Slanted Stixels: Representing San Francisco's Steepest Streets
This work addresses scene representation for autonomous driving in hilly urban environments, offering an incremental improvement over existing Stixel methods.
The authors tackled the problem of representing complex urban scenes with non-flat roads by developing a compact Stixel-based method that uses a novel depth model and joint semantic-depth cues, achieving real-time computation with only a slight accuracy drop.
In this work we present a novel compact scene representation based on Stixels that infers geometric and semantic information. Our approach overcomes the previous rather restrictive geometric assumptions for Stixels by introducing a novel depth model to account for non-flat roads and slanted objects. Both semantic and depth cues are used jointly to infer the scene representation in a sound global energy minimization formulation. Furthermore, a novel approximation scheme is introduced that uses an extremely efficient over-segmentation. In doing so, the computational complexity of the Stixel inference algorithm is reduced significantly, achieving real-time computation capabilities with only a slight drop in accuracy. We evaluate the proposed approach in terms of semantic and geometric accuracy as well as run-time on four publicly available benchmark datasets. Our approach maintains accuracy on flat road scene datasets while improving substantially on a novel non-flat road dataset.