Computree Documentation

Gaussian Mixture Models with Fast Point Feature Histograms

Plugin : SimpleForest
Nom de classe : SF_StepGnnFpfh

Description

For an input cloud the fast point feature histogram is computed for a given range. Gassian mixture model classification is performed to create 10 output clusters.

Paramètres

Paramètres de pré-configuration (non modifiables une fois l'étape ajoutée) :

  • Uncheck to deactivate parameterization possibilities of this step. Only recommended for beginners: Activé.

Paramètres de l'étape :


[Only one input cloud allowed otherwise no manual classification is possible].

[Crash of this step under Linux was observed].
  • Run the FPFH estimation with [range] of 0.150 (m)..


Normals used of FPFH are computed with [range] / 2.

The cloud is downscaled before all computations with [range] / 6. Later classification is backTransformed
  • Choose the [number] of gaussian mixture clusters: 0.

  • Downscale the 33 dimensional FPFH matrix to [dimensions]: 5.


Please excuse potential double citation with the step related citation for the

following general citation for SimpleForest (work on updated citable resource ongoing):





A majority of implementations are based on PCL library:





------------------------------------------------------------------------------

Données d'entrée

Structure des données d'entrée recherchées :

Result : Point Cloud
    ...
        Cloud Group (Group)
            Cloud (Item with points)

Références

Hackenberg Jan, Spiecker Heinrich, Calders Kim, Disney Mathias, Raumonen Pasi. 2015. SimpleTree - an efficient open source tool to build tree models from TLS clouds. Multidisciplinary Digital Publishing Institute. Forests.
Rusu Radu Bogdan, Cousins Steve. 2011. 3d is here: Point cloud library (pcl). IEEE. Robotics and Automation (ICRA), 2011 IEEE International Conference on.