Skip to main content
SpringerLink
Log in

Training Deep Learning Models for Geographic Feature Recognition from Historical Maps

  • Chapter
  • First Online:
Using Historical Maps in Scientific Studies

Part of the book series: SpringerBriefs in Geography ((BRIEFSGEOGRAPHY))

Abstract

Historical map scans contain valuable information (e.g., historical locations of roads, buildings) enabling the analyses that require long-term historical data of the natural and built environment. Many online archives now provide public access to a large number of historical map scans, such as the historical USGS (United States Geological Survey) topographic archive and the historical Ordnance Survey maps in the United Kingdom. Efficiently extracting information from these map scans remains a challenging task, which is typically achieved by manually digitizing the map content. In computer vision, the process of detecting and extracting the precise locations of objects from images is called semantic segmentation. Semantic segmentation processes take an image as input and classify each pixel of the image to an object class of interest. Machine learning models for semantic segmentation have been progressing rapidly with the emergence of Deep Convolutional Neural Networks (DCNNs or CNNs). A key factor for the success of CNNs is the wide availability of large amounts of (labeled) training data, but these training data are mostly for daily images not for historical (or any) maps. Today, generating training data needs a significant amount of manual labor that is often impractical for the application of historical map processing. One solution to the problem of training data scarcity is by transferring knowledge learned from a domain with a sufficient amount of labeled data to another domain lacking labeled data (i.e., transfer learning). This chapter presents an overview of deep-learning semantic segmentation models and discusses their strengths and weaknesses concerning geographic feature recognition from historical map scans. The chapter also examines a number of transfer learning strategies that can reuse the state-of-the-art CNN models trained from the publicly available training datasets for the task of recognizing geographic features from historical maps. Finally, this chapter presents a comprehensive experiment for extracting railroad features from USGS historical topographic maps as a case study.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
eBook
USD 16.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 16.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Notes

  1. 1.

    In this chapter, the term “historical maps” refer to the professionally prepared maps by cartographers and typically published by government mapping agencies. The term “map scan” refers to scanned images of maps.

  2. 2.

    http://www.image-net.org.

  3. 3.

    In this chapter, extracting or recognizing geographic features refers to the process of annotating each pixel in a map scan with a class label of a type of geographic feature (e.g., roads, text labels, or buildings).

  4. 4.

    http://host.robots.ox.ac.uk/pascal/VOC/index.html.

  5. 5.

    The reader is referred to [Gar+17] for a comprehensive review on semantic segmentation models.

  6. 6.

    Note that using the centerlines with a buffer helps generate approximated pixel-wise annotations of the railroad symbols efficiently, and manually annotating each railroad pixels in the map is impractical even for one map scan.

  7. 7.

    Keras is a high level deep learning Python library (https://keras.io) Currently, Keras provides a number of pre-trained CNN models (using ImageNet) for image classification, including VGG16, VGG19, ResNet, ResNetV2, ResNeXt, GoogLeNet, MobileNet, DenseNet, and NASNet.

  8. 8.

    Figures A.1, A.2, and A.3 in the appendix show the full size results.

  9. 9.

    The blue pixels are at the railroad locations in the map since they are correctly extracted railroad pixels.

  10. 10.

    https://github.com/hszhao/PSPNet/.

  11. 11.

    Figure 4.16 shows the shallow, middle, and deep layers in the backbone CNN of PSPNet. The red, green, and blue boxes represent shallow, middle, and deep layers, respectively.

  12. 12.

    Figures A.4, A.5, A.6, A.7, A.8, A.9, A.10, A.11, and A.12 in the appendix show the full size results.

