search

erikbohnsack / pmbm

Python implementation of Poisson Multi-Bernoulli Mixture Filter for Multi-Object Tracking.
64 stars 23 forks source link

Question about the derivation of the CV/CA model #5

Open zxiaomzxm opened 4 years ago

zxiaomzxm commented 4 years ago

https://github.com/erikbohnsack/pmbm/blob/9fc4dbbb81898f1a9bfaa19c7e387b0cab40be28/utils/motion_models.py#L96-L99

https://github.com/erikbohnsack/pmbm/blob/9fc4dbbb81898f1a9bfaa19c7e387b0cab40be28/utils/motion_models.py#L214-L219

Hi, I'm confused about the form of the covariancce matrix Q in the CV/CA model, how to derivate it?

erikbohnsack commented 1 year ago

Hello @zxiaomzxm! Sorry for taking 3 years for answering here, and even if it might not be relevant I figured I could answer if other people would wonder the same thing.

This is the description from our master thesis:

To help the search of good values for the parameters for the process noise and initial covariance for new objects, a genetic algorithm [63] was used with a combination of GOSPA, MOTP and MOTA, metrics described in Section 4.1, as evaluation function. The parameters from the genetic algorithm was manually fine-tuned afterwards

You can find the master thesis here: https://odr.chalmers.se/items/b2675ae4-9948-467f-b0ff-40084e00dba6