A Bayesian approach for color constancy based visual servoing

Visual servoing, or the control of motion on the basis of image analysis in a closed loop, is more and more recognized as an important tool in modern robotics. In this paper, we present a new model-driven approach to derive a description of the motion of a target object. This method can be subdivided into an illumination invariant target detection stage and a servoing process which uses an adaptive Kalman filter to update the model of the nonlinear system. This technique can be applied to any pan-tilt-zoom camera mounted on a mobile vehicle as well as to a static camera tracking moving environmental features.