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

Fabian Schenk, Matthias Rüther, Horst Bischof

Publikation: Beitrag in Buch/Bericht/KonferenzbandBeitrag in einem KonferenzbandForschungBegutachtung

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.
Originalspracheenglisch
Titel Proceedings of the 2nd International Conference on Geographical Information Systems Theory, Applications and Management (GISTAM), 2016
Seiten125-135
Seitenumfang11
Band1
AuflageGISTAM
ISBN (elektronisch)978-989-758-188-5
PublikationsstatusVeröffentlicht - 2016
VeranstaltungInternational Conference on Geographical Information Systems Theory, Applications and Management - Rome, Rome, Italien
Dauer: 25 Apr 201627 Apr 2016
Konferenznummer: 2
http://gistam.org/

Konferenz

KonferenzInternational Conference on Geographical Information Systems Theory, Applications and Management
KurztitelGISTAM
LandItalien
OrtRome
Zeitraum25/04/1627/04/16
Internetadresse

Fingerprint

Antennas
Planning

Schlagwörter

    Dies zitieren

    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 Aufl., Band 1, S. 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. Band 1 GISTAM. Aufl. 2016. S. 125-135.

    Publikation: Beitrag in Buch/Bericht/KonferenzbandBeitrag in einem KonferenzbandForschungBegutachtung

    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 Aufl., Bd. 1, S. 125-135, Rome, Italien, 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 Aufl. Band 1. 2016. S. 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. Band 1 GISTAM. Aufl. 2016. S. 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 -