Global Vision Based Tracking of Multiple Mobile Robots

Abstract

This paper presents a global vision system for tracking of multiple mobile robots as a part of intelligent space, with special emphasis on the following requirements: (i) the system must have the ability to track unlimited number of robots using images from one or more cameras, (ii) the system must have acceptable price, and (iii) the system must operate in real time, so algorithms with lower computational cost are preferred. In order to fulfill these requirements we used an IEEE 1394 camera with 80 fps, which delivers the image in so called Bayer format. We also designed a specific robot identification mark which enables measurement of robot locations directly in Bayer format image. In this way computational complexity was significantly reduced. Experimental testing demonstrated robust behavior of developed global vision system.