Fusion of Point Clouds derived from Aerial Images

Andreas Schönfelder, Karlheinz Gutjahr, Roland Perko, Mathias Schardt

Publikation: KonferenzbeitragPaperForschungBegutachtung

Abstract

State of the art dense image matching in combination with advances in camera technology enables the reconstruction of scenes in a novel high spatial resolution and offers new mapping potential. This work presents a strategy for fusing highly redundant disparity maps by applying a local filtering method to a set of classified and oriented 3D point clouds. The information obtained from stereo matching is enhanced by computing a set of normal maps and by classifying the disparity maps in quality classes based on total variation. With this information given, a filtering method is applied that fuses the oriented point clouds along the surface normals of the 3D geometry. The proposed fusion strategy aims at the reduction of point cloud artifacts while generating a non-redundant surface representation, which prioritize high quality disparities. The potential of the fusion method is evaluated based on airborne imagery (oblique and nadir) by using reference data from terrestrial laser scanners
Originalspracheenglisch
Seiten139
Seitenumfang144
PublikationsstatusVeröffentlicht - 2017
VeranstaltungOAGM and ARW Joint Workshop - Palais Eschenbach, Wien, Österreich
Dauer: 10 Mai 201712 Mai 2017

Konferenz

KonferenzOAGM and ARW Joint Workshop
LandÖsterreich
OrtWien
Zeitraum10/05/1712/05/17

Fingerprint

airborne sensing
nadir
scanner
artifact
spatial resolution
laser
geometry
method
state of the art

Dies zitieren

Schönfelder, A., Gutjahr, K., Perko, R., & Schardt, M. (2017). Fusion of Point Clouds derived from Aerial Images. 139. Beitrag in OAGM and ARW Joint Workshop, Wien, Österreich.

Fusion of Point Clouds derived from Aerial Images. / Schönfelder, Andreas; Gutjahr, Karlheinz; Perko, Roland; Schardt, Mathias.

2017. 139 Beitrag in OAGM and ARW Joint Workshop, Wien, Österreich.

Publikation: KonferenzbeitragPaperForschungBegutachtung

Schönfelder, A, Gutjahr, K, Perko, R & Schardt, M 2017, 'Fusion of Point Clouds derived from Aerial Images' Beitrag in OAGM and ARW Joint Workshop, Wien, Österreich, 10/05/17 - 12/05/17, S. 139.
Schönfelder A, Gutjahr K, Perko R, Schardt M. Fusion of Point Clouds derived from Aerial Images. 2017. Beitrag in OAGM and ARW Joint Workshop, Wien, Österreich.
Schönfelder, Andreas ; Gutjahr, Karlheinz ; Perko, Roland ; Schardt, Mathias. / Fusion of Point Clouds derived from Aerial Images. Beitrag in OAGM and ARW Joint Workshop, Wien, Österreich.144 S.
@conference{6515985ce76e41e6a7b533127619a8ba,
title = "Fusion of Point Clouds derived from Aerial Images",
abstract = "State of the art dense image matching in combination with advances in camera technology enables the reconstruction of scenes in a novel high spatial resolution and offers new mapping potential. This work presents a strategy for fusing highly redundant disparity maps by applying a local filtering method to a set of classified and oriented 3D point clouds. The information obtained from stereo matching is enhanced by computing a set of normal maps and by classifying the disparity maps in quality classes based on total variation. With this information given, a filtering method is applied that fuses the oriented point clouds along the surface normals of the 3D geometry. The proposed fusion strategy aims at the reduction of point cloud artifacts while generating a non-redundant surface representation, which prioritize high quality disparities. The potential of the fusion method is evaluated based on airborne imagery (oblique and nadir) by using reference data from terrestrial laser scanners.",
author = "Andreas Sch{\"o}nfelder and Karlheinz Gutjahr and Roland Perko and Mathias Schardt",
year = "2017",
language = "English",
pages = "139",
note = "OAGM and ARW Joint Workshop ; Conference date: 10-05-2017 Through 12-05-2017",

}

TY - CONF

T1 - Fusion of Point Clouds derived from Aerial Images

AU - Schönfelder, Andreas

AU - Gutjahr, Karlheinz

AU - Perko, Roland

AU - Schardt, Mathias

PY - 2017

Y1 - 2017

N2 - State of the art dense image matching in combination with advances in camera technology enables the reconstruction of scenes in a novel high spatial resolution and offers new mapping potential. This work presents a strategy for fusing highly redundant disparity maps by applying a local filtering method to a set of classified and oriented 3D point clouds. The information obtained from stereo matching is enhanced by computing a set of normal maps and by classifying the disparity maps in quality classes based on total variation. With this information given, a filtering method is applied that fuses the oriented point clouds along the surface normals of the 3D geometry. The proposed fusion strategy aims at the reduction of point cloud artifacts while generating a non-redundant surface representation, which prioritize high quality disparities. The potential of the fusion method is evaluated based on airborne imagery (oblique and nadir) by using reference data from terrestrial laser scanners.

AB - State of the art dense image matching in combination with advances in camera technology enables the reconstruction of scenes in a novel high spatial resolution and offers new mapping potential. This work presents a strategy for fusing highly redundant disparity maps by applying a local filtering method to a set of classified and oriented 3D point clouds. The information obtained from stereo matching is enhanced by computing a set of normal maps and by classifying the disparity maps in quality classes based on total variation. With this information given, a filtering method is applied that fuses the oriented point clouds along the surface normals of the 3D geometry. The proposed fusion strategy aims at the reduction of point cloud artifacts while generating a non-redundant surface representation, which prioritize high quality disparities. The potential of the fusion method is evaluated based on airborne imagery (oblique and nadir) by using reference data from terrestrial laser scanners.

M3 - Paper

SP - 139

ER -