Visual Tracking Based on 3D Probabilistic Reconstruction

Author

Simas, Gisele ; De Bem, Rodrigo ; Novelo, Lucas ; Fickel, Guilherme ; Botelho, Silvia

Author_Institution

Centro de Cienc. Computacionais - C3, Univ. Fed. do Rio Grande - FURG, Rio Grande, Brazil

fYear

2010

fDate

22-26 March 2010

Firstpage

403

Lastpage

409

Abstract

This paper presents an approach to the 3D visual tracking problem into multi-camera environments. This proposal executes the markerless visual tracking observing the environment through a model based in a volumetric reconstruction technique, called 3D Probabilistic Occupancy Grids, which is still seldom used for this purpose. The target is tracked by the use of Expectation-Maximization algorithm with an object representation model constructed with Gaussians blobs representing the object body parts.

Keywords

expectation-maximisation algorithm; image reconstruction; image representation; target tracking; 3D probabilistic occupancy grids; 3D probabilistic reconstruction; Gaussians blobs; expectation-maximization algorithm; multicamera environments; object representation model; visual tracking; volumetric reconstruction technique; Cameras; Conferences; Data mining; Expectation-maximization algorithms; Gaussian processes; Image reconstruction; Motion estimation; Proposals; Systems engineering and theory; Target tracking; 3D probabilistic reconstruction; 3D visual tracking; volumetric reconstruction;

fLanguage

English

Publisher

ieee

Conference_Titel

Engineering of Computer Based Systems (ECBS), 2010 17th IEEE International Conference and Workshops on

Conference_Location

Oxford

Print_ISBN

978-1-4244-6537-8

Electronic_ISBN

978-1-4244-6538-5

Type

conf

DOI

10.1109/ECBS.2010.53

Filename

5457744