Learning and recognition of objects inspired by early cognition

Maja Rudinac*, Gert Kootstra, Danica Kragic, Pieter P. Jonker

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference paper

8 Citations (Scopus)

Abstract

In this paper, we present a unifying approach for learning and recognition of objects in unstructured environments through exploration. Taking inspiration from how young infants learn objects, we establish four principles for object learning. First, early object detection is based on an attention mechanism detecting salient parts in the scene. Second, motion of the object allows more accurate object localization. Next, acquiring multiple observations of the object through manipulation allows a more robust representation of the object. And last, object recognition benefits from a multi-modal representation. Using these principles, we developed a unifying method including visual attention, smooth pursuit of the object, and a multi-view and multi-modal object representation. Our results indicate the effectiveness of this approach and the improvement of the system when multiple observations are acquired from active object manipulation.

Original languageEnglish
Title of host publication2012 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2012
PublisherIEEE Xplore
Pages4177-4184
Number of pages8
ISBN (Print)9781467317375
DOIs
Publication statusPublished - 1 Dec 2012
Externally publishedYes
Event25th IEEE/RSJ International Conference on Robotics and Intelligent Systems, IROS 2012 - Vilamoura, Algarve, Portugal
Duration: 7 Oct 201212 Oct 2012

Publication series

NameIEEE International Conference on Intelligent Robots and Systems
ISSN (Print)2153-0858
ISSN (Electronic)2153-0866

Conference

Conference25th IEEE/RSJ International Conference on Robotics and Intelligent Systems, IROS 2012
CountryPortugal
CityVilamoura, Algarve
Period7/10/1212/10/12

Fingerprint Dive into the research topics of 'Learning and recognition of objects inspired by early cognition'. Together they form a unique fingerprint.

Cite this