Relevance assessment of full-waveform lidar data for urban area classification

Publikation: Beitrag in FachzeitschriftArtikelForschungPeer-Review

Autoren

  • Clément Mallet
  • Frédéric Bretar
  • Michel Roux
  • Uwe Soergel
  • Christian Heipke

Externe Organisationen

  • Université Paris-Est Créteil Val-de-Marne (UPEC)
  • CETE Normandie Centre
  • Télécom ParisTech
Forschungs-netzwerk anzeigen

Details

OriginalspracheEnglisch
Seiten (von - bis)S71-S84
FachzeitschriftISPRS Journal of Photogrammetry and Remote Sensing
Jahrgang66
Ausgabenummer6 SUPPL.
Frühes Online-Datum12 Okt. 2011
PublikationsstatusVeröffentlicht - Dez. 2011

Abstract

Full-waveform lidar data are increasingly being available. Morphological features can be retrieved from the echoes composing the waveforms, and are now extensively used for a large variety of land-cover mapping issues. However, the genuine contribution of these features with respect to those computed from standard discrete return lidar systems has been barely theoretically investigated. This paper therefore aims to study the potential of full-waveform data through the automatic classification of urban areas in building, ground, and vegetation points. Two waveform processing methods, namely a non-linear least squares method and a marked point process approach, are used to fit the echoes both with symmetric and asymmetric modeling functions. The performance of the extracted full-waveform features for the classification problem are then compared to a large variety of multiple-pulse features thanks to three feature selection methods. A support vector machines classifier is finally used to label the point cloud according to various scenarios based on the rank of the features. This allows to find the best classification strategy as well as the minimal feature subsets allowing to achieve the highest classification accuracy possible for each of the three feature selection methods.The results show that the echo amplitude as well as two features computed from the radiometric calibration of full-waveform data, namely the cross-section and the backscatter coefficient, significantly contribute to the high classification accuracies reported in this paper (around 95%). Conversely, features extracted from the non Gaussian modelling of the echoes are not relevant for the discrimination of vegetation, ground, and buildings in urban areas.

ASJC Scopus Sachgebiete

Zitieren

Relevance assessment of full-waveform lidar data for urban area classification. / Mallet, Clément; Bretar, Frédéric; Roux, Michel et al.
in: ISPRS Journal of Photogrammetry and Remote Sensing, Jahrgang 66, Nr. 6 SUPPL., 12.2011, S. S71-S84.

Publikation: Beitrag in FachzeitschriftArtikelForschungPeer-Review

Mallet C, Bretar F, Roux M, Soergel U, Heipke C. Relevance assessment of full-waveform lidar data for urban area classification. ISPRS Journal of Photogrammetry and Remote Sensing. 2011 Dez;66(6 SUPPL.):S71-S84. Epub 2011 Okt 12. doi: 10.1016/j.isprsjprs.2011.09.008
Mallet, Clément ; Bretar, Frédéric ; Roux, Michel et al. / Relevance assessment of full-waveform lidar data for urban area classification. in: ISPRS Journal of Photogrammetry and Remote Sensing. 2011 ; Jahrgang 66, Nr. 6 SUPPL. S. S71-S84.
Download
@article{b48b8dc0f6024ac09151ef2fcb919daf,
title = "Relevance assessment of full-waveform lidar data for urban area classification",
abstract = "Full-waveform lidar data are increasingly being available. Morphological features can be retrieved from the echoes composing the waveforms, and are now extensively used for a large variety of land-cover mapping issues. However, the genuine contribution of these features with respect to those computed from standard discrete return lidar systems has been barely theoretically investigated. This paper therefore aims to study the potential of full-waveform data through the automatic classification of urban areas in building, ground, and vegetation points. Two waveform processing methods, namely a non-linear least squares method and a marked point process approach, are used to fit the echoes both with symmetric and asymmetric modeling functions. The performance of the extracted full-waveform features for the classification problem are then compared to a large variety of multiple-pulse features thanks to three feature selection methods. A support vector machines classifier is finally used to label the point cloud according to various scenarios based on the rank of the features. This allows to find the best classification strategy as well as the minimal feature subsets allowing to achieve the highest classification accuracy possible for each of the three feature selection methods.The results show that the echo amplitude as well as two features computed from the radiometric calibration of full-waveform data, namely the cross-section and the backscatter coefficient, significantly contribute to the high classification accuracies reported in this paper (around 95%). Conversely, features extracted from the non Gaussian modelling of the echoes are not relevant for the discrimination of vegetation, ground, and buildings in urban areas.",
keywords = "Classification, Feature selection, Full-waveform lidar data, Support vector machines, Urban areas",
author = "Cl{\'e}ment Mallet and Fr{\'e}d{\'e}ric Bretar and Michel Roux and Uwe Soergel and Christian Heipke",
year = "2011",
month = dec,
doi = "10.1016/j.isprsjprs.2011.09.008",
language = "English",
volume = "66",
pages = "S71--S84",
journal = "ISPRS Journal of Photogrammetry and Remote Sensing",
issn = "0924-2716",
publisher = "Elsevier",
number = "6 SUPPL.",

