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.