FD-YOLO: A YOLO Network Optimized for Fall Detection
Falls are defined by the World Health Organization (WHO) as incidents in which an individual unintentionally falls to the ground or a lower level. Falls represent a serious public health issue, ranking as the second leading cause of death from unintentional injuries, following traffic accidents. Whi...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/15/1/453 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841549327094251520 |
|---|---|
| author | Hoseong Hwang Donghyun Kim Hochul Kim |
| author_facet | Hoseong Hwang Donghyun Kim Hochul Kim |
| author_sort | Hoseong Hwang |
| collection | DOAJ |
| description | Falls are defined by the World Health Organization (WHO) as incidents in which an individual unintentionally falls to the ground or a lower level. Falls represent a serious public health issue, ranking as the second leading cause of death from unintentional injuries, following traffic accidents. While fall prevention is crucial, prompt intervention after a fall is equally necessary. Delayed responses can result in severe complications, reduced recovery potential, and a negative impact on quality of life. This study focuses on detecting fall situations using image-based methods. The fall images utilized in this research were created by combining three open-source datasets to enhance generalization and adaptability across diverse scenarios. Because falls must be detected promptly, the YOLO (You Only Look Once) network, known for its effectiveness in real-time detection, was applied. To better capture the complex body structures and interactions with the floor during a fall, two key techniques were integrated. First, a global attention module (GAM) based on the Convolutional Block Attention Module (CBAM) was employed to improve detection performance. Second, a Transformer-based Swin Transformer module was added to effectively learn global spatial information and enable a more detailed analysis of body movements. This study prioritized minimizing missed fall detections (false negatives, FN) as the key performance metric, since undetected falls pose greater risks than false detections. The proposed Fall Detection YOLO (FD-YOLO) network, developed by integrating the Swin Transformer and GAM into YOLOv9, achieved a high mAP@0.5 score of 0.982 and recorded only 134 missed fall incidents, demonstrating optimal performance. When implemented in environments equipped with standard camera systems, the proposed FD-YOLO network is expected to enable real-time fall detection and prompt post-fall responses. This technology has the potential to significantly improve public health and safety by preventing fall-related injuries and facilitating rapid interventions. |
| format | Article |
| id | doaj-art-1929f92dc2424646aecb8113119ca2ba |
| institution | Kabale University |
| issn | 2076-3417 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj-art-1929f92dc2424646aecb8113119ca2ba2025-01-10T13:15:36ZengMDPI AGApplied Sciences2076-34172025-01-0115145310.3390/app15010453FD-YOLO: A YOLO Network Optimized for Fall DetectionHoseong Hwang0Donghyun Kim1Hochul Kim2Department of Medical Artificial Intelligent, Eulji University, Seongnam-si 13135, Gyeonggi-do, Republic of KoreaDepartment of Medical Artificial Intelligent, Eulji University, Seongnam-si 13135, Gyeonggi-do, Republic of KoreaDepartment of Medical Artificial Intelligent, Eulji University, Seongnam-si 13135, Gyeonggi-do, Republic of KoreaFalls are defined by the World Health Organization (WHO) as incidents in which an individual unintentionally falls to the ground or a lower level. Falls represent a serious public health issue, ranking as the second leading cause of death from unintentional injuries, following traffic accidents. While fall prevention is crucial, prompt intervention after a fall is equally necessary. Delayed responses can result in severe complications, reduced recovery potential, and a negative impact on quality of life. This study focuses on detecting fall situations using image-based methods. The fall images utilized in this research were created by combining three open-source datasets to enhance generalization and adaptability across diverse scenarios. Because falls must be detected promptly, the YOLO (You Only Look Once) network, known for its effectiveness in real-time detection, was applied. To better capture the complex body structures and interactions with the floor during a fall, two key techniques were integrated. First, a global attention module (GAM) based on the Convolutional Block Attention Module (CBAM) was employed to improve detection performance. Second, a Transformer-based Swin Transformer module was added to effectively learn global spatial information and enable a more detailed analysis of body movements. This study prioritized minimizing missed fall detections (false negatives, FN) as the key performance metric, since undetected falls pose greater risks than false detections. The proposed Fall Detection YOLO (FD-YOLO) network, developed by integrating the Swin Transformer and GAM into YOLOv9, achieved a high mAP@0.5 score of 0.982 and recorded only 134 missed fall incidents, demonstrating optimal performance. When implemented in environments equipped with standard camera systems, the proposed FD-YOLO network is expected to enable real-time fall detection and prompt post-fall responses. This technology has the potential to significantly improve public health and safety by preventing fall-related injuries and facilitating rapid interventions.https://www.mdpi.com/2076-3417/15/1/453fallsartificial intelligencecomputer visionattention blockdeep learning |
| spellingShingle | Hoseong Hwang Donghyun Kim Hochul Kim FD-YOLO: A YOLO Network Optimized for Fall Detection Applied Sciences falls artificial intelligence computer vision attention block deep learning |
| title | FD-YOLO: A YOLO Network Optimized for Fall Detection |
| title_full | FD-YOLO: A YOLO Network Optimized for Fall Detection |
| title_fullStr | FD-YOLO: A YOLO Network Optimized for Fall Detection |
| title_full_unstemmed | FD-YOLO: A YOLO Network Optimized for Fall Detection |
| title_short | FD-YOLO: A YOLO Network Optimized for Fall Detection |
| title_sort | fd yolo a yolo network optimized for fall detection |
| topic | falls artificial intelligence computer vision attention block deep learning |
| url | https://www.mdpi.com/2076-3417/15/1/453 |
| work_keys_str_mv | AT hoseonghwang fdyoloayolonetworkoptimizedforfalldetection AT donghyunkim fdyoloayolonetworkoptimizedforfalldetection AT hochulkim fdyoloayolonetworkoptimizedforfalldetection |