IDENTITY AND APPLICATION ACTIONS FOR FALL DETECTION IN THE ELDERLY
Introduction
This is project of identity recognition and human action that is widely applied in life such as: falls in the elderly, stroke patients or behavior recognition in children
video demo
System Diagram
App
Dev
Member:
- DAO DUY NGU
- LE VAN THIEN
Instructor: TRAN THI MINH HANH
Usage
Install package
git clone https://github.com/DuyNguDao/Project_Graduate.git
cd Project_Graduate
conda create --name human_action python=3.8
pip install -r requirements.txt
Download
model yolov7 pose state dict:
yolov7_w6_pose
Quick start
start and config url
python run_video.py
start with terminal
python detect_video.py --fn <url if is video or 0>
Run App
note:
pip install opencv-python-headless==4.5.5.64
python app.py
Datasets and result model training
Dataset human action
Human action
Dataset Face Detection
Face detection
Dataset Face Recognition
Face recognition
Result face recognition
Diagram
Face detection
FDDB DATA
- Confusion matrix of YOLO5Face
- Confusion matrix of RetinaFace
WIDERFACE Val
- Confusion matrix of YOLO5Face
- Confusion matrix of RetinaFace
Result compare: Accuracy, Precision, Recall, Time processing
Config Computer:
- CPU: AMD Ryzen 7 4800H với 16G RAM DDR4
- GPU: NVIDIA GeForce GTX 1650 với 4G RAM DDR6
Face landmark loss
Face recognition
Backbone compare:
Methods compare: LOOCV (Leave One Of Cross Validation), Time processing with FaceScrub data
Diagram Accuracy Thresh
Result human action pose
Diagram
Confusion matrix
- Model LSTM (Long Short Term Memory)
- Model ST-GCN (Spatial Temporal - Graph Convolutional Network)
Methods compare
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
Compare ST-GCN + YOLOv7-Pose and ST-GCN + YOLOv3 + Alphapose
Config Computer:
- CPU: Intel® Core™ i5-8300H CPU @ 2.30GHz
- GPU: GEFORCE RTX 1050 với RAM 4G
- Confusion matrix of ST-GCN with skeleton data export from yolov3 + alphapose
Training
Human action
Face Detection
Face recognition
Address: Da Nang University of Science and Technology
Email: [email protected], [email protected]
Acknowledgements
评论