USING SPACE CONTINUITY AND ORIENTATION CONSTRAINTS FOR RANGE DATA-ACQUISITION

Fast range data acquisition of objects is often needed in computer vis ion applications such as robot vision. In this paper, a fast range dat a acquisition approach based on space continuity and orientation const raints is proposed. First a masking technique which can reconstruct ob jects efficiently with the epipolar constraint in trinocular vision is presented. Subsequently the artificial point problem is analysed and an artificial point removal algorithm based on a space continuity cons traint is proposed. In order to ensure correct initial reconstructed p oints, an orientation constraint is introduced. Finally, some reconstr uction experiments illustrate the feasibility of our approach.