{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T16:53:24Z","timestamp":1781110404081,"version":"3.54.1"},"reference-count":45,"publisher":"MDPI AG","issue":"6","license":[{"start":{"date-parts":[[2018,6,12]],"date-time":"2018-06-12T00:00:00Z","timestamp":1528761600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.mdpi.com"],"crossmark-restriction":true},"short-container-title":["Sensors"],"abstract":"<jats:p>Many accidents happen under shunting mode when the speed of a train is below 45 km\/h. In this mode, train attendants observe the railway condition ahead using the traditional manual method and tell the observation results to the driver in order to avoid danger. To address this problem, an automatic object detection system based on convolutional neural network (CNN) is proposed to detect objects ahead in shunting mode, which is called Feature Fusion Refine neural network (FR-Net). It consists of three connected modules, i.e., the depthwise-pointwise convolution, the coarse detection module, and the object detection module. Depth-wise-pointwise convolutions are used to improve the detection in real time. The coarse detection module coarsely refine the locations and sizes of prior anchors to provide better initialization for the subsequent module and also reduces search space for the classification, whereas the object detection module aims to regress accurate object locations and predict the class labels for the prior anchors. The experimental results on the railway traffic dataset show that FR-Net achieves 0.8953 mAP with 72.3 FPS performance on a machine with a GeForce GTX1080Ti with the input size of 320 \u00d7 320 pixels. The results imply that FR-Net takes a good tradeoff both on effectiveness and real time performance. The proposed method can meet the needs of practical application in shunting mode.<\/jats:p>","DOI":"10.3390\/s18061916","type":"journal-article","created":{"date-parts":[[2018,6,12]],"date-time":"2018-06-12T10:58:32Z","timestamp":1528801112000},"page":"1916","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":63,"title":["Automatic Railway Traffic Object Detection System Using Feature Fusion Refine Neural Network under Shunting Mode"],"prefix":"10.3390","volume":"18","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1814-530X","authenticated-orcid":false,"given":"Tao","family":"Ye","sequence":"first","affiliation":[{"name":"Beijing Institute of Remote Sensing and Equipment, 52 Yongding Road, Haidian District, Beijing 100039, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Baocheng","family":"Wang","sequence":"additional","affiliation":[{"name":"College of Computer and Science Technology, North China University of Technology, 5 Jin Yuan Zhuang Road, Shijingshan District, Beijing 100144, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7939-1902","authenticated-orcid":false,"given":"Ping","family":"Song","sequence":"additional","affiliation":[{"name":"School of Instrumentation Science and Opto-Electronics Engineering, Key Laboratory of Precision Opto-Mechatronics Technology, Ministry of Education, Beihang University, Beijing 100191, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Juan","family":"Li","sequence":"additional","affiliation":[{"name":"School of Instrumentation Science and Opto-Electronics Engineering, Key Laboratory of Precision Opto-Mechatronics Technology, Ministry of Education, Beihang University, Beijing 100191, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2018,6,12]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"81","DOI":"10.1049\/iet-its:20060081","article-title":"Intelligent transport systems and effects on road traffic accidents: State of the art","volume":"1","author":"Vaa","year":"2007","journal-title":"IET Intell. Transp. Syst."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"328","DOI":"10.1049\/iet-its.2011.0118","article-title":"Wireless technology applications to enhance traveller safety","volume":"6","author":"Edwards","year":"2012","journal-title":"IET Intell. Transp. Syst."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"454","DOI":"10.1049\/iet-its.2012.0138","article-title":"Proactive knowledge-based intelligent transportation system based on vehicular sensor networks","volume":"7","author":"Dimitrakopoulos","year":"2013","journal-title":"IET Intell. Transp. Syst."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"226","DOI":"10.1080\/15472450.2012.710158","article-title":"Perspectives on future transportation research: Impact of intelligent transportation system technologies on next-generation transportation modeling","volume":"16","author":"Ran","year":"2012","journal-title":"J. Intell. Transp. Syst."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"130","DOI":"10.1049\/iet-its.2015.0026","article-title":"Vision-based fault inspection of small mechanical components for train safety","volume":"10","author":"Liu","year":"2016","journal-title":"IET Intell. Transp. Syst."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"127","DOI":"10.1016\/j.neucom.2016.10.018","article-title":"Automatic multi-fault recognition in TFDS based on convolutional neural network","volume":"222","author":"Sun","year":"2017","journal-title":"Neurocomputing"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"2","DOI":"10.1109\/TIM.2015.2479101","article-title":"Automated Visual Inspection System for Bogie Block Key under Complex Freight Train Environment","volume":"65","author":"Liu","year":"2015","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"794","DOI":"10.1177\/0954409713495532","article-title":"Automated visual inspection of angle cocks during train operation","volume":"228","author":"Zhou","year":"2013","journal-title":"Proc. Inst. Mech. Eng. Part F"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"2611","DOI":"10.3923\/itj.2014.2611.2618","article-title":"Study of Moving Obstacle Detection at Railway Crossing by Machine Vision","volume":"13","author":"Pu","year":"2014","journal-title":"Inform. Technol. J."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"9","DOI":"10.1049\/iet-its.2012.0129","article-title":"Reliability of an in-vehicle warning system for railway level crossings\u2014A user-oriented analysis","volume":"8","year":"2014","journal-title":"IET Intell. Transp. Syst."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Silar, Z., and Dobrovolny, M. (2013, January 16\u201318). Utilization of Directional Properties of Optical Flow for Railway Crossing Occupancy Monitoring. Proceedings of the International Conference on IT Convergence and Security, Macau, China.","DOI":"10.1109\/ICITCS.2013.6717896"},{"key":"ref_12","unstructured":"Salmane, H., Khoudour, L., and Ruichek, Y. (September, January 30). Improving safety of level crossings by detecting hazard situations using video based processing. Proceedings of the IEEE International Conference on Intelligent Rail Transportation, Beijing, China."},{"key":"ref_13","first-page":"24","article-title":"Discussion on Increasing Establishment Quality of Shunting Operation Scheme","volume":"37","author":"Li","year":"2015","journal-title":"Railway Transp. Econ."},{"key":"ref_14","first-page":"28","article-title":"Thoughts on Shunting Operation Safety in Station","volume":"32","author":"Feng","year":"2014","journal-title":"Railway Freight Transp."},{"key":"ref_15","first-page":"63","article-title":"Thoughts on Safety Management of Railway Shunting Operation","volume":"32","author":"Feng","year":"2010","journal-title":"Railway Transp. Econ."},{"key":"ref_16","first-page":"26","article-title":"Analysis on Railway Shunting Accident and Study on the Countermeasure","volume":"31","author":"Zhang","year":"2009","journal-title":"China Railway"},{"key":"ref_17","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_18","doi-asserted-by":"crossref","first-page":"27","DOI":"10.1016\/j.neucom.2015.09.116","article-title":"Deep learning for visual understanding: A review","volume":"187","author":"Guo","year":"2016","journal-title":"Neurocomputing"},{"key":"ref_19","unstructured":"Howard, A.G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., Andreetto, M., and Adam, H. (arXiv, 2017). Mobilenets: Efficient convolutional neural networks for mobile vision applications, arXiv."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","article-title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","volume":"39","author":"Ren","year":"2017","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.Y., and Berg, A.C. (2016). SSD: Single Shot MultiBox Detector, Springer. Computer Vision\u2014ECCV 2016.","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"ref_22","unstructured":"(2018, June 09). Anti Collision Device Network [EB\/OL]. Available online: http:\/\/en.wikipedia.org\/wiki\/Anti_Collision_Device."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"234","DOI":"10.3724\/SP.J.1300.2013.20091","article-title":"A vehicle millimeter wave train collision avoidance radar system research","volume":"2","author":"Liu","year":"2013","journal-title":"J. Radar"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Silar, Z., and Dobrovolny, M. (2013, January 2\u20134). The obstacle detection on the railway crossing based on optical flow and clustering. Proceedings of the International Conference on Telecommunications and Signal Processing, Rome, Italy.","DOI":"10.1109\/TSP.2013.6614039"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"298","DOI":"10.2219\/rtriqr.58.4_298","article-title":"Frontal Obstacle Detection Using Background Subtraction and Frame Registration","volume":"58","author":"Nakasone","year":"2017","journal-title":"Q. Rep. RTRI"},{"key":"ref_26","unstructured":"Viola, P., and Jones, M. (2001, January 8\u201314). Rapid Object Detection using a Boosted Cascade of Simple Features. Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2001), Kauai, HI, USA."