search

PRBonn / semantic_suma

SuMa++: Efficient LiDAR-based Semantic SLAM (Chen et al IROS 2019)
MIT License
923 stars 205 forks source link

There are some issues with dynamic object culling #60

Open SSSSSSStar opened 1 year ago

SSSSSSStar commented 1 year ago

As mentioned in the paper, it uses semantic information to perform dynamic object removal during the map update phase, and provides a formula for the semantic consistency penalty function. However, I cannot find the relevant code for dynamic object removal in the code. Could you please tell me which files are included?

jbehley commented 8 months ago

A bit late, but maybe it helps someone else. Sorry :/

The dynamic object removal is only implicitly happening by putting a penalty on the association in the computation of the Jacobian:

https://github.com/PRBonn/semantic_suma/blob/531954dd602ef1803707a29b9f4a5eb50cdb07de/src/shader/Frame2Model_jacobians.geom#L143-L158

And the actual integration of this into the map building (to remove conflicting labels) is happening here:

https://github.com/PRBonn/semantic_suma/blob/531954dd602ef1803707a29b9f4a5eb50cdb07de/src/shader/update_surfels.vert#L187-L195

The penalty term then reduces the confidence and surfels below a certain confidence are then removed.