CloudCompare forum

I am working with airborne LiDAR datasets. As is often the case, the class distribution is heavily skewed. Some classes are much more prevalent than others.

Any recommendations for dealing with this?

One of my thoughts was to implementing a data augmentation workflow, but as I think we can only ...

Ok, I figured it out.

This is how you structure the config file,
# NAMES OF YOUR POINT CLOUDS
cloud: PC1=railway_000033_rail.laz # Point cloud for training
cloud: corepoints=railway_000033_rail_sub04.laz

# CORE POINTS
core_points: corepoints

# Feature points
cloud: CTX=railway_000033_rail.laz ...

When I try to run the 3DMASC -> train classifier through CloudCompare (ver. 2.13.2), I fail when trying to include the context based features DZx and DHy.

I have read the manual, but still cannot figure out how to correctly structure the config file.

This is how it looks like at the moment ...

I have now tried to re-run the process from scratch, using several different point clouds, without being able to reproduce the error. So, this is resolved.

Thank you again for your help!

Ok, thank you very much. I really appreciate your help!

Regarding this,
Are you sure about your configuration?

Could you clarify? Do you mean if I installed CC and its dependencies correctly, or do you mean the 3DMASC settings/configuration?

Anyway, I will give it another try. Sounds like it ...

I launched the training on the railway_000033.laz file at once, without using a subset as core_points.

This is the initial parameter file,

# NAMES OF YOUR POINT CLOUDS
#cloud: PC1=railway_000033_rail.laz # Point cloud for training
cloud: PC1=
#cloud: corepoints=railway_000033_rail_sub04.laz ...

I used the following settings,

Max depth: 25
Max tree count: 100
Active var count: 0
Min sample count: 10

Scales: 0.5:0.5:2

Thank you for the reply!

I used the railway_000033.laz file.

The classifier.yaml file is large (8,53 GB (9 160 938 366 bytes)). I will try to find a way to share it.
Is the size of the .yaml file as expected?

Hi,

When I try to load the classifier saved after the training step I get this error,

\opencv\modules\core\src\alloc.cpp:55: error: (-4) Failed to allocate 262144 bytes in function cv::OutOfMemoryError

Is there anything I can do/change to solve this?

My input point cloud is a fairly small (but ...