Real-time vision tracking algorithm Conference Paper uri icon

abstract

  • Real-time object tracking is recently becoming very important in many video processing tasks. Applications like video surveillance, robotics, people tracking, etc., need reliable and economically 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 that relies in the combination of a similarity measure with an euclidian metric. This approach infers the trajectory of a moving object by applying a very simple optimization method which makes the tracking algorithm robust and easy to implement. Experimental results are provided to demonstrate the performance of the proposed tracking algorithm in complex real-time video sequence scenarios. © Springer-Verlag Berlin Heidelberg 2006.

publication date

  • 2006-01-01