Point Cloud Library (PCL)
1.12.0
/builddir/build/BUILD/pcl-1.12.0/filters/filters.doxy
1
/**
2
\addtogroup filters Module filters
3
4
\section secFiltersPresentation Overview
5
6
The <b>pcl_filters</b> library contains outlier and noise removal mechanisms
7
for 3D point cloud data filtering applications.
8
9
An example of noise removal is presented in the figure below. Due to
10
measurement errors, certain datasets present a large number of <i>shadow
11
points</i>. This complicates the estimation of local point cloud 3D features.
12
Some of these outliers can be filtered by performing a statistical analysis on
13
each point's neighborhood, and trimming those which do not meet a certain
14
criteria. The sparse outlier removal implementation in PCL is based on the
15
computation of the distribution of point to neighbors distances in the input
16
dataset. For each point, the mean distance from it to all its neighbors is
17
computed. By assuming that the resulted distribution is Gaussian with a mean
18
and a standard deviation, all points whose mean distances are outside an
19
interval defined by the global distances mean and standard deviation can be
20
considered as outliers and trimmed from the dataset.
21
22
\image html http://www.pointclouds.org/assets/images/contents/documentation/filters_statistical_noise.png
23
24
25
\section secFiltersRequirements Requirements
26
- \ref common "common"
27
- \ref sample_consensus "sample_consensus"
28
- \ref search "search"
29
- \ref kdtree "kdtree"
30
- \ref octree "octree"
31
32
*/