序列图像目标跟踪的神经网络算法

Hopfield Network for Target Tracking in Sequential Images

针对序列图像面目标跟踪问题，在提取图像特征点的基础上，提出了一种最优化算法．该算法将序列图像面目标跟踪问题转化为相邻两帧图像特征点间的匹配问题．文中根据匹配问题的各种限制条件给出代价函数，并利用Ｈｏｐｆｉｅｌｄ神经网络最优化计算功能来求取该代价函数的局部极小值．其中神经元的状态用以表示相邻两帧图像特征点间的匹配关系，神经元间的权连结用以反映对应特征点间的匹配程序．也就是说，本文针对序列图像面目标跟踪问题的特点，通过给出各神经元的初始状态及其区分配性计算准则来求取神经网络的渐近稳定状态，从而达到实现序列图像面目标跟踪的目的．

An Optimization approach is used to solve the target tracking problem for a set of features extracted from sequential images. A cost function is defined to represent the constraints on the solution, which is then mapped onto a two-dimensional Hopfield neural network for minimization. Each neuron in the network represents a possible match between the features of two neighboring images in sequential images. Target tracking is achieved by initializing (exciting) each neuron and then allowing the network to settle down to a stable state. The network uses the initial inputs and the compatibility measures between the matched points to find a stable state.