Fuzzy vergence control for an active binocular vision system

Vergence control in binocular vision systems involves the adjustment of the angle between the two cameras´ axes so that they are both fixated at the same point of interest. Vergence enables stereo vision systems to perceive depth and to acquire obstacle maps. Vergence movement is directly related to the binocular fusion. Additionally, the decision for convergence or divergence is extracted either by motion affine models or by mathematical ones. In this paper, a new method for extracting the cameras´ movement direction, for verge or diverge, is presented. The movement decision is performed by a fuzzy control system, the inputs of which are the zero-mean normalized cross correlation (ZNCC) and the depth estimations at each time step. The suggested system can be used in any active binocular system and is computationally inexpensive. Moreover, the proposed system is independent to a priori camera calibration.