{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,30]],"date-time":"2026-05-30T02:25:03Z","timestamp":1780107903502,"version":"3.54.0"},"reference-count":34,"publisher":"MDPI AG","issue":"12","license":[{"start":{"date-parts":[[2025,12,16]],"date-time":"2025-12-16T00:00:00Z","timestamp":1765843200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"German Federal Ministry of Research, Technology and Space","award":["16IS22029C"],"award-info":[{"award-number":["16IS22029C"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Data"],"abstract":"<jats:p>The development of autonomous train systems relies heavily on machine learning (ML) models, which in turn depend on large, high-quality annotated datasets for training and evaluation. The railway domain lacks adequate public datasets and efficient annotation tools. To address this gap, we present Labels4Rails, a tool designed specifically for the annotation of railway scenes. It captures track topology, switch states including switch directions, and informational tags regarding the images\u2019 content and leverages consistent camera perspectives and the fixed track geometries inherent to railways for annotation efficiency. We used Labels4Rails to create the L4R_NLB reference dataset from Norwegian railway footage. The dataset contains 10,253 annotated images across four seasons, including 1415 switch annotations. Both the tool and dataset are publicly available.<\/jats:p>","DOI":"10.3390\/data10120210","type":"journal-article","created":{"date-parts":[[2025,12,16]],"date-time":"2025-12-16T11:00:26Z","timestamp":1765882826000},"page":"210","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Labels4Rails: A Railway Image Annotation Tool and Associated Reference Dataset"],"prefix":"10.3390","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-5797-5373","authenticated-orcid":false,"given":"Tina","family":"Hiebert","sequence":"first","affiliation":[{"name":"School of Engineering\u2013Energy and Information, HTW Berlin, 10313 Berlin, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-9490-0868","authenticated-orcid":false,"given":"Florian","family":"Hofstetter","sequence":"additional","affiliation":[{"name":"School of Engineering\u2013Energy and Information, HTW Berlin, 10313 Berlin, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0461-2058","authenticated-orcid":false,"given":"Carsten","family":"Thomas","sequence":"additional","affiliation":[{"name":"School of Engineering\u2013Energy and Information, HTW Berlin, 10313 Berlin, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-5803-3277","authenticated-orcid":false,"given":"Savera","family":"Mushtaq","sequence":"additional","affiliation":[{"name":"School of Engineering\u2013Energy and Information, HTW Berlin, 10313 Berlin, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-0672-798X","authenticated-orcid":false,"given":"Eero","family":"Kaan","sequence":"additional","affiliation":[{"name":"School of Engineering\u2013Energy and Information, HTW Berlin, 10313 Berlin, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-1334-4783","authenticated-orcid":false,"given":"Biranavan","family":"Parameswaran","sequence":"additional","affiliation":[{"name":"School of Engineering\u2013Energy and Information, HTW Berlin, 10313 Berlin, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2025,12,16]]},"reference":[{"key":"ref_1","unstructured":"Hiebert, T., Thomas, C., and Ja\u00df, P.F. (2025, August 20). Label4Rails Annotation Tool. Available online: https:\/\/github.com\/railway-perception-htw-berlin\/Labels4Rails."},{"key":"ref_2","unstructured":"Thomas, C., Hiebert, T., and Ja\u00df, P.F. (2025, August 20). L4R_NLB Dataset. Zenodo, Available online: https:\/\/zenodo.org\/records\/14260575."