An adaptive feature-based tracking system
Date
2008-03
Authors
Pretorius, Eugene
Journal Title
Journal ISSN
Volume Title
Publisher
Stellenbosch : University of Stellenbosch
Abstract
In this paper, tracking tools are developed based on object features to robustly track the object using particle filtering. Automatic on-line initialisation techniques use motion detection and dynamic background modelling to extract features of moving objects. Automatically adapting the feature models during tracking is implemented and tested.
Description
Thesis (MSc (Mathematical Sciences. Applied Mathematics))--University of Stellenbosch, 2008.
Keywords
Dissertations -- Applied mathematics, Theses -- Applied mathematics, Computer vision, Tracking tools, Particle filtering, Motion detection