- freely available
ISPRS Int. J. Geo-Inf. 2018, 7(4), 148; https://doi.org/10.3390/ijgi7040148
- What is the spatial and temporal coverage of the map archive content and does it vary across different cartographic scales? The user will need to know the potential extent, temporally and spatially, of the extracted data to understand benefit and value of the intended information extraction effort and for comparing different map archives.
- How accurate is the georeference of maps contained in the archive? Does the accuracy vary in the spatio-temporal domain? This constitutes a pressing question if ancillary geospatial data is used for the information extraction and certain degrees of spatial alignment with map features are required. For example, if it is possible to a priori identify map sheets likely to suffer from a high degree of positional inaccuracy, the user can exclude those map sheets from template or training data collection and, thus, reduce the amount of noise in the collected training data.
- How much variability is there in the map content, regarding color, hue, contrast, and in the cartographic styles used to represent the symbol of interest? This is a central question affecting the choice and design of a suitable recognition model. More powerful models or even different models for certain types of maps may be required if the representation of map content of interest varies heavily across the map archive. Furthermore, knowledge of variations in map content and similarity between individual map sheets is useful to optimize the design of training data sampling and to ensure the collection of representative and balanced training samples.
2. Background and Related Research
2.1. Map Processing
2.2. Recent Developments in Map-Based Information Extraction
2.3. Image Information Mining
4.1. Metadata Analysis
4.1.1. Spatio-Temporal Coverage Analysis
4.1.2. Assessing Positional Accuracy
4.2. Content-Based Image Analysis
4.2.1. Low-Level Image Descriptors
4.2.2. Dimensionality Reduction
4.2.3. Multi-Level Content Analysis
5.1. Metadata Analysis
5.1.1. Metadata-Based Spatial-Temporal Coverage Analysis
5.1.2. Metadata-Based Spatial-Temporal Analysis of Positional Accuracy
5.2. Content-Based Analysis
5.2.1. Content-Based Analysis at the Map Level
5.2.2. Content-Based Analysis at Within-Map Patch Level
5.2.3. Content-Based Analysis at the Cross-Map Patch Level
6. Conclusions and Outlook
- Spatio-temporal coverage analysis:
- Estimation of the spatio-temporal coverage of the extracted data; and
- Guidance for the design of the training data collection, to ensure the collection of balanced and representative training data across the spatio-temporal domain.
- Spatio-temporal analysis of spatial accuracy:
- Estimating the spatial accuracy of the extracted data; and
- Excluding map sheets of potential low spatial accuracy to ensure high degrees of spatial alignment of map and ancillary data used for training data collection and, thus, to reduce noise in the collected training data
- Content-based image analysis:
- Assessing the variations in map content as a fundamental step in order to choose adequate information extraction methods capable of handling data of the given variability and to create representative training data accounting for such variations.
Conflicts of Interest
- Fishburn, K.A.; Davis, L.R.; Allord, G.J. Scanning and georeferencing historical usgs quadrangles. In Fact Sheet; US Geological Survey: Reston, WV, USA, 2017. [Google Scholar]
- U.S. Library of Congress. Available online: http://www.loc.gov/rr/geogmap/sanborn/san6.html (accessed on 28 February 2018).
- U.S. Library of Congress. Available online: http://www.loc.gov/rr/geogmap/sanborn/ (accessed on 28 February 2018).
- U.S. Library of Congress. Available online: https://www.loc.gov/item/prn-17-074/sanborn-fire-insurance-maps-now-online/2017-05-25/ (accessed on 28 February 2018).
- National Library of Scotland. Available online: https://maps.nls.uk/os/index.html (accessed on 28 February 2018).
- National Library of Scotland. Available online: http://maps.nls.uk/geo/explore (accessed on 28 February 2018).
