Control Points Based Semi-Dense Matching

Zhong, Y; Zhang, H

Control Points Based Semi-Dense Matching

Zhong, Y Zhang, H

Permalink

Publisher:: ACCV
Publication Type:: Conference Proceeding
Citation:: Asian Conference on Computer Vision (ACCV2002), 2002, 1 pp. 374 - 379
Issue Date:: 2002-01

Closed Access

	Filename	Description	Size
	2006011962OK.pdf		247.75 kB		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	Zhong, Y	en_US
dc.contributor.author	Zhang, H	en_US
dc.contributor.editor	Suter, D	en_US
dc.contributor.editor	Bab-Hadiasha, A	en_US
dc.date	2002-01-23	en_US
dc.date.issued	2002-01	en_US
dc.identifier.citation	Asian Conference on Computer Vision (ACCV2002), 2002, 1 pp. 374 - 379	en_US
dc.identifier.isbn	0-9580256-1-4	en_US
dc.identifier.uri	http://hdl.handle.net/10453/12658
dc.description.abstract	The common practice to get more matching points between two perspective images proceeds from coarse matching to dense matching. However, in some applications, for example, in the visualization of point-based 3D reconstruction results, one usually needs more matching points than those which could be obtained in coarse matching process to reveal sufficient structures, and does not need clouded matching points from dense matching process which is additionally of heavy computational load. In addition, it is sometimes desirable that the matching points could be evenly distributed across the whole image. The technique proposed in this note is a tentative step to this end. By adaptively adjusting the related parameters in the propagation stage, an appropriate number of matching points are obtained and distributed evenly. The extensive experiments validate our proposed new technique.	en_US
dc.publisher	ACCV	en_US
dc.relation.ispartof	Asian Conference on Computer Vision (ACCV2002)	en_US
dc.relation.ispartof	Asian Conference on Computer Vision	en_US
dc.title	Control Points Based Semi-Dense Matching	en_US
dc.type	Conference Proceeding
utslib.citation.volume	1	en_US
utslib.location	Melbourne Australia	en_US
utslib.location.activity	Melbourne Australia	en_US
utslib.for	0801 Artificial Intelligence and Image Processing	en_US
dc.location.activity	Melbourne Australia	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/Faculty of Engineering and Information Technology/School of Electrical and Data Engineering
utslib.copyright.status	closed_access
pubs.consider-herdc	false	en_US
pubs.place-of-publication	Melbourne Australia	en_US
pubs.start-date	2002-01-23	en_US
pubs.volume	1	en_US

Abstract:

The common practice to get more matching points between two perspective images proceeds from coarse matching to dense matching. However, in some applications, for example, in the visualization of point-based 3D reconstruction results, one usually needs more matching points than those which could be obtained in coarse matching process to reveal sufficient structures, and does not need clouded matching points from dense matching process which is additionally of heavy computational load. In addition, it is sometimes desirable that the matching points could be evenly distributed across the whole image. The technique proposed in this note is a tentative step to this end. By adaptively adjusting the related parameters in the propagation stage, an appropriate number of matching points are obtained and distributed evenly. The extensive experiments validate our proposed new technique.

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

http://hdl.handle.net/10453/12658