Buildings Type Classification

Buildings classification using satellite images is becoming more important for several applications such as damage assessment, resource allocation, and population estimation. We focus, in this work on buildings type classification (BTC) of residential and non-residential buildings. We propose to rely solely on RGB satellite images and follow a 2-stage deep learning-based approach. In a nutshell,  in the first stage, buildings’ footprints are extracted using a semantic segmentation model, while in the second stage, the model classifies the cropped images around buildings into 2 classes; residential and non-residential.

Due to the lack of an appropriate dataset for the residential/non-residential building classification, we introduce a new dataset of high-resolution satellite images.
Finally, we validate the proposed approach showing excellent accuracy and F1-score metrics.

Paper preprint can be fetched here.