{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,29]],"date-time":"2026-08-29T03:29:50Z","timestamp":1787974190593,"version":"build-2784847793"},"reference-count":50,"publisher":"MDPI AG","issue":"12","license":[{"start":{"date-parts":[[2020,11,29]],"date-time":"2020-11-29T00:00:00Z","timestamp":1606608000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Micromachines"],"abstract":"<jats:p>Multiple projects within the rail industry across different regions have been initiated to address the issue of over-population. These expansion plans and upgrade of technologies increases the number of intersections, junctions, and level crossings. A level crossing is where a railway line is crossed by a road or right of way on the level without the use of a tunnel or bridge. Level crossings still pose a significant risk to the public, which often leads to serious accidents between rail, road, and footpath users and the risk is dependent on their unpredictable behavior. For Great Britain, there were three fatalities and 385 near misses at level crossings in 2015\u20132016. Furthermore, in its annual safety report, the Rail Safety and Standards Board (RSSB) highlighted the risk of incidents at level crossings during 2016\/17 with a further six fatalities at level crossings including four pedestrians and two road vehicles. The relevant authorities have suggested an upgrade of the existing sensing system and the integration of new novel technology at level crossings. The present work addresses this key issue and discusses the current sensing systems along with the relevant algorithms used for post-processing the information. The given information is adequate for a manual operator to make a decision or start an automated operational cycle. Traditional sensors have certain limitations and are often installed as a \u201csingle sensor\u201d. The single sensor does not provide sufficient information; hence another sensor is required. The algorithms integrated with these sensing systems rely on the traditional approach, where background pixels are compared with new pixels. Such an approach is not effective in a dynamic and complex environment. The proposed model integrates deep learning technology with the current Vision system (e.g., CCTV to detect and localize an object at a level crossing). The proposed sensing system should be able to detect and localize particular objects (e.g., pedestrians, bicycles, and vehicles at level crossing areas.) The radar system is also discussed for a \u201ctwo out of two\u201d logic interlocking system in case of fail-mechanism. Different techniques to train a deep learning model are discussed along with their respective results. The model achieved an accuracy of about 88% from the MobileNet model for classification and a loss metric of 0.092 for object detection. Some related future work is also discussed.<\/jats:p>","DOI":"10.3390\/mi11121055","type":"journal-article","created":{"date-parts":[[2020,11,29]],"date-time":"2020-11-29T21:00:57Z","timestamp":1606683657000},"page":"1055","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":45,"title":["Object Detection at Level Crossing Using Deep Learning"],"prefix":"10.3390","volume":"11","author":[{"given":"Muhammad Asad Bilal","family":"Fayyaz","sequence":"first","affiliation":[{"name":"Department of Engineering, Manchester Metropolitan University, Manchester M15 6BH, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1172-1383","authenticated-orcid":false,"given":"Christopher","family":"Johnson","sequence":"additional","affiliation":[{"name":"Department of Engineering, Manchester Metropolitan University, Manchester M15 6BH, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2020,11,29]]},"reference":[{"key":"ref_1","unstructured":"Network Rail (2020). Our Delivery Plan for 2019\u20132024, Network Rail. Available online: https:\/\/www.networkrail.co.uk\/who-we-are\/publications-and-resources\/our-delivery-plan-for-2019\u20132024\/#downloadall."},{"key":"ref_2","unstructured":"Network Rail (2020). Crossrail, Network Rail. Available online: https:\/\/www.networkrail.co.uk\/running-the-railway\/railway-upgrade-plan\/key-projects\/crossrail."},{"key":"ref_3","unstructured":"Network Rail (2020). Great North. Rail Project, Network Rail. Available online: https:\/\/www.networkrail.co.uk\/running-the-railway\/railway-upgrade-plan\/key-projects\/great-north-rail-project."},{"key":"ref_4","unstructured":"European Union Agency for Railways (2017). Railway Safety in the European Union\u2014Safety Overview 2017, Publications Office of the EU."},{"key":"ref_5","unstructured":"Steven, A. (2020, November 29). Level Crossings the Law Commission and The Scottish Law Commission, Available online: https:\/\/www.scotlawcom.gov.uk\/law-reform\/law-reform-projects\/completed-projects\/level-crossings\/."},{"key":"ref_6","unstructured":"Office of Rail and Road (2017). Annual Safety Performance Report. A Reference Guide to Safety Trends on GB Railways 2016\/17."},{"key":"ref_7","unstructured":"Office of Rail and Road (2020, November 29). Annual Health and Safety Report of Performance on Britain\u2019s Railways: 2015\u20132016. (Issue July), Available online: https:\/\/orr.gov.uk\/__data\/assets\/pdf_file\/0020\/22457\/annual-health-and-safety-report-july-2016."