基于多层前馈型神经元网络模型的摄像机定标算法

针对传统线性、非线性摄像机定标算法的鲁棒性,提出了基于多层前馈型神经元（MLFN）网络模型来替代传统精确的摄像机定标数学模型,MLFN网络模型作为层状网络可实现任意维复杂的输入／输出映射,对于无需计算摄像机构,外参数的应用场合,该模型提供了一种实用且有较好鲁棒性的摄像机定标算法,同时为了补偿摄影机非线性畸变,把图像按畸变程度分割成两个区域,分别建立各自基于MLFN网络的摄像机定标模型,实验表明,该方法有效补了畸变,并提高了模型精度,给出了基于MLFN网络模型摄像机定标算法实验,验证了该模型的有效性。

Camera Calibration Algorithm Based on Multiple-Layer-Forward-Neural Network

Compared to the robust of the classic linear or nonlinear camera calibration algorithms, this paper put out a novel camera calibration algorithm based on Multiple Layer Forward Neural (MLFN) network. As MLFN network is a multiple layer network, it can map any dimension of complicated input to output. It presents a useful and well robust camera calibration algorithm when it need not calculate the internal and exterior parameters. Furthermore, as to compensate for the camera's nonlinear distortion, the image is divided into two areas, and MLFN network models will be built on each of the areas. The experiments indicate the method can effectively compensate for the distortion of camera. Experiments of the camera calibration based on the MLFN network were presented at the end of this paper, which prove the effectiveness of the algorithm.