说明：  本次实验来源于opencv自带sample中的例子，该例子是用kalman来完成一个一维的跟踪，即跟踪一个不断变化的角度。在界面中表现为一个点在圆周上匀速跑，然后跟踪该点。看起来跟踪点是个二维的，其实转换成角度就是一维的了。 Kalman滤波理论主要应用在现实世界中个，并不是理想环境。主要是来跟踪的某一个变量的值，跟踪的依据是首先根据系统的运动方程来对该值做预测，比如说我们知道一个物体的运动速度，那么下面时刻它的位置按照道理是可以预测出来的，不过该预测肯定有误差，只能作为跟踪的依据。另一个依据是可以用测量手段来测量那个变量的值，当然该测量也是有误差的，也只能作为依据，不过这2个依据的权重比例不同。最后kalman滤波就是利用这两个依据进行一些列迭代进行目标跟踪的。
(This experiment from the examples the opencv own sample, the example is to complete a one-dimensional tracking using kalman, ie, tracking a changing point of view. Performance in the interface as a point in the circle on steady running, then track the points. Looks like the tracking point is a two-dimensional, in fact, convert the angle is one-dimensional. The main application of the Kalman filter theory in the real world, not the ideal environment. Is the value of a variable to keep track of the basis for tracking the first according to the equation of motion of the system to the value forecast, for example, we know the velocity of an object, then the following moment of its location in accordance with the truth can be predicted , but the forecast is certainly a margin of error, only as a basis for tracking. Another is based on measurements to measure the value of that variable, Of course, this measurement error can only be used as the basis of these two basis weights the different pr)