}

Download

TY - JOUR

T1 - Relevance assessment of full-waveform lidar data for urban area classification

AU - Mallet, Clément

AU - Bretar, Frédéric

AU - Roux, Michel

AU - Soergel, Uwe

AU - Heipke, Christian

PY - 2011/12

Y1 - 2011/12

N2 - Full-waveform lidar data are increasingly being available. Morphological features can be retrieved from the echoes composing the waveforms, and are now extensively used for a large variety of land-cover mapping issues. However, the genuine contribution of these features with respect to those computed from standard discrete return lidar systems has been barely theoretically investigated. This paper therefore aims to study the potential of full-waveform data through the automatic classification of urban areas in building, ground, and vegetation points. Two waveform processing methods, namely a non-linear least squares method and a marked point process approach, are used to fit the echoes both with symmetric and asymmetric modeling functions. The performance of the extracted full-waveform features for the classification problem are then compared to a large variety of multiple-pulse features thanks to three feature selection methods. A support vector machines classifier is finally used to label the point cloud according to various scenarios based on the rank of the features. This allows to find the best classification strategy as well as the minimal feature subsets allowing to achieve the highest classification accuracy possible for each of the three feature selection methods.The results show that the echo amplitude as well as two features computed from the radiometric calibration of full-waveform data, namely the cross-section and the backscatter coefficient, significantly contribute to the high classification accuracies reported in this paper (around 95%). Conversely, features extracted from the non Gaussian modelling of the echoes are not relevant for the discrimination of vegetation, ground, and buildings in urban areas.

AB - Full-waveform lidar data are increasingly being available. Morphological features can be retrieved from the echoes composing the waveforms, and are now extensively used for a large variety of land-cover mapping issues. However, the genuine contribution of these features with respect to those computed from standard discrete return lidar systems has been barely theoretically investigated. This paper therefore aims to study the potential of full-waveform data through the automatic classification of urban areas in building, ground, and vegetation points. Two waveform processing methods, namely a non-linear least squares method and a marked point process approach, are used to fit the echoes both with symmetric and asymmetric modeling functions. The performance of the extracted full-waveform features for the classification problem are then compared to a large variety of multiple-pulse features thanks to three feature selection methods. A support vector machines classifier is finally used to label the point cloud according to various scenarios based on the rank of the features. This allows to find the best classification strategy as well as the minimal feature subsets allowing to achieve the highest classification accuracy possible for each of the three feature selection methods.The results show that the echo amplitude as well as two features computed from the radiometric calibration of full-waveform data, namely the cross-section and the backscatter coefficient, significantly contribute to the high classification accuracies reported in this paper (around 95%). Conversely, features extracted from the non Gaussian modelling of the echoes are not relevant for the discrimination of vegetation, ground, and buildings in urban areas.

KW - Classification

KW - Feature selection

KW - Full-waveform lidar data

KW - Support vector machines

KW - Urban areas

UR - http://www.scopus.com/inward/record.url?scp=84355166634&partnerID=8YFLogxK

U2 - 10.1016/j.isprsjprs.2011.09.008

DO - 10.1016/j.isprsjprs.2011.09.008

M3 - Article

AN - SCOPUS:84355166634

VL - 66

SP - S71-S84

JO - ISPRS Journal of Photogrammetry and Remote Sensing

JF - ISPRS Journal of Photogrammetry and Remote Sensing

SN - 0924-2716

IS - 6 SUPPL.

ER -