CloudCompare forum

I am not sure to get the point here. I read that in your excerpt:

# 3DMASC classifier file
classifier: Param1-0.yaml

Files containing such lines are created automatically by 3DMASC when saving classifiers and you are not supposed to edit them yourself.
The standard parameter file, used for ...

First of all, you have to write 'feature: ' in front of each feature.
As in the sample https://lidar.univ-rennes.fr/sites/lida ... rams_0.txt.

What is your version of CloudCompare? Because it matters, you may use a too old release.

What do you mean by a bounding box? You want some kind of rectangular parallelepipeds instead of ellipsoids? You may post a request on the GitHub repository of G3Point for that.

We have two lasers in our sensor, one 1064nm (aka 'NIR') and one 532nm (aka 'green').

'green_' files are points measured with the green laser, 'NIR_' files are points measured with the NIR laser. We do not use the NIR field of the las format, we have two different lasers which point in sightly ...

Without data, quite hard for me to answer your questions, sorry. 12 hours seems quite long for 11500 points but without any information on your machine, impossible to say something. May take more time on a raspberry pi. ;-)
Your images are not displayed.
In the classify step, you should give points ...

To train your classifier, 1000 points of each class in the training cloud (your PCX), are enough. How many points do you have in the training cloud?
As a PC1 cloud, one generally uses a full density point cloud as features are computed in each point of PCX using the points of PC1 (seeing the ...

What you are trying to do is not clear, please reformulate your objectives.
Please provide a subset of your data if you want some help (CloudCompare .bin file with point clouds explicitly named and their association with PCX and PC1).

Hi,

In the parameter file related to the article, PC1 and PC2 are HD data which are used to compute features in the location specified by PCX.
PC1, PC2, PCX and CTX are just labels, you can use the names you want (except CORE and TEST which have specific roles).
What is important is i) the line ...

I finally posted the parameter file here https://lidar.univ-rennes.fr/3dmasc-datasets

Enjoy!

The code you find in the lidar-platform library IS the one developed for the 3DMASC paper. If you look for a kind of all-inclusive script or notebook which would allow you to rebuild the results of the article I am not sure that it exists somewhere. But the article, the dataset (https://lidar.univ ...