Issue No. 08 - August (1995 vol. 17)
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/34.400566
<p><it>Abstract</it>—A camera is mounted on a moving robot and can rotate, relative to the robot, about two axes. We show how the optical flow field can be used to control the camera’s motion to keep a target at the center of the camera’s field of view, but that this is not always possible when the target lies close to the plane defined by the camera’s two axes of rotation.</p><p>When the target is held at the center of the camera’s field of view, then the magnitude of the camera’s angular velocity about one axis never exceeds the magnitude of the flow vector associated with the target, but the angular velocity about the other axis is dependent on the inverse distance of the target from this axis, and hence can become large as this distance becomes small. Situations, where the magnitudes of the camera’s angular velocity and acceleration become large, are considered in the special case where the relative motion between the robot and its environment is purely translational. The tracking strategy is experimentally evaluated using computer-generated optical flow fields.</p>
Optical flow, gaze control, active vision.
G. Loizou and S. Reddi, "Analysis of Camera Behavior During Tracking," in IEEE Transactions on Pattern Analysis & Machine Intelligence, vol. 17, no. , pp. 765-778, 1995.