Skip to content

Conversation

huawei-sai
Copy link

This bug has been already highlighted and well explained in these two links. #11
#12
To check this - one can visualize the loop submap in RVIZ and can see the cluttered point cloud as it does not have correct registration.

This bug has been already highlighted and well explained in these two links.
gisbi-kim#11
gisbi-kim#12
To check this - one can visualize the loop submap in RVIZ and can see the cluttered point cloud as it does not have correct registration.
The function is also changed in the author's latest code base
https://github.com/gisbi-kim/lt-mapper/blob/bce4236d97bf0d9d97187f9355380e981ac7e499/ltslam/src/LTslam.cpp#L201

Basically loopFindNearKeyframesCloud function does not require the fourth input parameter that it initially had - it just creates more confusion and it never is used. Also while transforming the pointcloud to global coordinate frame (origin) and to accumulate surrounding frames, one does not need the fourth input parameter. Changed the function accordingly.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant