Mostra el registre d'ítem simple

dc.contributor.authorPerez Sala, Xavier
dc.contributor.authorDe La Torre, Fernando
dc.contributor.authorIgual, Laura
dc.contributor.authorEscalera, Sergio
dc.contributor.authorAngulo Bahón, Cecilio
dc.contributor.otherUniversitat Politècnica de Catalunya. Departament d'Enginyeria de Sistemes, Automàtica i Informàtica Industrial
dc.date.accessioned2014-11-11T11:05:55Z
dc.date.available2014-11-11T11:05:55Z
dc.date.created2014
dc.date.issued2014
dc.identifier.citationPerez, X. [et al.]. Subspace procrustes analysis. A: European Conference on Computer Vision. "ECCV Workshop on ChaLearn Looking at People". Zurich: 2014.
dc.identifier.urihttp://hdl.handle.net/2117/24672
dc.description.abstractProcrustes Analysis (PA) has been a popular technique to align and build 2-D statistical models of shapes. Given a set of 2-D shapes PA is applied to remove rigid transformations. Then, a non-rigid 2-D model is computed by modeling (e.g., PCA) the residual. Although PA has been widely used, it has several limitations for modeling 2-D shapes: occluded landmarks and missing data can result in local minima solutions, and there is no guarantee that the 2-D shapes provide a uniform sampling of the 3-D space of rotations for the object. To address previous issues, this paper proposes Subspace PA (SPA). Given several instances of a 3-D object, SPA computes the mean and a 2-D subspace that can simultaneously model all rigid and non-rigid deformations of the 3-D object. We propose a discrete (DSPA) and continuous (CSPA) formulation for SPA, assuming that 3-D samples of an object are provided. DSPA extends the traditional PA, and produces unbiased 2-D models by uniformly sampling different views of the 3-D object. CSPA provides a continuous approach to uniformly sample the space of 3-D rotations, being more effcient in space and time. Experiments using SPA to learn 2-D models of bodies from motion capture data illustrate the benefits of our approach.
dc.language.isoeng
dc.subjectÀrees temàtiques de la UPC::Informàtica::Intel·ligència artificial
dc.subject.lcshComputer vision
dc.subject.lcshPattern recognition systems
dc.titleSubspace procrustes analysis
dc.typeConference report
dc.subject.lemacReconeixement de formes (Informàtica)
dc.subject.lemacVisió per ordinador
dc.contributor.groupUniversitat Politècnica de Catalunya. GREC - Grup de Recerca en Enginyeria del Coneixement
dc.relation.publisherversionhttp://www.ca.cs.cmu.edu/papers/subspace_pa.pdf
dc.rights.accessOpen Access
local.identifier.drac15263239
dc.description.versionPreprint
local.citation.authorPerez, X.; De La Torre, F.; Igual, L.; Escalera, S.; Angulo, C.
local.citation.contributorEuropean Conference on Computer Vision
local.citation.pubplaceZurich
local.citation.publicationNameECCV Workshop on ChaLearn Looking at People


Fitxers d'aquest items

Thumbnail

Aquest ítem apareix a les col·leccions següents

Mostra el registre d'ítem simple