Direct Stereo Visual Odometry Based on Lines

Research output: Chapter in Book/Report/Conference proceedingConference contributionResearchpeer-review

Abstract

We propose a novel stereo visual odometry approach, which is especially suited for poorly textured environments. We introduce a novel, fast line segment detector and matcher, which detects vertical lines supported by an IMU. The patches around lines are then used to directly estimate the pose of consecutive cameras by minimizing the photometric error. Our algorithm outperforms state-of-the-art approaches in challenging environments. Our implementation runs in real-time and is therefore well suited for various robotics and augmented reality applications.
Original languageEnglish
Title of host publication11th International Conference on Computer Vision Theory and Applications (VISAPP), 2016
Publication statusPublished - Feb 2016
Event11th International Conference on Computer Vision Theory and Applications (VISAPP) - Rome, Italy
Duration: 27 Feb 201629 Feb 2016

Conference

Conference11th International Conference on Computer Vision Theory and Applications (VISAPP)
CountryItaly
CityRome
Period27/02/1629/02/16

Cite this

Holzmann, T., Fraundorfer, F., & Bischof, H. (2016). Direct Stereo Visual Odometry Based on Lines. In 11th International Conference on Computer Vision Theory and Applications (VISAPP), 2016

Direct Stereo Visual Odometry Based on Lines. / Holzmann, Thomas; Fraundorfer, Friedrich; Bischof, Horst.

11th International Conference on Computer Vision Theory and Applications (VISAPP), 2016. 2016.

Research output: Chapter in Book/Report/Conference proceedingConference contributionResearchpeer-review

Holzmann, T, Fraundorfer, F & Bischof, H 2016, Direct Stereo Visual Odometry Based on Lines. in 11th International Conference on Computer Vision Theory and Applications (VISAPP), 2016. 11th International Conference on Computer Vision Theory and Applications (VISAPP), Rome, Italy, 27/02/16.
Holzmann T, Fraundorfer F, Bischof H. Direct Stereo Visual Odometry Based on Lines. In 11th International Conference on Computer Vision Theory and Applications (VISAPP), 2016. 2016
Holzmann, Thomas ; Fraundorfer, Friedrich ; Bischof, Horst. / Direct Stereo Visual Odometry Based on Lines. 11th International Conference on Computer Vision Theory and Applications (VISAPP), 2016. 2016.
@inproceedings{817443d4a0bf4e49b814683eead04929,
title = "Direct Stereo Visual Odometry Based on Lines",
abstract = "We propose a novel stereo visual odometry approach, which is especially suited for poorly textured environments. We introduce a novel, fast line segment detector and matcher, which detects vertical lines supported by an IMU. The patches around lines are then used to directly estimate the pose of consecutive cameras by minimizing the photometric error. Our algorithm outperforms state-of-the-art approaches in challenging environments. Our implementation runs in real-time and is therefore well suited for various robotics and augmented reality applications.",
author = "Thomas Holzmann and Friedrich Fraundorfer and Horst Bischof",
year = "2016",
month = "2",
language = "English",
booktitle = "11th International Conference on Computer Vision Theory and Applications (VISAPP), 2016",

}

TY - GEN

T1 - Direct Stereo Visual Odometry Based on Lines

AU - Holzmann, Thomas

AU - Fraundorfer, Friedrich

AU - Bischof, Horst

PY - 2016/2

Y1 - 2016/2

N2 - We propose a novel stereo visual odometry approach, which is especially suited for poorly textured environments. We introduce a novel, fast line segment detector and matcher, which detects vertical lines supported by an IMU. The patches around lines are then used to directly estimate the pose of consecutive cameras by minimizing the photometric error. Our algorithm outperforms state-of-the-art approaches in challenging environments. Our implementation runs in real-time and is therefore well suited for various robotics and augmented reality applications.

AB - We propose a novel stereo visual odometry approach, which is especially suited for poorly textured environments. We introduce a novel, fast line segment detector and matcher, which detects vertical lines supported by an IMU. The patches around lines are then used to directly estimate the pose of consecutive cameras by minimizing the photometric error. Our algorithm outperforms state-of-the-art approaches in challenging environments. Our implementation runs in real-time and is therefore well suited for various robotics and augmented reality applications.

M3 - Conference contribution

BT - 11th International Conference on Computer Vision Theory and Applications (VISAPP), 2016

ER -