Exploiting spectral and spatial information in hyperspectral urban data with high resolution

F. Dell'Acqua; P. Gamba; A. Ferrari; J. A. Palmason; J. A. Benediktsson; K. Arnason

doi:10.1109/LGRS.2004.837009

Exploiting spectral and spatial information in hyperspectral urban data with high resolution

F. Dell'Acqua
, P. Gamba
, A. Ferrari
, J. A. Palmason
, J. A. Benediktsson
, K. Arnason

University of Iceland

University of Iceland

Research output: Contribution to journal › Article › peer-review

Abstract

Very high resolution hyperspectral data should be very useful to provide detailed maps of urban land cover. In order to provide such maps, both accurate and precise classification tools need, however, to be developed. In this letter, new methods for classification of hyperspectral remote sensing data are investigated, with the primary focus on multiple classifications and spatial analysis to improve mapping accuracy in urban areas. In particular, we compare spatial reclassification and mathematical morphology approaches. We show results for classification of DAIS data over the town of Pavia, in northern Italy. Classification maps of two test areas are given, and the overall and individual class accuracies are analyzed with respect to the parameters of the proposed classification procedures.

Original language	English
Pages (from-to)	322-326
Number of pages	5
Journal	IEEE Geoscience and Remote Sensing Letters
Volume	1
Issue number	4
DOIs	https://doi.org/10.1109/LGRS.2004.837009
Publication status	Published - Oct 2004

Bibliographical note

Funding Information: Manuscript received May 28, 2004; revised August 16, 2004. The work was supported in part by the European Union, in part by the Icelandic Research Council, and in part by the Research Fund of the University of Iceland. F. Dell’Acqua, P. Gamba, and A. Ferrari are with the Department of Electronics, University of Pavia, I-27100 Pavia, Italy. J. A. Palmason, J. A. Benediktsson, and K. Arnason are with the University of Iceland, IS-107 Reykjavik, Iceland. Digital Object Identifier 10.1109/LGRS.2004.837009 Funding Information: The data used in the experiments are very fine resolution hy-perspectral data, part of four recorded flight lines over the urban area of Pavia, Northern Italy. The spatial resolution is 2.6 m. The flight was flown in the framework of the HySens project, managed by Deutschen Zentrum fur Luft-und Raumfahrt (DLR) and sponsored by the European Union within the transnational access to major research infrastructures (contract HPRI-CT-1999-00075). The area was imaged using the Digital Airborne Imaging Spectrometer (DAIS), which detects in total 80 data channels in the visible and infrared wavelengths (seven are thermal infrared bands). For the present study it was decided to only take into account bands of reflective energy and, therefore, the seven thermal infrared bands were skipped. Also, it was necessary to remove the middle infrared bands above 1.958-m wavelengths because of heavy noise in those bands. Consequently, only the first 40 spectral bands of DAIS data are considered in this study.

Other keywords

Hyperspectral imaging
Morphology
Multiclassification
Urban remote sensing

Access to Document

10.1109/LGRS.2004.837009

Cite this

@article{d121b12327944a02ad9b7de7c19636e9,

title = "Exploiting spectral and spatial information in hyperspectral urban data with high resolution",

abstract = "Very high resolution hyperspectral data should be very useful to provide detailed maps of urban land cover. In order to provide such maps, both accurate and precise classification tools need, however, to be developed. In this letter, new methods for classification of hyperspectral remote sensing data are investigated, with the primary focus on multiple classifications and spatial analysis to improve mapping accuracy in urban areas. In particular, we compare spatial reclassification and mathematical morphology approaches. We show results for classification of DAIS data over the town of Pavia, in northern Italy. Classification maps of two test areas are given, and the overall and individual class accuracies are analyzed with respect to the parameters of the proposed classification procedures.",

keywords = "Hyperspectral imaging, Morphology, Multiclassification, Urban remote sensing",

author = "F. Dell'Acqua and P. Gamba and A. Ferrari and Palmason, \{J. A.\} and Benediktsson, \{J. A.\} and K. Arnason",

