loading
Papers

Research.Publish.Connect.

Paper

Authors: Farnoush Zohourian 1 ; Borislav Antic 2 ; Jan Siegemund 2 ; Mirko Meuter 2 and Josef Pauli 1

Affiliations: 1 University of Duisburg-Essen, Germany ; 2 Delphi Electronics & Saftey, Germany

ISBN: 978-989-758-290-5

Keyword(s): Superpixel, Semantic Segmentation, CNN, Deep Learning, Road Segmentation.

Abstract: Convolutional Neural Networks (CNN) contributed considerable improvements for image segmentation tasks in the field of computer vision. Despite their success, an inherent challenge is the trade-off between accuracy and computational cost. The high computational efforts for large networks operating on the image’s pixel grid makes them ineligible for many real time applications such as various Advanced Driver Assistance Systems (ADAS). In this work, we propose a novel CNN approach, based on the combination of super-pixels and high dimensional feature channels applied for road segmentation. The core idea is to reduce the computational complexity by segmenting the image into homogeneous regions (superpixels) and feed image descriptors extracted from these regions into a CNN rather than working on the pixel grid directly. To enable the necessary convolutional operations on the irregular arranged superpixels, we introduce a lattice projection scheme as part of the superpixel creation method , which composes neighbourhood relations and forces the topology to stay fixed during the segmentation process. Reducing the input to the superpixel domain allows the CNN’s structure to stay small and efficient to compute while keeping the advantage of convolutional layers. The method is generic and can be easily generalized for segmentation tasks other than road segmentation. (More)

PDF ImageFull Text

Download
CC BY-NC-ND 4.0

Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 3.214.184.124

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
Zohourian, F.; Antic, B.; Siegemund, J.; Meuter, M. and Pauli, J. (2018). Superpixel-based Road Segmentation for Real-time Systems using CNN.In Proceedings of the 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 5 VISAPP: VISAPP, ISBN 978-989-758-290-5, pages 257-265. DOI: 10.5220/0006612002570265

@conference{visapp18,
author={Farnoush Zohourian. and Borislav Antic. and Jan Siegemund. and Mirko Meuter. and Josef Pauli.},
title={Superpixel-based Road Segmentation for Real-time Systems using CNN},
booktitle={Proceedings of the 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 5 VISAPP: VISAPP,},
year={2018},
pages={257-265},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006612002570265},
isbn={978-989-758-290-5},
}

TY - CONF

JO - Proceedings of the 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 5 VISAPP: VISAPP,
TI - Superpixel-based Road Segmentation for Real-time Systems using CNN
SN - 978-989-758-290-5
AU - Zohourian, F.
AU - Antic, B.
AU - Siegemund, J.
AU - Meuter, M.
AU - Pauli, J.
PY - 2018
SP - 257
EP - 265
DO - 10.5220/0006612002570265

Login or register to post comments.

Comments on this Paper: Be the first to review this paper.