Skip to main content

Building Recognition using AI at Large-Scale

Project description

logo Building Recognition using AI at Large-Scale.

BRAILS

What is BRAILS

BRAILS is the acronym for Building Recognition using AI at Large-Scale, which is an AI-Based pipeline for city-scale building information modeling (BIM).

How to install

pip install BRAILS

How to use

The following example can be found in this Google Colab Notebook.

Example images can be downloaded like this.

wget https://zenodo.org/record/4095668/files/image_examples.zip
# import modules
from brails.RoofTypeClassifier import RoofClassifier
from brails.OccupancyClassClassifier import OccupancyClassifier
from brails.SoftstoryClassifier import SoftstoryClassifier

# initialize a roof classifier
roofModel = RoofClassifier()

# initialize an occupancy classifier
occupancyModel = OccupancyClassifier()

# initialize a soft-story classifier
ssModel = SoftstoryClassifier()

# use the roof classifier 

imgs = ['image_examples/Roof/gabled/76.png',
        'image_examples/Roof/hipped/54.png',
        'image_examples/Roof/flat/94.png']

predictions = roofModel.predict(imgs)

# use the occupancy classifier 

imgs = ['image_examples/Occupancy/RES1/51563.png',
        'image_examples/Occupancy/RES3/65883.png']

predictions = occupancyModel.predict(imgs)

# use the softstory classifier 

imgs = ['image_examples/Softstory/Others/3110.jpg',
        'image_examples/Softstory/Softstory/901.jpg']

predictions = ssModel.predict(imgs)

The predictions look like this:

Image :  image_examples/Roof/gabled/76.png     Class : gabled (83.21%)
Image :  image_examples/Roof/hipped/54.png     Class : hipped (100.0%)
Image :  image_examples/Roof/flat/94.png     Class : flat (97.68%)
Results written in file roofType_preds.csv

Image :  image_examples/Occupancy/RES1/51563.png     Class : RES1 (99.99%)
Image :  image_examples/Occupancy/RES3/65883.png     Class : RES3 (98.67%)
Results written in file occupancy_preds.csv

Image :  image_examples/Softstory/Others/3110.jpg     Class : others (96.13%)
Image :  image_examples/Softstory/Softstory/901.jpg     Class : softstory (96.31%)
Results written in file softstory_preds.csv

Documents

Read the document here.

More details in paper: here.

How to cite

Charles Wang, Qian Yu, Frank McKenna, Barbaros Cetiner, Stella X. Yu, Ertugrul Taciroglu & Kincho H. Law. (2019, October 11). NHERI-SimCenter/BRAILS: v1.0.1 (Version v1.0.1). Zenodo. http://doi.org/10.5281/zenodo.3483208

Acknowledgement

This material is based upon work supported by the National Science Foundation under Grant No. 1612843.

Contact

Charles Wang, NHERI SimCenter, UC Berkeley, c_w@berkeley.edu

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

BRAILS-1.9.3.6.tar.gz (15.5 kB view hashes)

Uploaded Source

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page