Road detection from aerial imagery

Yucong Lin, Srikanth Saripalli

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

28 Citations (Scopus)

Abstract

We present a fast, robust road detection algorithm for aerial images taken from an Unmanned Aerial Vehicle. A histogram-based adaptive threshold algorithm is used to detect possible road regions in an image. A probabilistic hough transform based line segment detection combined with a clustering method is implemented to further extract the road. The proposed algorithm has been extensively tested on desert and urban images obtained using an Unmanned Aerial Vehicle. Our results indicate that we are able to successfully and accurately detect roads in 97% of the images. We experimentally validated our algorithm on over ten thousand (10,000) aerial images obtained using our UAV. These images consist of intersecting roads, bifurcating roads and roundabouts in various conditions with significant changes in lighting and intensity. Our algorithm is able to successfully detect single roads effectively in almost all the images. It is also able to detect at least one road in over 95% of the images containing bifurcating or intersecting roads.

Original languageEnglish (US)
Title of host publicationProceedings - IEEE International Conference on Robotics and Automation
Pages3588-3593
Number of pages6
DOIs
StatePublished - 2012

Fingerprint

Antennas
Unmanned aerial vehicles (UAV)
Hough transforms
Lighting

ASJC Scopus subject areas

  • Software
  • Artificial Intelligence
  • Control and Systems Engineering
  • Electrical and Electronic Engineering

Cite this

Lin, Y., & Saripalli, S. (2012). Road detection from aerial imagery. In Proceedings - IEEE International Conference on Robotics and Automation (pp. 3588-3593). [6225112] https://doi.org/10.1109/ICRA.2012.6225112

Road detection from aerial imagery. / Lin, Yucong; Saripalli, Srikanth.

Proceedings - IEEE International Conference on Robotics and Automation. 2012. p. 3588-3593 6225112.

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

Lin, Y & Saripalli, S 2012, Road detection from aerial imagery. in Proceedings - IEEE International Conference on Robotics and Automation., 6225112, pp. 3588-3593. https://doi.org/10.1109/ICRA.2012.6225112
Lin Y, Saripalli S. Road detection from aerial imagery. In Proceedings - IEEE International Conference on Robotics and Automation. 2012. p. 3588-3593. 6225112 https://doi.org/10.1109/ICRA.2012.6225112
Lin, Yucong ; Saripalli, Srikanth. / Road detection from aerial imagery. Proceedings - IEEE International Conference on Robotics and Automation. 2012. pp. 3588-3593
@inproceedings{56bc266f1d9044d48a43cb2e2f515ff8,
title = "Road detection from aerial imagery",
abstract = "We present a fast, robust road detection algorithm for aerial images taken from an Unmanned Aerial Vehicle. A histogram-based adaptive threshold algorithm is used to detect possible road regions in an image. A probabilistic hough transform based line segment detection combined with a clustering method is implemented to further extract the road. The proposed algorithm has been extensively tested on desert and urban images obtained using an Unmanned Aerial Vehicle. Our results indicate that we are able to successfully and accurately detect roads in 97{\%} of the images. We experimentally validated our algorithm on over ten thousand (10,000) aerial images obtained using our UAV. These images consist of intersecting roads, bifurcating roads and roundabouts in various conditions with significant changes in lighting and intensity. Our algorithm is able to successfully detect single roads effectively in almost all the images. It is also able to detect at least one road in over 95{\%} of the images containing bifurcating or intersecting roads.",
author = "Yucong Lin and Srikanth Saripalli",
year = "2012",
doi = "10.1109/ICRA.2012.6225112",
language = "English (US)",
isbn = "9781467314039",
pages = "3588--3593",
booktitle = "Proceedings - IEEE International Conference on Robotics and Automation",

}

TY - GEN

T1 - Road detection from aerial imagery

AU - Lin, Yucong

AU - Saripalli, Srikanth

PY - 2012

Y1 - 2012

N2 - We present a fast, robust road detection algorithm for aerial images taken from an Unmanned Aerial Vehicle. A histogram-based adaptive threshold algorithm is used to detect possible road regions in an image. A probabilistic hough transform based line segment detection combined with a clustering method is implemented to further extract the road. The proposed algorithm has been extensively tested on desert and urban images obtained using an Unmanned Aerial Vehicle. Our results indicate that we are able to successfully and accurately detect roads in 97% of the images. We experimentally validated our algorithm on over ten thousand (10,000) aerial images obtained using our UAV. These images consist of intersecting roads, bifurcating roads and roundabouts in various conditions with significant changes in lighting and intensity. Our algorithm is able to successfully detect single roads effectively in almost all the images. It is also able to detect at least one road in over 95% of the images containing bifurcating or intersecting roads.

AB - We present a fast, robust road detection algorithm for aerial images taken from an Unmanned Aerial Vehicle. A histogram-based adaptive threshold algorithm is used to detect possible road regions in an image. A probabilistic hough transform based line segment detection combined with a clustering method is implemented to further extract the road. The proposed algorithm has been extensively tested on desert and urban images obtained using an Unmanned Aerial Vehicle. Our results indicate that we are able to successfully and accurately detect roads in 97% of the images. We experimentally validated our algorithm on over ten thousand (10,000) aerial images obtained using our UAV. These images consist of intersecting roads, bifurcating roads and roundabouts in various conditions with significant changes in lighting and intensity. Our algorithm is able to successfully detect single roads effectively in almost all the images. It is also able to detect at least one road in over 95% of the images containing bifurcating or intersecting roads.

UR - http://www.scopus.com/inward/record.url?scp=84864435928&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84864435928&partnerID=8YFLogxK

U2 - 10.1109/ICRA.2012.6225112

DO - 10.1109/ICRA.2012.6225112

M3 - Conference contribution

AN - SCOPUS:84864435928

SN - 9781467314039

SP - 3588

EP - 3593

BT - Proceedings - IEEE International Conference on Robotics and Automation

ER -