Deep learning in urban remote sensing

Organizers :

  • Jonathan Weber, Université de Haute-Alsace, France
  • Camille Kurtz, Université Paris Descartes, France
  • Germain Forestier, Université de Haute-Alsace, France

Abstract :

Deep learning approaches are currently revolutionizing the field of machine learning, especially for applications linked to image processing or more generally computer vision. Remote sensing field is not an exception and the community recently witnessed a growing number of contributions leveraging from deep learning to analyze remote sensing data (object detection & extraction, semantic segmentation, land cover mapping, etc.).

The aim of this special session is to popularize the use of these promising approaches. Indeed, although these methods have become very popular in computer vision over the last ten years, they are not enough validated on remote sensing applications, especially in the context of urban environment analysis. Our objectives are to gather both computer scientists (academics and professionals) familiar with deep learning and end-users close to geographical and environmental sciences who could give sense to raw data. We are also targeting potential new users interested by these approaches in order to stimulate deeper multidisciplinary interactions on this topic.