3D cost aggregation with multiple minimum spanning trees for stereo matching.

Li, L; Yu, X; Zhang, S; Zhao, X; Zhang, L

3D cost aggregation with multiple minimum spanning trees for stereo matching.

Li, L Yu, X

Zhang, S Zhao, X Zhang, L

Permalink

Publisher:: Optica
Publication Type:: Journal Article
Citation:: Applied Optics, 2017, 56, (12), pp. 3411-3420
Issue Date:: 2017-04-20

Closed Access

	Filename	Description	Size
	19286568_8349309940005671.pdf		2.5 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	Li, L
dc.contributor.author	Yu, X https://orcid.org/0000-0002-0269-5649
dc.contributor.author	Zhang, S
dc.contributor.author	Zhao, X
dc.contributor.author	Zhang, L
dc.date.accessioned	2022-07-27T03:05:49Z
dc.date.available	2022-07-27T03:05:49Z
dc.date.issued	2017-04-20
dc.identifier.citation	Applied Optics, 2017, 56, (12), pp. 3411-3420
dc.identifier.issn	1559-128X
dc.identifier.issn	1539-4522
dc.identifier.uri	http://hdl.handle.net/10453/159197
dc.description.abstract	Cost aggregation is one of the key steps in the stereo matching problem. In order to improve aggregation accuracy, we propose a cost-aggregation method that can embed minimum spanning tree (MST)-based support region filtering into PatchMatch 3D label search rather than aggregating on fixed size patches. However, directly combining PatchMatch label search and MST filtering is not straightforward, due to the extremely high complexity. Thus, we develop multiple MST structures for cost aggregation on plenty of 3D labels, and design the tree-level random search strategy to find possible 3D labels of each pixel. Extensive experiments show that our method reaches higher accuracy than the other existing cost-aggregation and global-optimization methods such as the 1D MST, the PatchMatch and the PatchMatch Filter, and currently ranks first on the Middlebury 3.0 benchmark.
dc.format	Print
dc.language	eng
dc.publisher	Optica
dc.relation.ispartof	Applied Optics
dc.relation.isbasedon	10.1364/AO.56.003411
dc.rights	info:eu-repo/semantics/closedAccess
dc.subject	0205 Optical Physics, 0906 Electrical and Electronic Engineering, 0913 Mechanical Engineering
dc.subject.classification	Optics
dc.title	3D cost aggregation with multiple minimum spanning trees for stereo matching.
dc.type	Journal Article
utslib.citation.volume	56
utslib.location.activity	United States
utslib.for	0205 Optical Physics
utslib.for	0906 Electrical and Electronic Engineering
utslib.for	0913 Mechanical Engineering
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 - AAII - Australian Artificial Intelligence Institute
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology/School of Computer Science
utslib.copyright.status	closed_access	*
pubs.consider-herdc	false
dc.date.updated	2022-07-27T03:05:47Z
pubs.issue	12
pubs.publication-status	Published
pubs.volume	56
utslib.citation.issue	12

Abstract:

Cost aggregation is one of the key steps in the stereo matching problem. In order to improve aggregation accuracy, we propose a cost-aggregation method that can embed minimum spanning tree (MST)-based support region filtering into PatchMatch 3D label search rather than aggregating on fixed size patches. However, directly combining PatchMatch label search and MST filtering is not straightforward, due to the extremely high complexity. Thus, we develop multiple MST structures for cost aggregation on plenty of 3D labels, and design the tree-level random search strategy to find possible 3D labels of each pixel. Extensive experiments show that our method reaches higher accuracy than the other existing cost-aggregation and global-optimization methods such as the 1D MST, the PatchMatch and the PatchMatch Filter, and currently ranks first on the Middlebury 3.0 benchmark.

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

http://hdl.handle.net/10453/159197