Classification of hyperspectral images by using morphological attribute filters and independent component analysis
International audience In this paper, a technique based on Independent Component Analysis (ICA) and morphological attribute filters is presented for the classification of high geometrical resolution hyperspectral images. The ICA is computed instead of the conventional principal component analysis (P...
Main Authors: | , , , , |
---|---|
Other Authors: | , , , , , , , , |
Format: | Conference Object |
Language: | English |
Published: |
HAL CCSD
2010
|
Subjects: | |
Online Access: | https://hal.science/hal-00578909 https://hal.science/hal-00578909/document https://hal.science/hal-00578909/file/ieee_grss_10_Dalla_Classification.pdf |
id |
ftunigrenoble:oai:HAL:hal-00578909v1 |
---|---|
record_format |
openpolar |
spelling |
ftunigrenoble:oai:HAL:hal-00578909v1 2024-04-14T08:13:40+00:00 Classification of hyperspectral images by using morphological attribute filters and independent component analysis Dalla Mura, Mauro Villa, Alberto Benediktsson, Jon Atli Chanussot, Jocelyn Bruzzone, Lorenzo University of Iceland Reykjavik Department of Information Engineering and Computer Science (DISI) Università degli Studi di Trento = University of Trento (UNITN) Grenoble Images Parole Signal Automatique (GIPSA-lab) Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Stendhal - Grenoble 3-Université Joseph Fourier - Grenoble 1 (UJF)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Centre National de la Recherche Scientifique (CNRS) GIPSA - Signal Images Physique (GIPSA-SIGMAPHY) Département Images et Signal (GIPSA-DIS) Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Stendhal - Grenoble 3-Université Joseph Fourier - Grenoble 1 (UJF)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Centre National de la Recherche Scientifique (CNRS)-Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Stendhal - Grenoble 3-Université Joseph Fourier - Grenoble 1 (UJF)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Centre National de la Recherche Scientifique (CNRS)-Grenoble Images Parole Signal Automatique (GIPSA-lab) Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Stendhal - Grenoble 3-Université Joseph Fourier - Grenoble 1 (UJF)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Centre National de la Recherche Scientifique (CNRS)-Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Stendhal - Grenoble 3-Université Joseph Fourier - Grenoble 1 (UJF)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Centre National de la Recherche Scientifique (CNRS) Reykjavik, Iceland 2010-06-14 https://hal.science/hal-00578909 https://hal.science/hal-00578909/document https://hal.science/hal-00578909/file/ieee_grss_10_Dalla_Classification.pdf en eng HAL CCSD hal-00578909 https://hal.science/hal-00578909 https://hal.science/hal-00578909/document https://hal.science/hal-00578909/file/ieee_grss_10_Dalla_Classification.pdf info:eu-repo/semantics/OpenAccess Proceedings of WHISPERS 2010 WHISPERS 2010 - 2nd Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing https://hal.science/hal-00578909 WHISPERS 2010 - 2nd Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing, Jun 2010, Reykjavik, Iceland. conference proceedings Mathematical morphology attribute filters independent component analysis decision fusion remote sensing [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV] info:eu-repo/semantics/conferenceObject Conference papers 2010 ftunigrenoble 2024-03-21T16:06:23Z International audience In this paper, a technique based on Independent Component Analysis (ICA) and morphological attribute filters is presented for the classification of high geometrical resolution hyperspectral images. The ICA is computed instead of the conventional principal component analysis (PCA) in order to better model the information in the hyperspectral image. The spatial characteristics of the objects in the scene are modeled by different multi-level attribute filters. Moreover, a method for increasing the robustness of the analysis based on a decision fusion strategy is proposed. A hyperspectral high resolution image acquired over the city of Pavia (Italy) was considered in the experiments. Conference Object Iceland Université Grenoble Alpes: HAL |
institution |
Open Polar |
collection |
Université Grenoble Alpes: HAL |
op_collection_id |
ftunigrenoble |
language |
English |
topic |
Mathematical morphology attribute filters independent component analysis decision fusion remote sensing [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV] |
spellingShingle |
