Update README.md
Browse files
README.md
CHANGED
|
@@ -17,11 +17,10 @@ datasets:
|
|
| 17 |
|
| 18 |
|
| 19 |
# Human Fall Detection with YOLOv11
|
| 20 |
-
|
| 21 |
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.
|
| 22 |
|
| 23 |
-
## 🚀 Quick Start (Usage)
|
| 24 |
|
|
|
|
| 25 |
You don't need to download the weights manually. You can load and run the model directly using the Python code below:
|
| 26 |
|
| 27 |
```python
|
|
@@ -36,8 +35,8 @@ model = YOLO(model_path)
|
|
| 36 |
results = model.predict(source="image1.jpg", conf=0.25, save=True)
|
| 37 |
```
|
| 38 |
|
| 39 |
-
## ✅ Supported Classes (Labels)
|
| 40 |
|
|
|
|
| 41 |
The model can detect and distinguish between the following three states:
|
| 42 |
```python
|
| 43 |
Fallen: Active falling motion or a person on the ground after a fall.
|
|
@@ -47,6 +46,7 @@ Sitting: People sitting on chairs, benches, or floor.
|
|
| 47 |
Standing: People in an upright, standing position.
|
| 48 |
```
|
| 49 |
|
|
|
|
| 50 |
## 📊 Model Information
|
| 51 |
```python
|
| 52 |
Architecture: YOLOv11 (Ultralytics)
|
|
@@ -58,6 +58,7 @@ Input Resolution: 640x640 pixels
|
|
| 58 |
Inference Speed: Optimized for real-time applications
|
| 59 |
```
|
| 60 |
|
|
|
|
| 61 |
## 🎯 Target Applications
|
| 62 |
```python
|
| 63 |
Elderly Safety: Automated fall detection for home or nursing home environments.
|
|
@@ -67,6 +68,7 @@ Occupational Health: Monitoring falls in hazardous work zones or construction si
|
|
| 67 |
Healthcare Support: Providing an extra layer of monitoring for patient rooms.
|
| 68 |
```
|
| 69 |
|
|
|
|
| 70 |
## 🛠 Training Details
|
| 71 |
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.
|
| 72 |
|
|
|
|
| 17 |
|
| 18 |
|
| 19 |
# Human Fall Detection with YOLOv11
|
|
|
|
| 20 |
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.
|
| 21 |
|
|
|
|
| 22 |
|
| 23 |
+
## 🚀 Quick Start (Usage)
|
| 24 |
You don't need to download the weights manually. You can load and run the model directly using the Python code below:
|
| 25 |
|
| 26 |
```python
|
|
|
|
| 35 |
results = model.predict(source="image1.jpg", conf=0.25, save=True)
|
| 36 |
```
|
| 37 |
|
|
|
|
| 38 |
|
| 39 |
+
## ✅ Supported Classes (Labels)
|
| 40 |
The model can detect and distinguish between the following three states:
|
| 41 |
```python
|
| 42 |
Fallen: Active falling motion or a person on the ground after a fall.
|
|
|
|
| 46 |
Standing: People in an upright, standing position.
|
| 47 |
```
|
| 48 |
|
| 49 |
+
|
| 50 |
## 📊 Model Information
|
| 51 |
```python
|
| 52 |
Architecture: YOLOv11 (Ultralytics)
|
|
|
|
| 58 |
Inference Speed: Optimized for real-time applications
|
| 59 |
```
|
| 60 |
|
| 61 |
+
|
| 62 |
## 🎯 Target Applications
|
| 63 |
```python
|
| 64 |
Elderly Safety: Automated fall detection for home or nursing home environments.
|
|
|
|
| 68 |
Healthcare Support: Providing an extra layer of monitoring for patient rooms.
|
| 69 |
```
|
| 70 |
|
| 71 |
+
|
| 72 |
## 🛠 Training Details
|
| 73 |
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.
|
| 74 |
|