Détection et suivi d'objets en mouvement dans des scenes complexes, application a la surveillance des conducteurs.

Aurélie Bugeau 1
1 VISTA - Vision spatio-temporelle et active
IRISA - Institut de Recherche en Informatique et Systèmes Aléatoires, Inria Rennes – Bretagne Atlantique
Abstract : Detecting and tracking moving objects in dynamic scenes is a hard but essential task in a large number of computer vision applications such as surveillance. Most existing methods only give good results in the case of persistent or slowly changing background, or if both the objects and the background can be characterized by simple parametric motions. This thesis aims at detecting, segmenting and tracking foreground moving objects in sequences (such as driver sequences) having highly dynamic backgrounds, illumination changes and low contrasts, and possibly shot by a moving camera. Two main steps compose the thesis. First, moving points, described by their motion and color, are selected within a sub-grid of image pixels. Clusters of points are then formed using a variable bandwidth mean shift with automatic bandwidth selection. In a second part, a tracking method is proposed. It combines color and motion distributions, the prediction of the tracked object and some external observations (which can be the clusters from the detector) into an energy function minimized with Graph Cuts. The algorithms are validated on several different sequences with complex dynamic contents.
Document type :
Theses
Complete list of metadatas

Cited literature [80 references]  Display  Hide  Download

https://tel.archives-ouvertes.fr/tel-00551601
Contributor : Aurélie Bugeau <>
Submitted on : Tuesday, January 4, 2011 - 10:45:18 AM
Last modification on : Friday, November 16, 2018 - 1:29:49 AM
Long-term archiving on : Tuesday, April 5, 2011 - 2:47:31 AM

Identifiers

  • HAL Id : tel-00551601, version 1

Citation

Aurélie Bugeau. Détection et suivi d'objets en mouvement dans des scenes complexes, application a la surveillance des conducteurs.. Interface homme-machine [cs.HC]. Université Rennes 1, 2007. Français. ⟨tel-00551601⟩

Share

Metrics

Record views

3037

Files downloads

27636