Real-Time Fall Detection for Elderly Care Using YOLOv8 with a Custom-Built Image Dataset
Keywords:
fall detection, YOLOv8, elderly care, computer vision, real-time monitoringAbstract
This paper aims to develop a model for human fall detection by simulating authentic fall incidents for implementation in a computer vision system designed to monitor falls in the elderly and deliver real-time notifications. The model development process commences with the utilization of a dataset comprising item bounding boxes and corresponding annotations. The YOLOv8 methodology is subsequently employed to train the dataset. The study dataset consists of 2,788 raw images that have been annotated and processed using Roboflow technology. The images are categorized into three groups: the training set comprises 77% of the data, totaling approximately 2,146 images; the validation set constitutes 12%, or about 338 images; and the test set accounts for 11%, roughly 304 images. Data augmentation methods were used in the fourth stage of the Roboflow platform to increase data diversity, resulting in 19,000 images. This expanded dataset enhances the model's ability to generalize by exposing it to a wider variety of scenarios and conditions. Consequently, the increased volume of images allows for more robust training, ultimately improving the accuracy and reliability of the model's predictions in real-world applications. The ideal value for improving model performance is one hundred epochs, which is how long model training was run. The model testing outcomes, carried out in the same setting as the training, show a mean average accuracy (mAP) of 90.97% and an overall accuracy of 95.36%, suggesting outstanding accuracy and appropriateness for practical use.
References
X. Fu and N. Angkawisittpan, “Detecting surface defects of heritage buildings based on deep learning,” in Journal of Intelligent Systems, vol. 13, no. 1, 20230048, 2024, doi: 10.1515/jisys-2023-0048.
S. Sonasang, S. Srisawat, R. Phromloungsri, W. Rattanangam and N. Angkawisittpan, “Liquid Level Measurement Using Sensors with Microstrip Parallel Coupled Lines,” 2019 IEEE 2nd International Conference on Power and Energy Applications (ICPEA2019), Singapore, 2019, pp. 106-109, doi: 10.1109/ICPEA.2019.8818540.
S. Balasubramaniam, J. R. Park, T. Mistry, N. Angkawisittpan, A. Akyurtlu, T. Rao and R. Nagarajan, “Conformal passive sensors for wireless structural health monitoring,” Materials Research Society Symposium Proceedings, Boston, Massachusetts, USA, 2009, vol. 1129, pp. 341-348, doi: 10.1557/PROC-1129-V04-19.
M. Sopa and N. Angkawisittpan, “An Application of Cuckoo Search Algorithm for Series System with Cost and Multiple Choices Constraints,” in Procedia Computer Science (iEECON2016), Chiang Mai, Thailand, vol. 86, pp. 453-456, 2016, doi: 10.1016/j.procs.2016.05.079.
N. Angkawisittpan and A. Siritaratiwat, “A Dual Frequency Monopole Antenna with Double Spurlines for PCS and Bluetooth Applications,” in Applied Computational Electromagnetics Society Journal, vol. 31, no. 8, pp. 976-981, 2016.
P. H. Ng, A. Mai and H. Nguyen, “Building an AI-powered IoT App for Fall Detection using YOLOv8 Approach,” Intelligence of Things: Technologies and Applications (ICIT 2023), Ho Chi Minh City, Vietnam, 2023, pp. 65-74, doi: 10.1007/978-3-031-46749-3_7.
M. G. Ragab, S. J. Abdulkadir, A. Muneer, A. Alqushaibi, E. H. Sumiea, R. Qureshi, S. M. Al-Selwi and H. Alhussian, “A Comprehensive Systematic Review of YOLO for Medical Object Detection (2018 to 2023),” in IEEE Access, vol. 12, pp. 57815-57836, 2024, doi: 10.1109/ACCESS.2024.3386826.
A. R. Khekan, H. S. Aghdasi and P. Salehpour, “Fast and High-Precision Human Fall Detection Using Improved YOLOv8 Model,” in IEEE Access, vol. 13, pp. 5271-5283, 2025, doi: 10.1109/ACCESS.2024.3470319.
Y. J. Mao, A. Y. C. Tam, Q. T. K. Shea, Y. P. Zheng and J. C. W. Cheung, “eNightTrack: Restraint-Free Depth-Camera-Based Surveillance and Alarm System for Fall Prevention Using Deep Learning Tracking,” in Algorithms, vol. 16, no. 10, 477, 2023, doi: 10.3390/a16100477.
X. Huang, X. Li, L. Yuan, Z. Jiang, H. Jin, W. Wu, R. Cai, M. Zheng and H. Bai, “SDES-YOLO: A high-precision and lightweight model for fall detection in complex environments,” in Scientific Reports, vol. 15, 2026, 2276, 2025, doi: 10.1038/s41598-025-86593-9.
C. Y. Wang and F. S. Lin, “AI-driven privacy in elderly care: Developing a comprehensive solution for camera-based monitoring of older adults,” in Applied Sciences, vol. 14, no. 10, 4150, 2024, doi: 10.3390/app14104150.
J. Moore, Y. Celik, S. Stuart, P. McMeekin, R. Walker, V. Hetherington and A. Godfrey, “Using Video Technology and AI within Parkinson’s Disease Free-Living Fall Risk Assessment,” in Sensors, vol. 24, no. 15, 4914, 2024, doi: 10.3390/s24154914.
A. T. Özdemir and B. Barshan, “Detecting Falls with Wearable Sensors Using Machine Learning Techniques,” in Sensors, vol. 14, no. 6, pp. 10691-10708, 2014, doi: 10.3390/s140610691.
J. Gutiérrez, V. Rodríguez and S. Martin, “Comprehensive Review of Vision-Based Fall Detection Systems,” in Sensors, vol. 21, no. 3, 947, 2021, doi: 10.3390/s21030947.
J. Redmon, S. Divvala, R. Girshick and A. Farhadi, “You Only Look Once: Unified, Real-Time Object Detection,” 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA, pp. 779-788, 2016, doi: 10.1109/CVPR.2016.91.
N. Ladi, “Object Detection with a pre-trained Ultralytics YOLOv8 model,” 2024, Available: https://www.ultralytics.com/blog/object-detection-with-a-pre-trained-ultralytics-yolov8-model
F. X. Gaya-Morey, C. Manresa-Yee and J. M. Buades-Rubio, “Deep learning for computer vision based activity recognition and fall detection of the elderly: a systematic review,” in Applied Intelligence, 54, pp. 8982–9007, 2024, doi: 10.1007/s10489-024-05645-1.
A. Bustamante, L. M. Belmonte, R. Morales, A. Pereira and A. F. Caballero, “Bridging the Appearance Domain Gap in Elderly Posture Recognition with YOLOv9,” in Applied Sciences, vol. 14, no. 21, 9695, 2024, doi: 10.3390/app14219695.
Roboflow, “Data augmentation and preprocessing tools,” Available: https://roboflow.com
M. Lupión, V. González-Ruiz, J. F. Sanjuan and P. M. Ortigosa, “Privacy-aware fall detection and alert management in smart environments using multimodal device,” in Internet of Things, vol. 30, 101526, 2025, doi: 10.1016/j.iot.2025.101526.
Ultralytics, “Explore Ultralytics YOLOv8,” 2023, Available: https://docs.ultralytics.com/models/yolov8/
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
