A voxel-based methodology to detect (clustered) outliers in aerial lidar point clouds
S.J. Griffioen (TU Delft - Architecture and the Built Environment)
More Info
expand_more
Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.
Abstract
To obtain 3D information of the Earth’s surface, airborne LiDAR technology
is used to quickly capture high-precision measurements of the terrain.
Unfortunately, laser scanning techniques are prone to producing outliers
and noise (i.e. wrong measurements). Therefore, a pre-process of the point
cloud is required to detect and remove spurious measurements. While outlier
detection in datasets has been extensively researched, in 3D point cloud
data it is still an ongoing problem. Especially, clustered outliers are hard to
detect with previous local-neighborhood based algorithms.
This research explores the possibilities of using a voxel-based approach to
automatically remove outliers from aerial point clouds. A workflow is designed
in which a series of voxel-based operations are integrated, with the
aim to detect all types of outliers and minimize false positives. Voxels can
be processed more efficiently than 3D points for two reasons: (1) A voxelgrid
can be analyzed using efficient image processing techniques; (2) Voxels
group inner points before feature extraction using neighborhood operators.
Outliers are detected in two steps. First, the source point cloud is voxelized.
Secondly, outliers are detected by computing connected components and labeling
voxels not connected to the largest region as outliers. Simultaneously,
analysis of the point’s local density, shape (planar) and intensity minimize
classification of false positives.
The presented algorithm generally detects outliers with a higher accuracy
than previous local neighborhood-based methods. A comparison with an
existing approach shows that more outliers are detected. Above all, clustered
outliers are removed. However, some issues can still be improved.
First, more research is necessary to classify outliers based on non-arbitrary
decisions. This could potentially be improved by introducing supervised
learning algorithms. Secondly, more attention is required to process massive
point clouds that do not fit in internal memory. This study proposes a
possible streaming solution.