Semi-automatic object tracking in video sequences

A method is presented for semi-automatic object tracking in video sequences using multiple features and a method for probabilistic relaxation to improve the tracking results producing smooth and accurate tracked borders. Starting from a given initial position of the object in the first frame the pro...

Descripción completa

Detalles Bibliográficos
Autores: Lecumberry, Federico, Pardo, Álvaro
Tipo de recurso: artículo
Estado:Versión publicada
Fecha de publicación:2005
País:Argentina
Institución:Universidad Nacional de La Plata
Repositorio:SEDICI (UNLP)
Idioma:inglés
OAI Identifier:oai:sedici.unlp.edu.ar:10915/9596
Acceso en línea:http://sedici.unlp.edu.ar/handle/10915/9596
Access Level:acceso abierto
Palabra clave:Ciencias Informáticas
Signal processing
Video (e.g., tape, disk, DVI)
Segmentation
Object recognition
Descripción
Sumario:A method is presented for semi-automatic object tracking in video sequences using multiple features and a method for probabilistic relaxation to improve the tracking results producing smooth and accurate tracked borders. Starting from a given initial position of the object in the first frame the proposed method automatically tracks the object in the sequence modelling the a posteriori probabilities of a set of features such as color, position and motion, depth, etc.