基于线性约束最小平方方法的神经数据融合算法与实现

提出了一种基于线性约束最小平方（Linear Constrained Least Square)方法的神经数据融合算法,LCLS方法用来最小化线性融合信息的能量,而神经网络算法则用来处理出现于LCLS方法中的样本协方差短阵的不良条件和奇异性问题,此算法用软件和硬件都能实现,与已有的融合方法相比,文章提出的神经数据融合方法具有非偏倚的统计特性而且不需要关于噪声协方差的任何先验知识,将此方法应用于图像融合,结果显示这两种方法能增强输出结果的质量。

Neural Data Fusion Algorithm and Implementation Based on a Linearly Constrained Least Square Method

In this paper, a neural data fusion algorithm based on a linearly constrained least square (LCLS) method is proposed. While the LCLS method is used to minimize the energy of the linearly fused information, the neural-network algorithm is developed to overcome the ill-conditioned and singular problems of the sample covariance matrix in the LCLS method. The proposed neural fusion algorithm is sample for implementation using both software and hardware. Compared with the existing fusion method, the proposed neural data fusion method has an unbiased statistical property and does not require any prior knowledge about the noise covariance. The proposed neural fusion method is used to image fusion, it is shown that the quality of the solution can be greatly enhanced by the proposed technique.