Aerial laser scanning and imagery data fusion for road detection in city scale

Anh Vu Vo, Linh Truong-Hong, Debra Laefer

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This paper presents a workflow including a novel algorithm for road detection from dense LiDAR fused with high-resolution aerial imagery data. Using a supervised machine learning approach point clouds are firstly classified into one of three groups: building, ground, or unassigned. Ground points are further processed by a novel algorithm to extract a road network. The algorithm exploits the high variance of slope and height of the point data in the direction orthogonal to the road boundaries. Applying the proposed approach on a 40 million point dataset successfully extracted a complex road network with an F-measure of 76.9%.

Original languageEnglish (US)
Title of host publication2015 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2015 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages4177-4180
Number of pages4
Volume2015-November
ISBN (Electronic)9781479979295
DOIs
StatePublished - Nov 10 2015
EventIEEE International Geoscience and Remote Sensing Symposium, IGARSS 2015 - Milan, Italy
Duration: Jul 26 2015Jul 31 2015

Other

OtherIEEE International Geoscience and Remote Sensing Symposium, IGARSS 2015
CountryItaly
CityMilan
Period7/26/157/31/15

Fingerprint

Data fusion
imagery
laser
Antennas
road
Scanning
Lasers
Learning systems
detection
city
road network

Keywords

  • aerial imagery
  • aerial laser scanning
  • data fusion
  • hybrid indexing
  • machine learning
  • road detection

ASJC Scopus subject areas

  • Computer Science Applications
  • Earth and Planetary Sciences(all)

Cite this

Vo, A. V., Truong-Hong, L., & Laefer, D. (2015). Aerial laser scanning and imagery data fusion for road detection in city scale. In 2015 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2015 - Proceedings (Vol. 2015-November, pp. 4177-4180). [7326746] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IGARSS.2015.7326746

Aerial laser scanning and imagery data fusion for road detection in city scale. / Vo, Anh Vu; Truong-Hong, Linh; Laefer, Debra.

2015 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2015 - Proceedings. Vol. 2015-November Institute of Electrical and Electronics Engineers Inc., 2015. p. 4177-4180 7326746.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Vo, AV, Truong-Hong, L & Laefer, D 2015, Aerial laser scanning and imagery data fusion for road detection in city scale. in 2015 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2015 - Proceedings. vol. 2015-November, 7326746, Institute of Electrical and Electronics Engineers Inc., pp. 4177-4180, IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2015, Milan, Italy, 7/26/15. https://doi.org/10.1109/IGARSS.2015.7326746
Vo AV, Truong-Hong L, Laefer D. Aerial laser scanning and imagery data fusion for road detection in city scale. In 2015 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2015 - Proceedings. Vol. 2015-November. Institute of Electrical and Electronics Engineers Inc. 2015. p. 4177-4180. 7326746 https://doi.org/10.1109/IGARSS.2015.7326746
Vo, Anh Vu ; Truong-Hong, Linh ; Laefer, Debra. / Aerial laser scanning and imagery data fusion for road detection in city scale. 2015 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2015 - Proceedings. Vol. 2015-November Institute of Electrical and Electronics Engineers Inc., 2015. pp. 4177-4180
@inproceedings{68a8349d3f1b41ef91ae7143abbb6b2a,
title = "Aerial laser scanning and imagery data fusion for road detection in city scale",
abstract = "This paper presents a workflow including a novel algorithm for road detection from dense LiDAR fused with high-resolution aerial imagery data. Using a supervised machine learning approach point clouds are firstly classified into one of three groups: building, ground, or unassigned. Ground points are further processed by a novel algorithm to extract a road network. The algorithm exploits the high variance of slope and height of the point data in the direction orthogonal to the road boundaries. Applying the proposed approach on a 40 million point dataset successfully extracted a complex road network with an F-measure of 76.9{\%}.",
keywords = "aerial imagery, aerial laser scanning, data fusion, hybrid indexing, machine learning, road detection",
author = "Vo, {Anh Vu} and Linh Truong-Hong and Debra Laefer",
year = "2015",
month = "11",
day = "10",
doi = "10.1109/IGARSS.2015.7326746",
language = "English (US)",
volume = "2015-November",
pages = "4177--4180",
booktitle = "2015 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2015 - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
address = "United States",

}

TY - GEN

T1 - Aerial laser scanning and imagery data fusion for road detection in city scale

AU - Vo, Anh Vu

AU - Truong-Hong, Linh

AU - Laefer, Debra

PY - 2015/11/10

Y1 - 2015/11/10

N2 - This paper presents a workflow including a novel algorithm for road detection from dense LiDAR fused with high-resolution aerial imagery data. Using a supervised machine learning approach point clouds are firstly classified into one of three groups: building, ground, or unassigned. Ground points are further processed by a novel algorithm to extract a road network. The algorithm exploits the high variance of slope and height of the point data in the direction orthogonal to the road boundaries. Applying the proposed approach on a 40 million point dataset successfully extracted a complex road network with an F-measure of 76.9%.

AB - This paper presents a workflow including a novel algorithm for road detection from dense LiDAR fused with high-resolution aerial imagery data. Using a supervised machine learning approach point clouds are firstly classified into one of three groups: building, ground, or unassigned. Ground points are further processed by a novel algorithm to extract a road network. The algorithm exploits the high variance of slope and height of the point data in the direction orthogonal to the road boundaries. Applying the proposed approach on a 40 million point dataset successfully extracted a complex road network with an F-measure of 76.9%.

KW - aerial imagery

KW - aerial laser scanning

KW - data fusion

KW - hybrid indexing

KW - machine learning

KW - road detection

UR - http://www.scopus.com/inward/record.url?scp=84962556656&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84962556656&partnerID=8YFLogxK

U2 - 10.1109/IGARSS.2015.7326746

DO - 10.1109/IGARSS.2015.7326746

M3 - Conference contribution

VL - 2015-November

SP - 4177

EP - 4180

BT - 2015 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2015 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

ER -