Includes bibliographical references and index.

Deep learning backgrounds -- Software -- Data used : the Tokyo dataset -- A simple convolutional neural network -- Fully convolutional neural network -- Classifiers on deep features -- Dealing with multiple sources -- Semantic segmentation of optical imagery -- Data used : the Amsterdam dataset -- Mapping buildings -- Gap filling of optical images : principle -- The Marmande dataset -- Pre-processing -- Model training -- Inference.

"In today's world, deep learning source codes and a plethora of open access geospatial images are available, but readers are missing the educational tools. This is the first practical book to introduce deep learning techniques using free open source tools for processing real world remote sensing images. The approaches are generic and adapted to suit many applications for various remote sensing images processing in landcover mapping, forestry, urban, in disaster mapping, image restoration, etc. Written with practitioners and students in mind, this book helps readers link together the theory and practical use of existing tools and data to create their own remote sensing data processing"--