Discriminative feature learning for efficient RGB-D object recognition

Research output: Chapter in Book/Conference paperConference paper

8 Citations (Scopus)

Abstract

© 2015 IEEE. This paper presents an efficient approach to recognize objects captured with an RGB-D sensor. The proposed approach uses a Bag-of-Words (BOW) model to learn feature representations from raw RGB-D point clouds in a weakly supervised manner. To this end, we introduce a novel method based on randomized clustering trees to learn visual vocabularies which are fast to compute and more discriminative compared to the vocabularies generated by classical methods such as k-means. We show that, when combined with standard spatial pooling strategies, our proposed approach yields a powerful feature representation for RGB-D object recognition. Our extensive experimental evaluation on two challenging RGB-D object datasets and live video streams from Kinect shows that our learned features result in superior object recognition accuracies compared with the state-of-the-art methods.
Original languageEnglish
Title of host publicationIEEE International Conference on Intelligent Robots and Systems
Place of PublicationUnited States
PublisherIEEE, Institute of Electrical and Electronics Engineers
Pages272-279
Volume2015
ISBN (Print)9781479999941
DOIs
Publication statusPublished - 2015
Event2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) - Congress Center Hamburg Am Dammtor / Marseiller Straße, Hamburg, Germany
Duration: 28 Sep 20152 Oct 2015
http://www.iros2015.org

Conference

Conference2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
CountryGermany
CityHamburg
Period28/09/152/10/15
Internet address

Fingerprint Dive into the research topics of 'Discriminative feature learning for efficient RGB-D object recognition'. Together they form a unique fingerprint.

Cite this