Abstract
This study explores enhancing security and automation in railway transportation by evaluating the BiSeNetV2, YOLO, and DNet models for railway monitoring and segmentation. Tests were conducted in the Gazebo simulation environment and the field using the Anafi4K UAV, comparing the effectiveness of different algorithms. Additionally, the role of mathematical methods, such as Bezier curves and Bernstein polynomials, in supporting the autonomous flight capabilities of UAVs was examined. These methods have proven effective in helping UAVs follow railway lines by increasing maneuverability, contributing to successful flights. The combination of the BiSeNetV2 model, YOLO models, and these mathematical methods offers a robust solution for railway monitoring and segmentation. Future advancements and broader adoption of these technologies in industrial applications could enhance the safety and efficiency of rail transport. Furthermore, the developed DNet model demonstrated a 99% accuracy rate in segmenting foreign objects around railway lines, proving to be a significant alternative among deep learning models for railway monitoring and segmentation. The model’s performance highlights its potential to provide crucial solutions for security and automation in railway transportation.
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11760-024-03723-y/MediaObjects/11760_2024_3723_Fig1_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11760-024-03723-y/MediaObjects/11760_2024_3723_Fig2_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11760-024-03723-y/MediaObjects/11760_2024_3723_Fig3_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11760-024-03723-y/MediaObjects/11760_2024_3723_Fig4_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11760-024-03723-y/MediaObjects/11760_2024_3723_Fig5_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11760-024-03723-y/MediaObjects/11760_2024_3723_Fig6_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11760-024-03723-y/MediaObjects/11760_2024_3723_Fig7_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11760-024-03723-y/MediaObjects/11760_2024_3723_Fig8_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11760-024-03723-y/MediaObjects/11760_2024_3723_Fig9_HTML.png)
Similar content being viewed by others
Data availability
No datasets were generated or analysed during the current study.
References
Yin, J., Tang, T., Yang, L., Xun, J., Huang, Y., Gao, Z.: Research and development of automatic train operation for railway transportation systems: a survey. Transp. Res. Part C: Emerg. Technol. 85, 548–572 (2017)
Banić, M., Miltenović, A., Pavlović, M., Ćirić, I.: Intelligent machine vision based railway infrastructure inspection and monitoring using UAV. Facta Univ. Ser. Mech. Eng. 17(3), 357–364 (2019)
Cao, H., Wang, Y., Chen, J., Jiang, D., Zhang, X., Tian, Q., Wang, M.: Swin-unet: Unet-like pure transformer for medical image segmentation. In European conference on computer vision, pp. 205–218. Cham: Springer Nature Switzerland (2022).
Khan, M.A.M., Kee, S.H., Nahid, A.A.: Vision-based concrete-crack detection on railway sleepers using dense Unet model. Algorithms 16(12), 568 (2023)
Mammeri, A., Jabbar Siddiqui, A., Zhao, Y.: UAV-assisted railway track segmentation based on convolutional neural networks. 2021 IEEE 93rd Vehicular Technology Conference, VTC2021-Spring (2021). https://doi.org/10.1109/vtc2021-spring51267.2021.9448887.
Cao, Z., Qin, Y., Xie, Z., Li, Y., Gao, Y.: A railway intrusion detection framework based on vehicle front video. In International Conference on Electrical and Information Technologies for Rail Transportation, pp. 38–44. Singapore: Springer Singapore (2021).
Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: Unified, real-time object detection. In Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 779–788 (2016).
Chen, Q., Liu, L., Han, R., Qian, J., Qi, D.: Image identification method on high speed railway contact network based on YOLO v3 and SENet. In 2019 Chinese Control Conference (CCC), pp. 8772–8777. IEEE (2019).
Güçlü, E., Aydın, İ., Akın, E.: Measurement of railway sleepers spacing using mask R-CNN. In 2022 International Conference on Decision Aid Sciences and Applications (DASA), pp. 1416–1420. IEEE (2022).
Ikshwaku, S., Srinivasan, A., Varghese, A., Gubbi, J.: Railway corridor monitoring using deep drone vision. In Computational Intelligence: Theories, Applications and Future Directions-Volume II: ICCI-2017, pp. 361–372. Singapore: Springer Singapore (2018).
Pavlović, M.G., Ćirić, I.T., Ristić-Durrant, D., Nikolić, V.D., Simonović, M.B., Ćirić, M.V., Banić, M.S.: Advanced thermal camera based system for object detection on rail tracks. Therm. Sci. 22(Suppl. 5), 1551–1561 (2018)
Sabetghadam, B., Cunha, R., Pascoal, A.: Real-time trajectory generation for multiple drones using bézier curves. IFAC-PapersOnLine 53(2), 9276–9281 (2020)
Zendel, O., Murschitz, M., Zeilinger, M., Steininger, D., Abbasi, S., Beleznai, C.: Railsem19: a dataset for semantic rail scene understanding. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, pp. 0–0 (2019).
