Alan R Lowe

Yes - arriving at a good configuration can be challenging. Are you able to share any extra details, like a log or a short movie (e.g. #125)? - I might...

@lupinthief - currently the tracker always uses the motion model, but the features are optional. Should we make both optional (but with the requirement to have at least one of...

Latest update allows you to specify which updates to perform (either `motion`, `visual` or both). API has changed a little bit because of this: ```python with btrack.BayesianTracker() as tracker: ......

@lupinthief - should work with Python 3.7 now.

Maybe we could make a generic `write_images` function that we re-use for segmentation?

Hi there, can you post a code snippet to show the generator? It looks like you're passing a single bool rather than a numpy array.

Hi @nitinsai20 - thanks for the report, and sorry for the delay in getting back to you. Can you explain a bit more? Are the divisions detected, it's just that...

On a quick inspection it looks like you will need to adjust some parameters. The sigma values for `P` and `R` are very high in your config - is there...

Hi @nhazwulf - the object model is used (in principle) to allow the tracker to understand different types of state transitions for a single object type. However, the implementation is...

It seems like you managed to get things to work in #85?