%0 Conference Proceedings
%T Slanted Stixels: Representing San Francisco's Steepest Streets}
%A Daniel Hernandez
%A Lukas Schneider
%A Antonio Espinosa
%A David Vazquez
%A Antonio Lopez
%A Uwe Franke
%A Marc Pollefeys
%A Juan C. Moure
%B 28th British Machine Vision Conference
%D 2017
%F Daniel Hernandez2017
%O ADAS; 600.118
%O exported from refbase (http://refbase.cvc.uab.es/show.php?record=2945), last updated on Fri, 21 Jan 2022 11:19:20 +0100
%X 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.
%U http://refbase.cvc.uab.es/files/HSE2017a.pdf