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Zendel, O., Murschitz, M., Zeilinger, M., Steininger, D., Abbasi, S., and Beleznai, C. (2019, January 16\u201317). RailSem19: A Dataset for Semantic Rail Scene Understanding. Proceedings of the 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Long Beach, CA, USA.","DOI":"10.1109\/CVPRW.2019.00161"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"143772","DOI":"10.1109\/ACCESS.2019.2945633","article-title":"RailNet: A Segmentation Network for Railroad Detection","volume":"7","author":"Wang","year":"2019","journal-title":"IEEE Access"},{"key":"ref_5","unstructured":"Harb, J., R\u00e9b\u00e9na, N., Chosidow, R., Roblin, G., Potarusov, R., and Hajri, H. (2020). FRSign: A Large-Scale Traffic Light Dataset for Autonomous Trains. arXiv."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Jahan, K., Niemeijer, J., Kornfeld, N., and Roth, M. (2021, January 5\u20137). Deep Neural Networks for Railway Switch Detection and Classification Using Onboard Camera Images. Proceedings of the 2021 IEEE Symposium Series on Computational Intelligence (SSCI), Orlando, FL, USA.","DOI":"10.1109\/SSCI50451.2021.9659983"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Zouaoui, A., Mahtani, A., Hadded, M.A., Ambellouis, S., Boonaert, J., and Wannous, H. (2022, January 5\u20137). RailSet: A Unique Dataset for Railway Anomaly Detection. Proceedings of the 2022 IEEE 5th International Conference on Image Processing Applications and Systems (IPAS), Genova, Italy.","DOI":"10.1109\/IPAS55744.2022.10052883"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"5530","DOI":"10.1002\/int.22801","article-title":"MRSI: A multimodal proximity remote sensing data set for environment perception in rail transit","volume":"37","author":"Chen","year":"2022","journal-title":"Int. J. Intell. Syst."},{"key":"ref_9","first-page":"1","article-title":"A Lightweight Framework for Obstacle Detection in the Railway Image Based on Fast Region Proposal and Improved YOLO-Tiny Network","volume":"71","author":"Guan","year":"2022","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Li, X., and Peng, X. (2022, January 10\u201314). Rail Detection: An Efficient Row-based Network and a New Benchmark. Proceedings of the 30th ACM International Conference on Multimedia (MM \u201922), Lisboa, Portugal.","DOI":"10.1145\/3503161.3548050"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Tagiew, R., Klasek, P., Tilly, R., K\u00f6ppel, M., Denzler, P., Neumaier, P., Klockau, T., Boekhoff, M., and Schwalbe, K. (2023, January 17\u201319). OSDaR23: Open Sensor Data for Rail 2023. Proceedings of the 2023 8th International Conference on Robotics and Automation Engineering (ICRAE), Singapore.","DOI":"10.1109\/ICRAE59816.2023.10458449"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"1332","DOI":"10.1177\/09544097231166472","article-title":"GERALD: A Novel Dataset for the Detection of German Mainline Railway Signals","volume":"237","author":"Leibner","year":"2023","journal-title":"Proc. Inst. Mech. Eng. Part F"},{"key":"ref_13","unstructured":"TARP Project (2025, October 24). Railway Obstacle Detection (ROD) Dataset. Roboflow, 2023. Available online: https:\/\/universe.roboflow.com\/tarp-proj\/obstacle-detection-t5lua."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Tagiew, R., Wunderlich, I., Zanitzer, P., Sastuba, M., Knoll, C., G\u00f6ller, K., Amjad, H., and Seitz, S. (2025, August 20). G\u00f6rlitz Rail Test Center CV Dataset 2024 (RailGoerl24). Available online: https:\/\/data.fid-move.de\/dataset\/railgoerl24.","DOI":"10.1109\/ERAS63351.2025.11135724"},{"key":"ref_15","first-page":"22","article-title":"Multisensordatensatz f\u00fcr die Umfeld\u00fcberwachung von Schienenfahrzeugen","volume":"2025","author":"Diotallevi","year":"2025","journal-title":"Deine Bahn"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"7142","DOI":"10.1109\/TITS.2025.3536024","article-title":"Real-Time Railway Obstacle Detection Based on Multitask Perception Learning","volume":"26","author":"Chen","year":"2025","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Moschidis, C., Vrochidou, E., and Papakostas, G.A. (2024, January 10\u201313). Annotation Tools for Computer Vision Tasks. Proceedings of the Seventeenth International Conference on Machine Vision (ICMV 2024), Edinburg, UK.","DOI":"10.1117\/12.3055065"},{"key":"ref_18","unstructured":"Sekatchev, B. (2025, October 24). CVAT\u2014Computer Vision Annotation Tool. Available online: https:\/\/github.com\/cvat-ai\/cvat."