{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T05:49:31Z","timestamp":1780638571545,"version":"3.54.1"},"reference-count":37,"publisher":"MDPI AG","issue":"21","license":[{"start":{"date-parts":[[2022,10,31]],"date-time":"2022-10-31T00:00:00Z","timestamp":1667174400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Bavarian State Ministry of Economic Affairs, Regional Development and Energy","award":["DIK0100\/03"],"award-info":[{"award-number":["DIK0100\/03"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Remote Sensing"],"abstract":"<jats:p>When integrating railway constructions and refurbishments into an existing infrastructure, it is beneficial to have knowledge of the exact state, geometry, and placement of the connected assets. While new constructions and the maintenance of existing lines can directly use existing digital models and incorporate them into their processes, existing railways often predate digital technologies. This gap in digital models leaves the planning processes of new constructions and refurbishments to primarily rely on non-automated and analogue workflows. With a multitude of asset types, layouts and country-specific standards, the automatic generation of adequate detection models is complicated and needs to be tailored to the current project environment, generating considerable overhead. Addressing this issue, this paper presents the concept of priming. Priming increases the adaptation performance to highly volatile, low-data environments by leveraging previous, existing CAD projects. We introduce a translation scheme that converts the existing 3D models into realistic, project-specific, synthetic surveys and a complemental dialled-in training routine. When applied to a convolutional neural network, we show that the primed training will converge faster and with greater stability, especially when using sparse training data. Our experiments show that priming can reduce the time for network adaptation by over 50%, while also improving resilience to underrepresented object types.<\/jats:p>","DOI":"10.3390\/rs14215482","type":"journal-article","created":{"date-parts":[[2022,11,1]],"date-time":"2022-11-01T06:01:28Z","timestamp":1667282488000},"page":"5482","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Enhancing Railway Detection by Priming Neural Networks with Project Exaptations"],"prefix":"10.3390","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9640-8005","authenticated-orcid":false,"given":"Felix","family":"Eickeler","sequence":"first","affiliation":[{"name":"Chair of Computational Modeling and Simulation, Technische Universit\u00e4t M\u00fcnchen, 80333 Munich, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2088-7254","authenticated-orcid":false,"given":"Andr\u00e9","family":"Borrmann","sequence":"additional","affiliation":[{"name":"Chair of Computational Modeling and Simulation, Technische Universit\u00e4t M\u00fcnchen, 80333 Munich, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2022,10,31]]},"reference":[{"key":"ref_1","unstructured":"EU.Stat (2022, July 25). EU Transport in Figures: Statistis Passenger Transport, 2020. Data Extracted on 19 Jul 2022 08:50 UTC (GMT) from OECD.Stat. Available online: https:\/\/stats.oecd.org\/Index.aspx?&datasetcode=ITF_PASSENGER_TRANSPORT#."},{"key":"ref_2","unstructured":"Union, E. (2020). EU Transport in Figures: Statistical Pocketbook 2020, Publications Office of the European Union. Transport in Figures."},{"key":"ref_3","unstructured":"Direct, E. (2021). The Journey Begins\u20142021 is the European Year of Rail!, European Commission. Technical Report."},{"key":"ref_4","unstructured":"Eickeler, F. (2022, July 25). RailTwin-Supplementary. Available online: https:\/\/github.com\/FelixEickeler\/RailTwin-Supplementary."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"012091","DOI":"10.1088\/1755-1315\/609\/1\/012091","article-title":"Accuracy Evaluation and Comparison of Mobile Laser Scanning and Mobile Photogrammetry Data","volume":"609","author":"Kalvoda","year":"2020","journal-title":"IOP Conf. Ser. Earth Environ. Sci."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Giben, X., Patel, V.M., and Chellappa, R. (2015, January 27\u201330). Material classification and semantic segmentation of railway track images with deep convolutional neural networks. Proceedings of the 2015 IEEE International Conference on Image Processing (ICIP), Quebec City, QC, Canada.","DOI":"10.1109\/ICIP.2015.7350873"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"172988141877394","DOI":"10.1177\/1729881418773943","article-title":"Computer vision\u2013based automatic rod-insulator defect detection in high-speed railway catenary system","volume":"15","author":"Han","year":"2018","journal-title":"Int. J. Adv. Robot. Syst."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Loktev, D.A., and Loktev, A.A. (2018, January 13\u201315). Diagnostics of External Defects of Railway Infrastructure by Analysis of its Images. Proceedings of the 2018 Global Smart Industry Conference (GloSIC), Chelyabinsk, Russia.","DOI":"10.1109\/GloSIC.2018.8570083"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"223","DOI":"10.5194\/isprsannals-II-5-W2-223-2013","article-title":"Rail Track Detection and Modelling in Mobile Laser Scanner Data","volume":"II-5\/W2","author":"Elberink","year":"2013","journal-title":"ISPRS Ann. Photogramm. Remote Sens. Spat. Inf. Sci."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"14916","DOI":"10.3390\/rs71114916","article-title":"Automated Recognition of Railroad Infrastructure in Rural Areas from LIDAR Data","volume":"7","author":"Arastounia","year":"2015","journal-title":"Remote Sens."},{"key":"ref_11","unstructured":"Valenta, C.R., Shaw, J.A., and Kimata, M. (2020, January 9\u201313). A rail extraction algorithm based on the generalized neighborhood height difference from mobile laser scanning data. Proceedings of the SPIE Future Sensing Technologies, Online."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Wilk, A., Koc, W., Specht, C., Judek, S., Karwowski, K., Chrostowski, P., Czaplewski, K., Dabrowski, P.S., Grulkowski, S., and Licow, R. (2020). Digital Filtering of Railway Track Coordinates in Mobile Multi\u2013Receiver GNSS Measurements. Sensors, 20.","DOI":"10.3390\/s20185018"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"04020105","DOI":"10.1061\/(ASCE)CO.1943-7862.0001894","article-title":"Detection of Railway Masts in Airborne LiDAR Data","volume":"146","author":"Ariyachandra","year":"2020","journal-title":"J. Constr. Eng. Manag."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"5565","DOI":"10.3390\/rs70505565","article-title":"Automatic Extraction of Railroad Centerlines from Mobile Laser Scanning Data","volume":"7","author":"Elberink","year":"2015","journal-title":"Remote Sens."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Ariyachandra, M.R.M.F., and Brilakis, I. (2021, January 26\u201328). Generating Railway Geometric Digital Twins from Airborne LiDAR Data. Proceedings of the 2021 European Conference on Computing in Construction, Online.","DOI":"10.35490\/EC3.2021.163"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"103703","DOI":"10.1016\/j.autcon.2021.103703","article-title":"Scan-to-BIM for the infrastructure domain: Generation of IFC-compliant models of road infrastructure assets and semantics using 3D point cloud data","volume":"127","author":"Justo","year":"2021","journal-title":"Autom. Constr."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"G\u00e9zero, L., and Antunes, C. (2019). Automated Three-Dimensional Linear Elements Extraction from Mobile LiDAR Point Clouds in Railway Environments. Infrastructures, 4.","DOI":"10.3390\/infrastructures4030046"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"S\u00e1nchez-Rodr\u00edguez, A., Soil\u00e1n, M., Cabaleiro, M., and Arias, P. (2019). Automated Inspection of Railway Tunnels\u2019 Power Line Using LiDAR Point Clouds. Remote Sens., 11.","DOI":"10.3390\/rs11212567"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"219","DOI":"10.5194\/isprs-archives-XLIII-B1-2020-219-2020","article-title":"Classification of Railway Assets in Mobile Mapping Point Clouds","volume":"XLIII-B1-2020","author":"Corongiu","year":"2020","journal-title":"Int. Arch. Photogramm. Remote Sens. Spat. Inf. Sci."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Chen, X., Chen, Z., Liu, G., Chen, K., Wang, L., Xiang, W., and Zhang, R. (2021). Railway Overhead Contact System Point Cloud Classification. Sensors, 21.","DOI":"10.3390\/s21154961"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"27","DOI":"10.5194\/isprs-annals-V-2-2021-27-2021","article-title":"Fast Weakly Supervised Detection of Railway-Related Infrastructures in Lidar Acquisitions","volume":"V-2-2021","author":"Guinard","year":"2021","journal-title":"ISPRS Ann. Photogramm. Remote Sens. Spat. Inf. Sci."