{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T18:41:33Z","timestamp":1776105693031,"version":"3.50.1"},"reference-count":43,"publisher":"MDPI AG","issue":"5","license":[{"start":{"date-parts":[[2020,5,25]],"date-time":"2020-05-25T00:00:00Z","timestamp":1590364800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IJGI"],"abstract":"<jats:p>Among cartographic generalisation problems, the generalisation of sinuous bends in mountain roads has always been a popular one due to its difficulty. Recent research showed the potential of deep learning techniques to overcome some remaining research problems regarding the automation of cartographic generalisation. This paper explores this potential on the popular mountain road generalisation problem, which requires smoothing the road, enlarging the bend summits, and schematising the bend series by removing some of the bends. We modelled the mountain road generalisation as a deep learning problem by generating an image from input vector road data, and tried to generate it as an output of the model a new image of the generalised roads. Similarly to previous studies on building generalisation, we used a U-Net architecture to generate the generalised image from the ungeneralised image. The deep learning model was trained and evaluated on a dataset composed of roads in the Alps extracted from IGN (the French national mapping agency) maps at 1:250,000 (output) and 1:25,000 (input) scale. The results are encouraging as the output image looks like a generalised version of the roads and the accuracy of pixel segmentation is around 65%. The model learns how to smooth the output roads, and that it needs to displace and enlarge symbols but does not always correctly achieve these operations. This article shows the ability of deep learning to understand and manage the geographic information for generalisation, but also highlights challenges to come.<\/jats:p>","DOI":"10.3390\/ijgi9050338","type":"journal-article","created":{"date-parts":[[2020,5,25]],"date-time":"2020-05-25T11:42:02Z","timestamp":1590406922000},"page":"338","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":53,"title":["Exploring the Potential of Deep Learning Segmentation for Mountain Roads Generalisation"],"prefix":"10.3390","volume":"9","author":[{"given":"Azelle","family":"Courtial","sequence":"first","affiliation":[{"name":"LASTIG, Univ Gustave Eiffel, ENSG, IGN, F-94160 Saint-Mand\u00e9, France"}]},{"given":"Achraf","family":"El Ayedi","sequence":"additional","affiliation":[{"name":"LASTIG, Univ Gustave Eiffel, ENSG, IGN, F-94160 Saint-Mand\u00e9, France"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6113-6903","authenticated-orcid":false,"given":"Guillaume","family":"Touya","sequence":"additional","affiliation":[{"name":"LASTIG, Univ Gustave Eiffel, ENSG, IGN, F-94160 Saint-Mand\u00e9, France"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5111-7848","authenticated-orcid":false,"given":"Xiang","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Resource and Environmental Sciences, Wuhan University, Wuhan 430079, China"}]}],"member":"1968","published-online":{"date-parts":[[2020,5,25]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Burghardt, D., Duch\u00eane, C., and Mackaness, W. (2014). Generalisation Operators. Abstracting Geographic Information in a Data Rich World, Springer International Publishing. Lecture Notes in Geoinformation and Cartography.","DOI":"10.1007\/978-3-319-00203-3"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Burghardt, D., Duch\u00eane, C., and Mackaness, W. (2014). Generalisation in Practice Within National Mapping Agencies. Abstracting Geographic Information in a Data Rich World, Springer International Publishing. Lecture Notes in Geoinformation and Cartography.","DOI":"10.1007\/978-3-319-00203-3"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Burghardt, D., Duch\u00eane, C., and Mackaness, W. (2014). Process Modelling, Web Services and Geoprocessing. Abstracting Geographic Information in a Data Rich World, Springer.","DOI":"10.1007\/978-3-319-00203-3"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"139","DOI":"10.1007\/3-540-60392-1_10","article-title":"Overcoming the knowledge acquisition bottleneck in map generalization: The role of interactive systems and computational intelligence","volume":"Volume 988","author":"Frank","year":"1995","journal-title":"Spatial Information Theory A Theoretical Basis for GIS"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1080\/136588100240930","article-title":"Kwoledge acquisition for automatic interpretation of spatial data","volume":"14","author":"Sester","year":"2000","journal-title":"Int. J. Geograph. Inf. Sci."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1559\/152304000783547993","article-title":"Knowledge Acquisition for Generalization Rules","volume":"27","author":"Kilpelainen","year":"2000","journal-title":"Cartogr. Geogr. Inf. Sci."