Least-squares algorithms for motion and shape recovery under perspective projection

Fuh, C-S; Maragos, P

dc.contributor.author	Fuh, C-S	en
dc.contributor.author	Maragos, P	en
dc.date.accessioned	2014-03-01T11:44:25Z
dc.date.available	2014-03-01T11:44:25Z
dc.date.issued	1996	en
dc.identifier.issn	10162364	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/36940
dc.relation.uri	http://www.scopus.com/inward/record.url?eid=2-s2.0-6144245085&partnerID=40&md5=b5fcc54a86f9490ab115245188b535fa	en
dc.relation.uri	http://www.informatik.uni-trier.de/~ley/db/journals/jise/jise12.html#FuhM96	en
dc.relation.uri	http://www.iis.sinica.edu.tw/page/jise/1996/199603_01.html	en
dc.subject	Computer vision	en
dc.subject	Correspondence	en
dc.subject	Motion analysis	en
dc.title	Least-squares algorithms for motion and shape recovery under perspective projection	en
heal.type	other	en
heal.publicationDate	1996	en
heal.abstract	This paper presents an algorithm for 3-D motion and shape recovery using two perspective views and their relative 2-D displacement field. The 2-D displacement vectors are estimated as parameters of a 2-D affine model that generalizes standard block matching by allowing affine shape deformations of image blocks and affine intensity transformations. The matching block size is effectively found via morphological size histograms. The parameters of the rigid body motion are estimated using a least-squares algorithm that requires solving a system of linear equations with rank three. Some stabilization of the recovered motion parameters under noise is achieved through a simple form of maximum a posteriori estimation. A multi-scale search in the parameter space is also used to improve accuracy without high computational cost. Experiments on applying this algorithm to various real world image sequences demonstrate that it can estimate dense displacement fields and recover motion parameters and object shape with relatively small errors.	en
heal.journalName	Journal of Information Science and Engineering	en
dc.identifier.volume	12	en
dc.identifier.issue	1	en
dc.identifier.spage	1	en
dc.identifier.epage	23	en