Evento
Learning mixed-state Markov models for statistical motion texture tracking
Tipo del evento:
Conferencia
Nombre del evento:
12th International Conference on Computer Vision Workshops
Fecha del evento:
27/09/2009
Institución Organizadora:
Institute of Electrical and Electronics Engineers;
Título del Libro:
12th International Conference on Computer Vision Workshops
Editorial:
Institute of Electrical and Electronics Engineers
ISBN:
978-1-4244-4442-7
Idioma:
Inglés
Clasificación temática:
Resumen
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.
Palabras clave:
MIXED STATES
,
MARKOV RANDOM FIELDS
,
DYNAMIC TEXTURES
Archivos asociados
Licencia
Identificadores
Colecciones
Eventos(IAM)
Eventos de INST.ARG.DE MATEMATICAS "ALBERTO CALDERON"
Eventos de INST.ARG.DE MATEMATICAS "ALBERTO CALDERON"
Citación
Learning mixed-state Markov models for statistical motion texture tracking; 12th International Conference on Computer Vision Workshops; Japón; 2009; 444-451
Compartir
Altmétricas