DRIVING SACCADE TO PURSUIT USING IMAGE MOTION

Within the context of active vision, scant attention has been paid to the execution of motion saccades-rapid re-adjustments of the direction of gaze to attend to moving objects. In this paper we first develop a methodology for, and give real-time demonstrations of, the use of mot ion detection and segmentation processes to initiate ''capture saccade s'' towards a moving object. The saccade is driven by both position an d velocity of the moving target under the assumption of constant targe t velocity, using prediction to overcome the delay introduced by visua l processing. We next demonstrate the use of a first order approximati on to the segmented motion field to compute bounds on the time-to-cont act in the presence of looming motion. If the bound falls below a safe limit, a ''panic saccade'' is fired, moving the camera away from the approaching object. We then describe the use of image motion to realiz e smooth pursuit, tracking using velocity information alone, where the camera is moved so as to null a single constant image motion fitted w ithin a central image region. Finally, we glue together capture saccad es with smooth pursuit, thus effecting changes in both what is being a ttended to and how it is being attended to. To couple the different vi sual activities of waiting, saccading, pursuing and panicking, we use a finite state machine which provides inherent robustness outside of v isual processing and provides a means of making repeated exploration. We demonstrate in repeated trials that the transition from saccadic mo tion to tracking is more likely to succeed using position and velocity control, than when using position alone.