Situation Awareness and Fatigue Detection for Semi-Automated Train Driving

<p dir="ltr">Ensuring rail safety is a critical concern where train drivers must maintain high vigilance to prevent incidents such as collisions, derailments, and Signal Passed at Danger (SPAD) events. A SPAD event occurs when a train passes a stop signal without authorization. This can happen due to various factors, including fatigue, misjudgments and driver errors. The current anti-SPAD system of the rail network operator employs video analytics to detect such risks, however the size and cost of the device, limits accessibility, particularly during emergencies. The proposed mobile application enhances manual train operations by enabling real-time monitoring of trackside objects through a smartphone mounted on the driving console. It utilizes real-time object detection (YOLOv11) and facial analysis, optimized for mobile devices, thus reducing deployment time and improves situational awareness and safety during critical operations. It could also form the basis of modeling fatigue in partially automated driving for train operations and autonomous vehicles.