A Study on the Influence of Omnidirectional Distortion on CNN-based Stereo Vision

Julian Seuffert, Ana Grassi, Tobias Scheck, Gangolf Hirtz

Abstract

Stereo vision is one of the most prominent strategies to reconstruct a 3D scene with computer vision techniques. With the advent of Convolutional Neural Networks (CNN), stereo vision has undergone a breakthrough. Always more works attend to recover the depth information from stereo images by using CNNs. However, most of the existing approaches are developed for images captured with perspective cameras. Perspective cameras have a very limited field of view of around 60â—¦ and only a small portion of a scene can be reconstructed with a standard binocular stereo system. In the last decades, much effort has been conducted in the research field of omnidirectional stereo vision, which allows an almost complete scene reconstruction if the cameras are mounted at the ceiling. However, as omnidirectional images show strong distortion artifacts, most of the approaches perform an image warping to reduce the reconstruction complexity. In this work, we examine the impact of the omnidirectional image distortion on the learning process of a CNN. We compare the results of a network training with perspective and omnidirectional stereo images. For this work, we use AnyNet and a novel dataset of synthetic omnidirectional and perspective stereo images.

Download


Paper Citation


in Harvard Style

Seuffert J., Grassi A., Scheck T. and Hirtz G. (2021). A Study on the Influence of Omnidirectional Distortion on CNN-based Stereo Vision.In Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP, ISBN 978-989-758-488-6, pages 809-816. DOI: 10.5220/0010324808090816


in Bibtex Style

@conference{visapp21,
author={Julian Seuffert and Ana Grassi and Tobias Scheck and Gangolf Hirtz},
title={A Study on the Influence of Omnidirectional Distortion on CNN-based Stereo Vision},
booktitle={Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP,},
year={2021},
pages={809-816},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010324808090816},
isbn={978-989-758-488-6},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP,
TI - A Study on the Influence of Omnidirectional Distortion on CNN-based Stereo Vision
SN - 978-989-758-488-6
AU - Seuffert J.
AU - Grassi A.
AU - Scheck T.
AU - Hirtz G.
PY - 2021
SP - 809
EP - 816
DO - 10.5220/0010324808090816