Automatic extraction of road features in urban environments using dense ALS data

Mario Soilán, Linh Truong-Hong, Belén Riveiro, Debra Laefer

Research output: Contribution to journalArticle

Abstract

This paper describes a methodology that automatically extracts semantic information from urban ALS data for urban parameterization and road network definition. First, building façades are segmented from the ground surface by combining knowledge-based information with both voxel and raster data. Next, heuristic rules and unsupervised learning are applied to the ground surface data to distinguish sidewalk and pavement points as a means for curb detection. Then radiometric information was employed for road marking extraction. Using high-density ALS data from Dublin, Ireland, this fully automatic workflow was able to generate a F-score close to 95% for pavement and sidewalk identification with a resolution of 20 cm and better than 80% for road marking detection.

Original languageEnglish (US)
Pages (from-to)226-236
Number of pages11
JournalInternational Journal of Applied Earth Observation and Geoinformation
Volume64
DOIs
StatePublished - 2018

Fingerprint

Pavements
road
Curbs
Unsupervised learning
Parameterization
pavement
Semantics
raster
heuristics
parameterization
learning
methodology
detection

Keywords

  • Airborne laser scanning
  • Pavements classification
  • Point cloud segmentation
  • Urban modelling

ASJC Scopus subject areas

  • Global and Planetary Change
  • Earth-Surface Processes
  • Computers in Earth Sciences
  • Management, Monitoring, Policy and Law

Cite this

Automatic extraction of road features in urban environments using dense ALS data. / Soilán, Mario; Truong-Hong, Linh; Riveiro, Belén; Laefer, Debra.

In: International Journal of Applied Earth Observation and Geoinformation, Vol. 64, 2018, p. 226-236.

Research output: Contribution to journalArticle

@article{07bfca19f2b046ea9523fafd5fe69dc5,
title = "Automatic extraction of road features in urban environments using dense ALS data",
abstract = "This paper describes a methodology that automatically extracts semantic information from urban ALS data for urban parameterization and road network definition. First, building fa{\cc}ades are segmented from the ground surface by combining knowledge-based information with both voxel and raster data. Next, heuristic rules and unsupervised learning are applied to the ground surface data to distinguish sidewalk and pavement points as a means for curb detection. Then radiometric information was employed for road marking extraction. Using high-density ALS data from Dublin, Ireland, this fully automatic workflow was able to generate a F-score close to 95{\%} for pavement and sidewalk identification with a resolution of 20 cm and better than 80{\%} for road marking detection.",
keywords = "Airborne laser scanning, Pavements classification, Point cloud segmentation, Urban modelling",
author = "Mario Soil{\'a}n and Linh Truong-Hong and Bel{\'e}n Riveiro and Debra Laefer",
year = "2018",
doi = "10.1016/j.jag.2017.09.010",
language = "English (US)",
volume = "64",
pages = "226--236",
journal = "International Journal of Applied Earth Observation and Geoinformation",
issn = "1569-8432",
publisher = "Elsevier",

}

TY - JOUR

T1 - Automatic extraction of road features in urban environments using dense ALS data

AU - Soilán, Mario

AU - Truong-Hong, Linh

AU - Riveiro, Belén

AU - Laefer, Debra

PY - 2018

Y1 - 2018

N2 - This paper describes a methodology that automatically extracts semantic information from urban ALS data for urban parameterization and road network definition. First, building façades are segmented from the ground surface by combining knowledge-based information with both voxel and raster data. Next, heuristic rules and unsupervised learning are applied to the ground surface data to distinguish sidewalk and pavement points as a means for curb detection. Then radiometric information was employed for road marking extraction. Using high-density ALS data from Dublin, Ireland, this fully automatic workflow was able to generate a F-score close to 95% for pavement and sidewalk identification with a resolution of 20 cm and better than 80% for road marking detection.

AB - This paper describes a methodology that automatically extracts semantic information from urban ALS data for urban parameterization and road network definition. First, building façades are segmented from the ground surface by combining knowledge-based information with both voxel and raster data. Next, heuristic rules and unsupervised learning are applied to the ground surface data to distinguish sidewalk and pavement points as a means for curb detection. Then radiometric information was employed for road marking extraction. Using high-density ALS data from Dublin, Ireland, this fully automatic workflow was able to generate a F-score close to 95% for pavement and sidewalk identification with a resolution of 20 cm and better than 80% for road marking detection.

KW - Airborne laser scanning

KW - Pavements classification

KW - Point cloud segmentation

KW - Urban modelling

UR - http://www.scopus.com/inward/record.url?scp=85032198349&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85032198349&partnerID=8YFLogxK

U2 - 10.1016/j.jag.2017.09.010

DO - 10.1016/j.jag.2017.09.010

M3 - Article

AN - SCOPUS:85032198349

VL - 64

SP - 226

EP - 236

JO - International Journal of Applied Earth Observation and Geoinformation

JF - International Journal of Applied Earth Observation and Geoinformation

SN - 1569-8432

ER -