Toni Rosinol
Toni Rosinol
It seems like setting `use_lcd=True` skips the registration of the IMU callback. @marcusabate any idea?
Hi @amburkoff , Mask-RCNN is the easiest/fastest to use, but any that outputs semantic labels on a per-pixel basis will do. We are planning to release a how-to wiki page...
Hi @zinuok, I'll have a look, in the meantime, try to set `autoInitialize` parameter in BackendParams.yaml to `1`, here: https://github.mit.edu/SPARK/Kimera-VIO/blob/fd348b11831f6cdb32c252bbead412ca092a1639/params/Euroc/BackendParams.yaml#L7
@RozDavid I also understood that when re-reading Eigen, the operations should already be vectorized... So it might well be we can't improve on that. It's fine for me, I think...
The core library is agnostic to ROS, but the interface with data is based on ROS. It should be easy to interface with other data sources.
@ruffsl I need to hold these PRs bcs we are in the middle of the [Go-SEEK challenge](https://github.com/MIT-TESSE/goseek-challenge), and this might break things...
I'll have a look thanks!
Voila:  Everything was there already thanks to @skohlbr I enumerated my changes here https://github.com/skohlbr/disparity_image_proc/issues/2
Hi @ZacharyTaylor is there any performance difference between using one or the other?