Deep Learning for Understanding Satellite Imagery: An Experimental Survey.

Journal: Frontiers in artificial intelligence
Published Date: Nov 16, 2020

Abstract

Translating satellite imagery into maps requires intensive effort and time, especially leading to inaccurate maps of the affected regions during disaster and conflict. The combination of availability of recent datasets and advances in computer vision made through deep learning paved the way toward automated satellite image translation. To facilitate research in this direction, we introduce the Satellite Imagery Competition using a modified SpaceNet dataset. Participants had to come up with different segmentation models to detect positions of buildings on satellite images. In this work, we present five approaches based on improvements of U-Net and Mask R-Convolutional Neuronal Networks models, coupled with unique training adaptations using boosting algorithms, morphological filter, Conditional Random Fields and custom losses. The good results-as high as and -from these models demonstrate the feasibility of Deep Learning in automated satellite image annotation.

Authors

  • Sharada Prasanna Mohanty
    Ecole Polytechnique Fédérale de Lausanne, Lausanne, Switzerland.
  • Jakub Czakon
    neptune.ml, Warsaw, Poland.
  • Kamil A Kaczmarek
    neptune.ml, Warsaw, Poland.
  • Andrzej Pyskir
    deepsense.ai, Warsaw, Poland.
  • Piotr Tarasiewicz
    deepsense.ai, Warsaw, Poland.
  • Saket Kunwar
    Centre for Natural Resources Management, Analysis, Training and Policy Research (NARMA), Kathmandu, Nepal.
  • Janick Rohrbach
    Zurich University of Applied Sciences, Zürich, Switzerland.
  • Dave Luo
    Anthropocene Labs, New York, NY, United States.
  • Manjunath Prasad
    Center for Cognitive Interaction Technology (CITEC), Bielefeld University, Bielefeld, Germany.
  • Sascha Fleer
    Center for Cognitive Interaction Technology (CITEC), Bielefeld University, Bielefeld, Germany.
  • Jan Philip Göpfert
    Center for Cognitive Interaction Technology (CITEC), Bielefeld University, Bielefeld, Germany.
  • Akshat Tandon
    Center for Cognitive Interaction Technology (CITEC), Bielefeld University, Bielefeld, Germany.
  • Guillaume Mollard
    Ecole Polytechnique Fédérale de Lausanne, Lausanne, Switzerland.
  • Nikhil Rayaprolu
    International Institute of Information Technology Hyderabad, Hyderabad, India.
  • Marcel Salathe
    Ecole Polytechnique Fédérale de Lausanne, Lausanne, Switzerland.
  • Malte Schilling
    Center for Cognitive Interaction Technology (CITEC), Bielefeld University, Bielefeld, Germany.

Keywords

No keywords available for this article.

External Resources

Popular Topics
Recent Journals