The first comprehensive Lebanese Building Footprints Map was autonomously generated using Deep Learning Models that were developed and tested at the Lebanese National Remote Sensing Center - CNRS.
We trained fully convolutional 'Encoder-Decoder' like Neural Networks on GEOEYE-1 high resolution satellite images (50 cm/pixel) from the Year 2013 for semantic segmentation of urban areas.
When you ZOOM IN, the dots on the map refer to the centroids of each building at a specific geographical location.
This ongoing research project is supervised by Dr. Ali J. Ghandour and Dr. Abed Ellatif Samhat and conducted by Eng. Hasan Nasrallah. Web development achieved by Kawthar Salami. Special thanks to nVidia GPU Grant and Dr Ghaleb Faour.