شناسایی مسیر حرکت قطار برای تشخیص مانع در راه‌آهن با استفاده از یادگیری‌عمیق

نوع مقاله : علمی - پژوهشی

نویسندگان
فاطمه خزاعی 1
محمدرضا محمدی 2
حسین بلندی 3
1 کارشناس ارشد، گروه مهندسی کنترل، دانشکده مهندسی برق، دانشگاه علم و صنعت ایران، تهران، ایران
2 استادیار، گروه هوش مصنوعی، دانشکده مهندسی کامپیوتر، دانشگاه علم و صنعت ایران، تهران، ایران
3 استاد، گروه مهندسی کنترل، دانشکده مهندسی برق، دانشگاه علم و صنعت ایران، تهران، ایران
10.22119/jte.2025.480785.2718
چکیده
در این مطالعه، روشی برای تشخیص مانع در راه‌آهن ارائه شده است. این فرایند به سه مرحله تفکیک‌پذیر است: در مرحله اول، تمامی‌ اشیاء موجود در تصویر توسط شبکه YOLO شناسایی می‌شوند. در مرحله دوم، نیاز است که تمامی ریل‌های موجود در تصویر شناسایی شوند، به همین منظور، شبکه UNet روی مجموعه‌داده  Railsem19آموزش داده شده است. در ادامه این مرحله، بایستی مسیر حرکت قطار از میان ریل‌های شناسایی شده جدا شود؛ بنابراین، به طراحی و شبیه‌سازی نوعی الگوریتم شناسایی مسیر حرکت قطار پرداخته شده که علاوه بر توانایی شناسایی مسیر حرکت قطار در شرایطی که ریل‌ها کاملاً از هم مجزا هستند، در بعضی از شرایط خاص مانند نواحی جلوی سوزن که ریل به دوشاخه تقسیم می‌شود، نیز توانایی تشخیص مسیر حرکت قطار را دارد. در مرحله سوم، اشتراک بین مسیر حرکت قطار و مکان اشیاء به‌دست‌آمده توسط YOLO بررسی می‌شود. در صورت اشتراک، مانع در مسیر حرکت قطار بوده و در غیر این صورت، مسیر ایمن در نظر گرفته می‌شود. الگوریتم پیشنهادی تشخیص مانع، پس از شبیه‌سازی، روی مجموعه‌داده شامل ۱۶۶۴ تصویر مورد ارزیابی قرار گرفت و  بادقت (Accuracy) حدود 87 درصد، قادر بود موانع را تشخیص دهد. سپس، به بررسی نتایج الگوریتم تشخیص سوزن پیشنهادی پرداخته شده و مشاهده شد که این الگوریتم نیز توانایی شناسایی مسیر حرکت قطار بادقت بالاAccuracy) نزدیک به 99 درصد) را دارد.

کلیدواژه‌ها

عنوان مقاله English

Identifying the Path of the Train to Detect the Obstacle in the Railway using Deep Learning

نویسندگان English

Fatemeh khazaee 1
Mohammad Reza Mohammadi 2
Hossein Blandi 3
1 M.Sc., Department of Control Engineering, School of Electrical Engineering, Iran University of Science and Technology, Tehran, Iran
2 Assistant Professor, Department of artificial intelligence, School of Computer Engineering, Iran University of Science and Technology, Tehran, Iran
3 Professor, Department of Control Engineering, School of Electrical Engineering, Iran University of Science and Technology, Tehran, Iran
چکیده English

In this paper, a method for obstacle detection in railways is presented. This process can be divided into three stages: In the first step, all the objects in the image are identified by the YOLO network. In the second step, it is necessary to identify all the rails in the image, for this purpose, the UNet network is trained on the Railsem19 dataset. In the continuation of this step, the train path must be separated from the identified rails; Therefore, the design and simulation of a kind of train path identification algorithm has been done, which in addition to the ability to identify the train path in conditions where the rails are completely separated, in some special conditions such as the areas in front of the Railroad switch where the rail is divided several branches, also has the ability It detects the direction of the train. In the third step, the correspondence between the train trajectory and the location of objects obtained by YOLO is checked. If there is a subscription, the obstacle is in the path of the train and otherwise, the path is considered safe. The proposed obstacle detection algorithm, after simulation, was evaluated on a dataset containing 1664 images and was able to detect obstacles with an accuracy of about 87%. Then, the results of the proposed Railroad switch detection algorithm were analyzed and it was observed that this algorithm also has the ability to identify the path of the train with high accuracy (accuracy close to 99%).

کلیدواژه‌ها English

Deep learning, Railway, Object detection, Railroad switch, Train path
- صندیدزاده, م., & کولائیان, س. (1402). فصلنامه مهندسی حمل و نقل. نظارت تصویری بر موانع حمل‌و‌نقل ریلی با استفاده از روش‌های مبتنی بر یادگیری عمیق.
 
- Zhang, Q., Yan , F., Song , W., Wang , R., & Li, G. (2023). Automatic Obstacle Detection Method for the Train Based on Deep Learning. Sustainability, 1-14.
 
- Badrinarayanan, V., Handa, A., & Cipolla, R. (2015). SegNet: A Deep Convolutional Encoder-Decoder Architecture for Robust Semantic Pixel-Wise Labelling. Computer Vision and Pattern Recognition, 1-10.
 
- Belyaev, S., Popov, I., Shubnikov, V., Popov, P., Boltenkova, E., & Savchuk, D. (2020). Railroad semantic segmentation on high-resolution images. IEEE 23rd International Conference on Intelligent Transportation Systems (ITSC).
- Cordts, M., Omran, M., Ramos, S., Rehfeld, T., Enzweiler, M., & Benenson, R. (2016). The Cityscapes Dataset for Semantic Urban Scene Understanding. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 3213-3223.
 
- Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009). ImageNet: A large-scale hierarchical image database. 2009 IEEE Conference on Computer Vision and Pattern Recognition, 248-255 , Miami, FL, USA.
 
- Dent, M., & Marinov, M. (2019). Introducing Automated Obstacle Detection to British Level Crossings. Springer International Publishing, 37-80.
- Drizi, H. K., & Boukadoum, M. (2024). CNN Model with Transfer learning and Data Augmentation for Obstacle Detection in Rail Systems. 2024 IEEE International Symposium on Circuits and Systems (ISCAS), 1-5, Singapore.
 
- Guan, L., Jia, L., Xie, Z., & Yin, C. (2022). A Lightweight Framework for Obstacle Detection in the Railway Image Based on Fast Region Proposal and Improved YOLO-Tiny Network. IEEE Access, 1-16.
 
- He, D., Zou, Z., Chen, Y., Liu, B., & Miao, J. (2021). Rail Transit Obstacle Detection Based on Improved CNN. IEEE Transactions on Instrumentation and Measurement, 1-14.
 
- He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep Residual Learning for Image Recognition. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 770-778. Las Vegas, NV, USA.
 
- Hsieh, H.-H., Hsu, C.-Y., Ke, P.-Y., Liu, G.-S., & Lin, C.-P. (2015). Appling Lidar-based obstacle detection and wireless image transmission system for improving safety at level crossings. 2015 International Carnahan Conference on Security Technology (ICCST), 363-367,Taipei, Taiwan.
 
- Karakose, M., Akın, E., & Tastimur, C. (2013). Image Processing Based Level Crossing Detection and Foreign Objects Recognition Approach in Railways,. International Journal of Applied Mathematics, Electronics and Computers,1,19-23.
 
- LI , Y., DONG, H., LI, H., ZHANG, X., Zhang, B., & XIAO, Z. (2020). Multi-block SSD based on small object detection for UAV railway scene surveillance. Chinese Journal of Aeronautics, 33(6), 1747-1755.
 
- Meng, C., Wang, Z., Shi, L., Gao, Y., Tao, Y., & Wei, L. (2023). SDRC-YOLO: A Novel Foreign Object Intrusion Detection Algorithm in Railway Scenarios. journal of Electronics, , 1-16.
 
- Nakason, R., Nagamine, N., Ukai, M., & Mukojima, H. (2017). Frontal Obstacle Detection Using Background Subtraction and Frame Registration. Quarterly Report of RTRI.
 
- Qi, S., & Yu, D. (2021). Railway obstacle detection based on radar and image data fusion. Journal of Physics: Conference Series, 1-8.
 
- Qi, Z., Ma, D., Xu, J., Xiang, A., & Qu, H. (2024). Improved YOLOv5 Based on Attention Mechanism and FasterNet for Foreign Object Detection on Railway and Airway tracks," Computer Vision and Pattern Recognition. Computer Vision and Pattern Recognition, 1-5.
 
- Rahman, F. U., Ahmed, M., Hasan, M., & Jahan , N. (2022). Real-Time Obstacle Detection Over Railway Track using Deep Neural Networks. Procedia Computer Science, 289-298.
 
- Ristic-Durrant , D., Haseeb, M. A., Franke, M., Banic, M. S., Simonovic, M., & Stamenković, D. (2020). Artificial Intelligence for Obstacle Detection in Railways: Project SMART and Beyond. Dependable Computing - EDCC 2020 Workshops,44-55.
 
- S, A. (2019). Image Processing based Real Time Obstacle Detection and Alert System for Trains. 2019 3rd International conference on Electronics, Communication and Aerospace Technology (ICECA), 740-745, Coimbatore, India.
 
- Sevi, M., & Aydın, İ. (2023). Detection of Foreign Objects Around the Railway Line with YOLOv8. Journal of Computer Science, 19-23.
 
- Wang, C.-Y., Bochkovskiy, A., & Liao, H.-Y. M. (2022). Yolov7: Trainable bag-of-freebies sets new state-of-the art for real-time object detectors. Conference on Computer Vision and Pattern Recognition (CVPR), 7464-7475.
 
- Wang, Y., Wang, L., Hu, Y., & Qiu, J. (2019). RailNet: A Segmentation Network for Railroad Detection. IEEE Access, 143772-143779.
 
- Wang, Z., Wu, X., Yu, G., & Li, M. (2018). Efficient Rail Area Detection Using Convolutional Neural Network. IEEE Access, 6, 77655-77664.
 
- Xu, Y., Gao, C., Yuan, L., Tang, S., Wei, G., & Wei, G. (2019). Real-time Obstacle Detection Over Rails Using Deep Convolutional Neural Network. 2019 IEEE Intelligent Transportation Systems Conference (ITSC), 1007-1012, Auckland, New Zealand.
 
- Yao, Z., He, D., Chen, Y., Liu, B., Miao, J., & Deng, J. (2020). Inspection of exterior substance on high-speed train bottom based on improved deep learning method. Journal of the International Measurement Confederation,1-12.
 
- Zendel, O., Murschitz, M., Zeilinger, M., Steininger, D., Abbasi, S., & Beleznai, C. (2019). RailSem19: A Dataset for Semantic Rail Scene Understanding. in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW),1221-1229.
 
- Zhao, Z., Kang, J., Sun , Z., Ye, T., & Wu, B. (2024). real-time and high-accuracy railway obstacle detection method using lightweight CNN and improved transformer. Journal of the International Measurement Confederation, 238,1-16.

  • تاریخ دریافت 08 مهر 1403
  • تاریخ بازنگری 01 بهمن 1403
  • تاریخ پذیرش 08 بهمن 1403