A clustering method for efficient segmentation of 3D laser data

By Klaas Klasing, Dirk Wollherr, Martin Buss. 2008

198 citations recorded by the source corpus.

Subfields: Computational Mechanics, Computer Vision and Pattern Recognition, Environmental Engineering

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Mechanics

In Computer Vision and Pattern Recognition

In Environmental Engineering

Citations in the corpus

Vehicle Detection from 3D Lidar Using Fully Convolutional Network (2016, background): “More delicate segmentation can be obtained by forming graphs on the point cloud [32, 14, 21, 29, 30].”
Performance of global descriptors for velodyne-based urban object recognition (2014, methodology): “For every scan (the set of points collected during the Velodyne LIDAR spins once), we assume that the ground segmentation and object cluster steps ( [1], [2], [3], [4], [5], [6]) have already been performed, and the outputs of the two steps are different objects.”
Segmentation of 3D lidar data in non-flat urban environments using a local convexity criterion (2009, unknown): “in [13], [ 18 ]) can be used for segmentation, which are easy to implement and fast.”
Fast segmentation of 3D point clouds for ground vehicles (2010, methodology): “Runtimes of our method (blue) compared to those of [10] (RBNN, red) and [1] (green) for 1000 scans on an Intel Core 2 Quad at 2.”
Comparison of surface normal estimation methods for range sensing applications (2009, methodology): “A description of the scanning setup can be found in [ 1 ].”
The three-dimensional normal-distributions transform : an efficient representation for registration, surface analysis, and loop detection (2009, methodology): “For this work, radially-bounded nearest-neighbour clustering [58] was used for segmenting the remaining points into contiguous regions.”
Laser-based segment classification using a mixture of bag-of-words (2013, methodology): “[12] directly use the point cloud to determine segments by an efficient distancebased clustering, where each cluster is defined by points with a given maximal distance to each other.”
What could move? Finding cars, pedestrians and bicyclists in 3D laser data (2012, background): “[12] perform clustering based on Euclidean distance between individual laser points, implicitly assuming that objects are not connected by scene clutter.”