{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T17:03:47Z","timestamp":1780506227993,"version":"3.54.1"},"reference-count":39,"publisher":"MDPI AG","issue":"14","license":[{"start":{"date-parts":[[2024,7,11]],"date-time":"2024-07-11T00:00:00Z","timestamp":1720656000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Xi\u2019an Science and Technology Plan Project","award":["23GXFW0032"],"award-info":[{"award-number":["23GXFW0032"]}]},{"name":"Xi\u2019an Science and Technology Plan Project","award":["23GXFW0033"],"award-info":[{"award-number":["23GXFW0033"]}]},{"name":"Xi\u2019an Science and Technology Plan Project","award":["2023-JC-YB-347"],"award-info":[{"award-number":["2023-JC-YB-347"]}]},{"name":"Natural Science Basic Research Program of Shaanxi","award":["23GXFW0032"],"award-info":[{"award-number":["23GXFW0032"]}]},{"name":"Natural Science Basic Research Program of Shaanxi","award":["23GXFW0033"],"award-info":[{"award-number":["23GXFW0033"]}]},{"name":"Natural Science Basic Research Program of Shaanxi","award":["2023-JC-YB-347"],"award-info":[{"award-number":["2023-JC-YB-347"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Addressing the limitations of current railway track foreign object detection techniques, which suffer from inadequate real-time performance and diminished accuracy in detecting small objects, this paper introduces an innovative vision-based perception methodology harnessing the power of deep learning. Central to this approach is the construction of a railway boundary model utilizing a sophisticated track detection method, along with an enhanced UNet semantic segmentation network to achieve autonomous segmentation of diverse track categories. By employing equal interval division and row-by-row traversal, critical track feature points are precisely extracted, and the track linear equation is derived through the least squares method, thus establishing an accurate railway boundary model. We optimized the YOLOv5s detection model in four aspects: incorporating the SE attention mechanism into the Neck network layer to enhance the model\u2019s feature extraction capabilities, adding a prediction layer to improve the detection performance for small objects, proposing a linear size scaling method to obtain suitable anchor boxes, and utilizing Inner-IoU to refine the boundary regression loss function, thereby increasing the positioning accuracy of the bounding boxes. We conducted a detection accuracy validation for railway track foreign object intrusion using a self-constructed image dataset. The results indicate that the proposed semantic segmentation model achieved an MIoU of 91.8%, representing a 3.9% improvement over the previous model, effectively segmenting railway tracks. Additionally, the optimized detection model could effectively detect foreign object intrusions on the tracks, reducing missed and false alarms and achieving a 7.4% increase in the mean average precision (IoU = 0.5) compared to the original YOLOv5s model. The model exhibits strong generalization capabilities in scenarios involving small objects. This proposed approach represents an effective exploration of deep learning techniques for railway track foreign object intrusion detection, suitable for use in complex environments to ensure the operational safety of rail lines.<\/jats:p>","DOI":"10.3390\/s24144483","type":"journal-article","created":{"date-parts":[[2024,7,11]],"date-time":"2024-07-11T11:33:22Z","timestamp":1720697602000},"page":"4483","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":25,"title":["Research on the Method of Foreign Object Detection for Railway Tracks Based on Deep Learning"],"prefix":"10.3390","volume":"24","author":[{"given":"Shanping","family":"Ning","sequence":"first","affiliation":[{"name":"School of Mechatronic Engineering, Xi\u2019an Technological University, Xi\u2019an 710016, China"},{"name":"Railway Transportation Institute, Guangdong Communication Polytechnic, Guangzhou 510650, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Feng","family":"Ding","sequence":"additional","affiliation":[{"name":"School of Mechatronic Engineering, Xi\u2019an Technological University, Xi\u2019an 710016, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bangbang","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Mechatronic Engineering, Xi\u2019an Technological University, Xi\u2019an 710016, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2024,7,11]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"91427","DOI":"10.1109\/ACCESS.2021.3091550","article-title":"Deployment of Autonomous Trains in Rail Transportation: Current Trends and Existing Challenges","volume":"9","author":"Singh","year":"2021","journal-title":"IEEE Access"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"459","DOI":"10.1109\/TII.2022.3149931","article-title":"A Deep Generative Approach for Rail Foreign Object Detections via Semisupervised Learning","volume":"19","author":"Wang","year":"2023","journal-title":"IEEE Trans. Ind. Inf."