Deep Learning for Earth Observation (DL4EO)

Tagging and data-mining are key elements of the final product. All the anotations work and data-centric model building is created efficiently and provided to the client. Applying Deep Learning to the specifics of satellite imagery is a real passion! Further research and specific training will probably be needed to achieve state-of-the-art performances. Aircraft detection is a recurrent subject for automatic detection in optical satellite imagery. The model has been trained on a combination of satellite images from various providers. Extracting pylons from satellite images is a subject in itself because these objects are mostly hollow and often can only be detected through their shadow in satellite images. This is a typical mix of deep learning techniques and precise measurement based on space technologies.