|
|
--- |
|
|
license: agpl-3.0 |
|
|
library_name: ultralytics |
|
|
pipeline_tag: object-detection |
|
|
tags: |
|
|
- yolo |
|
|
- ultralytics |
|
|
- yolov11 |
|
|
- object-detection |
|
|
- fall-detection |
|
|
- computer-vision |
|
|
- safety |
|
|
datasets: |
|
|
- custom |
|
|
--- |
|
|
|
|
|
 |
|
|
|
|
|
# Human Fall Detection with YOLOv11 |
|
|
This model is a specialized version of YOLOv11, fine-tuned to detect human falls in various environments. It is designed to provide real-time alerts for safety monitoring in elderly care facilities, hospitals, and industrial workplaces. |
|
|
|
|
|
|
|
|
## 🚀 Quick Start (Usage) |
|
|
You don't need to download the weights manually. You can load and run the model directly using the Python code below: |
|
|
|
|
|
```python |
|
|
from ultralytics import YOLO |
|
|
from huggingface_hub import hf_hub_download |
|
|
import os |
|
|
|
|
|
model_path = hf_hub_download(repo_id="melihuzunoglu/human-fall-detection", filename="best.pt") |
|
|
|
|
|
model = YOLO(model_path) |
|
|
|
|
|
results = model.predict(source="image1.jpg", conf=0.25, save=True) |
|
|
``` |
|
|
|
|
|
|
|
|
## ✅ Supported Classes (Labels) |
|
|
The model can detect and distinguish between the following three states: |
|
|
```python |
|
|
Fallen: Active falling motion or a person on the ground after a fall. |
|
|
|
|
|
Sitting: People sitting on chairs, benches, or floor. |
|
|
|
|
|
Standing: People in an upright, standing position. |
|
|
``` |
|
|
|
|
|
|
|
|
## 📊 Model Information |
|
|
```python |
|
|
Architecture: YOLOv11 (Ultralytics) |
|
|
|
|
|
Task: Object Detection (Fall Detection) |
|
|
|
|
|
Input Resolution: 640x640 pixels |
|
|
|
|
|
Inference Speed: Optimized for real-time applications |
|
|
``` |
|
|
|
|
|
|
|
|
## 🎯 Target Applications |
|
|
```python |
|
|
Elderly Safety: Automated fall detection for home or nursing home environments. |
|
|
|
|
|
Occupational Health: Monitoring falls in hazardous work zones or construction sites. |
|
|
|
|
|
Healthcare Support: Providing an extra layer of monitoring for patient rooms. |
|
|
``` |
|
|
|
|
|
|
|
|
## 🛠 Training Details |
|
|
The model was trained using the Ultralytics framework. The dataset was curated and pre-processed via Roboflow to ensure high accuracy and minimal false positives in common sitting or lying down scenarios. |
|
|
|
|
|
|
|
|
## 👤 Developer |
|
|
Author: Melih Uzunoğlu [Linkedin](https://www.linkedin.com/in/melih-uzunoglu/) |
|
|
|
|
|
Framework: Ultralytics YOLOv11 |
|
|
|
|
|
Dataset Source: Roboflow |
|
|
|
|
|
|
|
|
### Disclaimer |
|
|
This model is developed for educational and research purposes. For critical safety implementations, it should be integrated with professional-grade monitoring systems. |
