Orientation-selective building detection in aerial images

Andrea Manno-Kovacs, T. Szirányi

Research output: Contribution to journalArticle

23 Citations (Scopus)

Abstract

This paper introduces a novel aerial building detection method based on region orientation as a new feature, which is used in various steps throughout the presented framework. As building objects are expected to be connected with each other on a regional level, exploiting the main orientation obtained from the local gradient analysis provides further information for detection purposes. The orientation information is applied for an improved edge map design, which is integrated with classical features like shadow and color. Moreover, an orthogonality check is introduced for finding building candidates, and their final shapes defined by the Chan-Vese active contour algorithm are refined based on the orientation information, resulting in smooth and accurate building outlines. The proposed framework is evaluated on multiple data sets, including aerial and high resolution optical satellite images, and compared to six state-of-the-art methods in both object and pixel level evaluation, proving the algorithm's efficiency.

Original languageEnglish
Pages (from-to)94-112
Number of pages19
JournalISPRS Journal of Photogrammetry and Remote Sensing
Volume108
DOIs
Publication statusPublished - Oct 1 2015

Fingerprint

Antennas
Pixels
Satellites
Color
gradient analysis
orthogonality
detection method
pixel
candidacy
pixels
color
efficiency
gradients
detection
evaluation
high resolution
satellite image
state of the art
method

Keywords

  • Active contour
  • Building detection
  • Modified Harris for edges and corners
  • Orientation selectivity

ASJC Scopus subject areas

  • Atomic and Molecular Physics, and Optics
  • Computers in Earth Sciences
  • Engineering (miscellaneous)
  • Geography, Planning and Development
  • Computer Science Applications

Cite this

Orientation-selective building detection in aerial images. / Manno-Kovacs, Andrea; Szirányi, T.

In: ISPRS Journal of Photogrammetry and Remote Sensing, Vol. 108, 01.10.2015, p. 94-112.

Research output: Contribution to journalArticle

@article{64664ef9b59d4dd590cf88c840695346,
title = "Orientation-selective building detection in aerial images",
abstract = "This paper introduces a novel aerial building detection method based on region orientation as a new feature, which is used in various steps throughout the presented framework. As building objects are expected to be connected with each other on a regional level, exploiting the main orientation obtained from the local gradient analysis provides further information for detection purposes. The orientation information is applied for an improved edge map design, which is integrated with classical features like shadow and color. Moreover, an orthogonality check is introduced for finding building candidates, and their final shapes defined by the Chan-Vese active contour algorithm are refined based on the orientation information, resulting in smooth and accurate building outlines. The proposed framework is evaluated on multiple data sets, including aerial and high resolution optical satellite images, and compared to six state-of-the-art methods in both object and pixel level evaluation, proving the algorithm's efficiency.",
keywords = "Active contour, Building detection, Modified Harris for edges and corners, Orientation selectivity",
author = "Andrea Manno-Kovacs and T. Szir{\'a}nyi",
year = "2015",
month = "10",
day = "1",
doi = "10.1016/j.isprsjprs.2015.06.007",
language = "English",
volume = "108",
pages = "94--112",
journal = "ISPRS Journal of Photogrammetry and Remote Sensing",
issn = "0924-2716",
publisher = "Elsevier",

}

TY - JOUR

T1 - Orientation-selective building detection in aerial images

AU - Manno-Kovacs, Andrea

AU - Szirányi, T.

PY - 2015/10/1

Y1 - 2015/10/1

N2 - This paper introduces a novel aerial building detection method based on region orientation as a new feature, which is used in various steps throughout the presented framework. As building objects are expected to be connected with each other on a regional level, exploiting the main orientation obtained from the local gradient analysis provides further information for detection purposes. The orientation information is applied for an improved edge map design, which is integrated with classical features like shadow and color. Moreover, an orthogonality check is introduced for finding building candidates, and their final shapes defined by the Chan-Vese active contour algorithm are refined based on the orientation information, resulting in smooth and accurate building outlines. The proposed framework is evaluated on multiple data sets, including aerial and high resolution optical satellite images, and compared to six state-of-the-art methods in both object and pixel level evaluation, proving the algorithm's efficiency.

AB - This paper introduces a novel aerial building detection method based on region orientation as a new feature, which is used in various steps throughout the presented framework. As building objects are expected to be connected with each other on a regional level, exploiting the main orientation obtained from the local gradient analysis provides further information for detection purposes. The orientation information is applied for an improved edge map design, which is integrated with classical features like shadow and color. Moreover, an orthogonality check is introduced for finding building candidates, and their final shapes defined by the Chan-Vese active contour algorithm are refined based on the orientation information, resulting in smooth and accurate building outlines. The proposed framework is evaluated on multiple data sets, including aerial and high resolution optical satellite images, and compared to six state-of-the-art methods in both object and pixel level evaluation, proving the algorithm's efficiency.

KW - Active contour

KW - Building detection

KW - Modified Harris for edges and corners

KW - Orientation selectivity

UR - http://www.scopus.com/inward/record.url?scp=84937544617&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84937544617&partnerID=8YFLogxK

U2 - 10.1016/j.isprsjprs.2015.06.007

DO - 10.1016/j.isprsjprs.2015.06.007

M3 - Article

AN - SCOPUS:84937544617

VL - 108

SP - 94

EP - 112

JO - ISPRS Journal of Photogrammetry and Remote Sensing

JF - ISPRS Journal of Photogrammetry and Remote Sensing

SN - 0924-2716

ER -