Online adaptation of gaze fixation for a stereo-vergence system with foveated vision

In active vision systems, which direct their gaze to different visual targets in their environment, targets are represented in image coordinates and commands by which the gaze direction is changed are represented in motor coordinates. This requires knowledge of the mapping between two coordinate frames. In this work we present a robust mechanism that learns such a mapping. The mechanism can be applied to any active vision system performing arbitrary gaze shifts and runs online without interfering with any process in the vision system which it is integrated into. We show the feasibility of our approach by simulation and implementation of a stereo vision system with vergence and foveation.