A Global Vision System for Robotics Courses

This paper describes our work on practical global vision systems (DORAEMON and ERGO). These vision systems have formed the basis of several undergraduate and graduate courses since 1998 and have consistently been improved to perform accurately and robustly over a wide range of applications. DORAEMON uses a sophisticated camera calibration method and colour model to remove the need for an overhead view of the world. ERGO minimized the use of colour information to provide more robust object recognition under varying lighting scenarios. Most recently, these video servers have been used to control robots in a shared virtual/physical