Fast and High-Precision Human Fall Detection Using Improved YOLOv8 Model
Human falls refer to a sudden, accidental, unintentional, involuntary, and traumatizing action of a person losing stability and ending up lying down (often on the ground). These incidents of collapsing, tripping, crashing, tumbling, falling, etc. cause major harm and injuries to the elderly in our s...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10697972/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841550825062662144 |
|---|---|
| author | Ahlam R. Khekan Hadi S. Aghdasi Pedram Salehpour |
| author_facet | Ahlam R. Khekan Hadi S. Aghdasi Pedram Salehpour |
| author_sort | Ahlam R. Khekan |
| collection | DOAJ |
| description | Human falls refer to a sudden, accidental, unintentional, involuntary, and traumatizing action of a person losing stability and ending up lying down (often on the ground). These incidents of collapsing, tripping, crashing, tumbling, falling, etc. cause major harm and injuries to the elderly in our society. According to WHO, it is the second-leading cause of death worldwide. Therefore, having a fast and high-precision fall detection system operating in real time is crucial. It will ensure quick assistance and early treatment are provided to the impacted elderly individuals. Recently, Deep Learning based systems have shown promising results for detecting changes in postures and promptly responding to them in real-time. The You Only Look Once (YOLO) models have been widely used previously for designing and implementing human fall detection systems. This research presents an improved YOLOv8 model for fast and highly accurate human fall detection. The improvements include reducing the number of layers in the backbone of YOLOv8 and incorporating the attention mechanism in the head of the network. For training and evaluation, the CAUCAFall dataset is used. The original YOLOv8 and improved YOLOv8 are evaluated on the same dataset, achieving mAP of 0.995. Also, the training time of the improved YOLOv8 is 0.457 hours, faster than other YOLO models. Therefore, the presented model is a practical approach for human fall detection and can serve in public places for safeguarding the elderly of our society against potential injuries. |
| format | Article |
| id | doaj-art-1d546c3edf8c468286e7d309a6e6e727 |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-1d546c3edf8c468286e7d309a6e6e7272025-01-10T00:01:02ZengIEEEIEEE Access2169-35362025-01-01135271528310.1109/ACCESS.2024.347031910697972Fast and High-Precision Human Fall Detection Using Improved YOLOv8 ModelAhlam R. Khekan0https://orcid.org/0000-0001-7320-925XHadi S. Aghdasi1https://orcid.org/0000-0003-1613-7370Pedram Salehpour2https://orcid.org/0000-0002-1300-7848Faculty of Electrical and Computer Engineering, University of Tabriz, Tabriz, IranFaculty of Electrical and Computer Engineering, University of Tabriz, Tabriz, IranFaculty of Electrical and Computer Engineering, University of Tabriz, Tabriz, IranHuman falls refer to a sudden, accidental, unintentional, involuntary, and traumatizing action of a person losing stability and ending up lying down (often on the ground). These incidents of collapsing, tripping, crashing, tumbling, falling, etc. cause major harm and injuries to the elderly in our society. According to WHO, it is the second-leading cause of death worldwide. Therefore, having a fast and high-precision fall detection system operating in real time is crucial. It will ensure quick assistance and early treatment are provided to the impacted elderly individuals. Recently, Deep Learning based systems have shown promising results for detecting changes in postures and promptly responding to them in real-time. The You Only Look Once (YOLO) models have been widely used previously for designing and implementing human fall detection systems. This research presents an improved YOLOv8 model for fast and highly accurate human fall detection. The improvements include reducing the number of layers in the backbone of YOLOv8 and incorporating the attention mechanism in the head of the network. For training and evaluation, the CAUCAFall dataset is used. The original YOLOv8 and improved YOLOv8 are evaluated on the same dataset, achieving mAP of 0.995. Also, the training time of the improved YOLOv8 is 0.457 hours, faster than other YOLO models. Therefore, the presented model is a practical approach for human fall detection and can serve in public places for safeguarding the elderly of our society against potential injuries.https://ieeexplore.ieee.org/document/10697972/Human fall detectiondeep learningYOLOv8attention mechanismlightweight networkparameter reduction |
| spellingShingle | Ahlam R. Khekan Hadi S. Aghdasi Pedram Salehpour Fast and High-Precision Human Fall Detection Using Improved YOLOv8 Model IEEE Access Human fall detection deep learning YOLOv8 attention mechanism lightweight network parameter reduction |
| title | Fast and High-Precision Human Fall Detection Using Improved YOLOv8 Model |
| title_full | Fast and High-Precision Human Fall Detection Using Improved YOLOv8 Model |
| title_fullStr | Fast and High-Precision Human Fall Detection Using Improved YOLOv8 Model |
| title_full_unstemmed | Fast and High-Precision Human Fall Detection Using Improved YOLOv8 Model |
| title_short | Fast and High-Precision Human Fall Detection Using Improved YOLOv8 Model |
| title_sort | fast and high precision human fall detection using improved yolov8 model |
| topic | Human fall detection deep learning YOLOv8 attention mechanism lightweight network parameter reduction |
| url | https://ieeexplore.ieee.org/document/10697972/ |
| work_keys_str_mv | AT ahlamrkhekan fastandhighprecisionhumanfalldetectionusingimprovedyolov8model AT hadisaghdasi fastandhighprecisionhumanfalldetectionusingimprovedyolov8model AT pedramsalehpour fastandhighprecisionhumanfalldetectionusingimprovedyolov8model |