ScaleNet: Scale Invariant Network for Semantic Segmentation in Urban Driving Scenes

Mohammad Dawud Ansari, Stephan Krauß, Oliver Wasenmüller, Didier Stricker

2018

Abstract

The scale difference in driving scenarios is one of the essential challenges in semantic scene segmentation. Close objects cover significantly more pixels than far objects. In this paper, we address this challenge with a scale invariant architecture. Within this architecture, we explicitly estimate the depth and adapt the pooling field size accordingly. Our model is compact and can be extended easily to other research domains. Finally, the accuracy of our approach is comparable to the state-of-the-art and superior for scale problems. We evaluate on the widely used automotive dataset Cityscapes as well as a self-recorded dataset.

Paper Citation

in Harvard Style

Ansari M., Krauß S., Wasenmüller O. and Stricker D. (2018). ScaleNet: Scale Invariant Network for Semantic Segmentation in Urban Driving Scenes. In Proceedings of the 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2018) - Volume 5: VISAPP; ISBN 978-989-758-290-5, SciTePress, pages 399-404. DOI: 10.5220/0006723003990404

in Bibtex Style

@conference{visapp18,
author={Mohammad Dawud Ansari and Stephan Krauß and Oliver Wasenmüller and Didier Stricker},
title={ScaleNet: Scale Invariant Network for Semantic Segmentation in Urban Driving Scenes},
booktitle={Proceedings of the 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2018) - Volume 5: VISAPP},
year={2018},
pages={399-404},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006723003990404},
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 5: VISAPP
TI - ScaleNet: Scale Invariant Network for Semantic Segmentation in Urban Driving Scenes
SN - 978-989-758-290-5
AU - Ansari M.
AU - Krauß S.
AU - Wasenmüller O.
AU - Stricker D.
PY - 2018
SP - 399
EP - 404
DO - 10.5220/0006723003990404
PB - SciTePress