},{"key":"ref_7","first-page":"50","article-title":"Abstraction-Based Machine Learning Approach To Cartographic Generalisation","volume":"Volume 1a","author":"Zucker","year":"2000","journal-title":"Proceedings of the 9th International Symposium on Spatial Data Handling"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"142","DOI":"10.1080\/23729333.2019.1613071","article-title":"Is deep learning the new agent for map generalization?","volume":"5","author":"Touya","year":"2019","journal-title":"Int. J. Cartogr."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., and Brox, T. (2015, January 5\u20139). U-Net: Convolutional Networks for Biomedical Image Segmentation. Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention, Munich, Germany.","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Feng, Y., Thiemann, F., and Sester, M. (2019). Learning cartographic building generalization with deep convolutional neural networks. ISPRS J. Geo-Inf., 8.","DOI":"10.3390\/ijgi8060258"},{"key":"ref_11","unstructured":"Robert, C.T., and Dianne, E.R. (1999, January 14\u201321). The \u2018Good Continuation\u2019 Principle of Perceptual Organization applied to the Generalization of Road Networks. Proceedings of the ICA Proceedings, Ottawa, ON, Canada."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"595","DOI":"10.1111\/j.1467-9671.2010.01215.x","article-title":"A Road Network Selection Process Based on Data Enrichment and Structure Detection","volume":"14","author":"Touya","year":"2010","journal-title":"Trans. GIS"},{"key":"ref_13","unstructured":"Benz, S., and Weibel, R. (2013, January 23\u201324). Road network selection using an extended stroke-mesh combination algorithm. Proceedings of the 16th ICA Workshop on Generalisation and Multiple Representation, Dresden, Germany."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"264","DOI":"10.1559\/152304095782540249","article-title":"Simplification and Generalization of Large Scale Data for Roads: A Comparison of Two Filtring Algorithms","volume":"22","author":"Visvalingam","year":"1995","journal-title":"Cartogr. Geogr. Inf. Syst."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"161","DOI":"10.1023\/A:1009736628698","article-title":"A Platform for Research in Generalization: Application to Caricature","volume":"1","author":"Lecordix","year":"1997","journal-title":"GeoInformatica"},{"key":"ref_16","unstructured":"Duch\u00eane, C. (2014). Individual Road Generalisation in the 1997\u20132000 AGENT European Project, IGN, COGIT Lab. Technical Report."},{"key":"ref_17","unstructured":"Bader, M., and Barrault, M. (2001, January 2\u20134). Cartographic Displacement in Generalization: Introducing Elastic Beams. Proceedings of the 4th ICA Workshop on Progress in Automated Map Generalisation, Beijing, China."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"871","DOI":"10.1080\/13658810500161179","article-title":"Optimization approaches for generalization and data abstraction","volume":"19","author":"Sester","year":"2005","journal-title":"Int. J. Geogr. Inf. Sci."},{"key":"ref_19","unstructured":"Mustiere, S. (1998, January 7\u201311). GALBE: Adaptative generalization. The need for an adaptative process for automated generalisation an exemple on roads. Proceedings of the 1st GIS PlaNet Conference, Lisbon, Portugal."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"691","DOI":"10.1080\/13658816.2011.609990","article-title":"A comparative study of various strategies to concatenate road segments into strokes for map generalization","volume":"26","author":"Zhou","year":"2012","journal-title":"Int. J. Geogr. Inf. Sci."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"289","DOI":"10.1007\/s10707-007-0026-z","article-title":"Generalization-oriented road line classification by means of an artificial neural network","volume":"12","year":"2008","journal-title":"Geoinformatica"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"254","DOI":"10.1179\/1743277414Y.0000000083","article-title":"A comparative study of various supervised learning approaches to selective omission in a road network","volume":"54","author":"Zhou","year":"2016","journal-title":"Cartogr. J."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"115","DOI":"10.1080\/23729333.2019.1615729","article-title":"Transferring Multiscale Map Style Using Generative Adversarial Network","volume":"5","author":"Kang","year":"2019","journal-title":"Int. J. Cartogr."