note = "Funding Information: Manuscript received May 28, 2004; revised August 16, 2004. The work was supported in part by the European Union, in part by the Icelandic Research Council, and in part by the Research Fund of the University of Iceland. F. Dell{\textquoteright}Acqua, P. Gamba, and A. Ferrari are with the Department of Electronics, University of Pavia, I-27100 Pavia, Italy. J. A. Palmason, J. A. Benediktsson, and K. Arnason are with the University of Iceland, IS-107 Reykjavik, Iceland. Digital Object Identifier 10.1109/LGRS.2004.837009 Funding Information: The data used in the experiments are very fine resolution hy-perspectral data, part of four recorded flight lines over the urban area of Pavia, Northern Italy. The spatial resolution is 2.6 m. The flight was flown in the framework of the HySens project, managed by Deutschen Zentrum fur Luft-und Raumfahrt (DLR) and sponsored by the European Union within the transnational access to major research infrastructures (contract HPRI-CT-1999-00075). The area was imaged using the Digital Airborne Imaging Spectrometer (DAIS), which detects in total 80 data channels in the visible and infrared wavelengths (seven are thermal infrared bands). For the present study it was decided to only take into account bands of reflective energy and, therefore, the seven thermal infrared bands were skipped. Also, it was necessary to remove the middle infrared bands above 1.958-m wavelengths because of heavy noise in those bands. Consequently, only the first 40 spectral bands of DAIS data are considered in this study.",

year = "2004",

month = oct,

doi = "10.1109/LGRS.2004.837009",

language = "English",

volume = "1",

pages = "322--326",

journal = "IEEE Geoscience and Remote Sensing Letters",

issn = "1545-598X",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

number = "4",

}

TY - JOUR

T1 - Exploiting spectral and spatial information in hyperspectral urban data with high resolution

AU - Dell'Acqua, F.

AU - Gamba, P.

AU - Ferrari, A.

AU - Palmason, J. A.

AU - Benediktsson, J. A.

AU - Arnason, K.

N1 - Funding Information: Manuscript received May 28, 2004; revised August 16, 2004. The work was supported in part by the European Union, in part by the Icelandic Research Council, and in part by the Research Fund of the University of Iceland. F. Dell’Acqua, P. Gamba, and A. Ferrari are with the Department of Electronics, University of Pavia, I-27100 Pavia, Italy. J. A. Palmason, J. A. Benediktsson, and K. Arnason are with the University of Iceland, IS-107 Reykjavik, Iceland. Digital Object Identifier 10.1109/LGRS.2004.837009 Funding Information: The data used in the experiments are very fine resolution hy-perspectral data, part of four recorded flight lines over the urban area of Pavia, Northern Italy. The spatial resolution is 2.6 m. The flight was flown in the framework of the HySens project, managed by Deutschen Zentrum fur Luft-und Raumfahrt (DLR) and sponsored by the European Union within the transnational access to major research infrastructures (contract HPRI-CT-1999-00075). The area was imaged using the Digital Airborne Imaging Spectrometer (DAIS), which detects in total 80 data channels in the visible and infrared wavelengths (seven are thermal infrared bands). For the present study it was decided to only take into account bands of reflective energy and, therefore, the seven thermal infrared bands were skipped. Also, it was necessary to remove the middle infrared bands above 1.958-m wavelengths because of heavy noise in those bands. Consequently, only the first 40 spectral bands of DAIS data are considered in this study.

PY - 2004/10

Y1 - 2004/10

N2 - Very high resolution hyperspectral data should be very useful to provide detailed maps of urban land cover. In order to provide such maps, both accurate and precise classification tools need, however, to be developed. In this letter, new methods for classification of hyperspectral remote sensing data are investigated, with the primary focus on multiple classifications and spatial analysis to improve mapping accuracy in urban areas. In particular, we compare spatial reclassification and mathematical morphology approaches. We show results for classification of DAIS data over the town of Pavia, in northern Italy. Classification maps of two test areas are given, and the overall and individual class accuracies are analyzed with respect to the parameters of the proposed classification procedures.

AB - Very high resolution hyperspectral data should be very useful to provide detailed maps of urban land cover. In order to provide such maps, both accurate and precise classification tools need, however, to be developed. In this letter, new methods for classification of hyperspectral remote sensing data are investigated, with the primary focus on multiple classifications and spatial analysis to improve mapping accuracy in urban areas. In particular, we compare spatial reclassification and mathematical morphology approaches. We show results for classification of DAIS data over the town of Pavia, in northern Italy. Classification maps of two test areas are given, and the overall and individual class accuracies are analyzed with respect to the parameters of the proposed classification procedures.

KW - Hyperspectral imaging

KW - Morphology

KW - Multiclassification

KW - Urban remote sensing

UR - https://www.scopus.com/pages/publications/8344222887

U2 - 10.1109/LGRS.2004.837009

DO - 10.1109/LGRS.2004.837009

M3 - Article

SN - 1545-598X

VL - 1

SP - 322

EP - 326

JO - IEEE Geoscience and Remote Sensing Letters

JF - IEEE Geoscience and Remote Sensing Letters

IS - 4

ER -

Exploiting spectral and spatial information in hyperspectral urban data with high resolution

Abstract

Bibliographical note

Other keywords

Access to Document

Fingerprint

Cite this