search

yanyan-li / PlanarSLAM

A RGB-D SLAM system for structural scenes, which makes use of point-line-plane features and the Manhattan World assumption.
384 stars 85 forks source link

slow running #14

Closed aartykov closed 2 years ago

aartykov commented 2 years ago

Hi. First, thank you for the great work. I run it on my own rgb-d dataset, which img size is 480x640. It takes approximately 2-3 seconds to track a frame. I cannot understand the reason why it works so slowly. Can you suggest anything to improve the speed? Thanks in regard.

yanyan-li commented 2 years ago

Hi. First, thank you for the great work. I run it on my own rgb-d dataset, which img size is 480x640. It takes approximately 2-3 seconds to track a frame. I cannot understand the reason why it works so slowly. Can you suggest anything to improve the speed? Thanks in regard.

Hi @artykov1511 Thanks for testing our system. Since the released version keeps a very dense map, the depth-fusion step takes lots of computation time. Maybe you could change the voxel size used in Frame.cc and MapPlane.cc. 

 voxel.setLeafSize(0.1, 0.1, 0.1);

Hope it works for you.