Conditional filters for image sequence based tracking - application to point tracking

Élise Arnaud (1) , Etienne Mémin (1) , Bruno Cernuschi-Frias (2)

1 VISTA - Vision spatio-temporelle et active
2 CONICET - Consejo Nacional de Investigaciones Científicas y Técnicas [Buenos Aires]

In this paper, a new conditional formulation of classical filtering methods is proposed. This formulation is dedicated to image sequence based tracking. These conditional filters allow solving systems whose measurements and state equation are estimated from the image data. In particular, the model that is considered for point tracking combines a state equation relying on the optical flow constraint and measurements provided by a matching technique. Based on this, two point trackers are derived. The first one is a linear tracker well-suited to image sequences exhibiting global dominant motion. This filter is determined through the use of a new estimator, called the conditional linear minimum variance estimator. The second one is a nonlinear tracker, implemented from a conditional particle filter. It allows tracking of points whose motion may be only locally described. These conditional trackers significantly improve results in some general situations. In particular, they allow dealing with noisy sequences, abrupt changes of trajectories, occlusions and cluttered background.

Domaines: Traitement des images [eess.IV]

Élise Arnaud, Etienne Mémin, Bruno Cernuschi-Frias. Conditional filters for image sequence based tracking - application to point tracking. IEEE Transactions on Image Processing, 2005, 14 (1). ⟨inria-00306720⟩