Usability Study of Learning-Based Pose Estimation of Industrial Objects from Synthetic Depth Data

Thalhammer, S; Patten, T; Vincze, M

Usability Study of Learning-Based Pose Estimation of Industrial Objects from Synthetic Depth Data

Thalhammer, S Patten, T

Vincze, M

Permalink

Publisher:: Springer
Publication Type:: Chapter
Citation:: Smart Technologies for Precision Assembly, 2021, 620, pp. 285-296
Issue Date:: 2021-01-01

Closed Access

	Filename	Description	Size
	Usability.pdf	Published version	2 MB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Thalhammer, S
dc.contributor.author	Patten, T https://orcid.org/0000-0003-1139-9451
dc.contributor.author	Vincze, M
dc.contributor.editor	Ratchev, S
dc.date.accessioned	2021-09-02T05:05:41Z
dc.date.available	2021-09-02T05:05:41Z
dc.date.issued	2021-01-01
dc.identifier.citation	Smart Technologies for Precision Assembly, 2021, 620, pp. 285-296
dc.identifier.isbn	9783030726317
dc.identifier.uri	http://hdl.handle.net/10453/150296
dc.description.abstract	For visual assistance systems deployed in an industrial setting, precise object pose estimation is an important task in order to support scene understanding and to enable subsequent grasping and manipulation. Industrial environments are especially challenging since mesh-models are usually available while physical objects are not or are expensive to model. Manufactured objects are often similar in appearance, have limited to no textural cues and exhibit symmetries. Thus, these are especially challenging for recognizers that are meant to provide detection, classification and pose estimation on instance level. A usability study of a recent synthetically trained learning-based recognizer for these particular challenges is conducted. Experiments are performed on the challenging T-LESS dataset due to its relevance for industry.
dc.format.extent	27
dc.language	en
dc.publisher	Springer
dc.relation.ispartof	Smart Technologies for Precision Assembly
dc.relation.ispartofseries	IFIP Advances in Information and Communication Technology
dc.relation.isbasedon	10.1007/978-3-030-72632-4_21
dc.rights	info:eu-repo/semantics/closedAccess
dc.subject	0806 Information Systems
dc.title	Usability Study of Learning-Based Pose Estimation of Industrial Objects from Synthetic Depth Data
dc.type	Chapter
utslib.citation.volume	620
utslib.for	0806 Information Systems
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/Faculty of Engineering and Information Technology/School of Mechanical and Mechatronic Engineering
utslib.copyright.status	closed_access	*
pubs.consider-herdc	false
dc.date.updated	2021-09-02T05:05:39Z
pubs.place-of-publication	Switzerland
pubs.publication-status	Published
pubs.volume	620
dc.location	Switzerland

Abstract:

For visual assistance systems deployed in an industrial setting, precise object pose estimation is an important task in order to support scene understanding and to enable subsequent grasping and manipulation. Industrial environments are especially challenging since mesh-models are usually available while physical objects are not or are expensive to model. Manufactured objects are often similar in appearance, have limited to no textural cues and exhibit symmetries. Thus, these are especially challenging for recognizers that are meant to provide detection, classification and pose estimation on instance level. A usability study of a recent synthetically trained learning-based recognizer for these particular challenges is conducted. Experiments are performed on the challenging T-LESS dataset due to its relevance for industry.

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

http://hdl.handle.net/10453/150296