuhan Polytechnic University, 2024.
[9] Nizar Zaghden, Emad Ibrahim, Mukaram Safaldin, et al. Integrating Attention Mechanisms in YOLOv8 for Improved Fall Detection Performance. Computers, Materials & Continua, 2025, 83 (04): 1117-1147. DOI: https://doi.org/10.32604/cmc.2025.061948
[10] Fujia Zhou, Guangxu Zhu, Xiaoyang Li, Hang Li, Qingjiang Shi. Towards Pervasive Sensing: A multimodal approach via CSI and RGB image modalities fusion. In Proceedings of the 3rd ACM MobiCom Workshop on Integrated Sensing and Communications Systems (ISACom '23). Association for Computing Machinery, New York, NY, USA, 2023: 25–30. DOI: https://doi.org/10.1145/3615984.3616505
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Transactions on Computer Science and Intelligent Systems Research
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
