Kalman Filter Series - Part 5 (Python 1D Kalman Filter from scratch)

[@SteveRowe]

My eyes started glazing over as you went through the equations. The visuals relating the code back to the equations helped a lot. Thank you for this series!

[@dougblanding8791]

Thank you for this very clear presentation of a very abstruse topic. I am reading various tutorials to help me grasp the way Kalman filters work. I like your examples, and I especially like that you have included the Python code. However, I have noticed one thing that confused me a bit though. I believe you have switched the names R and Q from the way they are presented in other tutorials. I checked on Wikipedia and they have it as: Q is the covariance of the process noise; and R is the covariance of the observation noise. Just in case this might confuse other readers.

[@mohitks62]

Was eagerly waiting for it😊.

[@myetis1990]

at 4:12 , there is an error on formulas, R is the measurement noise covariance which should be in the kalman gain, and Q is process noise covariance which should be in the prediction . replace Q and R in the formulas please.

[@hummingbird19]

Some books/resources use Q for measurement noise and R for process noise, while some do the opposite. We follow the former. You can decide which convention to choose.

[@raghavmalhotra4018]

quick question, in line 61, 62 you make a prediction and update it. However, isn't the line 64 only logging the "prediction" step and now the value after it is updated?

[@sudhanshuprasad2666]

Great content sir!! Thank you😁😁

[@jacobsanoj5027]

When Part 6 sir?

[@owenvaughn9613]

😬 "promosm"