Automatic road extraction from historical maps using deep learning techniques: A regional case study of Turkey in a German world war II map

Burak Ekim, Elif Sertel*, M. Erdem Kabadayı

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

32 Citations (Scopus)

Abstract

Scanned historical maps are available from different sources in various scales and contents. Automatic geographical feature extraction from these historical maps is an essential task to derive valuable spatial information on the characteristics and distribution of transportation infrastructures and settlements and to conduct quantitative and geometrical analysis. In this research, we used the Deutsche Heereskarte 1:200,000 Türkei (DHK 200 Turkey) maps as the base geoinformation source to construct the past transportation networks using the deep learning approach. Five different road types were digitized and labeled to be used as inputs for the proposed deep learning-based segmentation approach. We adapted U-Net++ and ResneXt50_32×4d architectures to produce multi-class segmentation masks and perform feature extraction to determine various road types accurately. We achieved remarkable results, with 98.73% overall accuracy, 41.99% intersection of union, and 46.61% F1 score values. The proposed method can be implemented in DHK maps of different countries to automatically extract different road types and used for transfer learning of different historical maps.

Original languageEnglish
Article number492
JournalISPRS International Journal of Geo-Information
Volume10
Issue number8
DOIs
Publication statusPublished - Aug 2021

Bibliographical note

Publisher Copyright:
© 2021 by the authors. Licensee MDPI, Basel, Switzerland.

Funding

Funding: This work was supported by the European Research Council (ERC) project “Industrialisation and Urban Growth from the mid-nineteenth century Ottoman Empire to Contemporary Turkey in a Comparative Perspective, 1850–2000” under the European Union’s Horizon 2020 research and innovation program Grant Agreement No. 679097, acronym UrbanOccupationsOETR. M. Erdem Kabadayı is the principal investigator of UrbanOccupationsOETR. This work was supported by the European Research Council (ERC) project ?Industrialisa-tion and Urban Growth from the mid-nineteenth century Ottoman Empire to Contemporary Turkey in a Comparative Perspective, 1850?2000? under the European Union?s Horizon 2020 research and innovation program Grant Agreement No. 679097, acronym UrbanOccupationsOETR. M. Erdem Kabaday? is the principal investigator of UrbanOccupationsOETR. We sincerely thank Piet Gerrits, a member of UrbanOccupationsOETR, for constructing and maintaining our geospatial database and graphical user interface, with which other members of the project vectorized sheets of the DHK 200 Turkey. We are also grateful to Thomas Knoll, the Head Archivist of the Cartography Department/Historical Map Archive of the Austrian Federal Office of Metrology and Surveying, for his assistance in obtaining the digital copies of the DHK 200 Turkey.

FundersFunder number
Thomas Knoll
Horizon 2020 Framework Programme679097
European Research Council

    Keywords

    • Convolutional neural networks
    • Deep learning
    • Fully convolutional networks
    • Historical maps
    • Road classification
    • Segmentation

    Fingerprint

    Dive into the research topics of 'Automatic road extraction from historical maps using deep learning techniques: A regional case study of Turkey in a German world war II map'. Together they form a unique fingerprint.

    Cite this