SEQUENTIAL MODELLING OF BUILDING ROOFTOPS BY INTEGRATING AIRBORNE LIDAR DATA AND OPTICAL IMAGERY: PRELIMINARY RESULTS

SEQUENTIAL MODELLING OF BUILDING ROOFTOPS BY INTEGRATING AIRBORNE LIDAR DATA AND OPTICAL IMAGERY: PRELIMINARY RESULTS

This paper presents a sequential rooftop modelling method to refine initial rooftop models derived from airborne LiDAR data by integrating it with linear cues retrieved from single imagery. A cue integration between two datasets is facilitated by creating new topological features connecting between...

Full description

Bibliographic Details
Main Authors: G. Sohn, J. Jung, Y. Jwa, C. Armenakis
Format: Article
Language:English
Published: Copernicus Publications 2013-05-01
Series:ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Online Access:http://www.isprs-ann-photogramm-remote-sens-spatial-inf-sci.net/II-3-W1/27/2013/isprsannals-II-3-W1-27-2013.pdf
id doaj-4270537db7874229940c4d2372864d83
record_format Article
spelling doaj-4270537db7874229940c4d2372864d832020-11-24T21:57:44ZengCopernicus PublicationsISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences2194-90422194-90502013-05-01II-3/W1273310.5194/isprsannals-II-3-W1-27-2013SEQUENTIAL MODELLING OF BUILDING ROOFTOPS BY INTEGRATING AIRBORNE LIDAR DATA AND OPTICAL IMAGERY: PRELIMINARY RESULTSG. Sohn0J. Jung1Y. Jwa2C. Armenakis3GeoICT lab, Department of Earth and Space Science and Engineering, York University, 4700 Keele Street, Toronto, ON M3J 1P3, CanadaGeoICT lab, Department of Earth and Space Science and Engineering, York University, 4700 Keele Street, Toronto, ON M3J 1P3, CanadaGeoICT lab, Department of Earth and Space Science and Engineering, York University, 4700 Keele Street, Toronto, ON M3J 1P3, CanadaGeoICT lab, Department of Earth and Space Science and Engineering, York University, 4700 Keele Street, Toronto, ON M3J 1P3, CanadaThis paper presents a sequential rooftop modelling method to refine initial rooftop models derived from airborne LiDAR data by integrating it with linear cues retrieved from single imagery. A cue integration between two datasets is facilitated by creating new topological features connecting between the initial model and image lines, with which new model hypotheses (variances to the initial model) are produced. We adopt Minimum Description Length (MDL) principle for competing the model candidates and selecting the optimal model by considering the balanced trade-off between the model closeness and the model complexity. Our preliminary results, combined with the Vaihingen data provided by ISPRS WGIII/4 demonstrate the image-driven modelling cues can compensate the limitations posed by LiDAR data in rooftop modelling.http://www.isprs-ann-photogramm-remote-sens-spatial-inf-sci.net/II-3-W1/27/2013/isprsannals-II-3-W1-27-2013.pdf
collection DOAJ
language English
format Article
sources DOAJ
author G. Sohn
J. Jung
Y. Jwa
C. Armenakis
spellingShingle G. Sohn
J. Jung
Y. Jwa
C. Armenakis
SEQUENTIAL MODELLING OF BUILDING ROOFTOPS BY INTEGRATING AIRBORNE LIDAR DATA AND OPTICAL IMAGERY: PRELIMINARY RESULTS
ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
author_facet G. Sohn
J. Jung
Y. Jwa
C. Armenakis
author_sort G. Sohn
title SEQUENTIAL MODELLING OF BUILDING ROOFTOPS BY INTEGRATING AIRBORNE LIDAR DATA AND OPTICAL IMAGERY: PRELIMINARY RESULTS
title_short SEQUENTIAL MODELLING OF BUILDING ROOFTOPS BY INTEGRATING AIRBORNE LIDAR DATA AND OPTICAL IMAGERY: PRELIMINARY RESULTS
title_full SEQUENTIAL MODELLING OF BUILDING ROOFTOPS BY INTEGRATING AIRBORNE LIDAR DATA AND OPTICAL IMAGERY: PRELIMINARY RESULTS
title_fullStr SEQUENTIAL MODELLING OF BUILDING ROOFTOPS BY INTEGRATING AIRBORNE LIDAR DATA AND OPTICAL IMAGERY: PRELIMINARY RESULTS
title_full_unstemmed SEQUENTIAL MODELLING OF BUILDING ROOFTOPS BY INTEGRATING AIRBORNE LIDAR DATA AND OPTICAL IMAGERY: PRELIMINARY RESULTS
title_sort sequential modelling of building rooftops by integrating airborne lidar data and optical imagery: preliminary results
publisher Copernicus Publications
series ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
issn 2194-9042
2194-9050
publishDate 2013-05-01
description This paper presents a sequential rooftop modelling method to refine initial rooftop models derived from airborne LiDAR data by integrating it with linear cues retrieved from single imagery. A cue integration between two datasets is facilitated by creating new topological features connecting between the initial model and image lines, with which new model hypotheses (variances to the initial model) are produced. We adopt Minimum Description Length (MDL) principle for competing the model candidates and selecting the optimal model by considering the balanced trade-off between the model closeness and the model complexity. Our preliminary results, combined with the Vaihingen data provided by ISPRS WGIII/4 demonstrate the image-driven modelling cues can compensate the limitations posed by LiDAR data in rooftop modelling.
url http://www.isprs-ann-photogramm-remote-sens-spatial-inf-sci.net/II-3-W1/27/2013/isprsannals-II-3-W1-27-2013.pdf
work_keys_str_mv AT gsohn sequentialmodellingofbuildingrooftopsbyintegratingairbornelidardataandopticalimagerypreliminaryresults
AT jjung sequentialmodellingofbuildingrooftopsbyintegratingairbornelidardataandopticalimagerypreliminaryresults
AT yjwa sequentialmodellingofbuildingrooftopsbyintegratingairbornelidardataandopticalimagerypreliminaryresults
AT carmenakis sequentialmodellingofbuildingrooftopsbyintegratingairbornelidardataandopticalimagerypreliminaryresults
_version_ 1725853953841692672

Similar Items