Classification of hyperspectral data over urban areas based on extended morphological profile with partial reconstruction

Wenzhi Liao, Rik Bellens, Aleksandra Pizurica, Wilfried Philips, Youguo Pi, J Blanc-Talon (Editor), D Popescu (Editor), Paul Scheunders

Research output: Contribution to conferencePaper

7 Citations (Scopus)

Abstract

Extended morphological profiles with reconstruction are widely used in the classification of very high resolution hyperspectral data from urban areas. However, morphological profiles constructed by morphological openings and closings with reconstruction can lead to some undesirable effects. Objects expected to disappear at a certain scale remain present when using morphological openings and closings by reconstruction. In this paper, we apply extended morphological profiles with partial reconstruction (EMPP) to the classification of high resolution hyperspectral images from urban areas. We first used feature extraction to reduce the dimensionality of the hyperspectral data, as well as reduce the redundancy within the bands, then constructed EMPP on features extracted by PCA, independent component analysis and kernel PCA for the classification of high resolution hyperspectral images from urban areas. Experimental results on real urban hyperspectral image demonstrate that the proposed EMPP built on kernel principal components gets the best results, particularly in the case with small training sample sizes.

Conference

Conference14th International Conference on Advanced Concepts for Intelligent Vision Systems (ACIVS 2012)
Abbreviated titleACIVS 2012
CountryCzech Republic
CityBrno
Period4/09/127/09/12

Fingerprint

urban area
profiles
image resolution
closing
high resolution
redundancy
pattern recognition
education

Keywords

  • morphological profiles
  • classification
  • urban hyperspectral image
  • high resolution
  • feature extraction

Cite this

Liao, W., Bellens, R., Pizurica, A., Philips, W., Pi, Y., Blanc-Talon, J. (Ed.), ... Scheunders, P. (2012). Classification of hyperspectral data over urban areas based on extended morphological profile with partial reconstruction. 278-289. Paper presented at 14th International Conference on Advanced Concepts for Intelligent Vision Systems (ACIVS 2012), Brno, Czech Republic. https://doi.org/10.1007/978-3-642-33140-4_25
Liao, Wenzhi ; Bellens, Rik ; Pizurica, Aleksandra ; Philips, Wilfried ; Pi, Youguo ; Blanc-Talon, J (Editor) ; Popescu, D (Editor) ; Scheunders, Paul. / Classification of hyperspectral data over urban areas based on extended morphological profile with partial reconstruction. Paper presented at 14th International Conference on Advanced Concepts for Intelligent Vision Systems (ACIVS 2012), Brno, Czech Republic.12 p.
@conference{a849e87d60504be9b0171834b88a5338,
title = "Classification of hyperspectral data over urban areas based on extended morphological profile with partial reconstruction",
abstract = "Extended morphological profiles with reconstruction are widely used in the classification of very high resolution hyperspectral data from urban areas. However, morphological profiles constructed by morphological openings and closings with reconstruction can lead to some undesirable effects. Objects expected to disappear at a certain scale remain present when using morphological openings and closings by reconstruction. In this paper, we apply extended morphological profiles with partial reconstruction (EMPP) to the classification of high resolution hyperspectral images from urban areas. We first used feature extraction to reduce the dimensionality of the hyperspectral data, as well as reduce the redundancy within the bands, then constructed EMPP on features extracted by PCA, independent component analysis and kernel PCA for the classification of high resolution hyperspectral images from urban areas. Experimental results on real urban hyperspectral image demonstrate that the proposed EMPP built on kernel principal components gets the best results, particularly in the case with small training sample sizes.",
keywords = "morphological profiles, classification, urban hyperspectral image, high resolution, feature extraction",
author = "Wenzhi Liao and Rik Bellens and Aleksandra Pizurica and Wilfried Philips and Youguo Pi and J Blanc-Talon and D Popescu and Paul Scheunders",
year = "2012",
doi = "10.1007/978-3-642-33140-4_25",
language = "English",
pages = "278--289",
note = "14th International Conference on Advanced Concepts for Intelligent Vision Systems (ACIVS 2012), ACIVS 2012 ; Conference date: 04-09-2012 Through 07-09-2012",

