EFFICIENT AND GLOBALLY OPTIMAL MULTI VIEW DENSE MATCHING FOR AERIAL IMAGES
A variety of applications exist for aerial 3D reconstruction, ranging from the production of digital surface models (DSMs) and digital terrain models (DTMs) to the creation of true orthophoto and full 3D models of urban scenes that can be visualized through the web. In this paper we present an aut...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Copernicus Publications
2012-07-01
|
| Series: | ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
| Online Access: | https://www.isprs-ann-photogramm-remote-sens-spatial-inf-sci.net/I-3/227/2012/isprsannals-I-3-227-2012.pdf |
| _version_ | 1828765786368376832 |
|---|---|
| author | A. Irschara M. Rumpler P. Meixner T. Pock H. Bischof |
| author_facet | A. Irschara M. Rumpler P. Meixner T. Pock H. Bischof |
| author_sort | A. Irschara |
| collection | DOAJ |
| description | A variety of applications exist for aerial 3D reconstruction, ranging from the production of digital surface models (DSMs) and digital
terrain models (DTMs) to the creation of true orthophoto and full 3D models of urban scenes that can be visualized through the web. In
this paper we present an automated end-to-end workflow to create digital surface models from large scale and highly overlapping aerial
images. The core component of our approach is a multi-view dense matching algorithm that fully exploits the redundancy of the data.
This is in contrast to traditional two-view based stereo matching approaches in aerial photogrammetry. In particular, our solution to
dense depth estimation is based on a multi-view plane sweep approach with discontinuity preserving global optimization. We provide a
fully automatic framework for aerial triangulation, image overlap estimation and dense depth matching. Our algorithms are designed to
run on current graphics processing units (GPUs) which makes large scale processing feasible at low cost. We present dense matching
results from a large aerial survey comprising 3000 aerial images of Graz and give a detailed performance analysis in terms of accuracy
and processing time. |
| first_indexed | 2024-12-11T06:54:19Z |
| format | Article |
| id | doaj.art-503d88751b2c439b8cc8e6537aeca792 |
| institution | Directory Open Access Journal |
| issn | 2194-9042 2194-9050 |
| language | English |
| last_indexed | 2024-12-11T06:54:19Z |
| publishDate | 2012-07-01 |
| publisher | Copernicus Publications |
| record_format | Article |
| series | ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
| spelling | doaj.art-503d88751b2c439b8cc8e6537aeca7922022-12-22T01:16:49ZengCopernicus PublicationsISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences2194-90422194-90502012-07-01I-322723210.5194/isprsannals-I-3-227-2012EFFICIENT AND GLOBALLY OPTIMAL MULTI VIEW DENSE MATCHING FOR AERIAL IMAGESA. Irschara0M. Rumpler1P. Meixner2T. Pock3H. Bischof4Microsoft Photogrammety, Anzengrubergasse 8, A-8010 Graz, AustriaInstitute for Computer Graphics and Vision, Graz University of Technology, Inffeldgasse 16, A-8010 Graz, AustriaInstitute for Computer Graphics and Vision, Graz University of Technology, Inffeldgasse 16, A-8010 Graz, AustriaInstitute for Computer Graphics and Vision, Graz University of Technology, Inffeldgasse 16, A-8010 Graz, AustriaInstitute for Computer Graphics and Vision, Graz University of Technology, Inffeldgasse 16, A-8010 Graz, AustriaA variety of applications exist for aerial 3D reconstruction, ranging from the production of digital surface models (DSMs) and digital terrain models (DTMs) to the creation of true orthophoto and full 3D models of urban scenes that can be visualized through the web. In this paper we present an automated end-to-end workflow to create digital surface models from large scale and highly overlapping aerial images. The core component of our approach is a multi-view dense matching algorithm that fully exploits the redundancy of the data. This is in contrast to traditional two-view based stereo matching approaches in aerial photogrammetry. In particular, our solution to dense depth estimation is based on a multi-view plane sweep approach with discontinuity preserving global optimization. We provide a fully automatic framework for aerial triangulation, image overlap estimation and dense depth matching. Our algorithms are designed to run on current graphics processing units (GPUs) which makes large scale processing feasible at low cost. We present dense matching results from a large aerial survey comprising 3000 aerial images of Graz and give a detailed performance analysis in terms of accuracy and processing time.https://www.isprs-ann-photogramm-remote-sens-spatial-inf-sci.net/I-3/227/2012/isprsannals-I-3-227-2012.pdf |
| spellingShingle | A. Irschara M. Rumpler P. Meixner T. Pock H. Bischof EFFICIENT AND GLOBALLY OPTIMAL MULTI VIEW DENSE MATCHING FOR AERIAL IMAGES ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
| title | EFFICIENT AND GLOBALLY OPTIMAL MULTI VIEW DENSE MATCHING FOR AERIAL IMAGES |
| title_full | EFFICIENT AND GLOBALLY OPTIMAL MULTI VIEW DENSE MATCHING FOR AERIAL IMAGES |
| title_fullStr | EFFICIENT AND GLOBALLY OPTIMAL MULTI VIEW DENSE MATCHING FOR AERIAL IMAGES |
| title_full_unstemmed | EFFICIENT AND GLOBALLY OPTIMAL MULTI VIEW DENSE MATCHING FOR AERIAL IMAGES |
| title_short | EFFICIENT AND GLOBALLY OPTIMAL MULTI VIEW DENSE MATCHING FOR AERIAL IMAGES |
| title_sort | efficient and globally optimal multi view dense matching for aerial images |
| url | https://www.isprs-ann-photogramm-remote-sens-spatial-inf-sci.net/I-3/227/2012/isprsannals-I-3-227-2012.pdf |
| work_keys_str_mv | AT airschara efficientandgloballyoptimalmultiviewdensematchingforaerialimages AT mrumpler efficientandgloballyoptimalmultiviewdensematchingforaerialimages AT pmeixner efficientandgloballyoptimalmultiviewdensematchingforaerialimages AT tpock efficientandgloballyoptimalmultiviewdensematchingforaerialimages AT hbischof efficientandgloballyoptimalmultiviewdensematchingforaerialimages |