Trainable Attention Model Based Vergence Control for Active Stereo Vision System

Abstract

We propose a new human-like vergence control method for an active stereo vision system. The proposed system uses a trainable selective attention model to localize an interesting object area in each camera. The selected object area in the master camera is compared with that in the slave camera to identify whether the two cameras find a same landmark. If the left and right cameras successfully find a same landmark, the implemented active vision system with two cameras focuses on the landmark. Using the motor encoder information, we can detect the depth information automatically. Computer simulation and experimental results show that the proposed vergence control method is very effective in implementing the human-like active stereo vision system.