This article is part of the series Image Analysis for Multimedia Interactive Services – Part II.

Open Access Research Article

Tracking of Objects in Video Scenes with Time Varying Content

Amal Mahboubi1*, Jenny Benois-Pineau2 and Dominique Barba1

Author Affiliations

1 IRCCyN UMR 6597 CNRS EPUN, rue Christian Pauc La chantrerie, BP 60601, Nantes 44306, France

2 LABRI, CNRS UMR 5800, Université Bordeaux-1, Talence, 33405, France

For all author emails, please log on.

EURASIP Journal on Advances in Signal Processing 2002, 2002:750583  doi:10.1155/S1110865702000902


The electronic version of this article is the complete one and can be found online at: http://asp.eurasipjournals.com/content/2002/6/750583


Received: 27 July 2001
Revisions received: 5 February 2002
Published: 26 June 2002

© 2002 Mahboubi et al.

We propose a method for tracking of objects contained in video sequences. Each video object is represented by a set of polygonal regions. A bottom up approach (spatial segmentation/motion estimation) is applied for the initialisation of the method, a limited human interaction is used to build the semantic map of the first frame in video sequence. The tracking of this model along a video sequence is based on detecting and indexing new objects in a video scene. Semantic rules are used to label new objects and, the current state of segmentation is validated by forward projection of the background.

Keywords:
new region extraction; labelling; object indexing; forward projection

Research Article