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.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 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.
- 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.
- 5.
The reader is referred to [Gar+17] for a comprehensive review on semantic segmentation models.
- 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.
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.
Figures A.1, A.2, and A.3 in the appendix show the full size results.
- 9.
The blue pixels are at the railroad locations in the map since they are correctly extracted railroad pixels.
- 10.
- 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.
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
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
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
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)
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
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
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
M. Castelluccio, G. Poggi, C. Sansone, L. Verdoliva, Land use classification in remote sensing images by convolutional neural networks. arXiv: 1508.00092 (2015)
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
L. Chen, G. Papandreou, F. Schroff, H. Adam, Rethinking atrous convolution for semantic image segmentation. arXiv: 1706.05587 (2017)
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
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
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
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)
M. Everingham, L. Van Gool, C.K.I. Williams, J. Winn, A. Zisserman, The PASCAL Visual Object Classes Challenge 2012 (VOC2012) Results
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)
C. Fellbaum. WordNet: An Electronic Lexical Database (Bradford Books, 1998)
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)
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
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
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
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
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)
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
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
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
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)
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
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
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
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)
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
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)
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)
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)
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)
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
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)
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)
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)
J. Yosinski, J. Clune, A.M. Nguyen, T.J. Fuchs, H. Lipson, Understanding neural networks through deep visualization. arXiv: 1506.06579 (2015)
M.D. Zeiler, R. Fergus, Visualizing and understanding convolutional networks, in European Conference on Computer Vision (Springer, Berlin, 2014), pp. 818–833
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
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
Author information
Authors and Affiliations
Rights and permissions
Copyright information
© 2020 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this chapter
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
DOI: https://doi.org/10.1007/978-3-319-66908-3_4
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-66907-6
Online ISBN: 978-3-319-66908-3
eBook Packages: Earth and Environmental ScienceEarth and Environmental Science (R0)