Automatic Road Extraction from Historical Maps Using Deep Learning Techniques: A Regional Case Study of Turkey in a German World War II Map

被引:28
作者
Ekim, Burak [1 ,2 ]
Sertel, Elif [3 ]
Kabadayi, M. Erdem [2 ]
机构
[1] Istanbul Tech Univ, Inst Informat, Satellite Commun & Remote Sensing Program, TR-34469 Istanbul, Turkey
[2] Koc Univ, Coll Social Sci & Humanities, Dept Hist, TR-34450 Istanbul, Turkey
[3] Istanbul Tech Univ, Geomat Engn Dept, TR-34469 Istanbul, Turkey
基金
欧洲研究理事会;
关键词
convolutional neural networks; road classification; segmentation; deep learning; fully convolutional networks; historical maps; CLASSIFICATION;
D O I
10.3390/ijgi10080492
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
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 Turkei (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_32x4d 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.
引用
收藏
页数:15
相关论文
共 23 条
  • [1] Comparative Research on Deep Learning Approaches for Airplane Detection from Very High-Resolution Satellite Images
    Alganci, Ugur
    Soydas, Mehmet
    Sertel, Elif
    [J]. REMOTE SENSING, 2020, 12 (03)
  • [2] Andrade H.J.A., 2020, IEEE GEOSCI REMOTE S, DOI [10.1109/LGRS.2020.3023170, DOI 10.1109/LGRS.2020.3023170]
  • [3] Automatic Detection of Road Types From the Third Military Mapping Survey of Austria-Hungary Historical Map Series With Deep Convolutional Neural Networks
    Can, Yekta Said
    Gerrits, Petrus Johannes
    Kabadayi, M. Erdem
    [J]. IEEE ACCESS, 2021, 9 : 62847 - 62856
  • [4] Remote Sensing Image Scene Classification Meets Deep Learning: Challenges, Methods, Benchmarks, and Opportunities
    Cheng, Gong
    Xie, Xingxing
    Han, Junwei
    Guo, Lei
    Xia, Gui-Song
    [J]. IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, 2020, 13 : 3735 - 3756
  • [5] Chiang Y.-Y., 2020, SPRINGER BRIEFS GEOG
  • [6] A Survey of Digital Map Processing Techniques
    Chiang, Yao-Yi
    Leyk, Stefan
    Knoblock, Craig A.
    [J]. ACM COMPUTING SURVEYS, 2014, 47 (01)
  • [7] A general approach for extracting road vector data from raster maps
    Chiang, Yao-Yi
    Knoblock, Craig A.
    [J]. INTERNATIONAL JOURNAL ON DOCUMENT ANALYSIS AND RECOGNITION, 2013, 16 (01) : 55 - 81
  • [8] Accuracy assessment and validation of remotely sensed and other spatial information
    Congalton, RG
    [J]. INTERNATIONAL JOURNAL OF WILDLAND FIRE, 2001, 10 (3-4) : 321 - 328
  • [9] Harshness in image classification accuracy assessment
    Foody, Giles M.
    [J]. INTERNATIONAL JOURNAL OF REMOTE SENSING, 2008, 29 (11) : 3137 - 3158
  • [10] Aligning archive maps and extracting footprints for analysis of historic urban environments
    Laycock, S. D.
    Brown, P. G.
    Laycock, R. G.
    Day, A. M.
    [J]. COMPUTERS & GRAPHICS-UK, 2011, 35 (02): : 242 - 249