Potential of multi-temporal Sentinel-1A Dual polarization SAR images for vegetable classification in Indonesia

Mengmeng Li, W. Bijker

Research output: Chapter in Book/Report/Conference proceedingChapterAcademicpeer-review

3 Downloads (Pure)

Abstract

As part of the G4AW SMARTSeeds project, this study aims to investigate the potential of dense time series of Sentinel-1A dual polarization data for the classification of vegetables that are common in East Java, Indonesia. We first analyzed the temporal behavior of three main types of vegetables (i.e.chili, tomato and cucumber) in terms of backscatter (VH andVV) intensity, and of polarimetric features (i.e. entropy,al-pha and anisotropy) derived from polarization decomposition. We then applied a support vector machine with an intersection kernel to the time series data of vegetable samples collected infield. Our results showed that dense time series Sentinel-1Aimages are of high potential for vegetable classification. Be-sides using backscatter intensity, the polarimetric information can further improve the discrimination between three specific vegetable types.
Original languageEnglish
Title of host publicationIGARSS 2018 : IEEE International Geoscience and Remote Sensing Symposium : Observing, Understanding and Forecasting the Dynamics of Our Planet
PublisherIEEE
Pages3828-3831
Number of pages4
EditionIEEE Catalog Number: CFP18IGA-ART
ISBN (Electronic)978-1-5386-7150-4/18
ISBN (Print)978-1-5386-7150-4/18
Publication statusPublished - 2018
Event38th IEEE International Geoscience and Remote Sensing Symposium 2018: Observing, Understanding and Forcasting the Dynamics of Our Planet - Feria Valencia Convention & Exhibition Center, Valencia, Spain
Duration: 22 Jul 201827 Jul 2018
Conference number: 38
https://www.igarss2018.org/

Conference

Conference38th IEEE International Geoscience and Remote Sensing Symposium 2018
Abbreviated titleIGARSS 2018
CountrySpain
CityValencia
Period22/07/1827/07/18
Internet address

Fingerprint

vegetable
synthetic aperture radar
polarization
time series
backscatter
entropy
anisotropy
decomposition

Cite this

Li, M., & Bijker, W. (2018). Potential of multi-temporal Sentinel-1A Dual polarization SAR images for vegetable classification in Indonesia. In IGARSS 2018 : IEEE International Geoscience and Remote Sensing Symposium : Observing, Understanding and Forecasting the Dynamics of Our Planet (IEEE Catalog Number: CFP18IGA-ART ed., pp. 3828-3831). IEEE.
Li, Mengmeng ; Bijker, W. / Potential of multi-temporal Sentinel-1A Dual polarization SAR images for vegetable classification in Indonesia. IGARSS 2018 : IEEE International Geoscience and Remote Sensing Symposium : Observing, Understanding and Forecasting the Dynamics of Our Planet. IEEE Catalog Number: CFP18IGA-ART. ed. IEEE, 2018. pp. 3828-3831
@inbook{4c07a9553fcd48198e666af8d5b2ea2b,
title = "Potential of multi-temporal Sentinel-1A Dual polarization SAR images for vegetable classification in Indonesia",
abstract = "As part of the G4AW SMARTSeeds project, this study aims to investigate the potential of dense time series of Sentinel-1A dual polarization data for the classification of vegetables that are common in East Java, Indonesia. We first analyzed the temporal behavior of three main types of vegetables (i.e.chili, tomato and cucumber) in terms of backscatter (VH andVV) intensity, and of polarimetric features (i.e. entropy,al-pha and anisotropy) derived from polarization decomposition. We then applied a support vector machine with an intersection kernel to the time series data of vegetable samples collected infield. Our results showed that dense time series Sentinel-1Aimages are of high potential for vegetable classification. Be-sides using backscatter intensity, the polarimetric information can further improve the discrimination between three specific vegetable types.",
author = "Mengmeng Li and W. Bijker",
year = "2018",
language = "English",
isbn = "978-1-5386-7150-4/18",
pages = "3828--3831",
booktitle = "IGARSS 2018 : IEEE International Geoscience and Remote Sensing Symposium : Observing, Understanding and Forecasting the Dynamics of Our Planet",
publisher = "IEEE",
address = "United States",
edition = "IEEE Catalog Number: CFP18IGA-ART",

