×

WildDash Benchmark

New: RailSem19 dataset for semantic rail scene understanding.
Results of the 2018 CVPR challenge can be seen here: semantic / instance segmentation

RailSem19: A Dataset for Semantic Rail Scene Understanding

Closing a data gap for rail applications

RailSem19 offers 8500 unique images taken from a the ego-perspective of a rail vehicle (trains and trams). Extensive semantic annotations are provided, both geometry-based (rail-relevant polygons, all rails as polylines) and dense label maps with many Cityscapes-compatible road labels. Many frames show areas of intersection between road and rail vehicles (railway crossings, trams driving on city streets). RailSem19 is usefull for rail applications and road applications alike.

Complex rail scenarios

Inner-city tram scenes

From all over the world

Difficult weather / lighting

Free public dataset

RailSem19 is a dataset supplied to the scientific community for free (usage/license terms apply, see license and readme bundled with the release). All WildDash users can download RailSem19 at the Download section. We currently do not provide a benchmark dataset or public ranking for RailSem19.