Katar, O., Duman, E.: Automated semantic segmentation for autonomous railway vehicles. Tehnički glasnik 16(4), 484–490 (2022)
Wang, S., Li, X., Chen, Z., Liu, Y.: A railway accident prevention system using an intelligent pilot vehicle. IEEE Transactions on Intelligent Transportation Systems (2023).
Li, B., Yuan, D., Yang, G., Xu, T., Sun, W.: Flexibility-residual BiSeNetV2 for GPR image decluttering. IEEE Transactions on Geoscience and Remote Sensing (2023).
Yu, C., Gao, C., Wang, J., Yu, G., Shen, C., Sang, N.: Bisenet v2: bilateral network with guided aggregation for real-time semantic segmentation. Int. J. Comput. Vision 129, 3051–3068 (2021)
Talaat, F.M., ZainEldin, H.: An improved fire detection approach based on YOLO-v8 for smart cities. Neural Comput. Appl. 35(28), 20939–20954 (2023)
Viso AI. YOLOv7: A powerful object detection algorithm, https://viso.ai/deep-learning/yolov7-guide/; 2024 [accessed 30 May 2024].
Rivera, Z.B., De Simone, M.C., Guida, D.: Unmanned ground vehicle modelling in Gazebo/ROS-based environments. Machines 7(2), 42 (2019)
García, J., Molina, J.M.: Simulation in real conditions of navigation and obstacle avoidance with PX4/Gazebo platform. Pers. Ubiquit. Comput. 26(4), 1171–1191 (2022)
Weiss, T., Babu, V. S., Behl, M.: Bezier curve based end-to-end trajectory synthesis for agile autonomous driving. In NeurIPS 2020 Machine Learning for Autonomous Driving Workshop (2020).
Lasrado, R. N., & Vijayasherly, V.: Unconditional generation of scalable chinese characters as bézier curve sequences. In 2023 3rd International conference on Artificial Intelligence and Signal Processing (AISP), pp. 1–7. IEEE (2023).
Junfeng, A., Jiqiang, L., Mengmeng, L., Gang, L., Huasheng, S.: Image change combined with CNN power subway vent valve state monitoring. SIViP 18(3), 2151–2166 (2024)
Ronneberger, O., Fischer, P., Brox, T.: Unet: convolutional networks for biomedical image segmentation. In Medical Image Computing and Computer-Assisted Intervention–MICCAI 2015: 18th International Conference, Munich, Germany, October 5–9, 2015, Proceedings, Part III 18, pp. 234–241. Springer International Publishing (2015).
Guo, C., Szemenyei, M., Pei, Y., Yi, Y., Zhou, W.: SD-UNet: a structured dropout U-Net for retinal vessel segmentation. In 2019 IEEE 19th International Conference on Bioinformatics and Bioengineering (BIBE), pp. 439–444. IEEE (2019).
Piao, S., Liu, J.: Accuracy improvement of UNet based on dilated convolution. J. Phys. Conf. Ser. 1345(5), 052066 (2019)
Gao, X., Jin, B.: Research on crack detection based on improved UNet. In 2020 7th International Conference on Information Science and Control Engineering (ICISCE), pp. 2098–2103. IEEE (2020).
Jahan, K., Umesh, J. P., Roth, M.: Anomaly detection on the rail lines using semantic segmentation and self-supervised learning. In 2021 IEEE Symposium Series on Computational Intelligence (SSCI), pp. 1–7. IEEE (2021).
Sevi, M., Aydın, İ: Improving Unet segmentation performance using an ensemble model in images containing railway lines. Turk. J. Electr. Eng. Comput. Sci. 31(4), 739–750 (2023)
Song, H., Wang, S., Gu, Z., Dai, P., Du, X., Cheng, Y.: Modeling and optimization of semantic segmentation for track bed foreign object based on attention mechanism. IEEE Access 9, 86646–86656 (2021)
Acknowledgements
This work was supported by the Scientific Research Projects Coordination Unit of Fırat University. Project number ADEP.22.02.
Author information
Authors and Affiliations
Contributions
Authors’ contributions: Mehmet SEVİ: Conceptualization, Methodology, Software. İlhan AYDIN: Visualization, Analysis, Writing, review and editing.
Corresponding author
Ethics declarations
Competing interests
The authors declare no competing interests.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Sevi, M., Aydın, İ. Enhanced railway monitoring and segmentation using DNet and mathematical methods. SIViP 19, 106 (2025). https://doi.org/10.1007/s11760-024-03723-y
Received:
Revised:
Accepted:
Published:
DOI: https://doi.org/10.1007/s11760-024-03723-y