Karl Engelbert Wenzel, Andreas Masselli and Prof. Dr. Andreas Zell demonstrate a different visual tracking approach by using low-cost, lightweight commodity consumer hardware. As main sensor they use a Wii remote infrared (IR) camera, which allows robust tracking of a pattern of IR lights in conditions without direct sunlight. The system does not need to communicate with the ground vehicle and works with an onboard 8-bit microcontroller.This enables the UAV (unmanned aerial vehicle)they use, a quadrocopter, to fly fully autonomously, performing flight control, self-stabilisation and visual tracking of the ground vehicle.
Their latest developments enable the quadrocopter to automously take off, tracking and landing on a moving carrier vehicle. The data coming from the wii infrared camera quadrocopter is equiped contains the pixel position of the four blobs and optional information as intensity and bounding box. The task of calculating the position of a camera from a known pattern of control points and their projection onto the camera's image plane is well known as the perspective-n-point (PnP) problem. Excellent project and excellent results.
Complete project details and progress can be found here.