DLR-Logo -> http://www.dlr.de
DLR Portal Home | Imprint | Privacy Policy | Contact | Deutsch
Fontsize: [-] Text [+]

Land-Cover Evolution Class Analysis in Image Time Series of Landsat and Sentinel-2 Based on Latent Dirichlet Allocation

Espinoza-Molina, Daniela and Bahmanyar, Reza and Datcu, Mihai and Diaz-Delgado, Ricardo and Bustamante, Javier (2017) Land-Cover Evolution Class Analysis in Image Time Series of Landsat and Sentinel-2 Based on Latent Dirichlet Allocation. In: Proceeding of MultiTemp 2017. IEEExplore. Multitemp 2017, 27-29 Jun 2017, Bruges, Belgium.

[img] PDF


Satellite Image Time Series (SITS) are widely used in monitoring the Earth’s changes for various applications such as land-cover evolution analysis. In this paper, we propose an approach based on Latent Dirichlet Allocation (LDA) which considers spatial and spectral information to measure the land-cover changes in multispectral SITS. For our experiments, we focus on the vegetation dynamics of the Do˜nana National Park (in southwestern Spain) using a Landsat and a Sentinel-2 SITS dataset. The proposed approach represents each image by Normalized Difference Vegetation Index (NDVI) and tiles it into smaller patches. The patches are then modeled as Bag-of-Words (BoW) and LDA is applied to them in order to discover the latent structure of the image. The divergence between the latent structures of any two consecutive images is then considered as the measure of change. Results show that the changes measured by the proposed approach can represent the vegetation dynam- ics of the region of interest. Moreover, comparing the results obtained from the two datasets demonstrates that using high- level information allows the proposed approach to measure the changes independent of the sensor. This will support long-term monitoring through combining various available data.

Item URL in elib:https://elib.dlr.de/112926/
Document Type:Conference or Workshop Item (Speech)
Title:Land-Cover Evolution Class Analysis in Image Time Series of Landsat and Sentinel-2 Based on Latent Dirichlet Allocation
AuthorsInstitution or Email of AuthorsAuthors ORCID iD
Espinoza-Molina, Danieladaniela.espinozamolina (at) dlr.deUNSPECIFIED
Bahmanyar, Rezareza.bahmanyar (at) dlr.deUNSPECIFIED
Datcu, Mihaimihai.datcu (at) dlr.deUNSPECIFIED
Diaz-Delgado, Ricardolast, laboratory of gis and remote sensingUNSPECIFIED
Bustamante, Javierlast, laboratory of gis and remote sensingUNSPECIFIED
Date:27 June 2017
Journal or Publication Title:Proceeding of MultiTemp 2017
Refereed publication:No
Open Access:Yes
Gold Open Access:No
In ISI Web of Science:No
Keywords:Satellite Image Time Series, Latent Dirichlet Allocation, Sentinel-2, Land-Cover
Event Title:Multitemp 2017
Event Location:Bruges, Belgium
Event Type:international Conference
Event Dates:27-29 Jun 2017
Organizer:Belgian Science Policy Office (BELSPO) and VITO Remote Sensing
HGF - Research field:Aeronautics, Space and Transport
HGF - Program:Space
HGF - Program Themes:Earth Observation
DLR - Research area:Raumfahrt
DLR - Program:R EO - Erdbeobachtung
DLR - Research theme (Project):R - Vorhaben hochauflösende Fernerkundungsverfahren
Location: Oberpfaffenhofen
Institutes and Institutions:Remote Sensing Technology Institute > Photogrammetry and Image Analysis
Deposited By: Espinoza Molina, Daniela
Deposited On:28 Jun 2017 12:41
Last Modified:31 Jul 2019 20:10

Repository Staff Only: item control page

Help & Contact
electronic library is running on EPrints 3.3.12
Copyright © 2008-2017 German Aerospace Center (DLR). All rights reserved.