https://github.com/alihassanml/theft-detection
This project uses the YOLOv11 object detection model to identify theft activities, particularly focusing on individuals wearing black masks. The model is trained with a custom dataset and achieves an accuracy of 90%, making it a reliable solution for real-world theft detection scenarios.
https://github.com/alihassanml/theft-detection
python yolov11
Last synced: 7 months ago
JSON representation
This project uses the YOLOv11 object detection model to identify theft activities, particularly focusing on individuals wearing black masks. The model is trained with a custom dataset and achieves an accuracy of 90%, making it a reliable solution for real-world theft detection scenarios.
- Host: GitHub
- URL: https://github.com/alihassanml/theft-detection
- Owner: alihassanml
- License: mit
- Created: 2025-01-10T17:52:09.000Z (9 months ago)
- Default Branch: main
- Last Pushed: 2025-01-10T19:01:25.000Z (9 months ago)
- Last Synced: 2025-01-17T19:16:54.307Z (9 months ago)
- Topics: python, yolov11
- Language: Jupyter Notebook
- Homepage:
- Size: 22.3 MB
- Stars: 1
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Theft Detection using YOLOv11
This project uses the YOLOv11 object detection model to identify theft activities, particularly focusing on individuals wearing black masks. The model is trained with a custom dataset and achieves an accuracy of **90%**, making it a reliable solution for real-world theft detection scenarios.
## 🚀 Features
- Detects individuals wearing black masks as a theft indicator.
- Trained using YOLOv11 for state-of-the-art object detection performance.
- Real-time detection capabilities.
- Easily customizable and extendable for additional theft-related scenarios.
---
## 🛠️ Installation
1. Clone this repository:
```bash
https://www.kaggle.com/code/alihassanml/theft-classfication-using-yolo11
git clone https://github.com/alihassanml/Theft-Detection.git
cd Theft-Detection
```
2. Install dependencies:
```bash
pip install -r requirements.txt
```
3. Download the pre-trained YOLOv11 weights and place them in the `weights` directory:
- [YOLOv11 Weights](https://link-to-yolov11-weights)
4. Set up the configuration file:
- Modify the `config.yaml` file to match your environment and dataset paths.
---
## 🔍 Usage
### 1. Training
To train the model on your dataset:
```bash
python train.py --config config.yaml
```
### 2. Inference
To detect theft in a video or live feed:
```bash
python detect.py --source
```
Example:
```bash
python detect.py --source data/test_video.mp4
```
### 3. Evaluation
To evaluate the model on the test dataset:
```bash
python evaluate.py --config config.yaml
```
---
## 📂 Project Structure
```
Theft-Detection/
├── data/ # Dataset files
├── weights/ # Pre-trained YOLOv11 weights
├── models/ # YOLOv11 model architecture
├── utils/ # Utility scripts
├── train.py # Training script
├── detect.py # Inference script
├── evaluate.py # Evaluation script
├── config.yaml # Configuration file
└── README.md # Project documentation
```
---
## 🧠 Model Performance
- **Accuracy:** 90%
- **Precision/Recall:** Available in the `evaluation_results.txt` file.
---
## 💡 Future Improvements
- Support detection for more theft indicators (e.g., specific clothing or suspicious behavior).
- Enhance dataset diversity for better generalization.
- Implement a real-time alert system using IoT devices.
---
## 🤝 Contributing
Contributions are welcome! Please follow these steps:
1. Fork the repository.
2. Create a new branch (`feature-xyz`).
3. Commit your changes.
4. Open a Pull Request.
---
## 📜 License
This project is licensed under the [MIT License](LICENSE).
---
## ✉️ Contact
- **Ali Hassan**
- GitHub: [alihassanml](https://github.com/alihassanml)
- Email: alihassanbscs99@gmail.com
```
https://www.kaggle.com/code/alihassanml/theft-classfication-using-yolo11