zziz/kalman-filter

Kalman Filter implementation in Python using Numpy only in 30 lines.

kalman-filter's Issues

Shape error when H is 2x4

I've noticed self.m is not used.
The following changes fixed my problem:
self.m = H.shape[0]
self.R = np.eye(self.m) if R is None else R

Thanks.

you set the parameter of u=0, so the prediction paremeter of accelerate a has any meaning?

use @ instead of np.dot

it will make code be more clear :)

Ground truth is missing and the measurements is wrong.

You didn't have ground truth of states in your implementation, how could you show that your code really works well with Kalman Filter?
To show that your code actually implements Kalman Filter, your filtered states should have smaller error compared with predicted states. But in your code, only the filtered states are provided.

The measurements here is generated from a parabola -(x**2+2x02). But this is not the actual curve.