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. However, due to meteorological phenomena, such as clouds, these time series will become irregular in terms of temporal sampling and one will need to compare time series with different lengths. In this paper we present an approach to image time series analysis which is able to deal with irregularly sampled series and which also allows the comparison of pairs of time series where each element of the pair has a different number of samples. We present the Dynamic Time Warping from a theoretical point of view and illustrate its capabilities for domain adaptation.
| Original language | English |
|---|---|
| Title of host publication | 2011 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2011 - Proceedings |
| Publisher | IEEE, Institute of Electrical and Electronics Engineers |
| Pages | 3578-3581 |
| Number of pages | 4 |
| ISBN (Print) | 9781457710056 |
| DOIs | |
| Publication status | Published - 2011 |
| Externally published | Yes |
| Event | IEEE International Geoscience and Remote Sensing Symposium 2011 - Vancouver Convention Center, Vancouver BC, Canada Duration: 24 Jul 2011 → 29 Jul 2011 http://ieeexplore.ieee.org/xpl/mostRecentIssue.jsp?punumber=6034618 (IEEE Conference Proceedings) |
Conference
| Conference | IEEE International Geoscience and Remote Sensing Symposium 2011 |
|---|---|
| Abbreviated title | IGARSS 2011 |
| Country | Canada |
| City | Vancouver BC |
| Period | 24/07/11 → 29/07/11 |
| Internet address |
|
Keywords
- Classification
- Domain Adaptation
- Dynamic Time Warping
- Remote Sensing
- Satellite Image Time Series
Cite this
}
Temporal domain adaptation under time warping. / Petitjean, François; Inglada, Jordi; Gançarski, Pierre.
2011 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2011 - Proceedings. IEEE, Institute of Electrical and Electronics Engineers, 2011. p. 3578-3581 6049995.Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research › peer-review
TY - GEN
T1 - Temporal domain adaptation under time warping
AU - Petitjean, François
AU - Inglada, Jordi
AU - Gançarski, Pierre
PY - 2011
Y1 - 2011
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. However, due to meteorological phenomena, such as clouds, these time series will become irregular in terms of temporal sampling and one will need to compare time series with different lengths. In this paper we present an approach to image time series analysis which is able to deal with irregularly sampled series and which also allows the comparison of pairs of time series where each element of the pair has a different number of samples. We present the Dynamic Time Warping from a theoretical point of view and illustrate its capabilities for domain adaptation.
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. However, due to meteorological phenomena, such as clouds, these time series will become irregular in terms of temporal sampling and one will need to compare time series with different lengths. In this paper we present an approach to image time series analysis which is able to deal with irregularly sampled series and which also allows the comparison of pairs of time series where each element of the pair has a different number of samples. We present the Dynamic Time Warping from a theoretical point of view and illustrate its capabilities for domain adaptation.
KW - Classification
KW - Domain Adaptation
KW - Dynamic Time Warping
KW - Remote Sensing
KW - Satellite Image Time Series
UR - http://www.scopus.com/inward/record.url?scp=80955134440&partnerID=8YFLogxK
U2 - 10.1109/IGARSS.2011.6049995
DO - 10.1109/IGARSS.2011.6049995
M3 - Conference Paper
AN - SCOPUS:80955134440
SN - 9781457710056
SP - 3578
EP - 3581
BT - 2011 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2011 - Proceedings
PB - IEEE, Institute of Electrical and Electronics Engineers
ER -