Effect of hyperspectral image denoising with PCA and total variation on tree species mapping using Apex Data

Frieke Vancoillie, Wenzhi Liao, Flore Devriendt, Sidharta Gautama, Robert De Wulf, Kris Vandekerkhove, Loannis Gitas (Editor), Giorgios Mallinis (Editor), Petros Patias (Editor), Dimitris Stathakis (Editor), Georgios Zalidis (Editor)

Research output: Contribution to journalArticle

Abstract

In this paper, the impact of image denoising on feature selection and tree species mapping accuracy is assessed. We apply a novel algorithm for hyperspectral (HS) image denoising using principal component analysis (PCA) and total variation (TV). The method is embedded in an object‐based classification framework and tested for complex forests with closed canopies and scarce reference data. Results show that, under the given conditions, HS image denoising is beneficial yielding stable mapping results with acceptable accuracy levels. Denoising also affected feature selection processing time with a time gain of 41.6%.
Original languageEnglish
Pages (from-to)281-286
Number of pages6
JournalSouth-Eastern European Journal of Earth Observation and Geomatics
Volume3
Issue number25
Publication statusPublished - 24 May 2014
Event5th International conference on Geographic Object-Based Image Analysis (GEOBIA 2014) - Thessaloniki, Greece
Duration: 21 May 201424 May 2014

Fingerprint

principal components analysis
principal component analysis
apexes
canopies
canopy
effect

Keywords

  • denoising
  • broadleaved forest
  • object‐based tree species classification
  • hyperspectral data

Cite this

Vancoillie, F., Liao, W., Devriendt, F., Gautama, S., De Wulf, R., Vandekerkhove, K., ... Zalidis, G. (Ed.) (2014). Effect of hyperspectral image denoising with PCA and total variation on tree species mapping using Apex Data. South-Eastern European Journal of Earth Observation and Geomatics, 3(25), 281-286.
Vancoillie, Frieke ; Liao, Wenzhi ; Devriendt, Flore ; Gautama, Sidharta ; De Wulf, Robert ; Vandekerkhove, Kris ; Gitas, Loannis (Editor) ; Mallinis, Giorgios (Editor) ; Patias, Petros (Editor) ; Stathakis, Dimitris (Editor) ; Zalidis, Georgios (Editor). / Effect of hyperspectral image denoising with PCA and total variation on tree species mapping using Apex Data. In: South-Eastern European Journal of Earth Observation and Geomatics. 2014 ; Vol. 3, No. 25. pp. 281-286.
@article{54ceee5b23b64de9a90214a923d21acc,
title = "Effect of hyperspectral image denoising with PCA and total variation on tree species mapping using Apex Data",
abstract = "In this paper, the impact of image denoising on feature selection and tree species mapping accuracy is assessed. We apply a novel algorithm for hyperspectral (HS) image denoising using principal component analysis (PCA) and total variation (TV). The method is embedded in an object‐based classification framework and tested for complex forests with closed canopies and scarce reference data. Results show that, under the given conditions, HS image denoising is beneficial yielding stable mapping results with acceptable accuracy levels. Denoising also affected feature selection processing time with a time gain of 41.6{\%}.",
keywords = "denoising, broadleaved forest, object‐based tree species classification, hyperspectral data",
author = "Frieke Vancoillie and Wenzhi Liao and Flore Devriendt and Sidharta Gautama and {De Wulf}, Robert and Kris Vandekerkhove and Loannis Gitas and Giorgios Mallinis and Petros Patias and Dimitris Stathakis and Georgios Zalidis",
year = "2014",
month = "5",
day = "24",
language = "English",
volume = "3",
pages = "281--286",
number = "25",

}

Vancoillie, F, Liao, W, Devriendt, F, Gautama, S, De Wulf, R, Vandekerkhove, K, Gitas, L (ed.), Mallinis, G (ed.), Patias, P (ed.), Stathakis, D (ed.) & Zalidis, G (ed.) 2014, 'Effect of hyperspectral image denoising with PCA and total variation on tree species mapping using Apex Data', South-Eastern European Journal of Earth Observation and Geomatics, vol. 3, no. 25, pp. 281-286.

Effect of hyperspectral image denoising with PCA and total variation on tree species mapping using Apex Data. / Vancoillie, Frieke; Liao, Wenzhi; Devriendt, Flore; Gautama, Sidharta; De Wulf, Robert; Vandekerkhove, Kris; Gitas, Loannis (Editor); Mallinis, Giorgios (Editor); Patias, Petros (Editor); Stathakis, Dimitris (Editor); Zalidis, Georgios (Editor).

In: South-Eastern European Journal of Earth Observation and Geomatics, Vol. 3, No. 25, 24.05.2014, p. 281-286.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Effect of hyperspectral image denoising with PCA and total variation on tree species mapping using Apex Data

AU - Vancoillie, Frieke

AU - Liao, Wenzhi

AU - Devriendt, Flore

AU - Gautama, Sidharta

AU - De Wulf, Robert

AU - Vandekerkhove, Kris

A2 - Gitas, Loannis

A2 - Mallinis, Giorgios

A2 - Patias, Petros

A2 - Stathakis, Dimitris

A2 - Zalidis, Georgios

PY - 2014/5/24

Y1 - 2014/5/24

N2 - In this paper, the impact of image denoising on feature selection and tree species mapping accuracy is assessed. We apply a novel algorithm for hyperspectral (HS) image denoising using principal component analysis (PCA) and total variation (TV). The method is embedded in an object‐based classification framework and tested for complex forests with closed canopies and scarce reference data. Results show that, under the given conditions, HS image denoising is beneficial yielding stable mapping results with acceptable accuracy levels. Denoising also affected feature selection processing time with a time gain of 41.6%.

AB - In this paper, the impact of image denoising on feature selection and tree species mapping accuracy is assessed. We apply a novel algorithm for hyperspectral (HS) image denoising using principal component analysis (PCA) and total variation (TV). The method is embedded in an object‐based classification framework and tested for complex forests with closed canopies and scarce reference data. Results show that, under the given conditions, HS image denoising is beneficial yielding stable mapping results with acceptable accuracy levels. Denoising also affected feature selection processing time with a time gain of 41.6%.

KW - denoising

KW - broadleaved forest

KW - object‐based tree species classification

KW - hyperspectral data

UR - http://hdl.handle.net/1854/LU-5663339

M3 - Article

VL - 3

SP - 281

EP - 286

IS - 25

ER -

Vancoillie F, Liao W, Devriendt F, Gautama S, De Wulf R, Vandekerkhove K et al. Effect of hyperspectral image denoising with PCA and total variation on tree species mapping using Apex Data. South-Eastern European Journal of Earth Observation and Geomatics. 2014 May 24;3(25):281-286.