Peatland delineation under forest canopy with polsar data using model based decomposition technique

Oleg Antropov, Yrjö Rauste, J. Praks, M. Hallikainen, Tuomas Häme

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

3 Citations (Scopus)

Abstract

The paper describes evaluating the potential of peatland detection under forest canopy with L-band space borne quad-polarization data in the boreal forest zone. Particular emphasis was made on under what seasonal conditions this detection was possible using single SAR data-take. For this purpose multitemporal ALOS PALSAR imagery acquired over Kuortane test site in central Finland during 2007-2008 was used. Supervised classification experiments employing selected polarimetric features were performed using standard maximum likelihood approach and probabilistic neural network (PNN). Strong non-gaussianity effects were noted, with better performance demonstrated by PNN, utilizing non-parametric estimation of probability distributions of the respective polarimetric features. Suitability of several techniques aimed at compensating the presence of forest canopy was studied as well.
Original languageEnglish
Title of host publicationIEEE Geoscience and Remote Sensing Symposium 2012 Proceedings
PublisherInstitute of Electrical and Electronic Engineers IEEE
Pages4918-4921
ISBN (Electronic)978-1-4673-1159-5 , 978-1-4673-1158-8
ISBN (Print)978-1-4673-1160-1
DOIs
Publication statusPublished - 2012
MoE publication typeA4 Article in a conference publication

Fingerprint

forest canopy
peatland
decomposition
PALSAR
ALOS
image classification
boreal forest
synthetic aperture radar
imagery
polarization
experiment
detection
test
distribution
effect

Keywords

  • Peatland
  • SAR polarimetry
  • boreal forest
  • classification

Cite this

Antropov, O., Rauste, Y., Praks, J., Hallikainen, M., & Häme, T. (2012). Peatland delineation under forest canopy with polsar data using model based decomposition technique. In IEEE Geoscience and Remote Sensing Symposium 2012 Proceedings (pp. 4918-4921). Institute of Electrical and Electronic Engineers IEEE. https://doi.org/10.1109/IGARSS.2012.6352509
Antropov, Oleg ; Rauste, Yrjö ; Praks, J. ; Hallikainen, M. ; Häme, Tuomas. / Peatland delineation under forest canopy with polsar data using model based decomposition technique. IEEE Geoscience and Remote Sensing Symposium 2012 Proceedings. Institute of Electrical and Electronic Engineers IEEE, 2012. pp. 4918-4921
@inproceedings{1af69ef8340949528b965aaaa4b47a22,
title = "Peatland delineation under forest canopy with polsar data using model based decomposition technique",
abstract = "The paper describes evaluating the potential of peatland detection under forest canopy with L-band space borne quad-polarization data in the boreal forest zone. Particular emphasis was made on under what seasonal conditions this detection was possible using single SAR data-take. For this purpose multitemporal ALOS PALSAR imagery acquired over Kuortane test site in central Finland during 2007-2008 was used. Supervised classification experiments employing selected polarimetric features were performed using standard maximum likelihood approach and probabilistic neural network (PNN). Strong non-gaussianity effects were noted, with better performance demonstrated by PNN, utilizing non-parametric estimation of probability distributions of the respective polarimetric features. Suitability of several techniques aimed at compensating the presence of forest canopy was studied as well.",
keywords = "Peatland, SAR polarimetry, boreal forest, classification",
author = "Oleg Antropov and Yrj{\"o} Rauste and J. Praks and M. Hallikainen and Tuomas H{\"a}me",
note = "Project code: 71273",
year = "2012",
doi = "10.1109/IGARSS.2012.6352509",
language = "English",
isbn = "978-1-4673-1160-1",
pages = "4918--4921",
booktitle = "IEEE Geoscience and Remote Sensing Symposium 2012 Proceedings",
publisher = "Institute of Electrical and Electronic Engineers IEEE",
address = "United States",

}

Antropov, O, Rauste, Y, Praks, J, Hallikainen, M & Häme, T 2012, Peatland delineation under forest canopy with polsar data using model based decomposition technique. in IEEE Geoscience and Remote Sensing Symposium 2012 Proceedings. Institute of Electrical and Electronic Engineers IEEE, pp. 4918-4921. https://doi.org/10.1109/IGARSS.2012.6352509

Peatland delineation under forest canopy with polsar data using model based decomposition technique. / Antropov, Oleg; Rauste, Yrjö; Praks, J.; Hallikainen, M.; Häme, Tuomas.

IEEE Geoscience and Remote Sensing Symposium 2012 Proceedings. Institute of Electrical and Electronic Engineers IEEE, 2012. p. 4918-4921.

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

TY - GEN

T1 - Peatland delineation under forest canopy with polsar data using model based decomposition technique

AU - Antropov, Oleg

AU - Rauste, Yrjö

AU - Praks, J.

AU - Hallikainen, M.

AU - Häme, Tuomas

N1 - Project code: 71273

PY - 2012

Y1 - 2012

N2 - The paper describes evaluating the potential of peatland detection under forest canopy with L-band space borne quad-polarization data in the boreal forest zone. Particular emphasis was made on under what seasonal conditions this detection was possible using single SAR data-take. For this purpose multitemporal ALOS PALSAR imagery acquired over Kuortane test site in central Finland during 2007-2008 was used. Supervised classification experiments employing selected polarimetric features were performed using standard maximum likelihood approach and probabilistic neural network (PNN). Strong non-gaussianity effects were noted, with better performance demonstrated by PNN, utilizing non-parametric estimation of probability distributions of the respective polarimetric features. Suitability of several techniques aimed at compensating the presence of forest canopy was studied as well.

AB - The paper describes evaluating the potential of peatland detection under forest canopy with L-band space borne quad-polarization data in the boreal forest zone. Particular emphasis was made on under what seasonal conditions this detection was possible using single SAR data-take. For this purpose multitemporal ALOS PALSAR imagery acquired over Kuortane test site in central Finland during 2007-2008 was used. Supervised classification experiments employing selected polarimetric features were performed using standard maximum likelihood approach and probabilistic neural network (PNN). Strong non-gaussianity effects were noted, with better performance demonstrated by PNN, utilizing non-parametric estimation of probability distributions of the respective polarimetric features. Suitability of several techniques aimed at compensating the presence of forest canopy was studied as well.

KW - Peatland

KW - SAR polarimetry

KW - boreal forest

KW - classification

U2 - 10.1109/IGARSS.2012.6352509

DO - 10.1109/IGARSS.2012.6352509

M3 - Conference article in proceedings

SN - 978-1-4673-1160-1

SP - 4918

EP - 4921

BT - IEEE Geoscience and Remote Sensing Symposium 2012 Proceedings

PB - Institute of Electrical and Electronic Engineers IEEE

ER -

Antropov O, Rauste Y, Praks J, Hallikainen M, Häme T. Peatland delineation under forest canopy with polsar data using model based decomposition technique. In IEEE Geoscience and Remote Sensing Symposium 2012 Proceedings. Institute of Electrical and Electronic Engineers IEEE. 2012. p. 4918-4921 https://doi.org/10.1109/IGARSS.2012.6352509