Falls are a very common unexpected accident in the elderly that result in serious injuries such as broken bones, head injury. Detecting falls and taking fall patients to the emergency room in time is very important. In this project, we propose a method that combines face recognition and action recognition for fall detection. Specifically, we identify seven basic actions that take place in elderly daily life based on skeleton data detected using YOLOv7-Pose model. Two deep models which are Spatial Temporal Graph Convolutional Network (ST-GCN) and Long Short-Term Memory (LSTM) are employed for action recognition on the skeleton data. The experimental results on our dataset show that ST-GCN model achieved an accuracy of 90% higher than the LSTM model by 7%.

Member:
 - DAO DUY NGU
 - LE VAN THIEN
Instructor: TRAN THI MINH HANH

git clone https://github.com/DuyNguDao/Identity-Action.git

cd Identity-Action

conda create --name human_action python=3.8

pip install -r requirements.txt

model yolov7 pose state dict: yolov7_w6_pose

python run_video.py

python detect_video.py --fn <url if is video or 0>

note:

pip install opencv-python-headless==4.5.5.64

python app.py

Human action

Face detection

Face recognition

• Confusion matrix of YOLO5Face

• Confusion matrix of RetinaFace

• Confusion matrix of YOLO5Face

• Confusion matrix of RetinaFace

Config Computer:

• CPU: AMD Ryzen 7 4800H với 16G RAM DDR4
• GPU: NVIDIA GeForce GTX 1650 với 4G RAM DDR6

• MobileFaceNet

• ResNet18

• Model LSTM (Long Short Term Memory)

• Model ST-GCN (Spatial Temporal - Graph Convolutional Network)

Accuracy, Precision, Recall, F1-score, Time processing

Config Computer:

• CPU: AMD Ryzen 7 4800H với 16G RAM DDR4
• GPU: NVIDIA GeForce GTX 1650 với 4G RAM DDR6

Config Computer:

• CPU: AMD Ryzen 7 4800H với 16G RAM DDR4
• GPU: NVIDIA GeForce GTX 1650 với 4G RAM DDR6

• Confusion matrix of ST-GCN with skeleton data export from yolov3 + alphapose

• https://github.com/DuyNguDao/LSTM.git
• https://github.com/DuyNguDao/ST-GCN-Pytorch.git

• https://github.com/deepcam-cn/yolov5-face.git
• https://github.com/biubug6/Pytorch_Retinaface.git

• https://github.com/DuyNguDao/ArcFace_Pytorch.git

@article{
  title={The combination of face identification and action recognition for fall detection},
  author={Dao Duy Ngu, Le Van Thien, Tran Thi Minh Hanh, Nguyen Thi Hong Yen, Dao Duy Tuan},
  journal={Journal of Science and Technology, Issue on Information and Communications Technology, ISSN: 1859-1531},
  Pages={37-44, Vol. 20, No. 12.2, 2022}
  year={2022}
}

The University of Da Nang, The University of Science and Technology
Address: 54, Nguyen Luong Bang street, Lien Chieu district, Da Nang City, Viet Nam

• https://github.com/deepinsight/insightface.git
• https://github.com/deepcam-cn/yolov5-face.git
• https://github.com/WongKinYiu/yolov7.git
• https://github.com/biubug6/Pytorch_Retinaface.git
• https://github.com/GajuuzZ/Human-Falling-Detect-Tracks.git
• https://github.com/mikel-brostrom/Yolov5_StrongSORT_OSNet.git