Search papers, labs, and topics across Lattice.
This paper details the creation of a comprehensive multi-sensor dataset designed for enhancing the operational environment monitoring of automated railway systems, spanning from partially to fully automated operations. The dataset, developed under the Digitale Schiene Deutschland program, includes over 7 million high-quality annotations of both railway-specific and general perception objects, enabling AI systems to effectively detect and classify hazards in real time. By providing this extensive resource, the authors aim to significantly improve the training and validation of AI-based perception systems in the railway sector.
Over 7 million meticulously annotated data points now empower AI systems to enhance safety and efficiency in automated railway operations.
Reliable environment monitoring is essential for the safe and efficient operation of automated railway systems, covering all Grades of Automation (GoA), from partially automated (GoA2) to fully automated operation (GoA4). Artificial Intelligence (AI) plays a central role in enabling these systems to detect, classify, and react to potential hazards in real time. The development of such AI-based perception systems requires large volumes of accurately annotated data for training and validation. Within the Digitale Schiene Deutschland (DSD) program, DB InfraGO AG and understandAI GmbH have developed a comprehensive multi- sensor dataset tailored to the needs of railway environment perception. This dataset contains over 7 million high-quality annotations of both railway-specific and general perception objects, captured under varying operational scenarios. The finalized dataset can now be requested at the DB InfraGO AG and serve as a valuable resource for advancing AI-driven environment monitoring in the railway domain.