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"104425","DOI":"10.1016\/j.autcon.2022.104425","article-title":"Point cloud semantic segmentation of complex railway environments using deep learning","volume":"141","author":"Grandio","year":"2022","journal-title":"Autom. Constr."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"135","DOI":"10.5194\/isprs-annals-V-2-2022-135-2022","article-title":"Railway Lidar Semantic Segmentation with Axially Symmetrical Convolutional Learning","volume":"V-2-2022","author":"Manier","year":"2022","journal-title":"ISPRS Ann. Photogramm. Remote Sens. Spat. Inf. Sci."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"9","DOI":"10.1186\/s40537-016-0043-6","article-title":"A survey of transfer learning","volume":"3","author":"Weiss","year":"2016","journal-title":"J. Big Data"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Chronopoulou, A., Baziotis, C., and Potamianos, A. (2019, January 3\u20135). An Embarrassingly Simple Approach for Transfer Learning from Pretrained Language Models. Proceedings of the 2019 Annual Conference of the North American Chapter of the Association for Computational Linguistics, Minneapolis, MN, USA.","DOI":"10.18653\/v1\/N19-1213"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"281","DOI":"10.5194\/isprs-annals-V-2-2020-281-2020","article-title":"Semantic Segmentation of Point Clouds with Pointnet And Kpconv Architectures Applied to Railway Tunnels","volume":"V-2-2020","author":"Riveiro","year":"2020","journal-title":"ISPRS Ann. Photogramm. Remote Sens. Spat. Inf. Sci."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27\u201330). Deep Residual Learning for Image Recognition. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Thomas, H., Qi, C.R., Deschaud, J.E., Marcotegui, B., Goulette, F., and Guibas, L. (November, January 27). KPConv: Flexible and Deformable Convolution for Point Clouds. Proceedings of the 2019 IEEE\/CVF International Conference on Computer Vision (ICCV), Seoul, Korea.","DOI":"10.1109\/ICCV.2019.00651"},{"key":"ref_29","unstructured":"Hugues, T. (2019). Learning New Representations for 3D Point Cloud Semantic Segmentation. [Ph.D. Thesis, Universit\u00e9 Paris Sciences et Lettres]."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"e2019WR026058","DOI":"10.1029\/2019WR026058","article-title":"ECOSTRESS: NASA\u2019s Next Generation Mission to Measure Evapotranspiration From the International Space Station","volume":"56","author":"Fisher","year":"2020","journal-title":"Water Resour. Res."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"112772","DOI":"10.1016\/j.rse.2021.112772","article-title":"Virtual laser scanning with HELIOS++: A novel take on ray tracing-based simulation of topographic full-waveform 3D laser scanning","volume":"269","author":"Winiwarter","year":"2022","journal-title":"Remote Sens. Environ."},{"key":"ref_32","unstructured":"(2022, September 25). RIEGL VMX-RAIL. Available online: http:\/\/www.riegl.com\/nc\/products\/mobile-scanning\/produktdetail\/product\/scanner\/67."},{"key":"ref_33","unstructured":"Eickeler, F. (2022, July 25). RailTwin Track Models 2022. Available online: https:\/\/filedn.eu\/l4hiESSdAeuuEoSLE7Uolr4\/boosting_paper\/2022-08-16_boosting-trackmodels.zip."},{"key":"ref_34","unstructured":"Girardeau-Montaut, D. (2022, July 25). CloudCompare [GPL Software]. Available online: https:\/\/github.com\/CloudCompare\/CloudCompare."},{"key":"ref_35","unstructured":"Hugues, T. (2022, July 25). KPConv parameters for large outdoor scene with low point density. Available online: https:\/\/github.com\/HuguesTHOMAS\/KPConv-PyTorch\/issues\/90#issuecomment-808756261."},{"key":"ref_36","unstructured":"Eickeler, F. (2022, July 25). RailTwin-KPCopv. Available online: https:\/\/github.com\/FelixEickeler\/RailTwin-KPConv."},{"key":"ref_37","unstructured":"Thomas Hugues, L.H. (2022, July 25). KPConv-PyTorch. Available online: https:\/\/github.com\/HuguesTHOMAS\/KPConv-PyTorch."}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/14\/21\/5482\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T01:06:54Z","timestamp":1760144814000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/14\/21\/5482"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,31]]},"references-count":37,"journal-issue":{"issue":"21","published-online":{"date-parts":[[2022,11]]}},"alternative-id":["rs14215482"],"URL":"https:\/\/doi.org\/10.3390\/rs14215482","relation":{},"ISSN":["2072-4292"],"issn-type":[{"value":"2072-4292","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,10,31]]}}}