文中给出了模糊神经网络的结构和学习方法，并提出了一种阈值向量故障判别方法，使故障判别更具灵活性。
The structure of the FNN is given, and the learning method is presented. Meanwhile a fault discriminant method for threshold vector is employed, which makes fault discrimination even more flexible.
以此为前提，提出了距离阈值法和向量角度法相结合的数据精简算法。
Under this premise, the algorithm of data simplification is offered which combines the method of distance threshold with the one of vector angle.
采用改进的双阈值法和基于模型的方法进行渐变镜头的检测，根据运动向量的变化检测摄像机的运动状态。
Dual threshold and Basing on model are used to detect gradual changes, and the change of motorial vectors is used to detect the motion of the camera.
应用推荐