Incorporating Plane-Sweep in Convolutional Neural Network Stereo Imaging for Road Surface Reconstruction

Hauke Brunken, Clemens Gühmann

2019

Abstract

Convolutional neural networks, which estimate depth from stereo pictures in a single step, have become state of the art recently. The search space for matching pixels is hard coded in these networks and in literature is chosen to be the disparity space, corresponding to a search in the cameras viewing direction. In the proposed method, the search space is altered by a plane sweep approach, reducing necessary search steps for depth map estimation of flat surfaces. The described method is shown to provide high quality depth maps of road surfaces in the targeted application of pavement distress detection, where the stereo cameras are mounted behind the windshield of a moving vehicle. It provides a cheap replacement for laser scanning for this purpose.

Paper Citation

in Harvard Style

Brunken H. and Gühmann C. (2019). Incorporating Plane-Sweep in Convolutional Neural Network Stereo Imaging for Road Surface Reconstruction. In Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2019) - Volume 5: VISAPP; ISBN 978-989-758-354-4, SciTePress, pages 784-791. DOI: 10.5220/0007352107840791

in Bibtex Style

@conference{visapp19,
author={Hauke Brunken and Clemens Gühmann},
title={Incorporating Plane-Sweep in Convolutional Neural Network Stereo Imaging for Road Surface Reconstruction},
booktitle={Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2019) - Volume 5: VISAPP},
year={2019},
pages={784-791},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0007352107840791},
isbn={978-989-758-354-4},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2019) - Volume 5: VISAPP
TI - Incorporating Plane-Sweep in Convolutional Neural Network Stereo Imaging for Road Surface Reconstruction
SN - 978-989-758-354-4
AU - Brunken H.
AU - Gühmann C.
PY - 2019
SP - 784
EP - 791
DO - 10.5220/0007352107840791
PB - SciTePress