Advancing UAV-Based Inspection System: The USSA-Net Segmentation Approach to Crack Quantification

This repository contains the python implementation for the paper "Advancing UAV-Based Inspection System: The USSA-Net Segmentation Approach to Crack Quantification".

Dataset

Note: The data/ file does not have to be within your project, you can put it somewhere you want.

Get Started

Dependencies

We strongly recommend that you can use VSCode and Docker for this project, it can save you much time😁! Note that the related configurations has already been within .devcontainer. The detail information can be found in this Tutorial_for_Vscode&Dokcer.

Configurations

The realted configurations are all saved in config/.

🚀 Quick Start

🎓 Citation

If you find our work useful in your research, please consider citing:

@article{10568977,
  author={Tse, Kwai-Wa and Pi, Rendong and Yang, Wenyu and Yu, Xiang and Wen, Chih-Yung},
  journal={IEEE Transactions on Instrumentation and Measurement}, 
  title={Advancing UAV-Based Inspection System: The USSA-Net Segmentation Approach to Crack Quantification}, 
  year={2024},
  volume={73},
  number={},
  pages={1-14},
  keywords={Inspection;Autonomous aerial vehicles;Image segmentation;Accuracy;Laser radar;Cameras;Path planning;Attention module;autonomous inspection system;crack detection;crack quantification;crack segmentation;unmanned aircraft systems (UAS);U-shape network (UNET);unmanned aerial vehicle (UAV)},
  doi={10.1109/TIM.2024.3418073}}

Acknowledge

This repository adapts and integrates from some wonderful work, shown as follows:

• unet