},{"key":"ref_27","first-page":"6","article-title":"Object detection with discriminatively trained part-based models","volume":"47","author":"Felzenszwalb","year":"2014","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","article-title":"The Pascal Visual Object Classes (VOC) Challenge","volume":"88","author":"Everingham","year":"2010","journal-title":"Int. J. Comput. Vis."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"640","DOI":"10.1109\/TCSVT.2016.2630731","article-title":"Incremental Learning with Saliency Map for Moving Object Detection","volume":"28","author":"Pang","year":"2018","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Chen, B.H., Shi, L.F., and Ke, X. (2018). A Robust Moving Object Detection in Multi-Scenario Big Data for Video Surveillance. IEEE Trans. Circuits Syst. Video Technol.","DOI":"10.1109\/TCSVT.2018.2828606"},{"key":"ref_31","unstructured":"Krizhevsky, A., Sutskever, I., and Hinton, G.E. (2012, January 3\u20138). ImageNet classification with deep convolutional neural networks. Proceedings of the International Conference on Neural Information Processing Systems, Lake Tahoe, CA, USA."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"154","DOI":"10.1007\/s11263-013-0620-5","article-title":"Selective Search for Object Recognition","volume":"104","author":"Uijlings","year":"2013","journal-title":"Int. J. Comput. Vis."},{"key":"ref_33","first-page":"1990","article-title":"Learning to segment object candidates","volume":"2","author":"Pinheiro","year":"2015","journal-title":"Adv. Neural Inform. Process. Syst."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Girshick, R.B., Donahue, J., Darrell, T., and Malik, J. (2014, January 23\u201328). Rich feature hierarchies for accurate object detection and semantic segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Columbus, OH, USA.","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"1904","DOI":"10.1109\/TPAMI.2015.2389824","article-title":"Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition","volume":"37","author":"He","year":"2015","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_36","unstructured":"Sermanet, P., Eigen, D., Zhang, X., Mathieu, M., Fergus, R., and LeCun, Y. (arXiv, 2013). OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks, arXiv."},{"key":"ref_37","unstructured":"Redmon, J., Divvala, S., Girshick, R., and Farhadi, A. (July, January 26). You only Look Once: Unified, Real-Time Object Detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA."},{"key":"ref_38","unstructured":"Fu, C.Y., Liu, W., Ranga, A., Tyagi, A., and Berg, A.C. (arXiv, 2017). DSSD: Deconvolutional Single Shot Detector, arXiv."},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., He, K., and Doll\u00e1r, P. (arXiv, 2017). Focal Loss for Dense Object Detection, arXiv.","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Zhang, S., Zhu, X., Lei, Z., Shi, H., Wang, X., and Li, S.Z. (2017, January 22\u201329). S^3FD: Single Shot Scale-Invariant Face Detector. Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy.","DOI":"10.1109\/ICCV.2017.30"},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Alom, M.Z., Hasan, M., Yakopcic, C., Taha, T.M., and Asari, V.K. (arXiv, 2017). Improved Inception-Residual Convolutional Neural Network for Object Recognition, arXiv.","DOI":"10.1007\/s00521-018-3627-6"},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Wang, M., Liu, B., and Foroosh, H. (arXiv, 2016). Factorized convolutional neural networks, arXiv.","DOI":"10.1109\/ICCVW.2017.71"},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Lin, T., Doll\u00b4ar, P., Girshick, R.B., He, K., Hariharan, B., and Belongie, S.J. (2017, January 21\u201326). Feature pyramid networks for object detection. Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref_44","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_45","unstructured":"Chen, L., Papandreou, G., Kokkinos, I., Murphy, K., and Yuille, A.L. (2015, January 7\u20139). Semantic image segmentation with deep convolutionalnets and fully connected CRFS. Proceedings of the ICLR, San Diego, CA, USA."}],"updated-by":[{"DOI":"10.3390\/s19143044","type":"correction","label":"Correction","source":"publisher","updated":{"date-parts":[[2018,6,12]],"date-time":"2018-06-12T00:00:00Z","timestamp":1528761600000}}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/18\/6\/1916\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,3]],"date-time":"2025-08-03T22:45:19Z","timestamp":1754261119000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/18\/6\/1916"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,6,12]]},"references-count":45,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2018,6]]}},"alternative-id":["s18061916"],"URL":"https:\/\/doi.org\/10.3390\/s18061916","relation":{"correction":[{"id-type":"doi","id":"10.3390\/s19143044","asserted-by":"object"}]},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,6,12]]}}}