VHR Satellite Image Time Series analysis using expert knowledge modeling and user assistance

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

In this paper, we address land cover regions monitoring issue by introducing prior knowledge about the studied scene. Actually, remote sensing data growing volumes lead to increase the complexity of direct images interpretation. So, we attempt to overcome this problem by formalizing expert knowledge. The proposed method extends an expert knowledge formalism and temporal evolution graph representation to handle sub-graphs similarity. For this purpose, a user interaction through the proposition of a time window and concepts evolution is introduced. Hence, the proposed approach extracts the most similar temporal evolution to user request over the generated SITS subgraphs. Experiments are performed on synthesized and real STIS and compared to previously presented approaches for STIS analysis.

Original languageEnglish
Title of host publication2016 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2016 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages5173-5176
Number of pages4
ISBN (Electronic)9781509033324
DOIs
Publication statusPublished - 1 Nov 2016
Event36th IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2016 - Beijing, China
Duration: 10 Jul 201615 Jul 2016

Publication series

NameInternational Geoscience and Remote Sensing Symposium (IGARSS)
Volume2016-November

Conference

Conference36th IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2016
Country/TerritoryChina
CityBeijing
Period10/07/1615/07/16

Keywords

  • Spatio-temporal analysis
  • VHR-SITS
  • knowledge modeling
  • semantic
  • sub-graph
  • user assistance

Fingerprint

Dive into the research topics of 'VHR Satellite Image Time Series analysis using expert knowledge modeling and user assistance'. Together they form a unique fingerprint.

Cite this