3
$\begingroup$

i have to estimate a process which changes over time, not with respect to the system-evolution or the measurement-function, but regarding the number of objects that have to be estimated. So every iteration I have to estimate e.g. 5 more state variables of a new object. Do you know method to do this with a Kalman or Particle Filter?

Thank you very much!

$\endgroup$
  • 1
    $\begingroup$ I don't think this fits into any Kalman-like framework that I've seen before. Are the new state variables related to the existing ones, or could you track each set of new variables with a new, independent filter that you create each iteration? $\endgroup$ – Jason R May 8 '13 at 12:59
  • $\begingroup$ I've not used it, but this paper appears to do something of what you're after. $\endgroup$ – Peter K. May 8 '13 at 14:31
  • $\begingroup$ Could you please provide an example. Specifically, what happens when the state dimension expands. What is the dynamics of the new states? Are they coupled with the dynamics of the older states? $\endgroup$ – aiao May 25 '13 at 19:07

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.