Octree-based region growing for point cloud segmentation

Anh Vu Vo, Linh Truong-Hong, Debra Laefer, Michela Bertolotto

Research output: Contribution to journalArticle

Abstract

This paper introduces a novel, region-growing algorithm for the fast surface patch segmentation of three-dimensional point clouds of urban environments. The proposed algorithm is composed of two stages based on a coarse-to-fine concept. First, a region-growing step is performed on an octree-based voxelized representation of the input point cloud to extract major (coarse) segments. The output is then passed through a refinement process. As part of this, there are two competing factors related to voxel size selection. To balance the constraints, an adaptive octree is created in two stages. Empirical studies on real terrestrial and airborne laser scanning data for complex buildings and an urban setting show the proposed approach to be at least an order of magnitude faster when compared to a conventional region growing method and able to incorporate semantic-based feature criteria, while achieving precision, recall, and fitness scores of at least 75% and as much as 95%.

Original languageEnglish (US)
Pages (from-to)88-100
Number of pages13
JournalISPRS Journal of Photogrammetry and Remote Sensing
Volume104
DOIs
StatePublished - Jun 1 2015

Fingerprint

segmentation
airborne lasers
fitness
semantics
size selection
Semantics
Scanning
scanning
Lasers
output
building
laser
lasers
method

Keywords

  • Building reconstruction
  • LiDAR
  • Octree
  • Point cloud
  • Segmentation
  • Voxelization

ASJC Scopus subject areas

  • Geography, Planning and Development
  • Atomic and Molecular Physics, and Optics
  • Engineering (miscellaneous)
  • Computer Science Applications
  • Computers in Earth Sciences

Cite this

Octree-based region growing for point cloud segmentation. / Vo, Anh Vu; Truong-Hong, Linh; Laefer, Debra; Bertolotto, Michela.

In: ISPRS Journal of Photogrammetry and Remote Sensing, Vol. 104, 01.06.2015, p. 88-100.

Research output: Contribution to journalArticle

Vo, Anh Vu ; Truong-Hong, Linh ; Laefer, Debra ; Bertolotto, Michela. / Octree-based region growing for point cloud segmentation. In: ISPRS Journal of Photogrammetry and Remote Sensing. 2015 ; Vol. 104. pp. 88-100.
@article{f3edb61e4efc4711bf273fae749d320e,
title = "Octree-based region growing for point cloud segmentation",
abstract = "This paper introduces a novel, region-growing algorithm for the fast surface patch segmentation of three-dimensional point clouds of urban environments. The proposed algorithm is composed of two stages based on a coarse-to-fine concept. First, a region-growing step is performed on an octree-based voxelized representation of the input point cloud to extract major (coarse) segments. The output is then passed through a refinement process. As part of this, there are two competing factors related to voxel size selection. To balance the constraints, an adaptive octree is created in two stages. Empirical studies on real terrestrial and airborne laser scanning data for complex buildings and an urban setting show the proposed approach to be at least an order of magnitude faster when compared to a conventional region growing method and able to incorporate semantic-based feature criteria, while achieving precision, recall, and fitness scores of at least 75{\%} and as much as 95{\%}.",
keywords = "Building reconstruction, LiDAR, Octree, Point cloud, Segmentation, Voxelization",
author = "Vo, {Anh Vu} and Linh Truong-Hong and Debra Laefer and Michela Bertolotto",
year = "2015",
month = "6",
day = "1",
doi = "10.1016/j.isprsjprs.2015.01.011",
language = "English (US)",
volume = "104",
pages = "88--100",
journal = "ISPRS Journal of Photogrammetry and Remote Sensing",
issn = "0924-2716",
publisher = "Elsevier",

}

TY - JOUR

T1 - Octree-based region growing for point cloud segmentation

AU - Vo, Anh Vu

AU - Truong-Hong, Linh

AU - Laefer, Debra

AU - Bertolotto, Michela

PY - 2015/6/1

Y1 - 2015/6/1

N2 - This paper introduces a novel, region-growing algorithm for the fast surface patch segmentation of three-dimensional point clouds of urban environments. The proposed algorithm is composed of two stages based on a coarse-to-fine concept. First, a region-growing step is performed on an octree-based voxelized representation of the input point cloud to extract major (coarse) segments. The output is then passed through a refinement process. As part of this, there are two competing factors related to voxel size selection. To balance the constraints, an adaptive octree is created in two stages. Empirical studies on real terrestrial and airborne laser scanning data for complex buildings and an urban setting show the proposed approach to be at least an order of magnitude faster when compared to a conventional region growing method and able to incorporate semantic-based feature criteria, while achieving precision, recall, and fitness scores of at least 75% and as much as 95%.

AB - This paper introduces a novel, region-growing algorithm for the fast surface patch segmentation of three-dimensional point clouds of urban environments. The proposed algorithm is composed of two stages based on a coarse-to-fine concept. First, a region-growing step is performed on an octree-based voxelized representation of the input point cloud to extract major (coarse) segments. The output is then passed through a refinement process. As part of this, there are two competing factors related to voxel size selection. To balance the constraints, an adaptive octree is created in two stages. Empirical studies on real terrestrial and airborne laser scanning data for complex buildings and an urban setting show the proposed approach to be at least an order of magnitude faster when compared to a conventional region growing method and able to incorporate semantic-based feature criteria, while achieving precision, recall, and fitness scores of at least 75% and as much as 95%.

KW - Building reconstruction

KW - LiDAR

KW - Octree

KW - Point cloud

KW - Segmentation

KW - Voxelization

UR - http://www.scopus.com/inward/record.url?scp=84925354943&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84925354943&partnerID=8YFLogxK

U2 - 10.1016/j.isprsjprs.2015.01.011

DO - 10.1016/j.isprsjprs.2015.01.011

M3 - Article

VL - 104

SP - 88

EP - 100

JO - ISPRS Journal of Photogrammetry and Remote Sensing

JF - ISPRS Journal of Photogrammetry and Remote Sensing

SN - 0924-2716

ER -