Nonlinear Time-Series Adaptation for Land Cover Classification

Adeline Bailly 1, 2 Laetitia Chapel 2 Romain Tavenard 2, 1 Gustau Camps-Valls 3
1 LETG - Rennes - Littoral, Environnement, Télédétection, Géomatique
LETG - Littoral, Environnement, Télédétection, Géomatique UMR 6554
2 OBELIX - Environment observation with complex imagery
UBS - Université de Bretagne Sud, IRISA-D5 - SIGNAUX ET IMAGES NUMÉRIQUES, ROBOTIQUE
Abstract : Automatic land cover classification from satellite image time series is of paramount relevance to assess vegetation and crop status, with important implications in agriculture, biofuels and food. However, due to the high cost and human resources needed to characterize and classify land cover through field campaigns, a recurrent limiting factor is the lack of available labeled data. On top of this, the bio-geo-physical variables exhibit particular temporal structures that need to be exploited. Land cover classification based on image time series is very complex because of the data manifold distortions through time. We propose the use of the kernel manifold alignment (KEMA) method for domain adaptation of remote sensing time series before classification. KEMA is nonlinear, semi-supervised, and reduces to solve a simple generalized eigenproblem. We give empirical evidence of performance through classification of biophysical (LAI, fAPAR, FVC, NDVI) time series at a global scale.
Document type :
Journal articles
Complete list of metadatas

Cited literature [18 references]  Display  Hide  Download

https://halshs.archives-ouvertes.fr/halshs-01515283
Contributor : Romain Tavenard <>
Submitted on : Thursday, April 27, 2017 - 11:50:03 AM
Last modification on : Tuesday, May 7, 2019 - 6:30:09 PM
Long-term archiving on : Friday, July 28, 2017 - 12:42:43 PM

File

final_version.pdf
Files produced by the author(s)

Identifiers

Citation

Adeline Bailly, Laetitia Chapel, Romain Tavenard, Gustau Camps-Valls. Nonlinear Time-Series Adaptation for Land Cover Classification. IEEE Geoscience and Remote Sensing Letters, IEEE - Institute of Electrical and Electronics Engineers, 2017, ⟨10.1109/LGRS.2017.2686639⟩. ⟨halshs-01515283⟩

Share

Metrics

Record views

1032

Files downloads

518