Guided sparse camera pose estimation

Fabian Schenk; Ludwig Mohr; Matthias Rüther; Friedrich Fraundorfer; Horst Bischof

Guided sparse camera pose estimation

Fabian Schenk, Ludwig Mohr, Matthias Rüther, Friedrich Fraundorfer, Horst Bischof

Institute of Computer Graphics and Vision (7100)

Research output: Chapter in Book/Report/Conference proceeding › Conference paper › peer-review

Abstract

In this paper, we present an idea for a sparse approach to calculate camera poses from RGB images and laser distance measurements to perform subsequent facade reconstruction. The core idea is to guide the image recording process by choosing distinctive features with the laser range finder, e.g. building or window corners. From these distinctive features, we can establish correspondences between views to compute metrically accurate camera poses from just a few precise measurements. In our experiments, we achieve reasonable results in building facade reconstruction with only a fraction of features compared to standard structure from motion.

Original language	English
Title of host publication	Proceedings of The 40th Annual Workshop of the Austrian Association for Pattern Recognition (OAGM), 2016
Pages	139-146
Number of pages	8
Publication status	Published - 2016
Event	40th Annual Workshop of the Austrian Association for Pattern Recognition: Vison Meets Robotics: ÖAGM 2016 - FH OÖ Campus, Wels, Austria Duration: 11 May 2016 → 13 May 2016 Conference number: 40 https://www.fh-ooe.at/kongresse/2016/oagmaapr-arw/ https://www.fh-ooe.at/en/kongresse/2016/oagm-arw/

Workshop

Workshop	40th Annual Workshop of the Austrian Association for Pattern Recognition: Vison Meets Robotics
Abbreviated title	OAGM 2016
Country/Territory	Austria
City	Wels
Period	11/05/16 → 13/05/16
Other	OAGM & ARW Joint Workshop
Internet address	https://www.fh-ooe.at/kongresse/2016/oagmaapr-arw/ https://www.fh-ooe.at/en/kongresse/2016/oagm-arw/

Keywords

Structure-from-motion
3D reconstruction

Access to Document

Schenk_Fraundorfer_OAGMFinal published version, 193 KB

https://elib.dlr.de/104770/

Cite this

Schenk, F, Mohr, L, Rüther, M, Fraundorfer, F & Bischof, H 2016, Guided sparse camera pose estimation. in Proceedings of The 40th Annual Workshop of the Austrian Association for Pattern Recognition (OAGM), 2016. pp. 139-146, 40th Annual Workshop of the Austrian Association for Pattern Recognition: Vison Meets Robotics, Wels, Austria, 11/05/16. <https://elib.dlr.de/104770/>

@inproceedings{9ddcd4e4d68d48bf948e00ba4161ea6d,

title = "Guided sparse camera pose estimation",

abstract = "In this paper, we present an idea for a sparse approach to calculate camera poses from RGB images and laser distance measurements to perform subsequent facade reconstruction. The core idea is to guide the image recording process by choosing distinctive features with the laser range finder, e.g. building or window corners. From these distinctive features, we can establish correspondences between views to compute metrically accurate camera poses from just a few precise measurements. In our experiments, we achieve reasonable results in building facade reconstruction with only a fraction of features compared to standard structure from motion.",

keywords = "Structure-from-motion, 3D reconstruction",

author = "Fabian Schenk and Ludwig Mohr and Matthias R{\"u}ther and Friedrich Fraundorfer and Horst Bischof",

year = "2016",

language = "English",

pages = "139--146",

booktitle = "Proceedings of The 40th Annual Workshop of the Austrian Association for Pattern Recognition (OAGM), 2016",

note = "40th Annual Workshop of the Austrian Association for Pattern Recognition: Vison Meets Robotics : {\"O}AGM 2016, OAGM 2016 ; Conference date: 11-05-2016 Through 13-05-2016",

url = "https://www.fh-ooe.at/kongresse/2016/oagmaapr-arw/, https://www.fh-ooe.at/en/kongresse/2016/oagm-arw/",

}

TY - GEN

T1 - Guided sparse camera pose estimation

AU - Schenk, Fabian

AU - Mohr, Ludwig

AU - Rüther, Matthias

AU - Fraundorfer, Friedrich

AU - Bischof, Horst

N1 - Conference code: 40

PY - 2016

Y1 - 2016

N2 - In this paper, we present an idea for a sparse approach to calculate camera poses from RGB images and laser distance measurements to perform subsequent facade reconstruction. The core idea is to guide the image recording process by choosing distinctive features with the laser range finder, e.g. building or window corners. From these distinctive features, we can establish correspondences between views to compute metrically accurate camera poses from just a few precise measurements. In our experiments, we achieve reasonable results in building facade reconstruction with only a fraction of features compared to standard structure from motion.

AB - In this paper, we present an idea for a sparse approach to calculate camera poses from RGB images and laser distance measurements to perform subsequent facade reconstruction. The core idea is to guide the image recording process by choosing distinctive features with the laser range finder, e.g. building or window corners. From these distinctive features, we can establish correspondences between views to compute metrically accurate camera poses from just a few precise measurements. In our experiments, we achieve reasonable results in building facade reconstruction with only a fraction of features compared to standard structure from motion.

KW - Structure-from-motion

KW - 3D reconstruction

UR - http://elib.dlr.de/104770/1/Schenk_Fraundorfer_AAPR%20(3).pdf

M3 - Conference paper

SP - 139

EP - 146

BT - Proceedings of The 40th Annual Workshop of the Austrian Association for Pattern Recognition (OAGM), 2016

T2 - 40th Annual Workshop of the Austrian Association for Pattern Recognition: Vison Meets Robotics

Y2 - 11 May 2016 through 13 May 2016

ER -

Guided sparse camera pose estimation

Abstract

Workshop

Keywords

Access to Document

Other files and links

Fingerprint

Cite this