Depth Camera to Improve Segmenting People in Indoor Environments - Real Time RGB-Depth Video Segmentation

Arnaud Boucher, Olivier Martinot, Nicole Vincent

2015

Abstract

The paper addresses the problem of people extraction in a closed context in a video sequence including colour and depth information. The study is based on low cost depth captor included in products such as Kinect or Asus devices that contain a couple of cameras, colour and depth cameras. Depth cameras lack precision especially where a discontinuity in depth occur and some times fail to give an answer. Colour information may be ambiguous to discriminate between background and foreground. This made us use first depth information to achieve a coarse segmentation that is improved with colour information. Furthermore, color information is only used when a classification in two classes of fore/background pixels is clear enough. The developed method provides a reliable and robust segmentation and a natural visual rendering, while maintaining a real time processing.

Paper Citation

in Harvard Style

Boucher A., Martinot O. and Vincent N. (2015). Depth Camera to Improve Segmenting People in Indoor Environments - Real Time RGB-Depth Video Segmentation . In Proceedings of the 10th International Conference on Computer Vision Theory and Applications - Volume 3: VISAPP, (VISIGRAPP 2015) ISBN 978-989-758-091-8, pages 55-62. DOI: 10.5220/0005269700550062

in Bibtex Style

@conference{visapp15,
author={Arnaud Boucher and Olivier Martinot and Nicole Vincent},
title={Depth Camera to Improve Segmenting People in Indoor Environments - Real Time RGB-Depth Video Segmentation},
booktitle={Proceedings of the 10th International Conference on Computer Vision Theory and Applications - Volume 3: VISAPP, (VISIGRAPP 2015)},
year={2015},
pages={55-62},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005269700550062},
isbn={978-989-758-091-8},
}

in EndNote Style

TY - CONF
JO - Proceedings of the 10th International Conference on Computer Vision Theory and Applications - Volume 3: VISAPP, (VISIGRAPP 2015)
TI - Depth Camera to Improve Segmenting People in Indoor Environments - Real Time RGB-Depth Video Segmentation
SN - 978-989-758-091-8
AU - Boucher A.
AU - Martinot O.
AU - Vincent N.
PY - 2015
SP - 55
EP - 62
DO - 10.5220/0005269700550062