RGB-D object classification using covariance descriptors

Duc Fehr, William J. Beksi, Dimitris Zermas, Nikolaos P Papanikolopoulos

Research output: Contribution to journalConference article

9 Citations (Scopus)

Abstract

In This paper, we introduce a new covariance based feature descriptor To be used on 'colored' point clouds gathered by a mobile robot equipped with an RGB-D camera. Although many recent descriptors provide adequate results, There is not yet a clear consensus on how To best Tackle 'colored' point clouds. We present The notion of a covariance on RGB-D data. Covariances have not only been proven To be successful in image processing, but in other domains as well. Their main advantage is That They provide a compact and flexible description of point clouds. Our work is a first step Towards demonstrating The usability of The concept of covariances in conjunction with RGB-D data. Experiments performed on an RGB-D database and compared To previous results show The increased performance of our method.

Original languageEnglish (US)
Article number6907663
Pages (from-to)5467-5472
Number of pages6
JournalProceedings - IEEE International Conference on Robotics and Automation
DOIs
StatePublished - Sep 22 2014
Event2014 IEEE International Conference on Robotics and Automation, ICRA 2014 - Hong Kong, China
Duration: May 31 2014Jun 7 2014

Fingerprint

Mobile robots
Image processing
Cameras
Experiments

Cite this

RGB-D object classification using covariance descriptors. / Fehr, Duc; Beksi, William J.; Zermas, Dimitris; Papanikolopoulos, Nikolaos P.

In: Proceedings - IEEE International Conference on Robotics and Automation, 22.09.2014, p. 5467-5472.

Research output: Contribution to journalConference article

@article{640237a68f514a5bae8fa4820ba71617,
title = "RGB-D object classification using covariance descriptors",
abstract = "In This paper, we introduce a new covariance based feature descriptor To be used on 'colored' point clouds gathered by a mobile robot equipped with an RGB-D camera. Although many recent descriptors provide adequate results, There is not yet a clear consensus on how To best Tackle 'colored' point clouds. We present The notion of a covariance on RGB-D data. Covariances have not only been proven To be successful in image processing, but in other domains as well. Their main advantage is That They provide a compact and flexible description of point clouds. Our work is a first step Towards demonstrating The usability of The concept of covariances in conjunction with RGB-D data. Experiments performed on an RGB-D database and compared To previous results show The increased performance of our method.",
author = "Duc Fehr and Beksi, {William J.} and Dimitris Zermas and Papanikolopoulos, {Nikolaos P}",
year = "2014",
month = "9",
day = "22",
doi = "10.1109/ICRA.2014.6907663",
language = "English (US)",
pages = "5467--5472",
journal = "Proceedings - IEEE International Conference on Robotics and Automation",
issn = "1050-4729",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - JOUR

T1 - RGB-D object classification using covariance descriptors

AU - Fehr, Duc

AU - Beksi, William J.

AU - Zermas, Dimitris

AU - Papanikolopoulos, Nikolaos P

PY - 2014/9/22

Y1 - 2014/9/22

N2 - In This paper, we introduce a new covariance based feature descriptor To be used on 'colored' point clouds gathered by a mobile robot equipped with an RGB-D camera. Although many recent descriptors provide adequate results, There is not yet a clear consensus on how To best Tackle 'colored' point clouds. We present The notion of a covariance on RGB-D data. Covariances have not only been proven To be successful in image processing, but in other domains as well. Their main advantage is That They provide a compact and flexible description of point clouds. Our work is a first step Towards demonstrating The usability of The concept of covariances in conjunction with RGB-D data. Experiments performed on an RGB-D database and compared To previous results show The increased performance of our method.

AB - In This paper, we introduce a new covariance based feature descriptor To be used on 'colored' point clouds gathered by a mobile robot equipped with an RGB-D camera. Although many recent descriptors provide adequate results, There is not yet a clear consensus on how To best Tackle 'colored' point clouds. We present The notion of a covariance on RGB-D data. Covariances have not only been proven To be successful in image processing, but in other domains as well. Their main advantage is That They provide a compact and flexible description of point clouds. Our work is a first step Towards demonstrating The usability of The concept of covariances in conjunction with RGB-D data. Experiments performed on an RGB-D database and compared To previous results show The increased performance of our method.

UR - http://www.scopus.com/inward/record.url?scp=84929208210&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84929208210&partnerID=8YFLogxK

U2 - 10.1109/ICRA.2014.6907663

DO - 10.1109/ICRA.2014.6907663

M3 - Conference article

SP - 5467

EP - 5472

JO - Proceedings - IEEE International Conference on Robotics and Automation

JF - Proceedings - IEEE International Conference on Robotics and Automation

SN - 1050-4729

M1 - 6907663

ER -