Building Recognition using AI at Large-Scale (BRAILS)

Barbaros Cetiner , Chaofeng Wang , Frank McKenna , Sascha Hornauer , Yunhui Guo

BRAILS (Building Recognition using AI at Large-Scale) provides a set of Python modules that utilize deep learning (DL), and computer vision (CV) techniques to extract information from satellite and street level images. The BRAILS framework also provides turn-key applications allowing users to put individual modules together to determine multiple attributes in a single pass or train general-purpose image classification, object detection, or semantic segmentation models.

This document covers the features and capabilities of Version 3.0 of the tool. Users are encouraged to comment on what additional features and capabilities they would like to see in future versions of the application through the MessageBoard.

About

• 1. About
• 2. Acknowledgements
• 3. Copyright and License
• 4. How to Cite
• 5. Glossary
• 6. Abbreviations
• 7. Release Notes

User Manual

• 1. Installation
• 2. User Guide
• 3. Troubleshooting
• 4. Examples
• 5. Bugs & Feature Requests

Technical Manual

• 1. Theory and Implementation
• 2. Validation
• 3. Generalization

Contact

NHERI-SimCenter nheri-simcenter@berkeley.edu