References

  1. N. Audebert, B. Le Saux, S. Lefèvre, Semantic segmentation of earth observation data using multimodal and multi-scale deep networks, in: Computer Vision – ACCV 2016, ed. by S.-H. Lai, V. Lepetit, K. Nishino, Y. Sato (Springer, Cham, 2017), pp. 180–196. ISBN: 978-3-319-54181-5

    Chapter  Google Scholar 

  2. V.E. Balas, S.S. Roy, D. Sharma, P. Samui (eds.), Handbook of Deep Learning Applications (Springer, Berlin, 2019). ISBN: 978-3-030-11478-7. https://doi.org/10.1007/978-3-030-11479-4

    Google Scholar 

  3. V. Badrinarayanan, A. Kendall, R. Cipolla, Segnet: a deep convolutional encoder-decoder architecture for image segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 39(12), 2481–2495 (2017)

    Article  Google Scholar 

  4. P. Bilinski, V. Prisacariu, Dense decoder shortcut connections for single-pass semantic segmentation, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2018), pp. 6596–6605

    Google Scholar 

  5. G.J. Brostow, J. Shotton, J. Fauqueur, R. Cipolla, Segmentation and recognition using structure from motion point clouds, in European Conference on Computer Vision (Springer, Berlin, 2008), pp. 44–57

    Google Scholar 

  6. G. Bertasius, J. Shi, L. Torresani, High-for-low and low-for-high: efficient boundary detection from deep object features and its applications to high-level vision, in Proceedings of the IEEE International Conference on Computer Vision (2015), pp. 504–512

    Google Scholar 

  7. M. Castelluccio, G. Poggi, C. Sansone, L. Verdoliva, Land use classification in remote sensing images by convolutional neural networks. arXiv: 1508.00092 (2015)

    Google Scholar 

  8. A. Chaurasia, E. Culurciello, LinkNet: exploiting encoder representations for efficient semantic segmentation, in 2017 IEEE Visual Communications and Image Processing, VCIP 2017 (St. Petersburg, 2017), pp. 1–4

    Google Scholar 

  9. L. Chen, G. Papandreou, F. Schroff, H. Adam, Rethinking atrous convolution for semantic image segmentation. arXiv: 1706.05587 (2017)

    Google Scholar 

  10. Y.-Y. Chiang, C. A. Knoblock, A general approach for extracting road vector data from raster maps. Int. J. Doc. Anal. Recognit. 16(1), 55–81 (2013). https://doi.org/10.1007/s10032-011-0177-1

    Article  Google Scholar 

  11. Y.-Y. Chiang, S. Leyk, C.A. Knoblock, A survey of digital map processing techniques. ACM Comput. Surveys 47(1), 1–44 (2014). ISSN: 0360-0300. https://doi.org/10.1145/2557423

    Article  Google Scholar 

  12. D. Bin, B. Ding, W.K. Cheong, A system for automatic extraction of road network from maps, in Proceedings of the IEEE International Joint Symposia on Intelligence and Systems (Cat. No.98EX174) (1998). https://doi.org/10.1109/ijsis.1998.685476

  13. W. Duan, Y. Chiang, C.A. Knoblock, S. Leyk, J. Uhl, Automatic generation of precisely delineated geographic features from georeferenced historical maps using deep learning, in Proceedings of the AutoCarto (2018)

    Google Scholar 

  14. M. Everingham, L. Van Gool, C.K.I. Williams, J. Winn, A. Zisserman, The PASCAL Visual Object Classes Challenge 2012 (VOC2012) Results

    Google Scholar 

  15. M. Everingham, J. Winn, The PASCAL visual object classes challenge 2012 (VOC2012) development kit, in Pattern Analysis, Statistical Modelling and Computational Learning, Tech. Rep (2011)

    Google Scholar 

  16. C. Fellbaum. WordNet: An Electronic Lexical Database (Bradford Books, 1998)

    Book  Google Scholar 

  17. A. Garcia-Garcia, S. Orts-Escolano, S. Oprea, V. Villena-Martinez, J. Garcia-Rodriguez, A review on deep learning techniques applied to semantic segmentation. arXiv preprint arXiv:1704.06857 (2017)