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Simonovi\u0107, M., Bani\u0107, M., Stamenkovi\u0107, D., Franke, M., Michels, K., Schoolmann, I., Risti\u0107-Durrant, D., Ulianov, C., Dan-Stan, S., and Plesa, A. (2024). Toward the Enhancement of Rail Sustainability: Demonstration of a Holistic Approach to Obstacle Detection in Operational Railway Environments. Sustainability, 16.","DOI":"10.3390\/su16072613"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"9852","DOI":"10.1109\/JSEN.2020.3043193","article-title":"Research on Recognition Method of Railway Perimeter Intrusions Based on \u03a6-OTDR Optical Fiber Sensing Technology","volume":"21","author":"Meng","year":"2021","journal-title":"IEEE Sens. J."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1016\/j.sna.2016.11.026","article-title":"An optical fiber intrusion detection system for railway security","volume":"253","author":"Catalano","year":"2017","journal-title":"Sens. Actuators A Phys."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"232","DOI":"10.1016\/j.jsr.2022.08.019","article-title":"A pilot study evaluating the effectiveness of preventing railway suicides by mid-track fencing, which restrict easy access to high-speed train tracks","volume":"83","author":"Andersson","year":"2022","journal-title":"J. Saf. Res."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"423","DOI":"10.1080\/17457300.2019.1660376","article-title":"Patterns of pre-crash behaviour in railway suicides and the effect of corridor fencing: A natural experiment in New South Wales","volume":"26","author":"Gregor","year":"2019","journal-title":"Int. J. Inj. Control Saf. Promot."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"12180","DOI":"10.1109\/TITS.2023.3292934","article-title":"Skip Connection YOLO Architecture for Noise Barrier Defect De tection Using UAV-Based Images in High-Speed Railway","volume":"24","author":"Cui","year":"2023","journal-title":"IEEE Trans. Intell. Transp. 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","first-page":"101819","DOI":"10.1016\/j.aei.2022.101819","article-title":"UAV imagery based potential safety hazard evaluation for high-speed railroad using Real-time instance segmentation","volume":"55","author":"Wu","year":"2023","journal-title":"Adv. Eng. Inf."},{"key":"ref_11","first-page":"1","article-title":"RBNet: An Ultrafast Rendering-Based Architecture for Railway Defect Segmentation","volume":"72","author":"Li","year":"2023","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_12","first-page":"1","article-title":"An Efficient Few-Shot Object Detection Method for Railway Intrusion via Fine-Tune Approach and Contrastive Learning","volume":"72","author":"Ye","year":"2023","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"61973","DOI":"10.1109\/ACCESS.2020.2984264","article-title":"Multi-Target Defect Identification for Railway Track Line Based on Image Processing and Improved YOLOv3 Model","volume":"8","author":"Wei","year":"2020","journal-title":"IEEE Access"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"18051","DOI":"10.1109\/TITS.2022.3154751","article-title":"Foreign Body Detection in Rail Transit Based on a Multi-Mode Feature-Enhanced Convolutional Neural Network","volume":"23","author":"Ye","year":"2022","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref_15","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_16","doi-asserted-by":"crossref","first-page":"11301","DOI":"10.1109\/TITS.2021.3102613","article-title":"Enhanced Few-Shot Learning for Intrusion Detection in Railway Video Surveillance","volume":"23","author":"Gong","year":"2022","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"4011","DOI":"10.1109\/JSEN.2023.3340688","article-title":"An Improved Deep Learning Algorithm for Obstacle Detection in Complex Rail Transit Environments","volume":"24","author":"Qin","year":"2024","journal-title":"IEEE Sens. J."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"17952","DOI":"10.1109\/TITS.2022.3156267","article-title":"A Stable Lightweight and Adaptive Feature Enhanced Convolution Neural Network for Efficient Railway Transit Object Detection","volume":"23","author":"Ye","year":"2022","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Nan, Z., Zhu, G., Zhang, X., Lin, X., and Yang, Y. (2024). Development of a High-Precision Lidar System and Improvement of Key Steps for Railway Obstacle Detection Algorithm. Remote Sens., 16.","DOI":"10.3390\/rs16101761"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"57951","DOI":"10.1109\/ACCESS.2023.3284062","article-title":"EBSE-YOLO: High Precision Recognition Algorithm for Small Target Foreign Object Detection","volume":"11","author":"Wang","year":"2023","journal-title":"IEEE Access"},{"key":"ref_21","first-page":"1","article-title":"DALNet: A Rail Detection Network Based on Dynamic Anchor Line","volume":"73","author":"Yu","year":"2024","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"26550","DOI":"10.1109\/ACCESS.2024.3366184","article-title":"Research on Railway Track Extraction Method Based on Edge Detection and Attention Mechanism","volume":"12","author":"Weng","year":"2024","journal-title":"IEEE Access"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Dong, Q., Chen, X., Jiang, L., Wang, L., Chen, J., and Zhao, Y. (2024). Semantic Segmentation of Remote Sensing Images Depicting Environmental Hazards in High-Speed Rail Network Based on Large-Model Pre-Classification. Sensors, 24.","DOI":"10.3390\/s24061876"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"5135","DOI":"10.1007\/s00371-022-02650-8","article-title":"All-weather road drivable area segmentation method based on CycleGAN","volume":"39","author":"Chen","year":"2023","journal-title":"Vis. Comput."