| Hansen, M. and G. Sommer (1996). Active depth estimation with gaze and vergence control using Gabor filters. In In 13th Int. Conf. on Pattern Recognition, Volume A, Vienna, Austria, pp. 287--291. |
....rather than attempting to foveate by a single adjustment. This will reduce jerky moves in response to outliers. If more than one perceptionaction cycle is available for vergence, it is still possible to achieve good final accuracy. The traditional approach employs a closed loop PD control model (Hansen and Sommer 1996). The gains of such a controller are tuned in a simulated environment to achieve robust and fast performance in the presence of simulated noise. However, one can do better than that. Note that the match uncertainty arises from self similar scenes where several good matches compete, or more ....
Hansen, M. and G. Sommer (1996). Active depth estimation with gaze and vergence control using Gabor filters. In In 13th Int. Conf. on Pattern Recognition, Volume A, Vienna, Austria, pp. 287--291.
....i.e. undershoot, rather than attempt to foveate by a single adjustment. This will reduce jerky moves in response to outliers. If more than one perception action cycle is available, it is still possible to achieve good final accuracy. The traditional approach employs a closed loop PD control model [5]. The gains of such a controller are tuned in a simulated environment to achieve robust and fast performance in the presence of simulated noise. However, one can do better than that. Note that the match uncertainty arises from self similar scenes where several good matches compete, or more ....
M. Hansen and G. Sommer. Active depth estimation with gaze and vergence control using Gabor filters. In In 13th Int. Conf. on Pattern Recognition, volume A, pages 287--291, Vienna, Austria, 1996.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC