Multidirectional building detection in aerial images without shape templates

Andrea Manno-Kovacs, T. Szirányi

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

5 Citations (Scopus)

Abstract

The aim of this paper is to exploit orientation information of an urban area for extracting building contours without shape templates. Unlike using shape templates, these given contours describe more variability and reveal the fine details of the building outlines, resulting in a more accurate detection process, which is beneficial for many tasks, like map updating and city planning. According to our assumption, orientation of the closely located buildings is coherent, it is related to the road network, therefore adaptation of this information can lead to more efficient building detection results. The introduced method first extracts feature points for representing the urban area. Orientation information in the feature point neighborhoods is analyzed to define main orientations. Based on orientation information, the urban area is classified into different directional clusters. The edges of the classified building groups are then emphasized with shearlet based edge detection method, which is able to detect edges only in the main directions, resulting in an efficient connectivity map. In the last step, with the fusion of the feature points and connectivity map, building contours are detected with a non-parametric active contour method.

Original languageEnglish
Title of host publicationInternational Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives
PublisherInternational Society for Photogrammetry and Remote Sensing
Pages227-232
Number of pages6
Volume40
Edition1W1
Publication statusPublished - 2013
EventISPRS Hannover Workshop 2013 - Hannover, Germany
Duration: May 21 2013May 24 2013

Other

OtherISPRS Hannover Workshop 2013
CountryGermany
CityHannover
Period5/21/135/24/13

Fingerprint

Antennas
urban area
Urban planning
Edge detection
connectivity
Fusion reactions
road network
detection method
building
detection
planning
Group
method

Keywords

  • Aerial image detection
  • Building detection
  • Directional classification
  • Feature extraction

ASJC Scopus subject areas

  • Information Systems
  • Geography, Planning and Development

Cite this

Manno-Kovacs, A., & Szirányi, T. (2013). Multidirectional building detection in aerial images without shape templates. In International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives (1W1 ed., Vol. 40, pp. 227-232). International Society for Photogrammetry and Remote Sensing.

Multidirectional building detection in aerial images without shape templates. / Manno-Kovacs, Andrea; Szirányi, T.

International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives. Vol. 40 1W1. ed. International Society for Photogrammetry and Remote Sensing, 2013. p. 227-232.

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

Manno-Kovacs, A & Szirányi, T 2013, Multidirectional building detection in aerial images without shape templates. in International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives. 1W1 edn, vol. 40, International Society for Photogrammetry and Remote Sensing, pp. 227-232, ISPRS Hannover Workshop 2013, Hannover, Germany, 5/21/13.
Manno-Kovacs A, Szirányi T. Multidirectional building detection in aerial images without shape templates. In International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives. 1W1 ed. Vol. 40. International Society for Photogrammetry and Remote Sensing. 2013. p. 227-232
Manno-Kovacs, Andrea ; Szirányi, T. / Multidirectional building detection in aerial images without shape templates. International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives. Vol. 40 1W1. ed. International Society for Photogrammetry and Remote Sensing, 2013. pp. 227-232
@inproceedings{55fddc67206e4c9681b13af6a3399d3c,
title = "Multidirectional building detection in aerial images without shape templates",
abstract = "The aim of this paper is to exploit orientation information of an urban area for extracting building contours without shape templates. Unlike using shape templates, these given contours describe more variability and reveal the fine details of the building outlines, resulting in a more accurate detection process, which is beneficial for many tasks, like map updating and city planning. According to our assumption, orientation of the closely located buildings is coherent, it is related to the road network, therefore adaptation of this information can lead to more efficient building detection results. The introduced method first extracts feature points for representing the urban area. Orientation information in the feature point neighborhoods is analyzed to define main orientations. Based on orientation information, the urban area is classified into different directional clusters. The edges of the classified building groups are then emphasized with shearlet based edge detection method, which is able to detect edges only in the main directions, resulting in an efficient connectivity map. In the last step, with the fusion of the feature points and connectivity map, building contours are detected with a non-parametric active contour method.",
keywords = "Aerial image detection, Building detection, Directional classification, Feature extraction",
author = "Andrea Manno-Kovacs and T. Szir{\'a}nyi",
year = "2013",
language = "English",
volume = "40",
pages = "227--232",
booktitle = "International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives",
publisher = "International Society for Photogrammetry and Remote Sensing",
edition = "1W1",

}

TY - GEN

T1 - Multidirectional building detection in aerial images without shape templates

AU - Manno-Kovacs, Andrea

AU - Szirányi, T.

PY - 2013

Y1 - 2013

N2 - The aim of this paper is to exploit orientation information of an urban area for extracting building contours without shape templates. Unlike using shape templates, these given contours describe more variability and reveal the fine details of the building outlines, resulting in a more accurate detection process, which is beneficial for many tasks, like map updating and city planning. According to our assumption, orientation of the closely located buildings is coherent, it is related to the road network, therefore adaptation of this information can lead to more efficient building detection results. The introduced method first extracts feature points for representing the urban area. Orientation information in the feature point neighborhoods is analyzed to define main orientations. Based on orientation information, the urban area is classified into different directional clusters. The edges of the classified building groups are then emphasized with shearlet based edge detection method, which is able to detect edges only in the main directions, resulting in an efficient connectivity map. In the last step, with the fusion of the feature points and connectivity map, building contours are detected with a non-parametric active contour method.

AB - The aim of this paper is to exploit orientation information of an urban area for extracting building contours without shape templates. Unlike using shape templates, these given contours describe more variability and reveal the fine details of the building outlines, resulting in a more accurate detection process, which is beneficial for many tasks, like map updating and city planning. According to our assumption, orientation of the closely located buildings is coherent, it is related to the road network, therefore adaptation of this information can lead to more efficient building detection results. The introduced method first extracts feature points for representing the urban area. Orientation information in the feature point neighborhoods is analyzed to define main orientations. Based on orientation information, the urban area is classified into different directional clusters. The edges of the classified building groups are then emphasized with shearlet based edge detection method, which is able to detect edges only in the main directions, resulting in an efficient connectivity map. In the last step, with the fusion of the feature points and connectivity map, building contours are detected with a non-parametric active contour method.

KW - Aerial image detection

KW - Building detection

KW - Directional classification

KW - Feature extraction

UR - http://www.scopus.com/inward/record.url?scp=84924740616&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84924740616&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84924740616

VL - 40

SP - 227

EP - 232

BT - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives

PB - International Society for Photogrammetry and Remote Sensing

ER -