I am using a kalman filter (constant velocity model) to track postion and velocity of an object. I measure x,y of the object and track x,y,vx,vy . Which works but if a add gausian noise of +- 20 mm to the sensor readings x,y,vx,vy fluctuates even though the point is not moving just noise. For location that is good enough for my needs but velocity changes when the point is stationary and that is causing problems with my object speed calculations. Is there a way around this problem? also if switching to constant acceleration model improve on this? I am tracking a robot via a camera.

I am using opencv implementation and my kalman model is same as [1]

[1] http://www.morethantechnical.com/2011/06/17/simple-kalman-filter-for-tracking-using-opencv-2-2-w-code/

  • 1
    $\begingroup$ What you're observing is to be expected when you have noisy measurements. You can choose to assign a higher covariance to the measurements, which will cause your filter to prefer its current state estimate value more. This will reduce the amount of jitter that you see about the correct state value, but the filter will take a longer time initially to arrive at the correct state. $\endgroup$ – Jason R Dec 15 '15 at 16:31
  • $\begingroup$ @JasonR , when you say "assign a higher covariance to the measurements" which matrix are you referring to? measurement error covariance matrix? What exactly do I change? and also addition to this does switching to constant acceleration model improve on this also? $\endgroup$ – Hamza Yerlikaya Dec 15 '15 at 17:26
  • $\begingroup$ @Hamza : please share your model noise covariance matrix, Q , are you using the Singer model? Moreover, have you tried fine tuning Q,R? If you have wrong velocity estimation when the target is stationary adding an order (acceleration) to the game will not give better results. $\endgroup$ – Nir Regev Jan 6 '16 at 10:55

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.