},{"key":"ref_8","unstructured":"Network Rail (2018). Catalogue of Network Rail Standards, Network Rail. Available online: https:\/\/www.networkrail.co.uk\/wp-content\/uploads\/2018\/12\/NR_CAT_STP_001-Issue-110."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"45","DOI":"10.2174\/1874447801105010045","article-title":"A Video-Based Object Detection System for Improving Safety at Level Crossings","volume":"5","author":"Fakhfakh","year":"2011","journal-title":"Open Transp. J."},{"key":"ref_10","unstructured":"Darlington, P. (2020, November 29). Obstacle Detection for Level Crossings. Rail News. Available online: https:\/\/www.railengineer.co.uk\/2017\/05\/30\/obstacle-detection-for-level-crossings\/."},{"key":"ref_11","first-page":"121","article-title":"Methods for Detection of Obstacles on the Railway Level Crossing","volume":"16","year":"2016","journal-title":"Sci. Expert Conf. Railw. RAILCON"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Ohta, M. (2005). Level Crossings Obstacle Detection System Using Stereo Cameras. Quarterly Report of RTRI, Railway Technical Research Institute.","DOI":"10.2219\/rtriqr.46.110"},{"key":"ref_13","unstructured":"FLIR (2020, November 29). Thermal Imaging for Safety and Efficiency in Public Transportation. Available online: https:\/\/www.flir.co.uk\/discover\/traffic\/public-transportation\/thermal-imaging-for-safety-and-efficiency-in-public-transportation\/."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Sato, K., Arai, H., Shimizu, T., and Takada, M. (1998, January 20\u201323). Obstruction detector using ultrasonic sensors for upgrading the safety of a level crossing. Proceedings of the International Conference on Developments in Mass Transit Systems, London, UK.","DOI":"10.1049\/cp:19980140"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Amaral, V., Marques, F., Louren\u00e7o, A., Barata, J., and Santana, P. (2016). Laser-Based Obstacle Detection at Railway Level Crossings. J. Sens.","DOI":"10.1155\/2016\/1719230"},{"key":"ref_16","first-page":"51","article-title":"3-D laser radar level crossing obstacle detection system","volume":"41","author":"Hisamitsu","year":"2008","journal-title":"IHI Eng. Rev."},{"key":"ref_17","unstructured":"Spowart, F.M. (2014). Level Crossing CCTV Notes, Network Rail."},{"key":"ref_18","unstructured":"Hilleary, T.N., and John, R.S. (2011, January 18\u201321). Development and Testing of a Radar-Based Non-Embedded Vehicle Detection System for Four Quadrant Gate Warning Systems and Blocked Crossing Detection. Proceedings of the Arema 2011 Annual Conference, Minneapolis, MN, USA."},{"key":"ref_19","unstructured":"Network Rail (2012). Signalling Design: Module X02\u2014Level Crossings: Common Design Requirements, Network Rail."},{"key":"ref_20","first-page":"858","article-title":"Survey on Moving Object Detection Techniques","volume":"4","author":"Patel","year":"2015","journal-title":"Int. J. Comput. Sci. Mob. Comput."},{"key":"ref_21","unstructured":"Stauffer, C., and Grimson, W.E.L. (1999, January 23\u201325). Adaptive background mixture models for real-time tracking. Proceedings of the 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149), Fort Colling, CO, USA."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Allili, M.S., Bouguila, N., and Ziou, D. (2007, January 28\u201330). Finite Generalized Gaussian Mixture Modeling and Applications to Image and Video Foreground Segmentation. Proceedings of the Fourth Canadian Conference on Computer and Robot Vision (CRV\u201907), Montreal, QC, Canada.","DOI":"10.1109\/CRV.2007.33"},{"key":"ref_23","unstructured":"Piccardi, M. (2004, January 10\u201313). Background subtraction techniques: A review. Proceedings of the IEEE International Conference on Systems, Man and Cybernetics Background, Hague, The Netherlands."},{"key":"ref_24","unstructured":"Leonardis, A. (2020, November 29). Subspace Methods for Visual Learning and Recognition. In Faculty of Computer and Information Science. Available online: papers3:\/\/publication\/uuid\/F61BA0CC-4EF2-4B55-AFC1-8FCB13C40679."},{"key":"ref_25","first-page":"147","article-title":"Recent Advanced Statistical Background Modeling for Foreground Detection\u2014A Systematic Survey","volume":"4","author":"Bouwmans","year":"2011","journal-title":"Recent Pat. Comput. Sci."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"303","DOI":"10.1007\/s11263-010-0399-6","article-title":"Incremental Tensor Subspace Learning and Its Applications to Foreground Segmentation and Tracking","volume":"91","author":"Hu","year":"2010","journal-title":"Int. J. Comput. Vis."},{"key":"ref_27","unstructured":"Wang, J., Bebis, G., and Miller, R. (2006, January 17\u201322). Robust video-based surveillance by integrating target detection with tracking. Proceedings of the N 2006 Conference on Computer Vision and Pattern Recognition Workshop (CVPRW\u201906), New York, NY, USA."},{"key":"ref_28","first-page":"65","article-title":"A Technical Review on Background Subtraction and Object Tracking on the Detection of Objects","volume":"5","author":"Chinmayi","year":"2017","journal-title":"Int. J. Innov. Res. Comput. Commun. Eng."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"223","DOI":"10.2174\/2213275910902030223","article-title":"Subspace Learning for Background Modeling: A Survey","volume":"2","author":"Bouwmans","year":"2009","journal-title":"Recent Pat. Comput. Sci."