3D Descriptor for an Oriented-human Classification from Complete Point Cloud

Kyis Essmaeel, Cyrille Migniot, Albert Dipanda

2016

Abstract

In this paper we present a new 3D descriptor for the human classification. It is applied over a complete point cloud (i.e 360° view) acquired with a multi-kinect system. The proposed descriptor is derived from the Histogram of Oriented Gradient (HOG) descriptor: surface normal vectors are employed instead of gradients, 3D poins are expressed on a cylindrical space and 3D orientation quantization are computed by projecting the normal vectors on a regular polyhedron. Our descriptor is utilized through a Support Vector Machine (SVM) classifier. The SVM classifier is trained using an original database composed of data acquired by our multi-kinect system. The evaluation of the proposed 3D descriptor over a set of candidates shows very promising results. The descriptor can efficiently discriminate human from non-human candidates and provides the frontal direction of the human with a high precision. The comparison with a well known descriptor demonstrates significant improvements of results.

Paper Citation

in Harvard Style

Essmaeel K., Migniot C. and Dipanda A. (2016). 3D Descriptor for an Oriented-human Classification from Complete Point Cloud . In Proceedings of the 11th Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP, (VISIGRAPP 2016) ISBN 978-989-758-175-5, pages 353-360. DOI: 10.5220/0005679803530360

in Bibtex Style

@conference{visapp16,
author={Kyis Essmaeel and Cyrille Migniot and Albert Dipanda},
title={3D Descriptor for an Oriented-human Classification from Complete Point Cloud},
booktitle={Proceedings of the 11th Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP, (VISIGRAPP 2016)},
year={2016},
pages={353-360},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005679803530360},
isbn={978-989-758-175-5},
}

in EndNote Style

TY - CONF
JO - Proceedings of the 11th Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP, (VISIGRAPP 2016)
TI - 3D Descriptor for an Oriented-human Classification from Complete Point Cloud
SN - 978-989-758-175-5
AU - Essmaeel K.
AU - Migniot C.
AU - Dipanda A.
PY - 2016
SP - 353
EP - 360
DO - 10.5220/0005679803530360