Alan R Lowe

Yes, that sounds very reasonable! I don't think the `TrackManager` should need any modification, just the `MotionModel`.

There is a preliminary version of this here: https://github.com/quantumjot/btrack/tree/hypothesis-features

Hi Ollie - would you be able to post the tracking log? It really helps to debug

Ah - ok, I see. The optimiser timed out (DNF) so you didn't get any lineage information. This is usually because your parameters lead to a very large number of...

Yes, the parameters of the "motion model" are a good place to start. Also, is this 2D or 3D data? Sometimes setting the tracking volume (`tracker.volume`) incorrectly can lead to...

Hi @Micro-Sandworms, There are some examples of using features (object properties) in the [examples](https://github.com/quantumjot/BayesianTracker/blob/main/examples/example_tracking_pipeline-features.ipynb) folder - you can try adding the segmented volume as a feature. Some details of the...

@KristinaUlicna - would be good to have a btrack h5 file that included segmentation and tracks (with some properties ideally), and some ground truth trees

Checking for NaN and inf values would be a great start.

Looks like the bounds are set incorrectly now - maybe this would work? ```python bounds=((0,-1.,-10.), (10.,1.,0.)) ```

Hi @mnaqvi-code - do you want to open a pull request to fix this? I think @ergm3 added these equations.