- Datcu, M.; Daschiel, H.; Pelizzari, A.; Quartulli, M.; Galoppo, A.; Colapicchioni, A.; Pastori, M.; Seidel, K.; Marchetti, P.G.; D’Elia, S. Information mining in remote sensing image archives: System concepts. IEEE Trans. Geosci. Remote Sens. 2003, 41, 2923–2936. [Google Scholar] [CrossRef]
- Chiang, Y.-Y.; Leyk, S.; Knoblock, C.A. A survey of digital map processing techniques. ACM Comput. Surv. 2014, 47, 1–44. [Google Scholar] [CrossRef]
- Miyoshi, T.; Weiqing, L.; Kaneda, K.; Yamashita, H.; Nakamae, E. Automatic extraction of buildings utilizing geometric features of a scanned topographic map. In Proceedings of the ICPR 2004 17th International Conference on Pattern Recognition, Cambridge, UK, 26 August 2004. [Google Scholar]
- Laycock, S.D.; Brown, P.G.; Laycock, R.G.; Day, A.M. Aligning archive maps and extracting footprints for analysis of historic urban environments. Comput. Graph. 2011, 35, 242–249. [Google Scholar] [CrossRef][Green Version]
- Arteaga, M.G. Historical map polygon and feature extractor. In Proceedings of the 1st ACM SIGSPATIAL International Workshop on MapInteraction—MapInteract ’13; ACM Press: New York, NY, USA, 2013. [Google Scholar]
- Chiang, Y.-Y.; Leyk, S.; Knoblock, C.A. Efficient and robust graphics recognition from historical maps. In Graphics Recognition. New Trends and Challenges; Springer: Berlin/Heidelberg, Germany, 2013; pp. 25–35. [Google Scholar]
- Miao, Q.; Liu, T.; Song, J.; Gong, M.; Yang, Y. Guided superpixel method for topographic map processing. IEEE Trans. Geosci. Remote Sens. 2016, 54, 6265–6279. [Google Scholar] [CrossRef]
- Leyk, S.; Boesch, R. Extracting composite cartographic area features in low-quality maps. Cartogr. Geogr. Inf. Sci. 2009, 36, 71–79. [Google Scholar] [CrossRef]
- Chiang, Y.-Y.; Moghaddam, S.; Gupta, S.; Fernandes, R.; Knoblock, C.A. From map images to geographic names. In Proceedings of the 22nd ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems—SIGSPATIAL ’14, Dallas, TX, USA, 4–7 November 2014. [Google Scholar]
- Chiang, Y.-Y.; Leyk, S.; Honarvar Nazari, N.; Moghaddam, S.; Tan, T.X. Assessing the impact of graphical quality on automatic text recognition in digital maps. Comput. Geosci. 2016, 93, 21–35. [Google Scholar] [CrossRef]
- Tsorlini, A.; Iosifescu, I.; Iosifescu, C.; Hurni, L. A methodological framework for analyzing digitally historical maps using data from different sources through an online interactive platform. e-Perimetron 2014, 9, 153–165. [Google Scholar]
- Hurni, L.; Lorenz, C.; Oleggini, L. Cartographic reconstruction of historic settlement development by means of modern geo-data. In Proceedings of the 26th International cartographic conference, Dresden, Germany, 25–30 August 2013. [Google Scholar]
- Leyk, S.; Chiang, Y. Information extraction of hydrographic features from historical map archives using the concept of geographic context. In Proceedings of the AutoCarto 2016, Albuquerque, New Mexico, 14–16 September 2016. [Google Scholar]
- Iosifescu, I.; Tsorlini, A.; Hurni, L. Towards a comprehensive methodology for automatic vectorization of raster historical maps. e-Perimetron 2016, 11, 57–76. [Google Scholar]
- Budig, B.; van Dijk, T.C. Active learning for classifying template matches in historical maps. In Discovery Science; Springer: Berlin/Heidelberg, Germany, 2015; pp. 33–47. [Google Scholar]
- Budig, B.; Dijk, T.C.V.; Wolff, A. Matching labels and markers in historical maps. ACM Trans. Spat. Algorithms Syst. 2016, 2, 1–24. [Google Scholar] [CrossRef]
