Quantitative evaluation strategies for urban 3D model generation from remote sensing data

Linh Truong-Hong, Debra Laefer

Research output: Contribution to journalArticle

Abstract

Over the last decade, several automatic approaches have been proposed to reconstruct 3D building models from aerial laser scanning (ALS) data. Typically, they have been benchmarked with data sets having densities of less than 25 points/m2. However, these test data sets lack significant geometric points on vertical surfaces. With recent sensor improvements in airborne laser scanners and changes in flight path planning, the quality and density of ALS data have improved significantly. The paper presents quantitative evaluation strategies for building extraction and reconstruction when using dense data sets. The evaluation strategies measure not only the capacity of a method to detect and reconstruct individual buildings but also the quality of the reconstructed building models in terms of shape similarity and positional accuracy.

Original languageEnglish (US)
Pages (from-to)82-91
Number of pages10
JournalComputers and Graphics (Pergamon)
Volume49
DOIs
StatePublished - Jul 28 2015

Fingerprint

Remote sensing
Lasers
Antennas
Scanning
Flight paths
Motion planning
Sensors

Keywords

  • Aerial laser scanning
  • Building detection
  • Building reconstruction
  • Evaluation strategy
  • LiDAR data
  • Point cloud

ASJC Scopus subject areas

  • Engineering(all)
  • Human-Computer Interaction
  • Computer Graphics and Computer-Aided Design

Cite this

Quantitative evaluation strategies for urban 3D model generation from remote sensing data. / Truong-Hong, Linh; Laefer, Debra.

In: Computers and Graphics (Pergamon), Vol. 49, 28.07.2015, p. 82-91.

Research output: Contribution to journalArticle

@article{afe212c8528545af8b0149806aba2f38,
title = "Quantitative evaluation strategies for urban 3D model generation from remote sensing data",
abstract = "Over the last decade, several automatic approaches have been proposed to reconstruct 3D building models from aerial laser scanning (ALS) data. Typically, they have been benchmarked with data sets having densities of less than 25 points/m2. However, these test data sets lack significant geometric points on vertical surfaces. With recent sensor improvements in airborne laser scanners and changes in flight path planning, the quality and density of ALS data have improved significantly. The paper presents quantitative evaluation strategies for building extraction and reconstruction when using dense data sets. The evaluation strategies measure not only the capacity of a method to detect and reconstruct individual buildings but also the quality of the reconstructed building models in terms of shape similarity and positional accuracy.",
keywords = "Aerial laser scanning, Building detection, Building reconstruction, Evaluation strategy, LiDAR data, Point cloud",
author = "Linh Truong-Hong and Debra Laefer",
year = "2015",
month = "7",
day = "28",
doi = "10.1016/j.cag.2015.03.001",
language = "English (US)",
volume = "49",
pages = "82--91",
journal = "Computers and Graphics",
issn = "0097-8493",
publisher = "Elsevier Limited",

}

TY - JOUR

T1 - Quantitative evaluation strategies for urban 3D model generation from remote sensing data

AU - Truong-Hong, Linh

AU - Laefer, Debra

PY - 2015/7/28

Y1 - 2015/7/28

N2 - Over the last decade, several automatic approaches have been proposed to reconstruct 3D building models from aerial laser scanning (ALS) data. Typically, they have been benchmarked with data sets having densities of less than 25 points/m2. However, these test data sets lack significant geometric points on vertical surfaces. With recent sensor improvements in airborne laser scanners and changes in flight path planning, the quality and density of ALS data have improved significantly. The paper presents quantitative evaluation strategies for building extraction and reconstruction when using dense data sets. The evaluation strategies measure not only the capacity of a method to detect and reconstruct individual buildings but also the quality of the reconstructed building models in terms of shape similarity and positional accuracy.

AB - Over the last decade, several automatic approaches have been proposed to reconstruct 3D building models from aerial laser scanning (ALS) data. Typically, they have been benchmarked with data sets having densities of less than 25 points/m2. However, these test data sets lack significant geometric points on vertical surfaces. With recent sensor improvements in airborne laser scanners and changes in flight path planning, the quality and density of ALS data have improved significantly. The paper presents quantitative evaluation strategies for building extraction and reconstruction when using dense data sets. The evaluation strategies measure not only the capacity of a method to detect and reconstruct individual buildings but also the quality of the reconstructed building models in terms of shape similarity and positional accuracy.

KW - Aerial laser scanning

KW - Building detection

KW - Building reconstruction

KW - Evaluation strategy

KW - LiDAR data

KW - Point cloud

UR - http://www.scopus.com/inward/record.url?scp=84938202607&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84938202607&partnerID=8YFLogxK

U2 - 10.1016/j.cag.2015.03.001

DO - 10.1016/j.cag.2015.03.001

M3 - Article

AN - SCOPUS:84938202607

VL - 49

SP - 82

EP - 91

JO - Computers and Graphics

JF - Computers and Graphics

SN - 0097-8493

ER -