    Google Scholar 

  18. K. He, X. Zhang, S. Ren, J. Sun, Delving deep into rectifiers: surpassing human-level performance on ImageNet classification, in Proceedings of the IEEE International Conference on Computer Vision (2015), pp. 1026–1034

    Google Scholar 

  19. K. He, X. Zhang, S. Ren, J. Sun, Deep residual learning for image recognition, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2016), pp. 770–778

    Google Scholar 

  20. T.C. Henderson, T. Linton, S. Potupchik, A. Ostanin, Automatic segmentation of semantic classes in raster map images, in IAPR International Workshop on Graphics RECognition (2009), pp. 1–10

    Google Scholar 

  21. G. Huang, Z. Liu, L. Van Der Maaten, K.Q. Weinberger, Densely connected convolutional networks, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2017), pp. 4700–4708

    Google Scholar 

  22. Y. Jiang, X. Zhu, X. Wang, S. Yang, W. Li, H. Wang, P. Fu, Z. Luo, R2CNN: rotational region CNN for orientation robust scene text detection. arXiv: 1706.09579 (2017)

    Google Scholar 

  23. Ç. Kaymak, A. Uçar, A brief survey and an application of semantic image segmentation for autonomous driving, in Handbook of Deep Learning Applications (Springer, Berlin, 2019), pp. 161–200

    Google Scholar 

  24. X. Liu, Z. Deng, Y. Yang, Recent progress in semantic image segmentation, in Artificial Intelligence Review (2018). ISSN: 1573-7462. https://doi.org/10.1007/s10462-018-9641-3

    Article  Google Scholar 

  25. J. Long, E. Shelhamer, T. Darrell, Fully convolutional networks for semantic segmentation, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2015), pp. 3431–3440

    Google Scholar 

  26. D. Marmanis, M. Datcu, T. Esch, U. Stilla, Deep learning earth observation classification using ImageNet pretrained networks. IEEE Geosci. Remote Sens. Lett. 13(1), 105–109 (2016)

    Article  Google Scholar 

  27. F. Maire, L. Mejias, A. Hodgson, A convolutional neural network for automatic analysis of aerial imagery, in 2014 International Conference on Digital Image Computing: Techniques and Applications (DICTA) (IEEE, Piscataway, 2014), pp. 1–8

    Google Scholar 

  28. M. Oquab, L. Bottou, I. Laptev, J. Sivic, Learning and transferring mid-level image representations using convolutional neural networks, in 2014 IEEE Conference on Computer Vision and Pattern Recognition (2014), pp. 1717–1724. https://doi.org/10.1109/CVPR.2014.222

    Google Scholar 

  29. O. Ronneberger, P. Fischer, T. Brox, U-net: convolutional networks for biomedical image segmentation, in International Conference on Medical Image Computing and Computer-Assisted Intervention (Springer, Berlin, 2015), pp. 234–241

    Google Scholar 

  30. A. Romero, C. Gatta, G. Camps-Valls, Unsupervised deep feature extraction for remote sensing image classification. IEEE Trans. Geosci. Remote Sens. 54(3), 1349–1362 (2016)

    Article  Google Scholar 

  31. O. Russakovsky, J. Deng, H. Su, J. Krause, S. Satheesh, S. Ma, Z. Huang, A. Karpathy, A. Khosla, M. Bernstein, A.C. Berg, L. Fei-Fei, ImageNet large scale visual recognition challenge. Int. J. Comput. Vis. 115(3), 211–252 (2015). https://doi.org/10.1007/s11263-015-0816-y

    Article  Google Scholar 

  32. O. Russakovsky, J. Deng, H. Su, J. Krause, S. Satheesh, S. Ma, Z. Huang, A. Karpathy, A. Khosla, M. Bernstein, et al. ImageNet large scale visual recognition challenge. Int. J. Comput. Vis. 115(3), 211–252 (2015)

    Article  Google Scholar 

  33. P. Sermanet, D. Eigen, X. Zhang, M. Mathieu, R. Fergus, Y. Le-Cun, OverFeat: integrated recognition, localization and detection using convolutional networks, in 2nd International Conference on Learning Representations (ICLR 2014). Conference Track Proceedings (Banff, 2014)

    Google Scholar 

  34. R. Samet, E. Hancer, A new approach to the reconstruction of contour lines extracted from topographic maps. J. Vis. Commun. Image Represent. 23(4), 642–647 (2012)

    Article  Google Scholar 

  35. K. Simonyan, A. Zisserman, Very deep convolutional networks for large-scale image recognition, in 3rd International Conference on Learning Representations, ICLR 2015, Conference Track Proceedings (San Diego, 2015)

    Google Scholar 

  36. C. Szegedy, W. Liu, Y. Jia, P. Sermanet, S. Reed, D. Anguelov, D. Erhan, V. Vanhoucke, A. Rabinovich, Going deeper with convolutions, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2015), pp. 1–9

    Google Scholar 

  37. J.H. Uhl, S. Leyk, Y.-Y. Chiang, W. Duan, C.A. Knoblock, Extracting human settlement footprint from historical topographic map series using context-based machine learning, in IET Conference Proceedings (2017)

    Google Scholar 

  38. X. Yang, H. Sun, K. Fu, J. Yang, X. Sun, M. Yan, Z. Guo, Automatic ship detection in remote sensing images from Google Earth of complex scenes based on multiscale rotation dense feature pyramid networks. Remote Sens. 10(1), 132 (2018)

    Article  Google Scholar 

  39. F. Yu, V. Koltun, Multi-scale context aggregation by dilated convolutions, in 4th International Conference on Learning Representations, ICLR 2016, Conference Track Proceedings (San Juan, 2016)

    Google Scholar 

  40. J. Yosinski, J. Clune, A.M. Nguyen, T.J. Fuchs, H. Lipson, Understanding neural networks through deep visualization. arXiv: 1506.06579 (2015)

    Google Scholar 

  41. M.D. Zeiler, R. Fergus, Visualizing and understanding convolutional networks, in European Conference on Computer Vision (Springer, Berlin, 2014), pp. 818–833

    Google Scholar 

  42. H. Zhao, J. Shi, X. Qi, X. Wang, J. Jia, Pyramid scene parsing network, in Proceedings of the IEEE conference on Computer Vision and Pattern Recognition (2017), pp. 2881–2890

    Google Scholar 

  43. X. Zhou, C. Yao, H. Wen, Y. Wang, S. Zhou, W. He, J. Liang, EAST: an efficient and accurate scene text detector, in Proceedings of the IEEE conference on Computer Vision and Pattern Recognition (2017), pp. 5551–5560

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Spatial Sciences Institute, University of Southern California, Los Angeles, CA, USA

    Yao-Yi Chiang

  2. Department of Computer Science, University of Southern California, Los Angeles, CA, USA

    Weiwei Duan

  3. Department of Geography, University of Colorado, Boulder, CO, USA

    Stefan Leyk & Johannes H. Uhl

  4. Information Sciences Institute, University of Southern California, Marina del Rey, CA, USA

    Craig A. Knoblock

Authors
  1. Yao-Yi Chiang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Weiwei Duan
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Stefan Leyk
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Johannes H. Uhl
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Craig A. Knoblock
    View author publications

    You can also search for this author in PubMed Google Scholar

Rights and permissions

Reprints and permissions

Copyright information

© 2020 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this chapter

Check for updates. Verify currency and authenticity via CrossMark

Cite this chapter

Chiang, YY., Duan, W., Leyk, S., Uhl, J.H., Knoblock, C.A. (2020). Training Deep Learning Models for Geographic Feature Recognition from Historical Maps. In: Using Historical Maps in Scientific Studies. SpringerBriefs in Geography. Springer, Cham. https://doi.org/10.1007/978-3-319-66908-3_4

Download citation

Publish with us

Policies and ethics

Search

Navigation