Hybrid Elevation Maps: 3D Surface Models for Segmentation

Hybrid Elevation Maps: 3D Surface Models for Segmentation. Douillard, B., Underwood, J., Melkumyan, N., Singh, S., Vasudevan, S., & Brunner, C. 2010.
doi abstract bibtex

This paper presents an algorithm for segmenting 3D point clouds. It extends terrain elevation models by incorporating two types of representations: (1) ground representations based on averaging the height in the point cloud, (2) object models based on a voxelisation of the point cloud. The approach is deployed on Riegl data (dense 3D laser data) acquired in a campus type of environment and compared against six other terrain models. Amongst elevation models, it is shown to provide the best fit to the data as well as being unique in the sense that it jointly performs ground extraction, overhang representation and 3D segmentation. We experimentally demonstrate that the resulting model is also applicable to path planning.

@CONFERENCE{IROS2010.Douillard,
  author = {B. Douillard and J. Underwood and N. Melkumyan and S. Singh and S.
	Vasudevan and C. Brunner},
  title = {{Hybrid Elevation Maps}: {3D} Surface Models for Segmentation},
  booktitle = {Proceedings of the International Conference on Intelligent Robots
	and Systems ({IROS})},
  year = {2010},
  abstract = {This paper presents an algorithm for segmenting 3D point clouds. It
	extends terrain elevation models by incorporating two types of representations:
	(1) ground representations based on averaging the height in the point
	cloud, (2) object models based on a voxelisation of the point cloud.
	The approach is deployed on Riegl data (dense 3D laser data) acquired
	in a campus type of environment and compared against six other terrain
	models. Amongst elevation models, it is shown to provide the best
	fit to the data as well as being unique in the sense that it jointly
	performs ground extraction, overhang representation and 3D segmentation.
	We experimentally demonstrate that the resulting model is also applicable
	to path planning.},
  doi = {10.1109/IROS.2010.5650541},
  pdf = {IROS2010.Douillard.pdf}
}

Downloads: 0