Morphological attribute profiles with partial reconstruction

Wenzhi Liao, Mauro Dalla Mura, Jocelyn Chanussot, Rik Bellens, Wilfried Philips, Antonio J Plaza (Editor)

Research output: Contribution to journalArticle

15 Citations (Scopus)

Abstract

Extended attribute profiles (EAPs) have been widely used for the classification of high-resolution hyperspectral images. EAPs are obtained by computing a sequence of attribute operators. Attribute filters (AFs) are connected operators, so they can modify an image by only merging its flat zones. These filters are effective when dealing with very high resolution images since they preserve the geometrical characteristics of the regions that are not removed from the image. However, AFs, being connected filters, suffer the problem of “leakage” (i.e., regions related to different structures in the image that happen to be connected by spurious links will be considered as a single object). Objects expected to disappear at a certain threshold remain present when they are connected with other objects in the image. The attributes of small objects will be mixed with their larger connected objects. In this paper, we propose a novel framework for morphological AFs with partial reconstruction and extend it to the classification of high-resolution hyperspectral images. The ultimate goal of the proposed framework is to be able to extract spatial features which better model the attributes of different objects in the remote sensed imagery, which enables better performances on classification. An important characteristic of the presented approach is that it is very robust to the ranges of rescaled principal components, as well as the selection of attribute values. Our experimental results, conducted using a variety of hyperspectral images, indicate that the proposed framework for AFs with partial reconstruction provides state-of-the-art classification results. Compared to the methods using only single EAP and stacking all EAPs computed by existing attribute opening and closing together, the proposed framework benefits significant improvements in overall classification accuracy.
LanguageEnglish
Pages1738-1756
Number of pages19
JournalIEEE Transactions on Geoscience and Remote Sensing
Volume54
Issue number3
DOIs
Publication statusPublished - 4 Nov 2015

Fingerprint

filter
image resolution
Image resolution
Merging
attribute
stacking
leakage
imagery

Keywords

  • morphlogical filter
  • hyperspectral image
  • spatial information modelling
  • Remote sensing
  • hyperspectral image classification
  • supervised feature extraction
  • spatial classification
  • filters
  • algorithm
  • reduction
  • operators
  • selection
  • accuracy
  • fusion

Cite this

Liao, W., Dalla Mura, M., Chanussot, J., Bellens, R., Philips, W., & Plaza, A. J. (Ed.) (2015). Morphological attribute profiles with partial reconstruction. IEEE Transactions on Geoscience and Remote Sensing, 54(3), 1738-1756. https://doi.org/10.1109/TGRS.2015.2488280
Liao, Wenzhi ; Dalla Mura, Mauro ; Chanussot, Jocelyn ; Bellens, Rik ; Philips, Wilfried ; Plaza, Antonio J (Editor). / Morphological attribute profiles with partial reconstruction. In: IEEE Transactions on Geoscience and Remote Sensing. 2015 ; Vol. 54, No. 3. pp. 1738-1756.
@article{0fa74e9e3ede424f82ec92076d476fce,
title = "Morphological attribute profiles with partial reconstruction",
abstract = "Extended attribute profiles (EAPs) have been widely used for the classification of high-resolution hyperspectral images. EAPs are obtained by computing a sequence of attribute operators. Attribute filters (AFs) are connected operators, so they can modify an image by only merging its flat zones. These filters are effective when dealing with very high resolution images since they preserve the geometrical characteristics of the regions that are not removed from the image. However, AFs, being connected filters, suffer the problem of “leakage” (i.e., regions related to different structures in the image that happen to be connected by spurious links will be considered as a single object). Objects expected to disappear at a certain threshold remain present when they are connected with other objects in the image. The attributes of small objects will be mixed with their larger connected objects. In this paper, we propose a novel framework for morphological AFs with partial reconstruction and extend it to the classification of high-resolution hyperspectral images. The ultimate goal of the proposed framework is to be able to extract spatial features which better model the attributes of different objects in the remote sensed imagery, which enables better performances on classification. An important characteristic of the presented approach is that it is very robust to the ranges of rescaled principal components, as well as the selection of attribute values. Our experimental results, conducted using a variety of hyperspectral images, indicate that the proposed framework for AFs with partial reconstruction provides state-of-the-art classification results. Compared to the methods using only single EAP and stacking all EAPs computed by existing attribute opening and closing together, the proposed framework benefits significant improvements in overall classification accuracy.",
keywords = "morphlogical filter, hyperspectral image, spatial information modelling, Remote sensing, hyperspectral image classification, supervised feature extraction, spatial classification, filters, algorithm, reduction, operators, selection, accuracy, fusion",
author = "Wenzhi Liao and {Dalla Mura}, Mauro and Jocelyn Chanussot and Rik Bellens and Wilfried Philips and Plaza, {Antonio J}",
year = "2015",
month = "11",
day = "4",
doi = "10.1109/TGRS.2015.2488280",
language = "English",
volume = "54",
pages = "1738--1756",
journal = "IEEE Transactions on Geoscience and Remote Sensing",
issn = "0196-2892",
publisher = "IEEE",
number = "3",

