Introducing prior knowledge in temporal distances for Satellite Image Time Series analysis

Francois Petitjean, Jordi Inglada, Pierre Gancarski

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

1 Citation (Scopus)

Abstract

Satellite Image Time Series are becoming increasingly available and will continue to do so in the coming years thanks to the launch of space missions which aim at providing a coverage of the Earth every few days with high spatial resolution. In the case of optical imagery, it will be possible to produce land use and cover change maps with detailed nomenclatures. It has been shown that the Dynamic Time Warping similarity measure is a consistent tool for the comparison of radiometric profiles of temporal evolution. Actually, it makes it possible to compare time series with both different lengths and different sampling. This property allows us to make the most of partially cloud-covered images, but also to transfer the knowledge learned on an agronomical year in order to classify the next year without using reference data. This article pursues this work on satellite image time series analysis and focuses on the introduction of constraints in the distance in order to fit to the expert's knowledge about the observed phenomena.

Original languageEnglish
Title of host publicationIGARSS 2012 - 2012 IEEE International Geoscience and Remote Sensing Symposium
PublisherIEEE, Institute of Electrical and Electronics Engineers
Pages5426-5429
Number of pages4
DOIs
Publication statusPublished - 2012
Externally publishedYes
EventIEEE International Geoscience and Remote Sensing Symposium 2012 - International Congress Centre, Munich, Germany
Duration: 22 Jul 201227 Jul 2012
Conference number: 32nd
http://ieeexplore.ieee.org/xpl/mostRecentIssue.jsp?punumber=6334512 (IEEE Conference Proceedings)

Conference

ConferenceIEEE International Geoscience and Remote Sensing Symposium 2012
Abbreviated titleIGARSS 2012
CountryGermany
CityMunich
Period22/07/1227/07/12
Internet address

Keywords

  • Crops
  • Image classification
  • Knowledge management
  • Remote Sensing
  • Time series analysis

Cite this

Petitjean, F., Inglada, J., & Gancarski, P. (2012). Introducing prior knowledge in temporal distances for Satellite Image Time Series analysis. In IGARSS 2012 - 2012 IEEE International Geoscience and Remote Sensing Symposium (pp. 5426-5429). [6352379] IEEE, Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/IGARSS.2012.6352379
Petitjean, Francois ; Inglada, Jordi ; Gancarski, Pierre. / Introducing prior knowledge in temporal distances for Satellite Image Time Series analysis. IGARSS 2012 - 2012 IEEE International Geoscience and Remote Sensing Symposium. IEEE, Institute of Electrical and Electronics Engineers, 2012. pp. 5426-5429
@inproceedings{25f77738a1bd4c1881a89af45fc720a8,
title = "Introducing prior knowledge in temporal distances for Satellite Image Time Series analysis",
abstract = "Satellite Image Time Series are becoming increasingly available and will continue to do so in the coming years thanks to the launch of space missions which aim at providing a coverage of the Earth every few days with high spatial resolution. In the case of optical imagery, it will be possible to produce land use and cover change maps with detailed nomenclatures. It has been shown that the Dynamic Time Warping similarity measure is a consistent tool for the comparison of radiometric profiles of temporal evolution. Actually, it makes it possible to compare time series with both different lengths and different sampling. This property allows us to make the most of partially cloud-covered images, but also to transfer the knowledge learned on an agronomical year in order to classify the next year without using reference data. This article pursues this work on satellite image time series analysis and focuses on the introduction of constraints in the distance in order to fit to the expert's knowledge about the observed phenomena.",
keywords = "Crops, Image classification, Knowledge management, Remote Sensing, Time series analysis",
author = "Francois Petitjean and Jordi Inglada and Pierre Gancarski",
year = "2012",
doi = "10.1109/IGARSS.2012.6352379",
language = "English",
pages = "5426--5429",
booktitle = "IGARSS 2012 - 2012 IEEE International Geoscience and Remote Sensing Symposium",
publisher = "IEEE, Institute of Electrical and Electronics Engineers",
address = "United States of America",

}

Petitjean, F, Inglada, J & Gancarski, P 2012, Introducing prior knowledge in temporal distances for Satellite Image Time Series analysis. in IGARSS 2012 - 2012 IEEE International Geoscience and Remote Sensing Symposium., 6352379, IEEE, Institute of Electrical and Electronics Engineers, pp. 5426-5429, IEEE International Geoscience and Remote Sensing Symposium 2012, Munich, Germany, 22/07/12. https://doi.org/10.1109/IGARSS.2012.6352379

Introducing prior knowledge in temporal distances for Satellite Image Time Series analysis. / Petitjean, Francois; Inglada, Jordi; Gancarski, Pierre.

IGARSS 2012 - 2012 IEEE International Geoscience and Remote Sensing Symposium. IEEE, Institute of Electrical and Electronics Engineers, 2012. p. 5426-5429 6352379.

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

TY - GEN

T1 - Introducing prior knowledge in temporal distances for Satellite Image Time Series analysis

AU - Petitjean, Francois

AU - Inglada, Jordi

AU - Gancarski, Pierre

PY - 2012

Y1 - 2012

N2 - Satellite Image Time Series are becoming increasingly available and will continue to do so in the coming years thanks to the launch of space missions which aim at providing a coverage of the Earth every few days with high spatial resolution. In the case of optical imagery, it will be possible to produce land use and cover change maps with detailed nomenclatures. It has been shown that the Dynamic Time Warping similarity measure is a consistent tool for the comparison of radiometric profiles of temporal evolution. Actually, it makes it possible to compare time series with both different lengths and different sampling. This property allows us to make the most of partially cloud-covered images, but also to transfer the knowledge learned on an agronomical year in order to classify the next year without using reference data. This article pursues this work on satellite image time series analysis and focuses on the introduction of constraints in the distance in order to fit to the expert's knowledge about the observed phenomena.

AB - Satellite Image Time Series are becoming increasingly available and will continue to do so in the coming years thanks to the launch of space missions which aim at providing a coverage of the Earth every few days with high spatial resolution. In the case of optical imagery, it will be possible to produce land use and cover change maps with detailed nomenclatures. It has been shown that the Dynamic Time Warping similarity measure is a consistent tool for the comparison of radiometric profiles of temporal evolution. Actually, it makes it possible to compare time series with both different lengths and different sampling. This property allows us to make the most of partially cloud-covered images, but also to transfer the knowledge learned on an agronomical year in order to classify the next year without using reference data. This article pursues this work on satellite image time series analysis and focuses on the introduction of constraints in the distance in order to fit to the expert's knowledge about the observed phenomena.

KW - Crops

KW - Image classification

KW - Knowledge management

KW - Remote Sensing

KW - Time series analysis

UR - http://www.scopus.com/inward/record.url?scp=84873168203&partnerID=8YFLogxK

U2 - 10.1109/IGARSS.2012.6352379

DO - 10.1109/IGARSS.2012.6352379

M3 - Conference Paper

AN - SCOPUS:84873168203

SP - 5426

EP - 5429

BT - IGARSS 2012 - 2012 IEEE International Geoscience and Remote Sensing Symposium

PB - IEEE, Institute of Electrical and Electronics Engineers

ER -

Petitjean F, Inglada J, Gancarski P. Introducing prior knowledge in temporal distances for Satellite Image Time Series analysis. In IGARSS 2012 - 2012 IEEE International Geoscience and Remote Sensing Symposium. IEEE, Institute of Electrical and Electronics Engineers. 2012. p. 5426-5429. 6352379 https://doi.org/10.1109/IGARSS.2012.6352379