Russian Federation
employee
Russian Federation
Russian Federation
Russian Federation
Russian Federation
UDC 004.93
UDC 656.2
the article discusses an approach to building an intelligent system for detecting anomalous objects in the railway zone using real-time video stream. The relevance of the research is driven by the need to improve the efficiency and objectivity of monitoring the state of railway infrastructure and rolling stock, as well as to reduce the influence of the human factor in the analysis of visual information. Unlike classical detection tasks for predefined objects, this work focuses on identifying deviations from the normal state of the observed scene, which allows covering a wide class of potentially dangerous and technologically abnormal situations. A formalised problem statement for anomalous object detection is proposed, the main elements of the structural and functional diagram of the system are defined, and an algorithm for video stream processing is described, including the selection of the controlled zone, feature extraction, computation of an anomaly score, classification, and temporal verification of detected events. It is shown that the proposed approach can be applied both when using unmanned aerial systems and with stationary camera placement. Special attention is paid to the requirements for real-time system operation and the formation of an integral decision-making criterion. The conclusion is drawn about the promise of the proposed approach for subsequent experimental verification and integration into intelligent monitoring systems for railway transport facilities.
intelligent video surveillance, railway infrastructure, anomalous objects, computer vision, video stream processing, real-time operation, unmanned aerial systems, automation of monitoring
1. A literature review of Artificial Intelligence applications in railway systems / R. Tang [et al.] // Transportation Research Part C: Emerging Technologies. 2022. Vol. 140. Art. 103679. DOI:https://doi.org/10.1016/j.trc.2022.103679
2. Artificial intelligence in railway infrastructure: current research, challenges, and future opportunities / W. Phusakulkajorn [et al.] // Intelligent Transportation Infrastructure. 2023. Vol. 2. Art. liad016. DOI:https://doi.org/10.1093/iti/liad016
3. Anomaly Analysis in Images and Videos: A Comprehensive Review / T. M. Tran [et al.] // ACM Computing Surveys. 2022. Vol. 55, no. 7. Art. 148. Pp. 1–37. DOI:https://doi.org/10.1145/3544014
4. Generalized Video Anomaly Event Detection: Systematic Taxonomy and Comparison of Deep Models / Y. Liu [et al.] // ACM Computing Surveys. 2024. Vol. 56, no. 7. Art. 189. Pp. 1–38. DOI:https://doi.org/10.1145/3645101
5. Wang Y., Yu P. A Fast Intrusion Detection Method for High-Speed Railway Clearance Based on Low-Cost Embedded GPUs // Sensors. 2021. Vol. 21, no. 21. Art. 7279. DOI:https://doi.org/10.3390/s21217279
6. Automatic Obstacle Detection Method for the Train Based on Deep Learning / Q. Zhang [et al.] // Sustainability. 2023. Vol. 15, no. 2. Art. 1184. DOI:https://doi.org/10.3390/su15021184
7. SDRC-YOLO: A Novel Foreign Object Intrusion Detection Algorithm in Railway Scenarios / C. Meng [et al.] // Electronics. 2023. Vol. 12, no. 5. Art. 1256. DOI: 10.3390/ electronics12051256
8. Survey on Multi-Sensor Fusion Perimeter Intrusion Detection in High-Speed Railways / T. Shi [et al.] // Sensors. 2024. Vol. 24, no. 17. Art. 5463. DOI:https://doi.org/10.3390/s24175463
9. Qi M., Wu Y. Weakly supervised video anomaly detection based on hyperbolic space // Scientific Reports. 2024. Vol. 14. Art. 26348. DOI:https://doi.org/10.1038/s41598-024-77505-4
10. RailFDNet: A hybrid supervision and feature discrepancy enhancement model for railway anomalous object detection / T. Sun [et al.] // Expert Systems with Applications. 2025. Vol. 275. Art. 127005. DOI:https://doi.org/10.1016/j. eswa.2025.127005
11. Sacyuk A. V., Shvalov D. V. Avtonomnoe navedenie BPLA s ispol'zovaniem komp'yuternogo zreniya: problema tochnogo upravleniya rulyami // Avtomatika na transporte. 2024. T. 10, № 4. S. 372–381. DOI:https://doi.org/10.20295/2412– 9186-2024-10-04-372-381
12. Lipanov I. D., Homonenko A. D. Tehnologii i metody planirovaniya peremescheniya BPLA po marshrutnym tochkam // Intellektual'nye tehnologii na transporte. 2024. № 3 (39). S. 30–43. DOI:https://doi.org/10.20295/2413-2527- 2024-339-30-43
13. Gorbachev R. A., Zaripov M. N., Shishkov D. L. Intellektual'naya sistema tehnicheskogo zreniya dlya obnaruzheniya prepyatstviy i predskazaniya povedeniya dvizhuschihsya ob'ektov na zheleznodorozhnyh putyah // Izvestiya YuFU. Tehnicheskie nauki. 2022. № 1 (225). S. 256–268. DOI:https://doi.org/10.18522/2311-3103-2022-1-256-268
14. Pomehozaschischennost' intellektual'nyh transportnyh sistem tehnicheskogo zreniya dlya analiza izobrazheniy zheleznodorozhnoy infrastruktury / M. A. Kulagin [i dr.] // Avtomatika na transporte. 2025. T. 11, № 4. S. 313–326. DOI:https://doi.org/10.20295/2412-9186-2025-11-04- 313–326
15. LiDAR-Camera joint obstacle detection algorithm for railway track area / Z. Nan [et al.] // Expert Systems with Applications. 2025. Vol. 275. Art. 127089. DOI:https://doi.org/10.1016/j. eswa.2025.127089
16. Railway Intrusion Risk Quantification with Track Semantic Segmentation and Spatiotemporal Features / S. Ning [et al.] // Sensors. 2025. Vol. 25, no. 17. Art. 5266. DOI:https://doi.org/10.3390/s25175266
17. Pogreshnosti izmereniya rasstoyaniya do prepyatstviya sredstvami tehnicheskogo zreniya i prognoza puti tormozheniya v bespilotnyh sistemah upravleniya dvizheniem poezdov / L. A. Baranov [i dr.] // Mir transporta. 2021. T. 19. № 6 (97). S. 6–12. DOI:https://doi.org/10.30932/1992-3252- 2021-19-6-1
