Hi,

I have a question regarding the HornSchunck method and the partial time derivative:

ft = im2 - im1

ft = filter2(im1, kernelT) + filter2(im2, -kernelT)

with kernelT = np.ones((2, 2))*.25

If my understanding is correct, you substract the values from the second image from the ones in the first image.
In the Horn und Schunck paper I understood that you are supposed to do it the other way around.

Could you maybe tell me, if I understood it wrong or what the reasoning is to put this the other way around?

I also tried implementing the method myself, and exactly this issue seems to be my problem. If I implemented this with the minus sign in the im2 kernel, my directions are correct. I just donot understand why that is the case.

Thank you and greetings!

Hey,

Nice code!

The output is flipped. You probably have noticed. I fixed that with a simple np.flip.

im1 = np.flip(im1, 0)
im2 = np.flip(im2, 0)

Basically, I'm wondering if you could combine optical flow data from a camera with other sensor data using something like a KF or UKF. The application would be model aircraft, drones or stabilized model rockets. So the optic flow should be due primarily to rotations, translations and perspective effects. The camera would be aligned with one of the vehicles axes and could look at just rotation about that axis, for example.

Basically I'm wondering how fast it is, and if there is a way that you could feed it live data from a camera.

Obviously, I could hunt through the code, so answers that are equally as lazy as my question are welcome, haha!

  File "HornSchunck.py", line 22
    fn1 = f'{stem}.{i}{ext}'
                           ^
SyntaxError: invalid syntax

Above error appears when python HornSchunck.py data/box/box. Tested in Windows and Ubuntu, python 2.7