Automatic Object Segmentation on RGB-D Data using Surface Normals and Region Similarity

Hamdi Yalin Yalic, Ahmet Burak Can

2018

Abstract

In this study, a method for automatic object segmentation on RGB-D data is proposed. Surface normals extracted from depth data are used to determine segment candidates first. Filtering steps are applied to depth map to get a better representation of the data. After filtering, an adapted version of region growing segmentation is performed using surface normal comparisons on depth data. Extracted surface segments are then compared with their spatial color similarity and depth proximity, and finally region merging is applied to obtain object segments. The method is tested on a well-known dataset, which has some complex table-top scenes containing multiple objects. The method produces comparable segmentation results according to related works.

Download


Paper Citation


in Harvard Style

Yalic H. and Can A. (2018). Automatic Object Segmentation on RGB-D Data using Surface Normals and Region Similarity. 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 379-386. DOI: 10.5220/0006617303790386


in Bibtex Style

@conference{visapp18,
author={Hamdi Yalin Yalic and Ahmet Burak Can},
title={Automatic Object Segmentation on RGB-D Data using Surface Normals and Region Similarity},
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={379-386},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006617303790386},
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 - Automatic Object Segmentation on RGB-D Data using Surface Normals and Region Similarity
SN - 978-989-758-290-5
AU - Yalic H.
AU - Can A.
PY - 2018
SP - 379
EP - 386
DO - 10.5220/0006617303790386
PB - SciTePress