{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,13]],"date-time":"2026-08-13T04:30:09Z","timestamp":1786595409306,"version":"build-2736575974"},"reference-count":35,"publisher":"MDPI AG","issue":"16","license":[{"start":{"date-parts":[[2026,8,11]],"date-time":"2026-08-11T00:00:00Z","timestamp":1786406400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100008530","name":"European Regional Development Fund","doi-asserted-by":"crossref","award":["BG-RRP 2.004-0005"],"award-info":[{"award-number":["BG-RRP 2.004-0005"]}],"id":[{"id":"10.13039\/501100008530","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Human presence in rail track areas represents a critical safety risk, particularly under low-visibility conditions where RGB-based monitoring systems become unreliable. This paper presents a thermal-only railway monitoring framework for human detection, auxiliary pose-based skeletal representation, identity-preserving tracking, temporal refinement, track zone classification, and camera-to-human distance estimation. The proposed approach combines a YOLO-based human detector trained on annotated thermal railway images with a pretrained YOLO pose model used as an auxiliary module to obtain a reduced 13-keypoint skeletal representation for thermal-image interpretation. ByteTrack is used for identity association across frames, while Kalman filtering reduces frame-to-frame keypoint localization jitter and supports short-term trajectory continuity during temporary missed detections. Unlike fully learned monocular depth estimation, the proposed distance estimation method exploits rail track geometry as a physical scene reference. A YOLO-based rail track detection model extracts the rail region, after which rail line candidates are fitted, and the apparent rail track width is measured at the vertical position of the detected human. Distance is estimated using an inverse-perspective relationship based on the known railway gauge. Experiments on thermal video sequences acquired along the Ni\u0161\u2013Prokuplje railway line demonstrate reliable human detection, stable tracking, effective track zone classification, and distance estimation consistent with real distance trends.<\/jats:p>","DOI":"10.3390\/s26165080","type":"journal-article","created":{"date-parts":[[2026,8,11]],"date-time":"2026-08-11T08:09:36Z","timestamp":1786435776000},"page":"5080","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Deep Learning-Driven Pose Extraction and Spatiotemporal Refinement for Human Detection and Distance Estimation on Railway Tracks with Thermal Imaging"],"prefix":"10.3390","volume":"26","author":[{"given":"Milan","family":"Pavlovi\u0107","sequence":"first","affiliation":[{"name":"The Academy of Technical and Preschool Studies Ni\u0161, Beogradska 18, 18000 Ni\u0161, Serbia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0430-8937","authenticated-orcid":false,"given":"Ivan","family":"\u0106iri\u0107","sequence":"additional","affiliation":[{"name":"Faculty of Mechanical Engineering, University of Ni\u0161, Aleksandra Medvedeva 14, 18000 Ni\u0161, Serbia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9811-6615","authenticated-orcid":false,"given":"Danijela Risti\u0107","family":"Durrant","sequence":"additional","affiliation":[{"name":"Faculty of Mechanical Engineering, University of Ni\u0161, Aleksandra Medvedeva 14, 18000 Ni\u0161, Serbia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1364-7746","authenticated-orcid":false,"given":"Milo\u0161","family":"Simonovi\u0107","sequence":"additional","affiliation":[{"name":"Faculty of Mechanical Engineering, University of Ni\u0161, Aleksandra Medvedeva 14, 18000 Ni\u0161, Serbia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-2775-936X","authenticated-orcid":false,"given":"Mladen","family":"Kuzev","sequence":"additional","affiliation":[{"name":"Faculty of Mechanical Engineering, University of Ni\u0161, Aleksandra Medvedeva 14, 18000 Ni\u0161, Serbia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8584-5958","authenticated-orcid":false,"given":"Lubomir","family":"Dimitrov","sequence":"additional","affiliation":[{"name":"Faculty of Mechanical Engineering, Technical University Sofia, Bul. Sv. Kliment Ohridski 8, 1756 Sofia, Bulgaria"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vlastimir","family":"Nikoli\u0107","sequence":"additional","affiliation":[{"name":"Faculty of Mechanical Engineering, University of Ni\u0161, Aleksandra Medvedeva 14, 18000 Ni\u0161, Serbia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,8,11]]},"reference":[{"key":"ref_1","unstructured":"International Union of Railways (UIC) (2025). UIC Safety Report 2025\u2014Significant Accidents 2024, International Union of Railways. Available online: https:\/\/shop.uic.org\/en\/other-reports\/14997-uic-safety-report-2025-significant-accidents-2024.html."