Learn More
The present paper describes a concept for an onboard system specially designed for surveillance of catenaries of railways in front of trains. Damages to pantographs caused by defects or obstacles in catenaries will be avoided by such a system by retracting the pantograph in time. The special situation of this application is discussed. An overview of the(More)
The paper describes the latest improvements in the video-based obstacle detection system developed at Deutsche Bahn AG (Germany's leading railway operator). The system automatically detects obstacles in the pantograph gauge at a distance of up to 70 m and retracts the pantograph before collision with an obstacle. Due to the multitude of similar-looking(More)
This paper presents a novel system for measuring vegetation along railway tracks. The system, which is mounted on a train, consists of three multi-spectral cameras that are sensitive in the visible as well as in the near-infrared spectrum. The goal is to generate a vegetation profile and vegetation register for the efficient deployment of staff to eliminate(More)
Obstacles in the pantograph gauge cause damage and time delays when colliding with the pantograph. We have built an onboard system that avoids collisions by automatically detecting such obstacles at about 70 m in front of the train and retracting the pantograph in time. The system consists of three cameras mounted collinearly inside the train behind the(More)
Automobiles and railway vehicles have their specific safety standards, respectively. Still, they are both land vehicles and thus share a large set of common hazards and accident types. This calls for a common safety ontology covering both domains. Apart from many commonalities, we found some important differences between safety standards of these domains,(More)
The present paper describes the concept and first results of a system, capable to detect obstacles in catenaries as an onboard tool. To avoid a damage of the pantograph it must be retracted immediately after an obstacle is detected. The presented system is based on a triocular camera sensor system combined with smart image processing routines. The present(More)
  • 1