基于径向基函数网络的二维平面标定方法

2-D plane calibration algorithm based onradial basis function neural networks

二维平面的标定即恢复某平面上点的世界坐标.传统的考虑各种非线性畸变的标定方法十分繁琐,而径向基网络可以实现从输入到输出的任意非线性映射,因此可将径向基网络应用于二维平面的标定.用神经网络来拟合摄像机的反投影过程,经训练建模后,网络输出能够反映训练样本的特征,可以得到较高的标定精度.实验结果证明了该算法的可行性.

2\|D plane calibration is recovering the world coordinates of the points in a plane, because the conventional calibration algorithms taking account of nonlinear distortions are very complex, and RBF neural network can realize any nonlinear relationship from input to output, RBF neural network was applied in this paper. The neural network was used to approximate the back projective model.The experimental results show that the algorithm is feasible.