Viewpoint Evaluation for Online 3-D Active Object Classification

Patten, T; Zillich, M; Fitch, R; Vincze, M; Sukkarieh, S

Viewpoint Evaluation for Online 3-D Active Object Classification

Patten, T Zillich, M Fitch, R

Vincze, M Sukkarieh, S

Permalink

Publication Type:: Journal Article
Citation:: IEEE Robotics and Automation Letters, 2016, 1 (1), pp. 73 - 81
Issue Date:: 2016-01-01

Open Access

Copyright Clearance Process

Recently Added
In Progress
Open Access

This item is open access.

Adobe PDF

Download Accepted Manuscript VersionAdobe PDF (1.69 MB)

View on publisher's site

View statistics

Full metadata record

Field	Value	Language
dc.contributor.author	Patten, T	en_US
dc.contributor.author	Zillich, M	en_US
dc.contributor.author	Fitch, R https://orcid.org/0000-0003-2215-5188	en_US
dc.contributor.author	Vincze, M	en_US
dc.contributor.author	Sukkarieh, S	en_US
dc.date.issued	2016-01-01	en_US
dc.identifier.citation	IEEE Robotics and Automation Letters, 2016, 1 (1), pp. 73 - 81	en_US
dc.identifier.uri	http://hdl.handle.net/10453/89769
dc.description.abstract	© 2015 IEEE. We present an end-to-end method for active object classification in cluttered scenes from RGB-D data. Our algorithms predict the quality of future viewpoints in the form of entropy using both class and pose. Occlusions are explicitly modeled in predicting the visible regions of objects, which modulates the corresponding discriminatory value of a given view. We implement a one-step greedy planner and demonstrate our method online using a mobile robot. We also analyze the performance of our method compared to similar strategies in simulated execution using the Willow Garage dataset. Results show that our active method usefully reduces the number of views required to accurately classify objects in clutter as compared to traditional passive perception.	en_US
dc.relation.ispartof	IEEE Robotics and Automation Letters	en_US
dc.relation.isbasedon	10.1109/LRA.2015.2506901	en_US
dc.title	Viewpoint Evaluation for Online 3-D Active Object Classification	en_US
dc.type	Journal Article
utslib.citation.volume	1	en_US
utslib.for	080101 Adaptive Agents and Intelligent Robotics	en_US
utslib.for	091303 Autonomous Vehicles	en_US
utslib.for	0913 Mechanical Engineering	en_US
pubs.embargo.period	Not known	en_US
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	/University of Technology Sydney/Strength - CAS - Centre for Autonomous Systems
utslib.copyright.status	open_access
pubs.issue	1	en_US
pubs.publication-status	Published	en_US
pubs.volume	1	en_US

Abstract:

© 2015 IEEE. We present an end-to-end method for active object classification in cluttered scenes from RGB-D data. Our algorithms predict the quality of future viewpoints in the form of entropy using both class and pose. Occlusions are explicitly modeled in predicting the visible regions of objects, which modulates the corresponding discriminatory value of a given view. We implement a one-step greedy planner and demonstrate our method online using a mobile robot. We also analyze the performance of our method compared to similar strategies in simulated execution using the Willow Garage dataset. Results show that our active method usefully reduces the number of views required to accurately classify objects in clutter as compared to traditional passive perception.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/89769