# Viterbi algorithm for object tracking

I want to solve a problem of object tracking along time. The problem is - I have a sequence of images, and I need to find and track the creation of the objects, than their movement, and than their disappearance. There can be up to 3 objects overall, and sometimes there are less, or none. Another limitation is that for consecutive images there is a maximum distance that an object can move.

The practice I use is - estimating the locations for the objects in each image separately (using a neural network), up to 3 locations per image, and than filtering out clear mistakes (random locations with no continuation along time).

After a little research, I found that with some effort I can translate this problem into a hidden Markov model, and this one can be solved with Viterbi algorithm. The problem is that for each image there are more than 100 possible object locations, and with 3 objects we get >= 100000 different states.

My question is whether there exists a designated algorithm for this case of object tracking along time? Or otherwise, if there's a good and efficient way I can fit Viterbi algorithm for this problem?

Thank for any help!

• It would be helpful to see more of the setup of your problem, such as precisely how your hidden Markov model is formulated. Posting mathematical notation is usually a good way to convey such details, although it involves learning $\LaTeX$.
– hardmath
Aug 11, 2022 at 14:06