},{"key":"ref_2","unstructured":"European Commission (2026, June 16). Railway Safety Statistics in the European Union. Eurostat 2025. Available online: https:\/\/ec.europa.eu\/eurostat\/web\/products-eurostat-news\/w\/ddn-20251216-2."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., and Farhadi, A. (2016, January 27\u201330). You Only Look Once: Unified, Real-Time Object Detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref_4","unstructured":"Bochkovskiy, A., Wang, C.-Y., and Liao, H.-Y.M. (2020). YOLOv4: Optimal Speed and Accuracy of Object Detection. arXiv."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"You, S., Ji, Y., Liu, S., Mei, C., Yao, X., and Feng, Y. (2022). A Thermal Infrared Pedestrian-Detection Method for Edge Computing Devices. Sensors, 22.","DOI":"10.3390\/s22176710"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Liu, Y., Su, H., Zeng, C., and Li, X. (2021). A Robust Thermal Infrared Vehicle and Pedestrian Detection Method in Complex Scenes. Sensors, 21.","DOI":"10.3390\/s21041240"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"S1551","DOI":"10.2298\/TSCI18S5551P","article-title":"Advanced Thermal Camera Based System for Object Detection on Rail Tracks","volume":"22","year":"2018","journal-title":"Therm. Sci."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"103796","DOI":"10.1016\/j.infrared.2021.103796","article-title":"Human Detection in Aerial Thermal Imaging Using a Fully Convolutional Regression Network","volume":"116","author":"Haider","year":"2021","journal-title":"Infrared Phys. Technol."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Risti\u0107-Durrant, D., Franke, M., and Michels, K. (2021). A Review of Vision-Based On-Board Obstacle Detection and Distance Estimation in Railways. Sensors, 21.","DOI":"10.3390\/s21103452"},{"key":"ref_10","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_11","doi-asserted-by":"crossref","first-page":"72","DOI":"10.1038\/s41597-024-02918-9","article-title":"RailFOD23: A Dataset for Foreign Object Detection on Railroad Transmission Lines","volume":"11","author":"Chen","year":"2024","journal-title":"Sci. Data"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"1315","DOI":"10.1038\/s41597-024-03952-3","article-title":"An Unmanned Aerial Vehicle Captured Dataset for Railroad Segmentation and Obstacle Detection","volume":"11","author":"Rampriya","year":"2024","journal-title":"Sci. Data"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"115095","DOI":"10.1016\/j.engappai.2026.115095","article-title":"A Sparse-to-Dense Guided Fusion Framework for Three-Dimensional Object Detection in Railway Environments","volume":"178","author":"Chen","year":"2026","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"6319","DOI":"10.1109\/TITS.2026.3680498","article-title":"Graph-MDETR: A Graph-Guided Mamba-DETR Network for UAV Catenary Support Components Detection in Electrified Railways","volume":"27","author":"Yang","year":"2026","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"289","DOI":"10.1016\/j.procs.2022.12.031","article-title":"Real-Time Obstacle Detection over Railway Track Using Deep Neural Networks","volume":"215","author":"Rahman","year":"2022","journal-title":"Procedia Comput. Sci."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"K\u00f6nig, D., Adam, M., Jarvers, C., Layher, G., Neumann, H., and Teutsch, M. (2017, January 21\u201326). Fully Convolutional Region Proposal Networks for Multispectral Human Detection. Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Honolulu, HI, USA.","DOI":"10.1109\/CVPRW.2017.36"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Hwang, S., Park, J., Kim, N., Choi, Y., and Kweon, I.S. (2015, January 7\u201312). Multispectral Pedestrian Detection: Benchmark Dataset and Baseline. Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA, USA.","DOI":"10.1109\/CVPR.2015.7298706"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Xu, D., Ouyang, W., Ricci, E., Wang, X., and Sebe, N. (2017, January 21\u201326). Learning Cross-Modal Deep Representations for Robust Pedestrian Detection. Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.451"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Zhang, L., Zhu, X., Chen, X., Yang, X., Lei, Z., and Liu, Z. (November, January 27). Weakly Aligned Cross-Modal Learning for Multispectral Pedestrian Detection. Proceedings of the 2019 IEEE\/CVF International Conference on Computer Vision (ICCV), Seoul, Republic of Korea.","DOI":"10.1109\/ICCV.2019.00523"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"172","DOI":"10.1109\/TPAMI.2019.2929257","article-title":"OpenPose: Realtime Multi-Human 2D Pose Estimation Using Part Affinity Fields","volume":"43","author":"Cao","year":"2021","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Sun, K., Xiao, B., Liu, D., and Wang, J. (2019, January 15\u201320). Deep High-Resolution Representation Learning for Human Pose Estimation. Proceedings of the 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00584"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Maji, D., Nagori, S., Mathew, M., and Poddar, D. (2022, January 19\u201320). YOLO-Pose: Enhancing YOLO for Multi Human Pose Estimation Using Object Keypoint Similarity Loss. Proceedings of the 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), New Orleans, LA, USA.","DOI":"10.1109\/CVPRW56347.2022.00297"},{"key":"ref_23","unstructured":"(2026, June 16). Ultralytics. Pose Estimation. Ultralytics Docs. Available online: https:\/\/docs.ultralytics.com\/tasks\/pose\/."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Guo, Y., Chen, Y., Deng, J., Li, S., and Zhou, H. (2023). Identity-Preserved Human Posture Detection in Infrared Thermal Images: A Benchmark. Sensors, 23.","DOI":"10.3390\/s23010092"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"35352","DOI":"10.1109\/ACCESS.2023.3264714","article-title":"Human Pose Estimation Using Thermal Images","volume":"11","author":"Smith","year":"2023","journal-title":"IEEE Access"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Bewley, A., Ge, Z., Ott, L., Ramos, F., and Upcroft, B. (2016, January 25\u201328). Simple Online and Realtime Tracking. Proceedings of the 2016 IEEE International Conference on Image Processing (ICIP), Phoenix, AZ, USA.","DOI":"10.1109\/ICIP.2016.7533003"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Wojke, N., Bewley, A., and Paulus, D. (2017, January 17\u201320). Simple Online and Realtime Tracking with a Deep Association Metric. Proceedings of the 2017 IEEE International Conference on Image Processing (ICIP), Beijing, China.","DOI":"10.1109\/ICIP.2017.8296962"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Sun, P., Jiang, Y., Yu, D., Weng, F., Yuan, Z., Luo, P., Liu, W., and Wang, X. (2022, January 23\u201327). ByteTrack: Multi-Object Tracking by Associating Every Detection Box. Proceedings of the European Conference on Computer Vision (ECCV 2022), Tel Aviv, Israel.","DOI":"10.1007\/978-3-031-20047-2_1"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Liang, H., Ma, Z., and Zhang, Q. (2022). Self-Supervised Object Distance Estimation Using a Monocular Camera. Sensors, 22.","DOI":"10.3390\/s22082936"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Lee, S., Han, K., Park, S., and Yang, X. (2022). Vehicle Distance Estimation from a Monocular Camera for Advanced Driver Assistance Systems. Symmetry, 14.","DOI":"10.3390\/sym14122657"},{"key":"ref_31","unstructured":"Haseeb, M.A., Guan, J., Risti\u0107-Durrant, D., and Gr\u00e4ser, A. (2018, January 1\u20135). DisNet: A Novel Method for Distance Estimation from Monocular Camera. Proceedings of the 10th Planning, Perception and Navigation for Intelligent Vehicles (PPNIV18), IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS 2018), Madrid, Spain."},{"key":"ref_32","first-page":"611","article-title":"AI Powered Obstacle Distance Estimation for Onboard Autonomous Train Operation","volume":"29","year":"2022","journal-title":"Teh. Vjesn."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"\u0106iri\u0107, I., Pavlovi\u0107, M., Risti\u0107-Durrant, D., Dimitrov, L., and Nikoli\u0107, V. (2025). FuzzyH Method for Distance Estimation in Autonomous Train Operation. Symmetry, 17.","DOI":"10.3390\/sym17040509"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"108579","DOI":"10.1016\/j.patcog.2022.108579","article-title":"Low-Resolution Human Pose Estimation","volume":"126","author":"Wang","year":"2022","journal-title":"Pattern Recognit."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"307","DOI":"10.12700\/APH.23.1.2026.1.18","article-title":"Autonomous Train Operation Obstacle Detection Based on Night Vision System","volume":"23","author":"Tomov","year":"2026","journal-title":"Acta Polytech. Hung."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/16\/5080\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,13]],"date-time":"2026-08-13T04:17:52Z","timestamp":1786594672000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/16\/5080"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,11]]},"references-count":35,"journal-issue":{"issue":"16","published-online":{"date-parts":[[2026,8]]}},"alternative-id":["s26165080"],"URL":"https:\/\/doi.org\/10.3390\/s26165080","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,11]]}}}