},{"key":"ref_19","unstructured":"Skalski, P. (2025, October 24). Make Sense. Available online: https:\/\/github.com\/SkalskiP\/make-sense\/."},{"key":"ref_20","unstructured":"Ravi, N., Gabeur, V., Hu, Y.T., Hu, R., Ryali, C., Ma, T., Khedr, H., R\u00e4dle, R., Rolland, C., and Gustafson, L. (2024). SAM 2: Segment Anything in Images and Videos. arXiv."},{"key":"ref_21","unstructured":"(2025, August 20). Human Signal. Label-Studio. Available online: https:\/\/labelstud.io\/."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"157","DOI":"10.1007\/s11263-007-0090-8","article-title":"LabelMe: A Database and Web-Based Tool for Image Annotation","volume":"77","author":"Russell","year":"2008","journal-title":"Int. J. Comput. Vis."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., and Zitnick, C.L. (2014). Microsoft COCO: Common objects in context. European Conference on Computer Vision, Springer.","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref_24","unstructured":"Bochkovskiy, A., Wang, C.Y., and Liao, H.Y.M. (2020). YOLOv4: Optimal Speed and Accuracy of Object Detection. arXiv."},{"key":"ref_25","unstructured":"Jocher, G., Chaurasia, A., and Qiu, J. (2025, February 03). Ultralytics YOLOv8. Available online: https:\/\/github.com\/ultralytics\/ultralytics."},{"key":"ref_26","unstructured":"ASAM e.V. (2025, October 24). ASAM OpenLABEL. Available online: https:\/\/www.asam.net\/standards\/detail\/openlabel\/."},{"key":"ref_27","unstructured":"Barnhill, R.E., and Riesenfeld, R.F. (1974). A Class of Local Interpolating Splines. Computer Aided Geometric Design, Academic Press."},{"key":"ref_28","unstructured":"Laurent, T. (2024). Train Ego-Path Detection on Railway Tracks Using End-to-End Deep Learning. arXiv."},{"key":"ref_29","unstructured":"Radford, A., Kim, J.W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., and Clark, J. (2021). Learning Transferable Visual Models From Natural Language Supervision. arXiv."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Sagastiberri, I., Larrazabal, M., S\u00e1nchez, M., Aranjuelo, N., Nieto, M., and De Eribe, D.O. (2024, January 29\u201331). Annotation Pipeline for Railway Track Segmentation. Proceedings of the 2024 IEEE 12th International Conference on Intelligent Systems (IS), Varna, Bulgaria.","DOI":"10.1109\/IS61756.2024.10705179"},{"key":"ref_31","unstructured":"NRK (2025, October 24). Nordlandsbanen: Minute by Minute, Season by Season. Available online: https:\/\/nrkbeta.no\/2013\/01\/15\/nordlandsbanen-minute-by-minute-season-by-season\/."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"483","DOI":"10.1007\/s11623-023-1803-z","article-title":"CertML: Initial Steps Towards Using N-Version Neural Networks for Improving AI Safety","volume":"47","author":"Abukhashab","year":"2023","journal-title":"Datenschutz Datensicherheit\u2014DuD"},{"key":"ref_33","unstructured":"Ja\u00df, P., Thomas, C., Hiebert, T., and Plettig, G. (2024, January 11\u201312). Towards safe obstacle detection for autonomous train operation: Combining track and switch detection neural networks for robust railway ego track detection. Proceedings of the ERTS 2024, Toulouse, France."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Ja\u00df, P., and Thomas, C. (2025). Using N-Version Architectures for Railway Segmentation with Deep Neural Networks. Mach. Learn. Knowl. Extr., 7.","DOI":"10.3390\/make7020049"}],"container-title":["Data"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2306-5729\/10\/12\/210\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,16]],"date-time":"2025-12-16T11:17:11Z","timestamp":1765883831000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2306-5729\/10\/12\/210"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,16]]},"references-count":34,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["data10120210"],"URL":"https:\/\/doi.org\/10.3390\/data10120210","relation":{"has-preprint":[{"id-type":"doi","id":"10.36227\/techrxiv.175616666.63799213\/v1","asserted-by":"object"}]},"ISSN":["2306-5729"],"issn-type":[{"value":"2306-5729","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,16]]}}}