Railway safety remains a paramount concern amidst the global expansion of railway transportation. This study presents a YOLOv5-based approach aimed at detecting train occupancy disruption and pedestrian intrusion on railway tracks. Leveraging advanced image processing technologies, the proposed methodology integrates the SURF (Speeded Up Robust Features) and VIBE (Visual Background Extractor) algorithms with YOLOv5 to achieve multi-faceted detection capabilities. Through a systematic image analysis workflow, the system accurately identifies track occupancy, locomotive heads, carriages, and pedestrians, triggering alert and warning messages as needed. This research underscores the efficacy of image processing in real-time railway safety monitoring and emphasizes the integration of multiple algorithms to enhance detection accuracy. The findings not only contribute to the enhancement of railway safety management but also pave the way for innovative methodologies in railway safety monitoring and management. As technology progresses, the adoption of such methodologies promises to further fortify railway transportation safety, mitigating potential risks and ensuring train safety throughout the transportation process.
A YOLOv5-Based Approach for Detecting Train Occupancy Disruption and Pedestrian Intrusion on Railway Tracks
Lect. Notes Electrical Eng.
International Conference on SmartRail, Traffic and Transportation Engineering ; 2024 ; Chongqing, China October 25, 2024 - October 27, 2024
Advances and Applications in SmartRail, Traffic, and Transportation Engineering ; Chapter : 2 ; 10-21
2025-07-19
12 pages
Article/Chapter (Book)
Electronic Resource
English