Fast 3D Scene Alignment with Stereo Images using a Stixel-based 3D Model

Dennis W. J. M. van de Wouw, Willem P. Sanberg, Gijs Dubbelman, Peter H. N. de With

2018

Abstract

Scene alignment for images recorded from different viewpoints is a challenging task, especially considering strong parallax effects. This work proposes a diorama-box model for a 2.5D hierarchical alignment approach, which is specifically designed for image registration from a moving vehicle using a stereo camera. For this purpose, the Stixel World algorithm is used to partition the scene into super-pixels, which are transformed to 3D. This model is further refined by assigning a slanting orientation to each stixel and by interpolating between stixels, to prevent gaps in the 3D model. The resulting alignment shows promising results, where under normal viewing conditions, more than 96% of all annotated points are registered with an alignment error up to 5 pixels at a resolution of 1920x1440 pixels, executing at near-real time performance (4 fps) for the intended application.

Paper Citation

in Harvard Style

van de Wouw D., Sanberg W., Dubbelman G. and de With P. (2018). Fast 3D Scene Alignment with Stereo Images using a Stixel-based 3D Model. In Proceedings of the 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2018) - Volume 4: VISAPP; ISBN 978-989-758-290-5, SciTePress, pages 250-259. DOI: 10.5220/0006535302500259

in Bibtex Style

@conference{visapp18,
author={Dennis W. J. M. van de Wouw and Willem P. Sanberg and Gijs Dubbelman and Peter H. N. de With},
title={Fast 3D Scene Alignment with Stereo Images using a Stixel-based 3D Model},
booktitle={Proceedings of the 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2018) - Volume 4: VISAPP},
year={2018},
pages={250-259},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006535302500259},
isbn={978-989-758-290-5},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2018) - Volume 4: VISAPP
TI - Fast 3D Scene Alignment with Stereo Images using a Stixel-based 3D Model
SN - 978-989-758-290-5
AU - van de Wouw D.
AU - Sanberg W.
AU - Dubbelman G.
AU - de With P.
PY - 2018
SP - 250
EP - 259
DO - 10.5220/0006535302500259
PB - SciTePress