Classification of remote sensing images from urban areas using a fuzzy model

Jocelyn Chanussot; Jon Atli Benediktsson; Mathilde Vincent

Classification of remote sensing images from urban areas using a fuzzy model

Jocelyn Chanussot, Jon Atli Benediktsson, Mathilde Vincent

University of Iceland

University of Iceland

Research output: Contribution to conference › Paper › peer-review

Abstract

The problem of classification of high-resolution remotely sensed images from urban areas is addressed. Previous studies have shown the interest of exploiting the local geometrical information of each pixel to improve the classification. This is performed using the derivative morphological profile (DMP) obtained with a granulometric approach, using respectively opening and closing operators. For each pixel, this DMP constitutes the feature vector on which the classification is based In this paper, this vector is considered as a fuzzy measurement of the size of the structure. Compared with some possibility1 distributions, a membership degree is computed for each class. The decision is taken by selecting the class with the highest membership degree.

Original language	English
Pages	556-559
Number of pages	4
Publication status	Published - 2004
Event	2004 IEEE International Geoscience and Remote Sensing Symposium Proceedings: Science for Society: Exploring and Managing a Changing Planet. IGARSS 2004 - Anchorage, AK, United States Duration: 20 Sept 2004 → 24 Sept 2004

Conference

Conference	2004 IEEE International Geoscience and Remote Sensing Symposium Proceedings: Science for Society: Exploring and Managing a Changing Planet. IGARSS 2004
Country/Territory	United States
City	Anchorage, AK
Period	20/09/04 → 24/09/04

Other keywords

Classification
Fuzzy sets
Mathematical morphology
Possibility distribution

Cite this

@conference{3f93d1dd978e4ccdbf1b876476e3f18f,

title = "Classification of remote sensing images from urban areas using a fuzzy model",

abstract = "The problem of classification of high-resolution remotely sensed images from urban areas is addressed. Previous studies have shown the interest of exploiting the local geometrical information of each pixel to improve the classification. This is performed using the derivative morphological profile (DMP) obtained with a granulometric approach, using respectively opening and closing operators. For each pixel, this DMP constitutes the feature vector on which the classification is based In this paper, this vector is considered as a fuzzy measurement of the size of the structure. Compared with some possibility1 distributions, a membership degree is computed for each class. The decision is taken by selecting the class with the highest membership degree.",

keywords = "Classification, Fuzzy sets, Mathematical morphology, Possibility distribution",

author = "Jocelyn Chanussot and Benediktsson, \{Jon Atli\} and Mathilde Vincent",

year = "2004",

language = "English",

pages = "556--559",

note = "2004 IEEE International Geoscience and Remote Sensing Symposium Proceedings: Science for Society: Exploring and Managing a Changing Planet. IGARSS 2004 ; Conference date: 20-09-2004 Through 24-09-2004",

}

Classification of remote sensing images from urban areas using a fuzzy model. / Chanussot, Jocelyn; Benediktsson, Jon Atli; Vincent, Mathilde.
2004. 556-559 Paper presented at 2004 IEEE International Geoscience and Remote Sensing Symposium Proceedings: Science for Society: Exploring and Managing a Changing Planet. IGARSS 2004, Anchorage, AK, United States.

Research output: Contribution to conference › Paper › peer-review

TY - CONF

T1 - Classification of remote sensing images from urban areas using a fuzzy model

AU - Chanussot, Jocelyn

AU - Benediktsson, Jon Atli

AU - Vincent, Mathilde

PY - 2004

Y1 - 2004

N2 - The problem of classification of high-resolution remotely sensed images from urban areas is addressed. Previous studies have shown the interest of exploiting the local geometrical information of each pixel to improve the classification. This is performed using the derivative morphological profile (DMP) obtained with a granulometric approach, using respectively opening and closing operators. For each pixel, this DMP constitutes the feature vector on which the classification is based In this paper, this vector is considered as a fuzzy measurement of the size of the structure. Compared with some possibility1 distributions, a membership degree is computed for each class. The decision is taken by selecting the class with the highest membership degree.

AB - The problem of classification of high-resolution remotely sensed images from urban areas is addressed. Previous studies have shown the interest of exploiting the local geometrical information of each pixel to improve the classification. This is performed using the derivative morphological profile (DMP) obtained with a granulometric approach, using respectively opening and closing operators. For each pixel, this DMP constitutes the feature vector on which the classification is based In this paper, this vector is considered as a fuzzy measurement of the size of the structure. Compared with some possibility1 distributions, a membership degree is computed for each class. The decision is taken by selecting the class with the highest membership degree.

KW - Classification

KW - Fuzzy sets

KW - Mathematical morphology

KW - Possibility distribution

UR - https://www.scopus.com/pages/publications/15944409957

M3 - Paper

SP - 556

EP - 559

T2 - 2004 IEEE International Geoscience and Remote Sensing Symposium Proceedings: Science for Society: Exploring and Managing a Changing Planet. IGARSS 2004

Y2 - 20 September 2004 through 24 September 2004

ER -

Classification of remote sensing images from urban areas using a fuzzy model

Abstract

Conference

Other keywords

Fingerprint

Cite this