TelecomDWGConverter

Telecom DWG Converter

This project is an AI-powered tool for converting FTTH (Fiber to the Home) plan images to AutoCAD DWG files. It uses advanced computer vision techniques and machine learning to detect and classify various components in the FTTH plan images and generate corresponding DWG files.

Features

• Image preprocessing for noise reduction and enhancement
• Feature extraction using computer vision techniques
• Component classification using a custom-trained Detectron2 model
• DWG file generation with proper scaling and georeferencing
• Mobile app for capturing and uploading FTTH plan images
• API server for processing images and returning DWG files

Project Structure

• api_server/: Contains the API server code
• gui_app/: Contains the mobile app code
• model/: Contains the machine learning model training code and configuration
• tests/: Contains unit tests for various components
• data/: Contains training and testing data for the machine learning model

Setup and Installation

1. Clone the repository: git clone https://github.com/amoahfrank/TelecomDWGConverter.git

2. Set up the API server: cd api_server pip install -r requirements.txt

3. Set up the mobile app: cd gui_app/mobile flutter pub get

4. Train the machine learning model: cd model python train.py

Usage

1. Start the API server: cd api_server python main.py

2. Run the mobile app: cd gui_app/mobile flutter run

3. Use the mobile app to capture FTTH plan images and process them into DWG files.

Contributing

Please read CONTRIBUTING.md for details on our code of conduct and the process for submitting pull requests.

License

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