区域公路网络结构的几何模型及计算机实现、最短路的计算及其辨识在交通量预测中起着重要的作用。
The geometric model and computer programming of local highway network plays an important role in traffic estimate, as well as the calculation of shortcut and its reorganization.
由于坐标测量机几何误差变化规律复杂，采用一般的BP神经网络模型算法，速度慢且难以收敛。
Owing to the complicated variable rule of CMMs geometry error, it's difficult to convergence for using common BP neural network model arithmetic with a slow velocity.
提出了一种多特征融合的地形匹配算法，充分利用地形的各种不同的统计特征和几何特征，构造了一种地形匹配网络模型。
A new terrain matching neural network algorithm mode is constructed by means of multi-features fusion, which includes different statistical and geometrical features.
应用推荐