}

Liao, W, Dalla Mura, M, Chanussot, J, Bellens, R, Philips, W & Plaza, AJ (ed.) 2015, 'Morphological attribute profiles with partial reconstruction' IEEE Transactions on Geoscience and Remote Sensing, vol. 54, no. 3, pp. 1738-1756. https://doi.org/10.1109/TGRS.2015.2488280

Morphological attribute profiles with partial reconstruction. / Liao, Wenzhi; Dalla Mura, Mauro; Chanussot, Jocelyn; Bellens, Rik; Philips, Wilfried; Plaza, Antonio J (Editor).

In: IEEE Transactions on Geoscience and Remote Sensing, Vol. 54, No. 3, 04.11.2015, p. 1738-1756.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Morphological attribute profiles with partial reconstruction

AU - Liao, Wenzhi

AU - Dalla Mura, Mauro

AU - Chanussot, Jocelyn

AU - Bellens, Rik

AU - Philips, Wilfried

A2 - Plaza, Antonio J

PY - 2015/11/4

Y1 - 2015/11/4

N2 - Extended attribute profiles (EAPs) have been widely used for the classification of high-resolution hyperspectral images. EAPs are obtained by computing a sequence of attribute operators. Attribute filters (AFs) are connected operators, so they can modify an image by only merging its flat zones. These filters are effective when dealing with very high resolution images since they preserve the geometrical characteristics of the regions that are not removed from the image. However, AFs, being connected filters, suffer the problem of “leakage” (i.e., regions related to different structures in the image that happen to be connected by spurious links will be considered as a single object). Objects expected to disappear at a certain threshold remain present when they are connected with other objects in the image. The attributes of small objects will be mixed with their larger connected objects. In this paper, we propose a novel framework for morphological AFs with partial reconstruction and extend it to the classification of high-resolution hyperspectral images. The ultimate goal of the proposed framework is to be able to extract spatial features which better model the attributes of different objects in the remote sensed imagery, which enables better performances on classification. An important characteristic of the presented approach is that it is very robust to the ranges of rescaled principal components, as well as the selection of attribute values. Our experimental results, conducted using a variety of hyperspectral images, indicate that the proposed framework for AFs with partial reconstruction provides state-of-the-art classification results. Compared to the methods using only single EAP and stacking all EAPs computed by existing attribute opening and closing together, the proposed framework benefits significant improvements in overall classification accuracy.

AB - Extended attribute profiles (EAPs) have been widely used for the classification of high-resolution hyperspectral images. EAPs are obtained by computing a sequence of attribute operators. Attribute filters (AFs) are connected operators, so they can modify an image by only merging its flat zones. These filters are effective when dealing with very high resolution images since they preserve the geometrical characteristics of the regions that are not removed from the image. However, AFs, being connected filters, suffer the problem of “leakage” (i.e., regions related to different structures in the image that happen to be connected by spurious links will be considered as a single object). Objects expected to disappear at a certain threshold remain present when they are connected with other objects in the image. The attributes of small objects will be mixed with their larger connected objects. In this paper, we propose a novel framework for morphological AFs with partial reconstruction and extend it to the classification of high-resolution hyperspectral images. The ultimate goal of the proposed framework is to be able to extract spatial features which better model the attributes of different objects in the remote sensed imagery, which enables better performances on classification. An important characteristic of the presented approach is that it is very robust to the ranges of rescaled principal components, as well as the selection of attribute values. Our experimental results, conducted using a variety of hyperspectral images, indicate that the proposed framework for AFs with partial reconstruction provides state-of-the-art classification results. Compared to the methods using only single EAP and stacking all EAPs computed by existing attribute opening and closing together, the proposed framework benefits significant improvements in overall classification accuracy.

KW - morphlogical filter

KW - hyperspectral image

KW - spatial information modelling

KW - Remote sensing

KW - hyperspectral image classification

KW - supervised feature extraction

KW - spatial classification

KW - filters

KW - algorithm

KW - reduction

KW - operators

KW - selection

KW - accuracy

KW - fusion

UR - http://hdl.handle.net/1854/LU-7011472

U2 - 10.1109/TGRS.2015.2488280

DO - 10.1109/TGRS.2015.2488280

M3 - Article

VL - 54

SP - 1738

EP - 1756

JO - IEEE Transactions on Geoscience and Remote Sensing

T2 - IEEE Transactions on Geoscience and Remote Sensing

JF - IEEE Transactions on Geoscience and Remote Sensing

SN - 0196-2892

IS - 3

ER -