- Budig, B.; van Dijk, T.C.; Feitsch, F.; Arteaga, M.G. Polygon consensus. In Proceedings of the 24th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems—GIS ’16, San Francisco, CA, USA, 31 October–3 November 2016. [Google Scholar]
- Maire, F.; Mejias, L.; Hodgson, A. A convolutional neural network for automatic analysis of aerial imagery. In Proceedings of the 2014 International Conference on Digital Image Computing: Techniques and Applications (DICTA), Wollongong, Australia, 25–27 November 2014. [Google Scholar]
- Castelluccio, M.; Poggi, G.; Sansone, C.; Verdoliva, L. Training convolutional neural networks for semantic classification of remote sensing imagery. In Proceedings of the 2017 Joint Urban Remote Sensing Event (JURSE), Dubai, United Arab Emirates, 6–8 March 2017. [Google Scholar]
- Audebert, N.; Le Saux, B.; Lefèvre, S. Semantic segmentation of earth observation data using multimodal and multi-scale deep networks. In Computer Vision—ACCV 2016; Springer: Berlin/Heidelberg, Germany, 2017; pp. 180–196. [Google Scholar]
- Marmanis, D.; Datcu, M.; Esch, T.; Stilla, U. Deep learning earth observation classification using imagenet pretrained networks. IEEE Geosci. Remote Sens. Lett. 2016, 13, 105–109. [Google Scholar] [CrossRef]
- Romero, A.; Gatta, C.; Camps-Valls, G. Unsupervised deep feature extraction for remote sensing image classification. IEEE Trans. Geosci. Remote Sens. 2016, 54, 1349–1362. [Google Scholar] [CrossRef]
- Scott, G.J.; England, M.R.; Starms, W.A.; Marcum, R.A.; Davis, C.H. Training deep convolutional neural networks for land–cover classification of high-resolution imagery. IEEE Geosci. Remote Sens. Lett. 2017, 14, 549–553. [Google Scholar] [CrossRef]
- Zhao, W.; Jiao, L.; Ma, W.; Zhao, J.; Zhao, J.; Liu, H.; Cao, X.; Yang, S. Superpixel-based multiple local cnn for panchromatic and multispectral image classification. IEEE Trans. Geosci. Remote Sens. 2017, 55, 4141–4156. [Google Scholar] [CrossRef]
- Zhang, L.; Zhang, L.; Du, B. Deep learning for remote sensing data: A technical tutorial on the state of the art. IEEE Geosci. Remote Sens Mag. 2016, 4, 22–40. [Google Scholar] [CrossRef]
- Zhu, X.X.; Tuia, D.; Mou, L.; Xia, G.-S.; Zhang, L.; Xu, F.; Fraundorfer, F. Deep learning in remote sensing: A comprehensive review and list of resources. IEEE Geosci. Remote Sens Mag. 2017, 5, 8–36. [Google Scholar] [CrossRef]
- Ball, J.E.; Anderson, D.T.; Chan, C.S. Comprehensive survey of deep learning in remote sensing: Theories, tools, and challenges for the community. J. Appl. Remote Sens. 2017, 11. [Google Scholar] [CrossRef]
- Uhl, J.H.; Leyk, S.; Yao-Yi, C.; Weiwei, D.; Knoblock, C.A. Extracting human settlement footprint from historical topographic map series using context-based machine learning. In Proceedings of the 8th International Conference of Pattern Recognition Systems (ICPRS 2017), Madrid, Spain, 11–13 July 2017; Institution of Engineering and Technology: Stevenage, UK, 2017; Volume 8, p. 15. [Google Scholar]
- Duan, W.; Chiang, Y.-Y.; Knoblock, C.A.; Jain, V.; Feldman, D.; Uhl, J.H.; Leyk, S. Automatic alignment of geographic features in contemporary vector data and historical maps. In Proceedings of the 1st Workshop on Artificial Intelligence and Deep Learning for Geographic Knowledge Discovery—GeoAI ’17, Redondo Beach, CA, USA, 7–10 November 2017. [Google Scholar]
- Duan, W.; Chiang, Y.-Y.; Knoblock, C.A.; Uhl, J.H.; Leyk, S. Automatic generation of precisely delineated geographic features from georeferenced historical maps using deep learning. In Proceedings of the AutoCarto 2018, Madison, WI, USA, 22–24 May 2018. accepted. [Google Scholar]
