RoadSaW Logo

Road Surface and Wetness

<Under Construction>

Dataset for Camera-Based Road Surface and Wetness Estimation

Objective: Evaluation of Approaches for Road Condition Estimation [1]
  • Bird's eye view road patches at different vehicle distances generated from calibrated cameras
  • Three different surfaces: asphalt, cobblestone, concrete
  • Accurate water film height measurements; sprinklers provide controlled conditions

Presentation at CVPR 2022: Workshop on Autonomous Driving
  • 06-20-2022, 3:45 pm: Poster presentation

  • Supplementary video soon on our youtube channel



Version 1.0
release tbd

RoadSaW Paper:

[1] K. Cordes, C. Reinders, P. Hindricks, J. Lammers, B. Rosenhahn, H. Broszio: "RoadSaW: A Large-Scale Dataset for Camera-Based Road Surface and Wetness Estimation", CVPR Workshop on Autonomous Driving, 2022