The First Experimental Study of Monocular Visual Localization for Trains

The development of a scalable and adaptable trackside and on-board coordinated control system (CCS+) is a top priority for the digital and automated train operations of future railways. One of the most important and reliable solutions in CCS+ is train positioning, which is called GLAT (generic location-awareness tools). The underlying technologies that GLAT can rely on many methods like GNSS. However, the GNSS precise positioning of trains in “satellite signal blind spots” such as tunnels and mountainous areas must rely on trackside equipment such as balise. For alleviating the need of trackside equipment, one way is using INS/GNSS integrated navigation scheme. However, with the development of computer vision, it is an attractive and challenging way. Therefore, we carry out the visual train positioning research in the China National Railway Test Center (east suburban branch). By using ORB descriptor and monocular camera, we successfully obtain the trajectory tracking of the train. We study the relationship between the number of feature points, feature tracking, and train speed in our experiments, and find that the impact of tunnels on feature tracking is vital. Through further analysis, we draw two import conclusions.