Classification of multitemporal SAR images using convolutional neural networks and Markov random fields

C. Danilla, C. Persello, Valentyn Tolpekin, J. R. Bergado

Research output: Chapter in Book/Report/Conference proceedingChapterAcademicpeer-review

3 Citations (Scopus)
Original languageUndefined
Title of host publication2017 IEEE International Geoscience and Remote Sensing Symposium (IGARSS)
Subtitle of host publication23-28 Jly 2017, Fort Worth Texas, USA
PublisherIEEE
Pages2231-2234
Number of pages4
ISBN (Electronic)978-1-5090-4951-6
DOIs
Publication statusPublished - 1 Jul 2017

Keywords

  • Markov processes
  • geophysical image processing
  • image classification
  • learning (artificial intelligence)
  • neural nets
  • radar imaging
  • remote sensing by radar
  • synthetic aperture radar
  • terrain mapping
  • Flevoland
  • Markov Random Fields
  • Markov random fields
  • Sentinel-1 images
  • The Netherlands
  • agricultural field mapping
  • classification accuracy
  • classification system
  • complex task
  • convolutional neural networks
  • extract spatial-contextual features
  • land-cover map
  • multitemporal SAR images
  • multitemporal series
  • post-classification label
  • scattering mechanism
  • spatial filters
  • spatial-contextual features
  • speckle noise
  • strong noise
  • synthetic aperture radar images
  • texture mechanism
  • Classification algorithms
  • Feature extraction
  • Filtering
  • Radio frequency
  • Speckle
  • Support vector machines
  • Synthetic aperture radar
  • Convolutional neural networks
  • Sentinel-1
  • speckle filtering

Cite this

Danilla, C., Persello, C., Tolpekin, V., & Bergado, J. R. (2017). Classification of multitemporal SAR images using convolutional neural networks and Markov random fields. In 2017 IEEE International Geoscience and Remote Sensing Symposium (IGARSS): 23-28 Jly 2017, Fort Worth Texas, USA (pp. 2231-2234). IEEE. https://doi.org/10.1109/IGARSS.2017.8127432