CGAL 4.13 Classification

classic Classic list List threaded Threaded
4 messages Options
Reply | Threaded
Open this post in threaded view
|

CGAL 4.13 Classification

williamlai3a
Hi,

I am excited to test out the new classification concept, especially the mesh
classifier.
However, I have some doubts on the entire classification process:
1. Is training dataset a MUST?
2. From my understanding, we only needa label one region per label in the
dataset (just like the example data given). What if my class has more
variation in terms of shapes? Shall I give more regions labelled in the
training dataset?
2.1 Would colored point cloud benefit for both training and classification?
3. Are there any good recommendation software for preparing the .ply
training data? So I can select and label, then export the property as label
included in the .ply? (I googled and cannot find any useful one).
4. From the given example data, it seems that the points / surfaces are
spatially disconnected quite sharply. Would the classifier be still working
well if I have a possion reconstructed surface which is fully connected?

Thanks!
William



--
Sent from: http://cgal-discuss.949826.n4.nabble.com/

--
You are currently subscribed to cgal-discuss.
To unsubscribe or access the archives, go to
https://sympa.inria.fr/sympa/info/cgal-discuss


Reply | Threaded
Open this post in threaded view
|

Re: CGAL 4.13 Classification

williamlai3a
[Added]

5. I am working on similar point cloud like Figure 75.7, however, no example
codes and data which reproduce Figure 75.7 are given / found. It would be
great if it is also released:
- guides on how the training data can be prepared
- what are the parameters yielding results in Figure 75.7

Thanks!
William



--
Sent from: http://cgal-discuss.949826.n4.nabble.com/

--
You are currently subscribed to cgal-discuss.
To unsubscribe or access the archives, go to
https://sympa.inria.fr/sympa/info/cgal-discuss


Reply | Threaded
Open this post in threaded view
|

Re: CGAL 4.13 Classification

Simon Giraudot-2
In reply to this post by williamlai3a
Hello,

Le 15/10/2018 à 10:13, williamlai3a a écrit :
> Hi,
>
> I am excited to test out the new classification concept, especially the mesh
> classifier.
> However, I have some doubts on the entire classification process:
> 1. Is training dataset a MUST?
Yes it is. You can use classification without training if you use the
Sum_of_weighted_features classifier, but in that case the parameters are
not easy at all to select (especially if use a large number of
features). I would strongly advise using the
ETHZ_random_forest_classifier with a training set.
> 2. From my understanding, we only needa label one region per label in the
> dataset (just like the example data given). What if my class has more
> variation in terms of shapes? Shall I give more regions labelled in the
> training dataset?
In general, the larger your training set is, the better the results will
be. It's especially true if you have a wide variety of local geometric
features among a label: the training set should be as representative as
possible.
> 2.1 Would colored point cloud benefit for both training and classification?
Yes, colors can be used and may help classifying better (for example
with the color channel predefined feature:
https://doc.cgal.org/latest/Classification/classCGAL_1_1Classification_1_1Feature_1_1Color__channel.html 
).

Note that as the same features should be used for training and for
classification, you can only use colors for classification if you
trained your classifier with colors first (and vice versa, a classifier
trained with colors won't be able to handle point sets without colors).
> 3. Are there any good recommendation software for preparing the .ply
> training data? So I can select and label, then export the property as label
> included in the .ply? (I googled and cannot find any useful one).
I don't really know one.

If you just want to experiment, you can use the classification plugin of
the Polyhedron_3 demo of CGAL:
https://github.com/CGAL/cgal/tree/master/Polyhedron/demo/Polyhedron
You can't save labels for a mesh for now (although we should probably
add such functionality - it only works for point sets so far), but you
can easily select some facets for training and run classification.

You can see an example on how to use it here:
https://www.youtube.com/watch?v=xLFm8Aw8vuY
(The video uses a point set, but you can achieve the same thing with
surface meshes along with the selection plugin.)
> 4. From the given example data, it seems that the points / surfaces are
> spatially disconnected quite sharply. Would the classifier be still working
> well if I have a possion reconstructed surface which is fully connected?
Yes, it should also work. In that case, when creating a training set, it
will help to provide an accurate training set on the connected regions
where labels change (otherwise the transitions might be messy).
> [Added]
>
> 5. I am working on similar point cloud like Figure 75.7, however, no example
> codes and data which reproduce Figure 75.7 are given / found. It would be
> great if it is also released:
> - guides on how the training data can be prepared
> - what are the parameters yielding results in Figure 75.7
The figure was done with the demo similarly as what is shown on the
video, using all existing features on 5 scales (default
behavior/parameters).

Best regards,

--
Simon Giraudot, PhD
R&D Engineer
GeometryFactory - http://geometryfactory.com/


--
You are currently subscribed to cgal-discuss.
To unsubscribe or access the archives, go to
https://sympa.inria.fr/sympa/info/cgal-discuss


Reply | Threaded
Open this post in threaded view
|

Re: CGAL 4.13 Classification

williamlai3a
Hi Simon,

Thank you so much for your fantastic reply.
I didn't aware there are a list of demo to follow, was kept reading the user
manual only.
Thanks for the pointer.

Would like to follow up one more question:
If I am using point cloud reconstructed from photo based SfM+MVS pipeline,
the point cloud is super noisy (unlike LiDAR scanned point cloud as shown in
demo). Would you please advise on what parameters or features should be
aware in order to achieve the best result?

Thanks again!

William



--
Sent from: http://cgal-discuss.949826.n4.nabble.com/

--
You are currently subscribed to cgal-discuss.
To unsubscribe or access the archives, go to
https://sympa.inria.fr/sympa/info/cgal-discuss