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Li, Z., Yuan, J., Li, G., Wang, H., Li, X., Li, D., and Wang, X. (2023). RSI-YOLO: Object Detection Method for Remote Sensing Images Based on Improved YOLO. Sensors, 23.","DOI":"10.3390\/s23146414"},{"key":"ref_26","first-page":"100571","article-title":"Railway obstacle intrusion warning mechanism integrating YOLO-based detection and risk assessment","volume":"38","author":"Zhang","year":"2024","journal-title":"J. Ind. Inf. Integr."},{"key":"ref_27","first-page":"3403137","article-title":"Railway Track Multi-component Segmentation Based on Residual Contextual Transformer","volume":"5","author":"Qiu","year":"2024","journal-title":"IEEE Sens. J."},{"key":"ref_28","first-page":"1","article-title":"CNN and Binocular Vision-Based Target Detection and Ranging Framework of Intelligent Railway System","volume":"73","author":"Liu","year":"2024","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"258","DOI":"10.1016\/j.patrec.2021.07.014","article-title":"Soft-Boundary Label Relaxation with class placement constraints for semantic segmentation of the railway environment","volume":"150","author":"Yuki","year":"2021","journal-title":"Pattern Recognit. Lett."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"1283","DOI":"10.1007\/s11442-020-1782-z","article-title":"Spatial pattern and developing mechanism of railway geo-systems based on track gauge: A case study of Eurasia","volume":"8","author":"Wang","year":"2020","journal-title":"J. Geogr. Sci."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Lv, H., Yan, H., Liu, K., Zhou, Z., and Jing, J. (2022). YOLOv5-AC: Attention Mechanism-Based Lightweight YOLOv5 for Track Pedestrian Detection. Sensors, 22.","DOI":"10.3390\/s22155903"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Zhou, J., Su, T., Li, K., and Dai, J. (2024). Small Target-YOLOv5: Enhancing the Algorithm for Small Object Detection in Drone Aerial Imagery Based on YOLOv5. Sensors, 24.","DOI":"10.3390\/s24010134"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"10719","DOI":"10.1007\/s00521-022-07007-9","article-title":"CDNet: A real-time and robust crosswalk detection network on Jetson nano based on YOLOv5","volume":"34","author":"Zhang","year":"2022","journal-title":"Neural Comput."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"104518","DOI":"10.1016\/j.imavis.2022.104518","article-title":"An improved YOLOv5 method for large objects detection with multi-scale feature cross-layer fusion network","volume":"125","author":"Qu","year":"2022","journal-title":"Image Vis. Comput."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"6083","DOI":"10.1109\/JSTARS.2021.3087555","article-title":"Multi-Scale Ship Detection From SAR and Optical Imagery Via A More Accurate YOLOv3","volume":"14","author":"Hong","year":"2021","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"60070","DOI":"10.1109\/ACCESS.2024.3392638","article-title":"Power Adapter Appearance Defect Detection Based on Task Feature Decoupling YOLOv8n","volume":"12","author":"Chen","year":"2024","journal-title":"IEEE Access"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"3717","DOI":"10.1109\/TIP.2023.3290519","article-title":"Conditional Boundary Loss for Semantic Segmentation","volume":"32","author":"Wu","year":"2023","journal-title":"IEEE Trans. Image Process."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"e2325572","DOI":"10.1080\/17452759.2024.2325572","article-title":"AM-SegNet for additive manufacturing in situ X-ray image segmentation and feature quantification","volume":"19","author":"Li","year":"2024","journal-title":"Virtual Phys. Prototyp."},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Zheng, X., Zou, J., Du, S., and Zhong, P. (2024). Small Target Detection in Refractive Panorama Surveillance Based on Improved YOLOv8. Sensors, 24.","DOI":"10.3390\/s24030819"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/24\/14\/4483\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T15:15:01Z","timestamp":1760109301000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/24\/14\/4483"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,11]]},"references-count":39,"journal-issue":{"issue":"14","published-online":{"date-parts":[[2024,7]]}},"alternative-id":["s24144483"],"URL":"https:\/\/doi.org\/10.3390\/s24144483","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,7,11]]}}}