An object-tracking algorithm based on Bayesian-learning Conference Paper

•  
• Overview
•  
• Research
•  
• Identity
•  
• Additional Document Info
•  
• View All
•  

Overview

abstract

• Real-time object tracking is recently becoming very important in many video processing tasks. Applications as video surveillance, robotics, people tracking, etc., need reliable and affordable video tracking tools. Most of current available solutions are, however, computationally intensive and sometimes require expensive video hardware. In this paper, we propose a new object tracking algorithm for real-time video based on a new probabilistic approach that results in a Bayesian-Learning process. This approach infers the trajectory of a moving object by applying a very simple optimization method, which makes the tracking algorithm robust and simple to implement. Experimental results are provided to demonstrate the performance of the proposed tracking algorithm in complex real-time video sequence scenarios. ©2007 IEEE.

authors

• Campos Delgado Daniel Ulises
• Gutierrez-Navarro O.
• Luna Rivera José Martín

publication date

• 2007-01-01

published in

• IEEE International Symposium on Industrial Electronics  Proceedings

Research

keywords

• Automation; Bayesian networks; Chlorine compounds; Electronics industry; Imaging techniques; Industrial electronics; Learning algorithms; Photography; Technical presentations; Video recording; Bayesian; International symposium; Learning processes; Moving objects; Object tracking algorithm; Object-tracking; Optimization methods; People tracking; Probabilistic approaches; Real time videos; Real-time object tracking; Tracking algorithms; Video processing; Video tracking; Video-surveillance; Security systems

Identity

Digital Object Identifier (DOI)

• 10.1109/ISIE.2007.4374857

Additional Document Info

start page

• 1681

end page

• 1686