AI-assisted wood knots detection from historic timber structure imaging

This git repository contains the codes, training results and test code for Junquan Pan's master thesis at the Chair xAI of the University of Bamberg.
Explore the docs »

View Demo · Report Bug · Request Feature

Table of Contents

1. About The Project
   • Built With
2. Getting Started
   • Prerequisites
   • Installation
3. Usage
4. Roadmap
5. Contributing
6. License
7. Contact
8. Acknowledgments

About The Project

This project focuses on developing an AI-powered system for detecting wood knots on historic timber surfaces, contributing to the preservation and sustainability of invaluable heritage structures. Traditional manual methods for assessing timber integrity are often time-consuming, error-prone, and limited in challenging conditions. This project introduces a modern, automated solution leveraging machine learning and deep learning techniques.

Key Features

1. Two-Stage Detection Process:
   • Stage 1: Timber surface segmentation using models like Detectron2.
   • Stage 2: Knot detection with YOLOv8.
2. Geometric Analysis: Realistic measurements from mobile phone sensors are integrated to estimate knot dimensions.
3. Dataset Integration: Tests conducted on both labeled datasets and unseen collections ensure the system's reliability and adaptability.

Goals

• Accurate Documentation: Provide detailed analysis of timber surfaces to assist heritage conservation.
• Efficiency: Reduce time and errors associated with traditional methods.
• Accessibility: Implement a mobile application for conservators to streamline inspection and analysis.

Future Enhancements

Ongoing research aims to refine model accuracy and stability for diverse environmental conditions, ensuring a robust and reliable tool for the conservation community.

---

(back to top)

Built With

• 
• 

(back to top)

Usage

Use this space to show useful examples of how a project can be used. Additional screenshots, code examples and demos work well in this space. You may also link to more resources.

For more examples, please refer to the Documentation

(back to top)

Contributing

Contributions are what make the open source community such an amazing place to learn, inspire, and create. Any contributions you make are greatly appreciated.

If you have a suggestion that would make this better, please fork the repo and create a pull request. You can also simply open an issue with the tag "enhancement". Don't forget to give the project a star! Thanks again!

1. Fork the Project
2. Create your Feature Branch (git checkout -b feature/AmazingFeature)
3. Commit your Changes (git commit -m 'Add some AmazingFeature')
4. Push to the Branch (git push origin feature/AmazingFeature)
5. Open a Pull Request

(back to top)

License

Distributed under the MIT License. See LICENSE.txt for more information.

(back to top)

Contact

Your Name - @JunquanPan - junqan_pan@163.com

Project Link: https://github.com/happy-panda-ops/xAI_Masterthesis_Pan

(back to top)

(back to top)