Abs6187/Helmet_Detection_OCR_ANPR

Combined ANPR and Helmet Detection System

A comprehensive traffic violation detection system that combines Automatic Number Plate Recognition (ANPR) and Helmet Detection using YOLOv8.

Features

• —Real-time license plate detection and recognition
• —Helmet detection for two-wheeler riders
• —Modern Gradio interface with real-time processing
• —Adjustable confidence threshold for detection
• —Combined visual annotations from both models
• —Queue support for multiple users
• —Comprehensive error handling

Prerequisites

• —Python 3.8 or higher
• —CUDA-capable GPU (recommended for better performance)
• —8GB RAM minimum

Installation

1. 1.Clone the repository:

git clone <repository-url>
cd <repository-name>

1. 1.Create and activate a virtual environment:

python -m venv venv
source venv/bin/activate  # On Windows: venv\Scripts\activate

1. 1.Install dependencies:

pip install -r requirements.txt

Usage

1. 1.Start the application:

python app.py

1. 1.Open your web browser and navigate to:

http://localhost:7860

1. 1.Upload an image or use the example images to test the system.

Model Files

The following model files are required:

• —ANPR_IND/licence_plat.pt: License plate detection model
• —ANPR_IND/licence_character.pt: Character recognition model
• —Helmet-Detect-model/best.pt: Helmet detection model

API Endpoints

The application exposes the following endpoints:

• —/api/predict: POST endpoint for image processing
• —/api/health: GET endpoint for health check

Deployment

Local Deployment

python app.py

Docker Deployment

docker build -t traffic-detection .
docker run -p 7860:7860 traffic-detection

Contributing

1. 1.Fork the repository
2. 2.Create your feature branch
3. 3.Commit your changes
4. 4.Push to the branch
5. 5.Create a new Pull Request

License

This project is licensed under the MIT License - see the LICENSE file for details.