Automated Segmentation of the Walkable Area from Aerial Images for Evacuation Simulation

Fabian Schenk, Matthias Rüther, Horst Bischof

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

Computer-aided evacuation simulation is a very import preliminary step when planning safety measures for major public events. We propose a novel, efficient and fast method to extract the walkable area from highresolution aerial images for the purpose of evacuation simulation. In contrast to previous work, where the authors only extracted streets and roads or worked on indoor scenarios, we present an approach to accurately segment the walkable area of large outdoor areas. For this task we use a sophisticated seeded region growing (SRG) algorithm incorporating the information of digital surface models, true-orthophotos and inclination maps calculated from aerial images. Further, we introduce a new annotation and evaluation scheme especially designed for assessing the segmentation quality of evacuation maps. An extensive qualitative and quantitative evaluation, where we study various combinations of SRG methods and parameter settings by the example of different real-world scenarios, shows the feasibility of our approach.
LanguageEnglish
Title of host publication Proceedings of the 2nd International Conference on Geographical Information Systems Theory, Applications and Management (GISTAM), 2016
Pages125-135
Number of pages11
Volume1
EditionGISTAM
ISBN (Electronic)978-989-758-188-5
StatusPublished - 2016
EventInternational Conference on Geographical Information Systems Theory, Applications and Management - Rome, Rome, Italy
Duration: 25 Apr 2016 → 27 Apr 2016
Conference number: 2
http://gistam.org/

Conference

ConferenceInternational Conference on Geographical Information Systems Theory, Applications and Management
Abbreviated titleGISTAM
CountryItaly
CityRome
Period25/04/16 → 27/04/16
Internet address

Fingerprint

Antennas
Planning

Keywords

  • Aerial Images
  • Walkable Area Segmentation
  • Evacuation Simulation

Cite this

Schenk, F., Rüther, M., & Bischof, H. (2016). Automated Segmentation of the Walkable Area from Aerial Images for Evacuation Simulation. In Proceedings of the 2nd International Conference on Geographical Information Systems Theory, Applications and Management (GISTAM), 2016 (GISTAM ed., Vol. 1, pp. 125-135)

Automated Segmentation of the Walkable Area from Aerial Images for Evacuation Simulation. / Schenk, Fabian; Rüther, Matthias; Bischof, Horst.

Proceedings of the 2nd International Conference on Geographical Information Systems Theory, Applications and Management (GISTAM), 2016. Vol. 1 GISTAM. ed. 2016. p. 125-135.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Schenk, F, Rüther, M & Bischof, H 2016, Automated Segmentation of the Walkable Area from Aerial Images for Evacuation Simulation. in Proceedings of the 2nd International Conference on Geographical Information Systems Theory, Applications and Management (GISTAM), 2016. GISTAM edn, vol. 1, pp. 125-135, International Conference on Geographical Information Systems Theory, Applications and Management, Rome, Italy, 25/04/16.
Schenk F, Rüther M, Bischof H. Automated Segmentation of the Walkable Area from Aerial Images for Evacuation Simulation. In Proceedings of the 2nd International Conference on Geographical Information Systems Theory, Applications and Management (GISTAM), 2016. GISTAM ed. Vol. 1. 2016. p. 125-135.
Schenk, Fabian ; Rüther, Matthias ; Bischof, Horst. / Automated Segmentation of the Walkable Area from Aerial Images for Evacuation Simulation. Proceedings of the 2nd International Conference on Geographical Information Systems Theory, Applications and Management (GISTAM), 2016. Vol. 1 GISTAM. ed. 2016. pp. 125-135
@inproceedings{f2025b4621974df99b6b16e063128490,
title = "Automated Segmentation of the Walkable Area from Aerial Images for Evacuation Simulation",
abstract = "Computer-aided evacuation simulation is a very import preliminary step when planning safety measures for major public events. We propose a novel, efficient and fast method to extract the walkable area from highresolution aerial images for the purpose of evacuation simulation. In contrast to previous work, where the authors only extracted streets and roads or worked on indoor scenarios, we present an approach to accurately segment the walkable area of large outdoor areas. For this task we use a sophisticated seeded region growing (SRG) algorithm incorporating the information of digital surface models, true-orthophotos and inclination maps calculated from aerial images. Further, we introduce a new annotation and evaluation scheme especially designed for assessing the segmentation quality of evacuation maps. An extensive qualitative and quantitative evaluation, where we study various combinations of SRG methods and parameter settings by the example of different real-world scenarios, shows the feasibility of our approach.",
keywords = "Aerial Images, Walkable Area Segmentation, Evacuation Simulation",
author = "Fabian Schenk and Matthias R{\"u}ther and Horst Bischof",
year = "2016",
language = "English",
volume = "1",
pages = "125--135",
booktitle = "Proceedings of the 2nd International Conference on Geographical Information Systems Theory, Applications and Management (GISTAM), 2016",
edition = "GISTAM",

}

TY - GEN

T1 - Automated Segmentation of the Walkable Area from Aerial Images for Evacuation Simulation

AU - Schenk,Fabian

AU - Rüther,Matthias

AU - Bischof,Horst

PY - 2016

Y1 - 2016

N2 - Computer-aided evacuation simulation is a very import preliminary step when planning safety measures for major public events. We propose a novel, efficient and fast method to extract the walkable area from highresolution aerial images for the purpose of evacuation simulation. In contrast to previous work, where the authors only extracted streets and roads or worked on indoor scenarios, we present an approach to accurately segment the walkable area of large outdoor areas. For this task we use a sophisticated seeded region growing (SRG) algorithm incorporating the information of digital surface models, true-orthophotos and inclination maps calculated from aerial images. Further, we introduce a new annotation and evaluation scheme especially designed for assessing the segmentation quality of evacuation maps. An extensive qualitative and quantitative evaluation, where we study various combinations of SRG methods and parameter settings by the example of different real-world scenarios, shows the feasibility of our approach.

AB - Computer-aided evacuation simulation is a very import preliminary step when planning safety measures for major public events. We propose a novel, efficient and fast method to extract the walkable area from highresolution aerial images for the purpose of evacuation simulation. In contrast to previous work, where the authors only extracted streets and roads or worked on indoor scenarios, we present an approach to accurately segment the walkable area of large outdoor areas. For this task we use a sophisticated seeded region growing (SRG) algorithm incorporating the information of digital surface models, true-orthophotos and inclination maps calculated from aerial images. Further, we introduce a new annotation and evaluation scheme especially designed for assessing the segmentation quality of evacuation maps. An extensive qualitative and quantitative evaluation, where we study various combinations of SRG methods and parameter settings by the example of different real-world scenarios, shows the feasibility of our approach.

KW - Aerial Images

KW - Walkable Area Segmentation

KW - Evacuation Simulation

M3 - Conference contribution

VL - 1

SP - 125

EP - 135

BT - Proceedings of the 2nd International Conference on Geographical Information Systems Theory, Applications and Management (GISTAM), 2016

ER -

Access to Document