Historical Maps – Machine learning helps us over the map vectorisation crux
| Autor: | Mads Linnet Perner, Stig Roar Svenningsen, G. B. Groom, Gregor Levin |
|---|---|
| Přispěvatelé: | Irás, Krisztina |
| Jazyk: | angličtina |
| Rok vydání: | 2020 |
| Předmět: | |
| Zdroj: | Groom, G B, Levin, G, Svenningsen, S & Perner, M L 2020, ' Historical Maps – Machine learning helps us over the map vectorisation crux ', Paper presented at International Workshop on Automatic Vectorisation of Historical Maps-13 March 2020-ELTE, Budapest, Budapest, Hungary, 13/03/2020-13/03/2020 . https://doi.org/10.21862/avhm2020.11 Groom, G B, Levin, G, Svenningsen, S R & Linnet Perner, M 2020, Historical Maps – Machine learning helps us over the map vectorisation crux . in K Irás (ed.), AUTOMATIC VECTORISATION OF HISTORICAL MAPS : International workshop organized by the ICA Commission on Cartographic Heritage into the Digital . Department of Cartography and Geoinformatics, ELTE Eötvös Loránd University, Budapest, pp. 89-98, Automatic vectorisation of historical maps, Budapest, Hungary, 13/03/2020 . < http://lazarus.elte.hu/avhm/AVHM_Proceedings.pdf#page=89 > |
| DOI: | 10.21862/avhm2020.11 |
| Popis: | Modern geography is massively digital with respect to both map data production and map data analysis. When we consider historical maps, as a key resource for historical geography studies, the situation is different. There are many historical maps available as hardcopy, some of which are scanned to raster data. However, relatively few historical maps are truly digital, as machine-readable geo-data layers. The Danish “Høje Målebordsblade” (HMB) map set, comprising approximately 1100 sheets, national coverage (i.e. Denmark 1864-1920), and geometrically correct, topographic, 1 : 20 000, surveyed between 1842 and1899, is a case in point. Having the HMB maps as vector geo-data has a high priority for Danish historical landscape, environmental and cultural studies. We present progress made, during 2019, in forming vector geo-data of key land categories (water bodies, wetland, forest, heath, sand dune) from scanned HMBprinted map sheets. The focus here is on the role in that work of machine learning methods, specifically the deep learning tool convolutional neural networks (CNN) to map occurrences of specific map symbols associated with the target land categories. Demonstration is made of how machine learning is applied in conjunction with pixel and object based analyses, and not merely in isolation. Thereby, the strengths of machine learning are utilised, and the weaknesses of the applied machine learning are acknowledged andworked with. Symbols detected by machine learning serve as guidance for appropriate values to apply in pixel based image data thresholding. The resulting map products for two study areas (450 and 300 km2) have overall false-positive and false-negative levels of around 10% for all target categories. The ability to utilise the cartographic symbols of the HMB maps enabled production of higher quality vector geo-data of the target land categories than would otherwise have been possible. That these methods are in this work developed and applied via a commercial software (Trimble eCognition) recognizes the significance of a tried-and-tested and easy-to-use, graphical-user-interface and a fast, versatile processing architecture for development of new, complex digital solutions. The components of the resulting workflow are, inprinciple, alternatively usable via various free and open source software environments. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|