}

Liao, W, Bellens, R, Pizurica, A, Philips, W, Pi, Y, Blanc-Talon, J (ed.), Popescu, D (ed.) & Scheunders, P 2012, 'Classification of hyperspectral data over urban areas based on extended morphological profile with partial reconstruction' Paper presented at 14th International Conference on Advanced Concepts for Intelligent Vision Systems (ACIVS 2012), Brno, Czech Republic, 4/09/12 - 7/09/12, pp. 278-289. https://doi.org/10.1007/978-3-642-33140-4_25

Classification of hyperspectral data over urban areas based on extended morphological profile with partial reconstruction. / Liao, Wenzhi; Bellens, Rik; Pizurica, Aleksandra; Philips, Wilfried; Pi, Youguo; Blanc-Talon, J (Editor); Popescu, D (Editor); Scheunders, Paul.

2012. 278-289 Paper presented at 14th International Conference on Advanced Concepts for Intelligent Vision Systems (ACIVS 2012), Brno, Czech Republic.

Research output: Contribution to conferencePaper

TY - CONF

T1 - Classification of hyperspectral data over urban areas based on extended morphological profile with partial reconstruction

AU - Liao, Wenzhi

AU - Bellens, Rik

AU - Pizurica, Aleksandra

AU - Philips, Wilfried

AU - Pi, Youguo

AU - Scheunders, Paul

A2 - Blanc-Talon, J

A2 - Popescu, D

PY - 2012

Y1 - 2012

N2 - Extended morphological profiles with reconstruction are widely used in the classification of very high resolution hyperspectral data from urban areas. However, morphological profiles constructed by morphological openings and closings with reconstruction can lead to some undesirable effects. Objects expected to disappear at a certain scale remain present when using morphological openings and closings by reconstruction. In this paper, we apply extended morphological profiles with partial reconstruction (EMPP) to the classification of high resolution hyperspectral images from urban areas. We first used feature extraction to reduce the dimensionality of the hyperspectral data, as well as reduce the redundancy within the bands, then constructed EMPP on features extracted by PCA, independent component analysis and kernel PCA for the classification of high resolution hyperspectral images from urban areas. Experimental results on real urban hyperspectral image demonstrate that the proposed EMPP built on kernel principal components gets the best results, particularly in the case with small training sample sizes.

AB - Extended morphological profiles with reconstruction are widely used in the classification of very high resolution hyperspectral data from urban areas. However, morphological profiles constructed by morphological openings and closings with reconstruction can lead to some undesirable effects. Objects expected to disappear at a certain scale remain present when using morphological openings and closings by reconstruction. In this paper, we apply extended morphological profiles with partial reconstruction (EMPP) to the classification of high resolution hyperspectral images from urban areas. We first used feature extraction to reduce the dimensionality of the hyperspectral data, as well as reduce the redundancy within the bands, then constructed EMPP on features extracted by PCA, independent component analysis and kernel PCA for the classification of high resolution hyperspectral images from urban areas. Experimental results on real urban hyperspectral image demonstrate that the proposed EMPP built on kernel principal components gets the best results, particularly in the case with small training sample sizes.

KW - morphological profiles

KW - classification

KW - urban hyperspectral image

KW - high resolution

KW - feature extraction

UR - http://hdl.handle.net/1854/LU-2963016

U2 - 10.1007/978-3-642-33140-4_25

DO - 10.1007/978-3-642-33140-4_25

M3 - Paper

SP - 278

EP - 289

ER -

Liao W, Bellens R, Pizurica A, Philips W, Pi Y, Blanc-Talon J, (ed.) et al. Classification of hyperspectral data over urban areas based on extended morphological profile with partial reconstruction. 2012. Paper presented at 14th International Conference on Advanced Concepts for Intelligent Vision Systems (ACIVS 2012), Brno, Czech Republic. https://doi.org/10.1007/978-3-642-33140-4_25