Multi-view dense matching supported by triangular meshes

Research output: Contribution to journalArticleResearchpeer review

Authors

  • Dimitri Bulatov
  • Peter Wernerus
  • Christian Heipke

External Research Organisations

  • Fraunhofer-Institute of Optronics, System Technologies and Image Exploitation (IOSB)
View graph of relations

Details

Original languageEnglish
Pages (from-to)907-918
Number of pages12
JournalISPRS Journal of Photogrammetry and Remote Sensing
Volume66
Issue number6
Early online date15 Aug 2011
Publication statusPublished - Nov 2011

Abstract

We present a new procedure to compute dense 3D point clouds from a sequential set of images. This procedure is considered as a second step of a three-step algorithm for 3D reconstruction from image sequences, whose first step consists of image orientation and the last step is shape reconstruction. We assume that the camera matrices as well as a sparse set of 3D points are available and we strive for obtaining a dense and reliable 3D point cloud. Three novel ideas are presented: (1) for sparse tracking and triangulation, the search space for correspondences is reduced to a line segment by means of known camera matrices and disparity ranges are provided by triangular meshes from the already available points; (2) triangular meshes from extended sets of points are used for dense matching, because these meshes help to reconstruct points in weakly textured areas and present a natural way to obtain subpixel accuracy; (3) two non-local optimization methods, namely, 1D dynamic programming along horizontal lines and semi-global optimization were employed for refinement of local results obtained from an arbitrary number of images. All methods were extensively tested on a benchmark data set and an infrared video sequence. Both visual and quantitative results demonstrate the effectiveness of our algorithm.

Keywords

    Depth map, Matching, Multi-view, Semi-global, Triangle mesh

ASJC Scopus subject areas

Cite this

Multi-view dense matching supported by triangular meshes. / Bulatov, Dimitri; Wernerus, Peter; Heipke, Christian.
In: ISPRS Journal of Photogrammetry and Remote Sensing, Vol. 66, No. 6, 11.2011, p. 907-918.

Research output: Contribution to journalArticleResearchpeer review

Bulatov D, Wernerus P, Heipke C. Multi-view dense matching supported by triangular meshes. ISPRS Journal of Photogrammetry and Remote Sensing. 2011 Nov;66(6):907-918. Epub 2011 Aug 15. doi: 10.1016/j.isprsjprs.2011.06.006
Bulatov, Dimitri ; Wernerus, Peter ; Heipke, Christian. / Multi-view dense matching supported by triangular meshes. In: ISPRS Journal of Photogrammetry and Remote Sensing. 2011 ; Vol. 66, No. 6. pp. 907-918.
Download
@article{54a22fe0a7ee4aa98d52e024aaaf710f,
title = "Multi-view dense matching supported by triangular meshes",
abstract = "We present a new procedure to compute dense 3D point clouds from a sequential set of images. This procedure is considered as a second step of a three-step algorithm for 3D reconstruction from image sequences, whose first step consists of image orientation and the last step is shape reconstruction. We assume that the camera matrices as well as a sparse set of 3D points are available and we strive for obtaining a dense and reliable 3D point cloud. Three novel ideas are presented: (1) for sparse tracking and triangulation, the search space for correspondences is reduced to a line segment by means of known camera matrices and disparity ranges are provided by triangular meshes from the already available points; (2) triangular meshes from extended sets of points are used for dense matching, because these meshes help to reconstruct points in weakly textured areas and present a natural way to obtain subpixel accuracy; (3) two non-local optimization methods, namely, 1D dynamic programming along horizontal lines and semi-global optimization were employed for refinement of local results obtained from an arbitrary number of images. All methods were extensively tested on a benchmark data set and an infrared video sequence. Both visual and quantitative results demonstrate the effectiveness of our algorithm.",
keywords = "Depth map, Matching, Multi-view, Semi-global, Triangle mesh",
author = "Dimitri Bulatov and Peter Wernerus and Christian Heipke",
year = "2011",
month = nov,
doi = "10.1016/j.isprsjprs.2011.06.006",
language = "English",
volume = "66",
pages = "907--918",
journal = "ISPRS Journal of Photogrammetry and Remote Sensing",
issn = "0924-2716",
publisher = "Elsevier",
number = "6",

}

Download

TY - JOUR

T1 - Multi-view dense matching supported by triangular meshes

AU - Bulatov, Dimitri

AU - Wernerus, Peter

AU - Heipke, Christian

PY - 2011/11

Y1 - 2011/11

N2 - We present a new procedure to compute dense 3D point clouds from a sequential set of images. This procedure is considered as a second step of a three-step algorithm for 3D reconstruction from image sequences, whose first step consists of image orientation and the last step is shape reconstruction. We assume that the camera matrices as well as a sparse set of 3D points are available and we strive for obtaining a dense and reliable 3D point cloud. Three novel ideas are presented: (1) for sparse tracking and triangulation, the search space for correspondences is reduced to a line segment by means of known camera matrices and disparity ranges are provided by triangular meshes from the already available points; (2) triangular meshes from extended sets of points are used for dense matching, because these meshes help to reconstruct points in weakly textured areas and present a natural way to obtain subpixel accuracy; (3) two non-local optimization methods, namely, 1D dynamic programming along horizontal lines and semi-global optimization were employed for refinement of local results obtained from an arbitrary number of images. All methods were extensively tested on a benchmark data set and an infrared video sequence. Both visual and quantitative results demonstrate the effectiveness of our algorithm.

AB - We present a new procedure to compute dense 3D point clouds from a sequential set of images. This procedure is considered as a second step of a three-step algorithm for 3D reconstruction from image sequences, whose first step consists of image orientation and the last step is shape reconstruction. We assume that the camera matrices as well as a sparse set of 3D points are available and we strive for obtaining a dense and reliable 3D point cloud. Three novel ideas are presented: (1) for sparse tracking and triangulation, the search space for correspondences is reduced to a line segment by means of known camera matrices and disparity ranges are provided by triangular meshes from the already available points; (2) triangular meshes from extended sets of points are used for dense matching, because these meshes help to reconstruct points in weakly textured areas and present a natural way to obtain subpixel accuracy; (3) two non-local optimization methods, namely, 1D dynamic programming along horizontal lines and semi-global optimization were employed for refinement of local results obtained from an arbitrary number of images. All methods were extensively tested on a benchmark data set and an infrared video sequence. Both visual and quantitative results demonstrate the effectiveness of our algorithm.

KW - Depth map

KW - Matching

KW - Multi-view

KW - Semi-global

KW - Triangle mesh

UR - http://www.scopus.com/inward/record.url?scp=81555211159&partnerID=8YFLogxK

U2 - 10.1016/j.isprsjprs.2011.06.006

DO - 10.1016/j.isprsjprs.2011.06.006

M3 - Article

AN - SCOPUS:81555211159

VL - 66

SP - 907

EP - 918

JO - ISPRS Journal of Photogrammetry and Remote Sensing

JF - ISPRS Journal of Photogrammetry and Remote Sensing

SN - 0924-2716

IS - 6

ER -