Autonomous motion vision

Earlier, the author (1991) introduced a direct method called fixation for the recovery of shape and motion in the general case. The method uses neither feature correspondence nor optical flow. Instead, it directly employs the spatio-temporal gradients of images brightnesses. The present paper reports the experimental results of applying some of the fixation algorithms to a sequence of real images where the motion is a combination of translation and rotation. Techniques for autonomous choice of parameters which result in good estimates for important motion parameters are also described.<>