Modified Fuzzy C-Means as a Stereo Segmentation Method

Michal Krumnikl, Eduard Sojka, Jan Gaura

2014

Abstract

This paper presents an extension to the popular fuzzy c-means clustering method by introducing an additional disparity cue. The creation of the clusters is driven by a degree of the stereo match and thus is able to separate the objects based on their different colour and spatial depth. In contrast to the other popular approaches, the clustering is not performed on the individual input images, but on the stereo pair, and takes into account the matching properties. The algorithm is capable of producing the segmentations, as well as the disparity maps. The results of this algorithm show that the proposed method can improve the segmentation, under the condition of having the stereo image pair of the segmented scene.

Paper Citation

in Harvard Style

Krumnikl M., Sojka E. and Gaura J. (2014). Modified Fuzzy C-Means as a Stereo Segmentation Method . In Proceedings of the 3rd International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM, ISBN 978-989-758-018-5, pages 40-47. DOI: 10.5220/0004793000400047

in Bibtex Style

@conference{icpram14,
author={Michal Krumnikl and Eduard Sojka and Jan Gaura},
title={Modified Fuzzy C-Means as a Stereo Segmentation Method},
booktitle={Proceedings of the 3rd International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,},
year={2014},
pages={40-47},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004793000400047},
isbn={978-989-758-018-5},
}

in EndNote Style

TY - CONF
JO - Proceedings of the 3rd International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,
TI - Modified Fuzzy C-Means as a Stereo Segmentation Method
SN - 978-989-758-018-5
AU - Krumnikl M.
AU - Sojka E.
AU - Gaura J.
PY - 2014
SP - 40
EP - 47
DO - 10.5220/0004793000400047