Object classification using dictionary learning and RGB-D covariance descriptors

William J. Beksi, Nikolaos P Papanikolopoulos

Research output: Contribution to journalArticle

12 Citations (Scopus)

Abstract

In this paper, we introduce a dictionary learning framework using RGB-D covariance descriptors on point cloud data for performing object classification. Dictionary learning in combination with RGB-D covariance descriptors provides a compact and flexible description of point cloud data. Furthermore, the proposed framework is ideal for updating and sharing dictionaries among robots in a decentralized or cloud network. This work demonstrates the increased performance of 3D object classification utilizing covariance descriptors and dictionary learning over previous results with experiments performed on a publicly available RGB-D database.

Original languageEnglish (US)
Article number7139443
Pages (from-to)1880-1885
Number of pages6
JournalProceedings - IEEE International Conference on Robotics and Automation
Volume2015-June
Issue numberJune
DOIs
StatePublished - Jan 1 2015

Fingerprint

Glossaries
Robots
Experiments

Cite this

Object classification using dictionary learning and RGB-D covariance descriptors. / Beksi, William J.; Papanikolopoulos, Nikolaos P.

In: Proceedings - IEEE International Conference on Robotics and Automation, Vol. 2015-June, No. June, 7139443, 01.01.2015, p. 1880-1885.

Research output: Contribution to journalArticle

@article{220b512470ea447d9fcb829c23abaa74,
title = "Object classification using dictionary learning and RGB-D covariance descriptors",
abstract = "In this paper, we introduce a dictionary learning framework using RGB-D covariance descriptors on point cloud data for performing object classification. Dictionary learning in combination with RGB-D covariance descriptors provides a compact and flexible description of point cloud data. Furthermore, the proposed framework is ideal for updating and sharing dictionaries among robots in a decentralized or cloud network. This work demonstrates the increased performance of 3D object classification utilizing covariance descriptors and dictionary learning over previous results with experiments performed on a publicly available RGB-D database.",
author = "Beksi, {William J.} and Papanikolopoulos, {Nikolaos P}",
year = "2015",
month = "1",
day = "1",
doi = "10.1109/ICRA.2015.7139443",
language = "English (US)",
volume = "2015-June",
pages = "1880--1885",
journal = "Proceedings - IEEE International Conference on Robotics and Automation",
issn = "1050-4729",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "June",

}

TY - JOUR

T1 - Object classification using dictionary learning and RGB-D covariance descriptors

AU - Beksi, William J.

AU - Papanikolopoulos, Nikolaos P

PY - 2015/1/1

Y1 - 2015/1/1

N2 - In this paper, we introduce a dictionary learning framework using RGB-D covariance descriptors on point cloud data for performing object classification. Dictionary learning in combination with RGB-D covariance descriptors provides a compact and flexible description of point cloud data. Furthermore, the proposed framework is ideal for updating and sharing dictionaries among robots in a decentralized or cloud network. This work demonstrates the increased performance of 3D object classification utilizing covariance descriptors and dictionary learning over previous results with experiments performed on a publicly available RGB-D database.

AB - In this paper, we introduce a dictionary learning framework using RGB-D covariance descriptors on point cloud data for performing object classification. Dictionary learning in combination with RGB-D covariance descriptors provides a compact and flexible description of point cloud data. Furthermore, the proposed framework is ideal for updating and sharing dictionaries among robots in a decentralized or cloud network. This work demonstrates the increased performance of 3D object classification utilizing covariance descriptors and dictionary learning over previous results with experiments performed on a publicly available RGB-D database.

UR - http://www.scopus.com/inward/record.url?scp=84938234038&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84938234038&partnerID=8YFLogxK

U2 - 10.1109/ICRA.2015.7139443

DO - 10.1109/ICRA.2015.7139443

M3 - Article

VL - 2015-June

SP - 1880

EP - 1885

JO - Proceedings - IEEE International Conference on Robotics and Automation

JF - Proceedings - IEEE International Conference on Robotics and Automation

SN - 1050-4729

IS - June

M1 - 7139443

ER -