Modified 2-1/2-D Visual Servo-based Determination of Next Best Views in Automatic 3D Reconstruction

Determining next best view (NBV) is the key problem of automatic view planning which is the primary task in automatic 3D reconstruction. Since the classical mass vector chain (MVC) can only determine the NBV direction, a visual servo-based approach is proposed in this paper for determining the NBV spatial position. In the new approach, the eye-in-hand configuration is used and the 2-1/2-D visual servoing is modified for more simple control. The orientation of the end effector is controlled by MVC method in an open loop, which decreases the dimensionality of the image Jacobian. Some image features are extracted for position control of the end effector. The experimental results show that the proposed method can guide the robot to the desired orientation and position for automatic multiview planning. The final produced curve surface is basically complete, only with a few tiny blind areas due to too many concave small surface patches of the object.