},{"key":"ref_30","first-page":"567","article-title":"Vision based obstacle detection on railway track","volume":"116","author":"Manikandan","year":"2017","journal-title":"Int. J. Pure Appl. Math."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep Learning","volume":"521","author":"LeCun","year":"2015","journal-title":"Nature"},{"key":"ref_32","unstructured":"Matlab (2020, February 26). What Is Deep Learning? 3 Things You Need to Know. Available online: https:\/\/uk.mathworks.com\/discovery\/deep-learning.html."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Colangelo, P., Nasiri, N., Mishra, A., Nurvitadhi, E., Margala, M., and Nealis, K. (May, January 29). Exploration of Low Numeric Precision Deep Learning Inference Using Intel FPGAs. Proceedings of the 2018 IEEE 26th Annual International Symposium on Field-Programmable Custom Computing Machines (FCCM), Boulder, CO, USA.","DOI":"10.1109\/FCCM.2018.00020"},{"key":"ref_34","unstructured":"Wang, N., Choi, J., and Gopalakrishnan, K. (2020, November 29). 8-Bit Precision for Training Deep Learning Systems. IBM 2018. Available online: https:\/\/www.ibm.com\/blogs\/research\/2018\/12\/8-bit-precision-training\/."},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Fayyaz, M.A.B., Alexoulis-Chrysovergis, A.C., Southgate, M.J., and Johnson, C. (2020). A review of the technological developments for interlocking at level crossing. Proceedings of the Institution of Mechanical Engineers, Part. F. J. Rail Rapid Transit.","DOI":"10.1177\/0954409720941726"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"1263","DOI":"10.1109\/LRA.2020.2967272","article-title":"CNN Based Road User Detection Using the 3D Radar Cube","volume":"5","author":"Palffy","year":"2020","journal-title":"IEEE Robot. Autom. Lett."},{"key":"ref_37","unstructured":"Kaul, P., De Martini, D., Gadd, M., and Newman, P. (November, January 19). RSS-Net: Weakly-Supervised Multi-Class Semantic Segmentation with FMCW Radar. Proceedings of the IEEE Intelligent Vehicles Symposium, Las Vegas, NV, USA."},{"key":"ref_38","unstructured":"Anwar, A. (2020, November 29). Difference between AlexNet, VGGNet, ResNet and Inception. Medium-Towards Data Science. Available online: https:\/\/towardsdatascience.com\/the-w3h-of-alexnet-vggnet-resnet-and-inception-7baaaecccc96."},{"key":"ref_39","unstructured":"Simonyan, K., and Zisserman, A. (2015, January 7\u20139). Very deep convolutional networks for large-scale image recognition. Proceedings of the ICLR, San Diego, CA, USA."},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., Van Der Maaten, L., and Weinberger, K.Q. (2017, January 21\u201326). Densely connected convolutional networks. Proceedings of the 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., and Rabinovich, A. (2015, January 7\u201312). Going Deeper with Convolutions. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA.","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Chollet, F. (2017, January 21\u201326). Xception: Deep learning with depthwise separable convolutions. Proceedings of the 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.195"},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 12). Deep residual learning for image recognition. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_44","unstructured":"Howard, A.G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., Andreetto, M., and Adam, H. (2013). MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications. arXiv."},{"key":"ref_45","doi-asserted-by":"crossref","unstructured":"Tompson, J., Goroshin, R., Jain, A., Lecun, Y., and Bregler, C. (2015, January 7\u201312). Efficient Object Localization Using Convolutional Networks. Proceedings of the Conference on Computer Vision and Pattern Recognition, Boston, MA, USA.","DOI":"10.1109\/CVPR.2015.7298664"},{"key":"ref_46","unstructured":"Ren, S., He, K., and Girshick, R. (2015). Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. Adv. Neural Inf. Process. Syst., 91\u201399."},{"key":"ref_47","doi-asserted-by":"crossref","unstructured":"Lin, T., Dollar, P., Girshick, R., He, K., Hariharan, B., and Belongie, S. (2017, January 21\u201326). Feature pyramid network for object detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref_48","first-page":"10","article-title":"A review of design and maintenance for railway safety-the current status and future aspects in the UK railway industry","volume":"2","author":"An","year":"2005","journal-title":"World J. Eng."},{"key":"ref_49","unstructured":"Ebeling, C.E. (2004). An Introduction to Reliability and Maintainability Engineering, Tata McGraw-Hill Education."},{"key":"ref_50","unstructured":"Nicholls, D. (2005). System Reliability Toolkit, Riac."}],"container-title":["Micromachines"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-666X\/11\/12\/1055\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T10:39:10Z","timestamp":1760179150000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-666X\/11\/12\/1055"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,11,29]]},"references-count":50,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2020,12]]}},"alternative-id":["mi11121055"],"URL":"https:\/\/doi.org\/10.3390\/mi11121055","relation":{},"ISSN":["2072-666X"],"issn-type":[{"value":"2072-666X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,11,29]]}}}