Human Fall Detection Through Velocity-Driven Temporal Deep Learning
Issued Date
2025-01-01
Resource Type
Scopus ID
2-s2.0-105041688146
Journal Title
2025 28th International Conference on Computer and Information Technology Iccit 2025
Start Page
2169
End Page
2174
Rights Holder(s)
SCOPUS
Bibliographic Citation
2025 28th International Conference on Computer and Information Technology Iccit 2025 (2025) , 2169-2174
Suggested Citation
Ahmed N., Hasan M.R., Shakib F.H., Rabbani H., Rabbi R., Khan S.T., Zereen A.N. Human Fall Detection Through Velocity-Driven Temporal Deep Learning. 2025 28th International Conference on Computer and Information Technology Iccit 2025 (2025) , 2169-2174. 2174. doi:10.1109/ICCIT68739.2025.11491387 Retrieved from: https://repository.li.mahidol.ac.th/handle/123456789/117421
Title
Human Fall Detection Through Velocity-Driven Temporal Deep Learning
Author's Affiliation
Corresponding Author(s)
Other Contributor(s)
Abstract
Accidental falls remain one of the most frequent and dangerous incidents among older adults, often leading to hospitalization, long-term disability, and loss of independence. This research presents a novel, non-wearable, vision-based system that addresses the challenge of real-time fall detection and instability recognition in home environments. The system uses monocular-camera-captured video to track human motion and classify it into three categories: normal, fall, or unstable. By employing YOLOv8 for keypoint extraction and a two-stage deep learning framework, the model predicts human movement velocity and classifies activities based on temporal skeleton keypoint dynamics. The two-stage framework consists of two separate LSTM-based models: the first stage predicts velocity from keypoint sequences using regression, and the second stage classifies motion into three categories. Evaluation on a primary dataset of 3449 annotated high-resolution video clips demonstrates a 90% classification accuracy. Compared to baseline methods, the proposed system improves the accuracy of fall detection, showing strong potential for practical deployment in elderly care settings. The approach offers a scalable and unobtrusive solution for continuous monitoring, eliminating the need for wearable devices.