The road and lane estimation benchmark consists of 289 training and 290 test images. We evaluate road and lane estimation performance in the bird's-eye-view space. It contains different categories of road scenes:

• uu - urban unmarked (98/100)
• um - urban marked (95/96)
• umm - urban multiple marked lanes (96/94)
• urban - combination of the three above

Data Collection

We equipped a standard station wagon with two high-resolution color and grayscale video cameras. Accurate ground truth is provided by a Velodyne laser scanner and a GPS localization system. Our datsets are captured by driving around the mid-size city of Karlsruhe, in rural areas and on highways. Up to 15 cars and 30 pedestrians are visible per image.