Mathematical morphology attribute filters independent component analysis decision fusion remote sensing [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV] Dalla Mura, Mauro Villa, Alberto Benediktsson, Jon Atli Chanussot, Jocelyn Bruzzone, Lorenzo Classification of hyperspectral images by using morphological attribute filters and independent component analysis |
topic_facet |
Mathematical morphology attribute filters independent component analysis decision fusion remote sensing [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV] |
description |
International audience In this paper, a technique based on Independent Component Analysis (ICA) and morphological attribute filters is presented for the classification of high geometrical resolution hyperspectral images. The ICA is computed instead of the conventional principal component analysis (PCA) in order to better model the information in the hyperspectral image. The spatial characteristics of the objects in the scene are modeled by different multi-level attribute filters. Moreover, a method for increasing the robustness of the analysis based on a decision fusion strategy is proposed. A hyperspectral high resolution image acquired over the city of Pavia (Italy) was considered in the experiments. |
author2 |
University of Iceland Reykjavik Department of Information Engineering and Computer Science (DISI) Università degli Studi di Trento = University of Trento (UNITN) Grenoble Images Parole Signal Automatique (GIPSA-lab) Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Stendhal - Grenoble 3-Université Joseph Fourier - Grenoble 1 (UJF)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Centre National de la Recherche Scientifique (CNRS) GIPSA - Signal Images Physique (GIPSA-SIGMAPHY) Département Images et Signal (GIPSA-DIS) Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Stendhal - Grenoble 3-Université Joseph Fourier - Grenoble 1 (UJF)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Centre National de la Recherche Scientifique (CNRS)-Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Stendhal - Grenoble 3-Université Joseph Fourier - Grenoble 1 (UJF)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Centre National de la Recherche Scientifique (CNRS)-Grenoble Images Parole Signal Automatique (GIPSA-lab) Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Stendhal - Grenoble 3-Université Joseph Fourier - Grenoble 1 (UJF)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Centre National de la Recherche Scientifique (CNRS)-Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Stendhal - Grenoble 3-Université Joseph Fourier - Grenoble 1 (UJF)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Centre National de la Recherche Scientifique (CNRS) |
format |
Conference Object |
author |
Dalla Mura, Mauro Villa, Alberto Benediktsson, Jon Atli Chanussot, Jocelyn Bruzzone, Lorenzo |
author_facet |
Dalla Mura, Mauro Villa, Alberto Benediktsson, Jon Atli Chanussot, Jocelyn Bruzzone, Lorenzo |
author_sort |
Dalla Mura, Mauro |
title |
Classification of hyperspectral images by using morphological attribute filters and independent component analysis |
title_short |
Classification of hyperspectral images by using morphological attribute filters and independent component analysis |
title_full |
Classification of hyperspectral images by using morphological attribute filters and independent component analysis |
title_fullStr |
Classification of hyperspectral images by using morphological attribute filters and independent component analysis |
title_full_unstemmed |
Classification of hyperspectral images by using morphological attribute filters and independent component analysis |
title_sort |
classification of hyperspectral images by using morphological attribute filters and independent component analysis |
publisher |
HAL CCSD |
publishDate |
2010 |
url |
https://hal.science/hal-00578909 https://hal.science/hal-00578909/document https://hal.science/hal-00578909/file/ieee_grss_10_Dalla_Classification.pdf |
op_coverage |
Reykjavik, Iceland |
genre |
Iceland |
genre_facet |
Iceland |
op_source |
Proceedings of WHISPERS 2010 WHISPERS 2010 - 2nd Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing https://hal.science/hal-00578909 WHISPERS 2010 - 2nd Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing, Jun 2010, Reykjavik, Iceland. conference proceedings |
op_relation |
hal-00578909 https://hal.science/hal-00578909 https://hal.science/hal-00578909/document https://hal.science/hal-00578909/file/ieee_grss_10_Dalla_Classification.pdf |
op_rights |
info:eu-repo/semantics/OpenAccess |
_version_ |
1796311707226734592 |