RailVision: An Integrated Solution for Train Detection, Speed Estimation, and Direction Analysis in Railway Environments
Open Access
- 20 November 2026
- book chapter
- Published by Springer Nature
- p. 1207-1214
Abstract
Accurate train detection, speed, and direction estimation are vital for railway safety and intelligent transport. This paper proposes a vision-based system integrating object detection, tracking, and homography-based motion estimation using fixed cameras. By applying geometric transformations and temporal analysis without additional hardware, the system achieves average errors below 10 km/h for speed and 10 $$^{\circ }$$ for direction. The approach maintains real-time performance with latency under 40 ms. Experimental results validate the system’s reliability, scalability, and cost-effectiveness for real-world deployment on existing infrastructure.
This publication has 25 references indexed in Scilit:
- RailEINet:A novel scene segmentation network for automatic train operation based on feature alignmentEngineering Applications of Artificial Intelligence, 2024
- Microcontroller-based track axle counter system designJournal of Physics: Conference Series, 2024
- Accurate Vehicles Detection and Speed Estimation Using Homography Based Background Subtraction and Deep Learning Approaches2023
- Research on target detection and tracking algorithm for campus driverless vehicle based on improved DeepSORT2022
- Geometric invariant features for the detection and analysis of vehicleMultimedia Tools and Applications, 2022
- Autonomous Railway Traffic Object Detection Using Feature-Enhanced Single-Shot DetectorIEEE Access, 2020
- Background subtraction in real applications: Challenges, current models and future directionsComputer Science Review, 2020
- Infrared Image Vehicle Detection Based on Haar-like Feature2018
- Data-driven perspectives for energy efficient operations in railway systems: Current practices and future opportunitiesTransportation Research Part C: Emerging Technologies, 2018
- You Only Look Once: Unified, Real-Time Object Detection2016