Road network extraction and intersection detection from aerial images by tracking road footprints

Jiuxiang Hu, Anshuman Razdan, John C. Femiani, Ming Cui, Peter Wonka

Research output: Contribution to journalArticle

220 Citations (Scopus)

Abstract

In this paper, a new two-step approach (detecting and pruning) for automatic extraction of road networks from aerial images is presented. The road detection step is based on shape classification of a local homogeneous region around a pixel. The local homogeneous region is enclosed by a polygon, called the footprint of the pixel. This step involves detecting road footprints, tracking roads, and growing a road tree. We use a spoke wheel operator to obtain the road footprint. We propose an automatic road seeding method based on rectangular approximations to road footprints and a toe-finding algorithm to classify footprints for growing a road tree. The road tree pruning step makes use of a Bayes decision model based on the area-to-perimeter ratio (the A/P ratio) of the footprint to prune the paths that leak into the surroundings. We introduce a lognormal distribution to characterize the conditional probability of A/P ratios of the footprints in the road tree and present an automatic method to estimate the parameters that are related to the Bayes decision model. Results are presented for various aerial images. Evaluation of the extracted road networks using representative aerial images shows that the completeness of our road tracker ranges from 84% to 94%, correctness is above 81%, and quality is from 82% to 92%.

Original languageEnglish (US)
Pages (from-to)4144-4157
Number of pages14
JournalIEEE Transactions on Geoscience and Remote Sensing
Volume45
Issue number12
DOIs
StatePublished - Dec 2007
Externally publishedYes

Fingerprint

footprints
roads
footprint
intersections
Antennas
road
Pixels
Wheels
pruning
pixel
detection
road network
pixels
spokes
polygon
seeding
polygons
completeness
inoculation
wheels

Keywords

  • Bayes decision rule
  • Road extraction
  • Road footprint
  • Road tracking
  • Road tree pruning

ASJC Scopus subject areas

  • Geochemistry and Petrology
  • Geophysics
  • Computers in Earth Sciences
  • Electrical and Electronic Engineering

Cite this

Road network extraction and intersection detection from aerial images by tracking road footprints. / Hu, Jiuxiang; Razdan, Anshuman; Femiani, John C.; Cui, Ming; Wonka, Peter.

In: IEEE Transactions on Geoscience and Remote Sensing, Vol. 45, No. 12, 12.2007, p. 4144-4157.

Research output: Contribution to journalArticle

Hu, Jiuxiang ; Razdan, Anshuman ; Femiani, John C. ; Cui, Ming ; Wonka, Peter. / Road network extraction and intersection detection from aerial images by tracking road footprints. In: IEEE Transactions on Geoscience and Remote Sensing. 2007 ; Vol. 45, No. 12. pp. 4144-4157.
@article{1b6b1ff7b38d4b628624c1bd7d84c490,
title = "Road network extraction and intersection detection from aerial images by tracking road footprints",
abstract = "In this paper, a new two-step approach (detecting and pruning) for automatic extraction of road networks from aerial images is presented. The road detection step is based on shape classification of a local homogeneous region around a pixel. The local homogeneous region is enclosed by a polygon, called the footprint of the pixel. This step involves detecting road footprints, tracking roads, and growing a road tree. We use a spoke wheel operator to obtain the road footprint. We propose an automatic road seeding method based on rectangular approximations to road footprints and a toe-finding algorithm to classify footprints for growing a road tree. The road tree pruning step makes use of a Bayes decision model based on the area-to-perimeter ratio (the A/P ratio) of the footprint to prune the paths that leak into the surroundings. We introduce a lognormal distribution to characterize the conditional probability of A/P ratios of the footprints in the road tree and present an automatic method to estimate the parameters that are related to the Bayes decision model. Results are presented for various aerial images. Evaluation of the extracted road networks using representative aerial images shows that the completeness of our road tracker ranges from 84{\%} to 94{\%}, correctness is above 81{\%}, and quality is from 82{\%} to 92{\%}.",
keywords = "Bayes decision rule, Road extraction, Road footprint, Road tracking, Road tree pruning",
author = "Jiuxiang Hu and Anshuman Razdan and Femiani, {John C.} and Ming Cui and Peter Wonka",
year = "2007",
month = "12",
doi = "10.1109/TGRS.2007.906107",
language = "English (US)",
volume = "45",
pages = "4144--4157",
journal = "IEEE Transactions on Geoscience and Remote Sensing",
issn = "0196-2892",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "12",

}

TY - JOUR

T1 - Road network extraction and intersection detection from aerial images by tracking road footprints

AU - Hu, Jiuxiang

AU - Razdan, Anshuman

AU - Femiani, John C.

AU - Cui, Ming

AU - Wonka, Peter

PY - 2007/12

Y1 - 2007/12

N2 - In this paper, a new two-step approach (detecting and pruning) for automatic extraction of road networks from aerial images is presented. The road detection step is based on shape classification of a local homogeneous region around a pixel. The local homogeneous region is enclosed by a polygon, called the footprint of the pixel. This step involves detecting road footprints, tracking roads, and growing a road tree. We use a spoke wheel operator to obtain the road footprint. We propose an automatic road seeding method based on rectangular approximations to road footprints and a toe-finding algorithm to classify footprints for growing a road tree. The road tree pruning step makes use of a Bayes decision model based on the area-to-perimeter ratio (the A/P ratio) of the footprint to prune the paths that leak into the surroundings. We introduce a lognormal distribution to characterize the conditional probability of A/P ratios of the footprints in the road tree and present an automatic method to estimate the parameters that are related to the Bayes decision model. Results are presented for various aerial images. Evaluation of the extracted road networks using representative aerial images shows that the completeness of our road tracker ranges from 84% to 94%, correctness is above 81%, and quality is from 82% to 92%.

AB - In this paper, a new two-step approach (detecting and pruning) for automatic extraction of road networks from aerial images is presented. The road detection step is based on shape classification of a local homogeneous region around a pixel. The local homogeneous region is enclosed by a polygon, called the footprint of the pixel. This step involves detecting road footprints, tracking roads, and growing a road tree. We use a spoke wheel operator to obtain the road footprint. We propose an automatic road seeding method based on rectangular approximations to road footprints and a toe-finding algorithm to classify footprints for growing a road tree. The road tree pruning step makes use of a Bayes decision model based on the area-to-perimeter ratio (the A/P ratio) of the footprint to prune the paths that leak into the surroundings. We introduce a lognormal distribution to characterize the conditional probability of A/P ratios of the footprints in the road tree and present an automatic method to estimate the parameters that are related to the Bayes decision model. Results are presented for various aerial images. Evaluation of the extracted road networks using representative aerial images shows that the completeness of our road tracker ranges from 84% to 94%, correctness is above 81%, and quality is from 82% to 92%.

KW - Bayes decision rule

KW - Road extraction

KW - Road footprint

KW - Road tracking

KW - Road tree pruning

UR - http://www.scopus.com/inward/record.url?scp=36348958613&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=36348958613&partnerID=8YFLogxK

U2 - 10.1109/TGRS.2007.906107

DO - 10.1109/TGRS.2007.906107

M3 - Article

AN - SCOPUS:36348958613

VL - 45

SP - 4144

EP - 4157

JO - IEEE Transactions on Geoscience and Remote Sensing

JF - IEEE Transactions on Geoscience and Remote Sensing

SN - 0196-2892

IS - 12

ER -