INTEGRATION OF A GENERALISED BUILDING MODEL INTO THE POSE ESTIMATION OF UAS IMAGES

Publikation: Beitrag in FachzeitschriftKonferenzaufsatz in FachzeitschriftForschungPeer-Review

Autoren

  • J. Unger
  • F. Rottensteiner
  • C. Heipke
Forschungs-netzwerk anzeigen

Details

OriginalspracheEnglisch
Seiten (von - bis)1057-1064
Seitenumfang8
FachzeitschriftInternational Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives
Jahrgang41
AusgabenummerB1
PublikationsstatusVeröffentlicht - 6 Juni 2016
Veranstaltung23rd International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences Congress, ISPRS 2016 - Prague, Tschechische Republik
Dauer: 12 Juli 201619 Juli 2016

Abstract

A hybrid bundle adjustment is presented that allows for the integration of a generalised building model into the pose estimation of image sequences. These images are captured by an Unmanned Aerial System (UAS) equipped with a camera flying in between the buildings. The relation between the building model and the images is described by distances between the object coordinates of the tie points and building model planes. Relations are found by a simple 3D distance criterion and are modelled as fictitious observations in a Gauss-Markov adjustment. The coordinates of model vertices are part of the adjustment as directly observed unknowns which allows for changes in the model. Results of first experiments using a synthetic and a real image sequence demonstrate improvements of the image orientation in comparison to an adjustment without the building model, but also reveal limitations of the current state of the method.

ASJC Scopus Sachgebiete

Zitieren

INTEGRATION OF A GENERALISED BUILDING MODEL INTO THE POSE ESTIMATION OF UAS IMAGES. / Unger, J.; Rottensteiner, F.; Heipke, C.
in: International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives, Jahrgang 41, Nr. B1, 06.06.2016, S. 1057-1064.

Publikation: Beitrag in FachzeitschriftKonferenzaufsatz in FachzeitschriftForschungPeer-Review

Unger, J, Rottensteiner, F & Heipke, C 2016, 'INTEGRATION OF A GENERALISED BUILDING MODEL INTO THE POSE ESTIMATION OF UAS IMAGES', International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives, Jg. 41, Nr. B1, S. 1057-1064. https://doi.org/10.5194/isprsarchives-XLI-B1-1057-2016, https://doi.org/10.5194/isprs-archives-XLI-B1-1057-2016
Unger, J., Rottensteiner, F., & Heipke, C. (2016). INTEGRATION OF A GENERALISED BUILDING MODEL INTO THE POSE ESTIMATION OF UAS IMAGES. International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives, 41(B1), 1057-1064. https://doi.org/10.5194/isprsarchives-XLI-B1-1057-2016, https://doi.org/10.5194/isprs-archives-XLI-B1-1057-2016
Unger J, Rottensteiner F, Heipke C. INTEGRATION OF A GENERALISED BUILDING MODEL INTO THE POSE ESTIMATION OF UAS IMAGES. International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives. 2016 Jun 6;41(B1):1057-1064. doi: 10.5194/isprsarchives-XLI-B1-1057-2016, 10.5194/isprs-archives-XLI-B1-1057-2016
Unger, J. ; Rottensteiner, F. ; Heipke, C. / INTEGRATION OF A GENERALISED BUILDING MODEL INTO THE POSE ESTIMATION OF UAS IMAGES. in: International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives. 2016 ; Jahrgang 41, Nr. B1. S. 1057-1064.
Download
@article{9bfe53d5fa6348869158e32375634939,
title = "INTEGRATION OF A GENERALISED BUILDING MODEL INTO THE POSE ESTIMATION OF UAS IMAGES",
abstract = "A hybrid bundle adjustment is presented that allows for the integration of a generalised building model into the pose estimation of image sequences. These images are captured by an Unmanned Aerial System (UAS) equipped with a camera flying in between the buildings. The relation between the building model and the images is described by distances between the object coordinates of the tie points and building model planes. Relations are found by a simple 3D distance criterion and are modelled as fictitious observations in a Gauss-Markov adjustment. The coordinates of model vertices are part of the adjustment as directly observed unknowns which allows for changes in the model. Results of first experiments using a synthetic and a real image sequence demonstrate improvements of the image orientation in comparison to an adjustment without the building model, but also reveal limitations of the current state of the method.",
keywords = "Building model, Hybrid bundle adjustment, Pose estimation, UAS, Unmanned aerial system, hybrid bundle adjustment, pose estimation, building model, unmanned aerial system",
author = "J. Unger and F. Rottensteiner and C. Heipke",
note = "Copyright: Copyright 2017 Elsevier B.V., All rights reserved.; 23rd International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences Congress, ISPRS 2016 ; Conference date: 12-07-2016 Through 19-07-2016",
year = "2016",
month = jun,
day = "6",
doi = "10.5194/isprsarchives-XLI-B1-1057-2016",
language = "English",
volume = "41",
pages = "1057--1064",
number = "B1",

}

Download

TY - JOUR

T1 - INTEGRATION OF A GENERALISED BUILDING MODEL INTO THE POSE ESTIMATION OF UAS IMAGES

AU - Unger, J.

AU - Rottensteiner, F.

AU - Heipke, C.

N1 - Copyright: Copyright 2017 Elsevier B.V., All rights reserved.

PY - 2016/6/6

Y1 - 2016/6/6

N2 - A hybrid bundle adjustment is presented that allows for the integration of a generalised building model into the pose estimation of image sequences. These images are captured by an Unmanned Aerial System (UAS) equipped with a camera flying in between the buildings. The relation between the building model and the images is described by distances between the object coordinates of the tie points and building model planes. Relations are found by a simple 3D distance criterion and are modelled as fictitious observations in a Gauss-Markov adjustment. The coordinates of model vertices are part of the adjustment as directly observed unknowns which allows for changes in the model. Results of first experiments using a synthetic and a real image sequence demonstrate improvements of the image orientation in comparison to an adjustment without the building model, but also reveal limitations of the current state of the method.

AB - A hybrid bundle adjustment is presented that allows for the integration of a generalised building model into the pose estimation of image sequences. These images are captured by an Unmanned Aerial System (UAS) equipped with a camera flying in between the buildings. The relation between the building model and the images is described by distances between the object coordinates of the tie points and building model planes. Relations are found by a simple 3D distance criterion and are modelled as fictitious observations in a Gauss-Markov adjustment. The coordinates of model vertices are part of the adjustment as directly observed unknowns which allows for changes in the model. Results of first experiments using a synthetic and a real image sequence demonstrate improvements of the image orientation in comparison to an adjustment without the building model, but also reveal limitations of the current state of the method.

KW - Building model

KW - Hybrid bundle adjustment

KW - Pose estimation

KW - UAS

KW - Unmanned aerial system

KW - hybrid bundle adjustment

KW - pose estimation

KW - building model

KW - unmanned aerial system

UR - http://www.scopus.com/inward/record.url?scp=84987880414&partnerID=8YFLogxK

U2 - 10.5194/isprsarchives-XLI-B1-1057-2016

DO - 10.5194/isprsarchives-XLI-B1-1057-2016

M3 - Conference article

AN - SCOPUS:84987880414

VL - 41

SP - 1057

EP - 1064

JO - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives

JF - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives

SN - 1682-1750

IS - B1

T2 - 23rd International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences Congress, ISPRS 2016

Y2 - 12 July 2016 through 19 July 2016

ER -