Slanted Stixels: Representing San Francisco's Steepest Streets

Daniel Hernandez-Juarez, Lukas Schneider, Antonio Espinosa, Juan Moure, David Vazquez, Antonio López, Uwe Franke and Marc Pollefeys

Abstract

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.

Session

Orals - Scene Understanding

Files

Paper (PDF)

DOI

10.5244/C.31.87
https://dx.doi.org/10.5244/C.31.87

Citation

Bibtex

            @inproceedings{BMVC2017_87,
                title={Slanted Stixels: Representing San Francisco's Steepest Streets},
                author={Daniel Hernandez-Juarez, Lukas Schneider, Antonio Espinosa, Juan Moure, David Vazquez, Antonio López, Uwe Franke and Marc Pollefeys},
                year={2017},
                month={September},
                pages={87.1-87.12},
                articleno={87},
                numpages={12},
                booktitle={Proceedings of the British Machine Vision Conference (BMVC)},
                publisher={BMVA Press},
                editor={Tae-Kyun Kim, Stefanos Zafeiriou, Gabriel Brostow and Krystian Mikolajczyk},
                doi={10.5244/C.31.87},
                isbn={1-901725-60-X},
                url={https://dx.doi.org/10.5244/C.31.87}
            }