There are 0 repository under building-segmentation topic.
We present a novel complex-valued convolutional and multi-feature fusion network (CVCMFF Net) specifically for building semantic segmentation of InSAR images. It can effectively segment the layover, shadow, and background on both the simulated InSAR building images and the real airborne InSAR images. The segmentation performance of CVCMFF Net is significantly improved compared with other state-of-the-art networks. The comparative experiments are link to https://github.com/Jiankun-chen/building-semantic-segmentation-of-InSAR-images
Codes for TGRS paper: DisOptNet: Distilling Semantic Knowledge from Optical Images for Weather-independent Building Segmentation
Aerial Image segmentation using different EfficientNet based backbone encoders with UNet on Massachusetts Building and Road dataset
Python notebook for building semantic segmentation from high resolution satellite imagery. A part of project SEERI, a collaboration between Braga Tech. and GIZ in developing website for estimating solar potential on building rooftop.
A deep learning approach for buildings segmentation using detectron2 model developed by facebook research group (META)
Description repository for MapAI competition organized by NMI and NORA