Camera Calibration Based on the RBF Neural Network with Tunable Nodes forVisual Servoing in Robotics

In this paper, a new approach based on the radial basis function network for solving the camera calibration problem in visual servoing robot is proposed. In this approach, an extended multi-input and multi-output orthogonal forward selection algorithm based on the leave-one-out criterion is applied for the construction of radial basis function (RBF) networks with tunable nodes. This algorithm is computationally efficient and is capable of identifying parsimonious RBF networks that generalize well. Moreover, the proposed algorithm is fully automatic and the user does not need to specify a termination criterion for the construction process. The constructed parsimonious multi-input and multi-output RBF network can complete camera calibration automatically and rapidly, and the simulation has proved that the approach is feasible