Object classification using dictionary learning and RGB-D covariance descriptors

William J. Beksi, Nikolaos Papanikolopoulos

Research output: Contribution to journalConference articlepeer-review

15 Scopus citations

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 - Jun 29 2015
Event2015 IEEE International Conference on Robotics and Automation, ICRA 2015 - Seattle, United States
Duration: May 26 2015May 30 2015

Bibliographical note

Publisher Copyright:
© 2015 IEEE.

Fingerprint

Dive into the research topics of 'Object classification using dictionary learning and RGB-D covariance descriptors'. Together they form a unique fingerprint.

Cite this