- Quartulli, M.; Olaizola, I.G. A review of EO image information mining. ISPRS J. Photogramm. Remote Sens. 2013, 75, 11–28. [Google Scholar] [CrossRef]
- Espinoza-Molina, D.; Alonso, K.; Datcu, M. Visual data mining for feature space exploration using in-situ data. In Proceedings of the 2016 IEEE International Geoscience and Remote Sensing Symposium (IGARSS), Beijing, China, 10–15 July 2016. [Google Scholar]
- Espinoza Molina, D.; Datcu, M. Data mining and knowledge discovery tools for exploiting big earth-observation data. ISPRS Int. Arch. Photogramm. Remote Sens. Spat. Inf. Sci. 2015, 40, 627–633. [Google Scholar] [CrossRef]
- Griparis, A.; Faur, D.; Datcu, M. Dimensionality reduction for visual data mining of earth observation archives. IEEE Geosci. Remote Sens. Lett. 2016, 13, 1701–1705. [Google Scholar] [CrossRef]
- Durbha, S.S.; King, R.L. Semantics-enabled framework for knowledge discovery from earth observation data archives. IEEE Trans. Geosci. Remote Sens. 2005, 43, 2563–2572. [Google Scholar] [CrossRef]
- Kurte, K.R.; Durbha, S.S.; King, R.L.; Younan, N.H.; Vatsavai, R. Semantics-enabled framework for spatial image information mining of linked earth observation data. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 2017, 10, 29–44. [Google Scholar] [CrossRef]
- Silva, M.P.S.; Camara, G.; Souza, R.C.M.; Valeriano, D.M.; Escada, M.I.S. Mining patterns of change in remote sensing image databases. In Proceedings of the Fifth IEEE International Conference on Data Mining (ICDM’05), Houston, TX, USA, 27–30 November 2005. [Google Scholar]
- U.S. Geological Survey. Available online: https://ngmdb.usgs.gov/topoview/viewer (accessed on 28 February 2018).
- Library of Congress. Available online: http://www.loc.gov/rr/geogmap/sanborn/country.php?countryID=1 (accessed on 28 February 2018).
- Huang, Z.-C.; Chan, P.P.K.; Ng, W.W.Y.; Yeung, D.S. Content-based image retrieval using color moment and gabor texture feature. In Proceedings of the 2010 International Conference on Machine Learning and Cybernetics, Qingdao, China, 11–14 July 2010. [Google Scholar]
- Van der Maaten, L.; Hinton, G. Visualizing data using t-SNE. J. Mach. Learn. Res. 2008, 9, 2579–2605. [Google Scholar]
- Fisher, R.A. Applications of ‘Student’s’ Distribution. Metron 1925, 5, 3–17. [Google Scholar]
- Leyk, S.; Uhl, J.H.; Balk, D.; Jones, B. Assessing the accuracy of multi-temporal built-up land layers across rural-urban trajectories in the united states. Remote Sens. Environ. 2018, 204, 898–917. [Google Scholar] [CrossRef] [PubMed]
- ESRI Basemaps: Esri, DigitalGlobe, GeoEye, Earthstar Geographics, CNES/Airbus DS, USDA, USGS, AEX, Getmapping, Aerogrid, IGN, IGP, Swisstopo, and the GIS User Community. Available online: https://services.arcgisonline.com/ArcGIS/rest/services/World_Imagery/MapServer (accessed on 28 February 2018).
- U.S. Geological Survey. 1999; Map Accuracy Standards, Fact Sheet 171-99. Available online: https://pubs.er.usgs.gov/publication/fs17199 (accessed on 28 February 2018). [Google Scholar]
- Gorelick, N.; Hancher, M.; Dixon, M.; Ilyushchenko, S.; Thau, D.; Moore, R. Google earth engine: Planetary-scale geospatial analysis for everyone. Remote Sens. Environ. 2017, 202, 18–27. [Google Scholar] [CrossRef]
- Esch, T.; Üreyen, S.; Zeidler, J.; Metz-Marconcini, A.; Hirner, A.; Asamer, H.; Marconcini, M. Exploiting big earth data from space–first experiences with the timescan processing chain. Big Earth Data 2018, 1–20. [Google Scholar] [CrossRef]
- Van Rees, E. DigitalGlobe and big data. GeoInformatics 2016, 19, 6. [Google Scholar]
© 2018 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).