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Mackaness, W.A., Ruas, A., and Sarjakoski, L.T. (2007). Chapter 5\u2014Evaluation in the Map Generalisation Process. Generalisation of Geographic Information, International Cartographic Association, Elsevier Science B.V.","DOI":"10.1016\/B978-008045374-3\/50007-7"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Burghardt, D., Duch\u00eane, C., and Mackaness, W. (2014). Evaluation in Generalisation. Abstracting Geographic Information in a Data Rich World, Springer.","DOI":"10.1007\/978-3-319-00203-3"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Touya, G. (2012). Social Welfare to Assess the Global Legibility of a Generalized Map. International Conference on Geographic Information Science, Springer.","DOI":"10.1007\/978-3-642-33024-7_15"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"435","DOI":"10.1007\/s10707-007-0040-1","article-title":"Matching networks with different levels of detail","volume":"12","author":"Mustiere","year":"2008","journal-title":"Geoinformatica"},{"key":"ref_28","first-page":"21","article-title":"Knowledge Formalization for Vector Data Matching Using Belief Theory","volume":"10","author":"Ruas","year":"2015","journal-title":"J. Spat. Inf. Sci."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"259","DOI":"10.1016\/j.isprsjprs.2019.02.010","article-title":"A graph convolutional neural network for classification of building patterns using spatial vector data","volume":"150","author":"Yan","year":"2019","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"695","DOI":"10.1007\/s11769-012-0544-y","article-title":"Errors Prediction for Vector-to-Raster Conversion Based on Map Load and Cell Size","volume":"22","author":"Shunbao","year":"2012","journal-title":"Chin. Geogr. Sci."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3382080","article-title":"Deep Learning for Enrichment of Vector Spatial Databases: Application to Highway Interchange","volume":"6","author":"Touya","year":"2020","journal-title":"ACM Trans. Spat. Algorithms Syst."},{"key":"ref_32","unstructured":"Peter, B., and Weibel, R. (1999, January 12\u201314). Using vector and raster-based techniques in categorical map generalization. Proceedings of the Third ICA Workshop on Progress in Automated Map Generalization, Ottawa, ON, Canada."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"322","DOI":"10.1080\/00087041.2017.1413787","article-title":"Experiments to Distribute and Parallelize Map Generalization Processes","volume":"54","author":"Touya","year":"2017","journal-title":"Cartogr. J."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Ruas, A. (1999). Mod\u00e8le de G\u00e9n\u00e9ralisation de Donn\u00e9es G\u00e9graphiques \u00e0 Base de Contraintes et d\u2019Autonomie. [Ph.D. Thesis, Universit\u00e9 de Marne la Vall\u00e9e].","DOI":"10.4000\/cybergeo.5227"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"60","DOI":"10.1186\/s40537-019-0197-0","article-title":"A survey on Image Data Augmentation for Deep Learning","volume":"6","author":"Shorten","year":"2019","journal-title":"J. Big Data"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/2897824.2925974","article-title":"Learning to Simplify: Fully Convolutional Networks for Rough Sketch Cleanup","volume":"35","author":"Iizuka","year":"2016","journal-title":"ACM Trans. Graph."},{"key":"ref_37","unstructured":"Olaf, R., Philipp, F., and Thomas, B. (2015, January 5\u20139). U-Net: Convolutional Networks for BiomedicalImage Segmentation. Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention, Munich, Germany."},{"key":"ref_38","unstructured":"Gabriela, C., Diane, L., and Florent, P. (2013, January 9\u201313). What is a good evaluation measure for semantic segmentation?. Proceedings of the BMVC, Bristol, UK."},{"key":"ref_39","unstructured":"Chollet, F. (2018). Deep Learning with Python, Apress."},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Touya, G., Lokhat, I., and Duch\u00eane, C. (2019, January 15\u201320). CartAGen: An Open Source Research Platform for Map Generalization. Proceedings of the ICA, Tokyo, Japan.","DOI":"10.5194\/ica-proc-2-134-2019"},{"key":"ref_41","first-page":"198","article-title":"Clutter and Map Legibility in Automated Cartography: A Research Agenda","volume":"51","author":"Touya","year":"2016","journal-title":"Cartogr. Int. J. Geogr. Inf. Geovis."},{"key":"ref_42","unstructured":"Dumont, M., Touya, G., and Duch\u00eane, C. (2016, January 14). Assessing the Variation of Visual Complexity in Multi-Scale Maps with Clutter Measures. Proceedings of the ICA Workshop on Generalisation and Multiple Representation, lsinki, Finland."},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Gatys, L.A., Ecker, A., and Bethge, M. (2016, January 27\u201330). Image Style Transfer Using Convolutional Neural Networks. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.265"}],"container-title":["ISPRS International Journal of Geo-Information"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2220-9964\/9\/5\/338\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T09:32:19Z","timestamp":1760175139000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2220-9964\/9\/5\/338"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5,25]]},"references-count":43,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2020,5]]}},"alternative-id":["ijgi9050338"],"URL":"https:\/\/doi.org\/10.3390\/ijgi9050338","relation":{},"ISSN":["2220-9964"],"issn-type":[{"value":"2220-9964","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,5,25]]}}}