Mostrar el registro sencillo del ítem

dc.contributor.author
Crivelli, Tomás  
dc.contributor.author
Bouthemy, Patrick  
dc.contributor.author
Cernuschi Frias, Bruno  
dc.contributor.author
Yao, Jian-Feng  
dc.date.available
2023-01-25T12:11:35Z  
dc.date.issued
2009  
dc.identifier.citation
Learning mixed-state Markov models for statistical motion texture tracking; 12th International Conference on Computer Vision Workshops; Japón; 2009; 444-451  
dc.identifier.isbn
978-1-4244-4442-7  
dc.identifier.uri
http://hdl.handle.net/11336/185505  
dc.description.abstract
A motion texture is the instantaneous scalar map of apparent motion values extracted from a dynamic or temporal texture. It is mostly displayed by natural scene elements (fire, smoke, water) but also involves more general textured motion patterns (eg. a crowd of people, a flock). In this work we are interested in the modeling and tracking of motion textures. Experimentally we observe that such motion maps exhibit values of a mixed type: a discrete component at zero and a continuous component of non-null motion values. Thus, we propose a statistical characterization of motion textures based on a mixed-state causal modeling. Next, the problem of tracking is considered. A set of mixed-state model parameters is learned as a descriptive feature of the motion texture to track and displacement estimation is solved using the conditional Kullback-Leibler divergence for statistical window matching. Results and comparisons are presented on real sequences.  
dc.format
application/pdf  
dc.language.iso
eng  
dc.publisher
Institute of Electrical and Electronics Engineers  
dc.rights
info:eu-repo/semantics/restrictedAccess  
dc.rights.uri
https://creativecommons.org/licenses/by-nc-sa/2.5/ar/  
dc.subject
MIXED STATES  
dc.subject
MARKOV RANDOM FIELDS  
dc.subject
DYNAMIC TEXTURES  
dc.subject.classification
Ingeniería de Sistemas y Comunicaciones  
dc.subject.classification
Ingeniería Eléctrica, Ingeniería Electrónica e Ingeniería de la Información  
dc.subject.classification
INGENIERÍAS Y TECNOLOGÍAS  
dc.title
Learning mixed-state Markov models for statistical motion texture tracking  
dc.type
info:eu-repo/semantics/publishedVersion  
dc.type
info:eu-repo/semantics/conferenceObject  
dc.type
info:ar-repo/semantics/documento de conferencia  
dc.date.updated
2022-11-09T19:35:01Z  
dc.journal.pagination
444-451  
dc.journal.pais
Estados Unidos  
dc.description.fil
Fil: Crivelli, Tomás. Universidad de Buenos Aires; Argentina  
dc.description.fil
Fil: Bouthemy, Patrick. Institut National de Recherche en Informatique et en Automatique; Francia  
dc.description.fil
Fil: Cernuschi Frias, Bruno. Consejo Nacional de Investigaciones Científicas y Técnicas. Oficina de Coordinación Administrativa Saavedra 15. Instituto Argentino de Matemática Alberto Calderón; Argentina  
dc.description.fil
Fil: Yao, Jian-Feng. Instituto de Investigación Matemática de Rennes; Francia  
dc.relation.alternativeid
info:eu-repo/semantics/altIdentifier/doi/http://dx.doi.org/10.1109/ICCVW.2009.5457666  
dc.relation.alternativeid
info:eu-repo/semantics/altIdentifier/url/https://ieeexplore.ieee.org/document/5457666  
dc.conicet.rol
Autor  
dc.conicet.rol
Autor  
dc.conicet.rol
Autor  
dc.conicet.rol
Autor  
dc.coverage
Internacional  
dc.type.subtype
Conferencia  
dc.description.nombreEvento
12th International Conference on Computer Vision Workshops  
dc.date.evento
2009-09-27  
dc.description.paisEvento
Japón  
dc.type.publicacion
Book  
dc.description.institucionOrganizadora
Institute of Electrical and Electronics Engineers  
dc.source.libro
12th International Conference on Computer Vision Workshops  
dc.date.eventoHasta
2009-10-04  
dc.type
Conferencia