}

Li, M & Bijker, W 2018, Potential of multi-temporal Sentinel-1A Dual polarization SAR images for vegetable classification in Indonesia. in IGARSS 2018 : IEEE International Geoscience and Remote Sensing Symposium : Observing, Understanding and Forecasting the Dynamics of Our Planet. IEEE Catalog Number: CFP18IGA-ART edn, IEEE, pp. 3828-3831, 38th IEEE International Geoscience and Remote Sensing Symposium 2018, Valencia, Spain, 22/07/18.

Potential of multi-temporal Sentinel-1A Dual polarization SAR images for vegetable classification in Indonesia. / Li, Mengmeng; Bijker, W.

IGARSS 2018 : IEEE International Geoscience and Remote Sensing Symposium : Observing, Understanding and Forecasting the Dynamics of Our Planet. IEEE Catalog Number: CFP18IGA-ART. ed. IEEE, 2018. p. 3828-3831.

Research output: Chapter in Book/Report/Conference proceedingChapterAcademicpeer-review

TY - CHAP

T1 - Potential of multi-temporal Sentinel-1A Dual polarization SAR images for vegetable classification in Indonesia

AU - Li, Mengmeng

AU - Bijker, W.

PY - 2018

Y1 - 2018

N2 - As part of the G4AW SMARTSeeds project, this study aims to investigate the potential of dense time series of Sentinel-1A dual polarization data for the classification of vegetables that are common in East Java, Indonesia. We first analyzed the temporal behavior of three main types of vegetables (i.e.chili, tomato and cucumber) in terms of backscatter (VH andVV) intensity, and of polarimetric features (i.e. entropy,al-pha and anisotropy) derived from polarization decomposition. We then applied a support vector machine with an intersection kernel to the time series data of vegetable samples collected infield. Our results showed that dense time series Sentinel-1Aimages are of high potential for vegetable classification. Be-sides using backscatter intensity, the polarimetric information can further improve the discrimination between three specific vegetable types.

AB - As part of the G4AW SMARTSeeds project, this study aims to investigate the potential of dense time series of Sentinel-1A dual polarization data for the classification of vegetables that are common in East Java, Indonesia. We first analyzed the temporal behavior of three main types of vegetables (i.e.chili, tomato and cucumber) in terms of backscatter (VH andVV) intensity, and of polarimetric features (i.e. entropy,al-pha and anisotropy) derived from polarization decomposition. We then applied a support vector machine with an intersection kernel to the time series data of vegetable samples collected infield. Our results showed that dense time series Sentinel-1Aimages are of high potential for vegetable classification. Be-sides using backscatter intensity, the polarimetric information can further improve the discrimination between three specific vegetable types.

UR - https://ezproxy2.utwente.nl/login?url=https://webapps.itc.utwente.nl/library/2018/chap/bijker_pot.pdf

M3 - Chapter

SN - 978-1-5386-7150-4/18

SP - 3828

EP - 3831

BT - IGARSS 2018 : IEEE International Geoscience and Remote Sensing Symposium : Observing, Understanding and Forecasting the Dynamics of Our Planet

PB - IEEE

ER -

Li M, Bijker W. Potential of multi-temporal Sentinel-1A Dual polarization SAR images for vegetable classification in Indonesia. In IGARSS 2018 : IEEE International Geoscience and Remote Sensing Symposium : Observing, Understanding and Forecasting the Dynamics of Our Planet. IEEE Catalog Number: CFP18IGA-ART ed. IEEE. 2018. p. 3828-3831