Point Cloud Library (PCL)
1.7.0
|
00001 /** 00002 \addtogroup filters Module filters 00003 00004 \section secFiltersPresentation Overview 00005 00006 The <b>pcl_filters</b> library contains outlier and noise removal mechanisms 00007 for 3D point cloud data filtering applications. 00008 00009 An example of noise removal is presented in the figure below. Due to 00010 measurement errors, certain datasets present a large number of <i>shadow 00011 points</i>. This complicates the estimation of local point cloud 3D features. 00012 Some of these outliers can be filtered by performing a statistical analysis on 00013 each point's neighborhood, and trimming those which do not meet a certain 00014 criteria. The sparse outlier removal implementation in PCL is based on the 00015 computation of the distribution of point to neighbors distances in the input 00016 dataset. For each point, the mean distance from it to all its neighbors is 00017 computed. By assuming that the resulted distribution is Gaussian with a mean 00018 and a standard deviation, all points whose mean distances are outside an 00019 interval defined by the global distances mean and standard deviation can be 00020 considered as outliers and trimmed from the dataset. 00021 00022 \image html http://www.pointclouds.org/assets/images/contents/documentation/filters_statistical_noise.png 00023 00024 00025 \section secFiltersRequirements Requirements 00026 - \ref common "common" 00027 - \ref sample_consensus "sample_consensus" 00028 - \ref search "search" 00029 - \ref kdtree "kdtree" 00030 - \ref octree "octree" 00031 00032 */