2014b), where it has been successfully applied for visual scene understanding in autonomous driving. It has shown its potential particularly in the Bertha-Benz drive (Ziegler et al.
This success has led to increased interest in the model from the intelligent vehicles community over the past years The Stixel world has been successfully used for representing traffic scenes, as introduced in Pfeiffer and Franke ( 2011). Our approach maintains accuracy on flat road scene datasets while improving substantially on a novel non-flat road dataset.
We evaluate the proposed methods in terms of semantic and geometric accuracy as well as run-time on four publicly available benchmark datasets. This work presents a novel over-segmentation strategy based on a fully convolutional network, which outperforms an approach based on using local extrema of the disparity map. The idea is to first perform an over-segmentation of the image, discarding the unlikely Stixel cuts, and apply the algorithm only on the remaining Stixel cuts. Furthermore, a novel approximation scheme is introduced in order to significantly reduce the computational complexity of the Stixel algorithm, and then achieve real-time computation capabilities. Both semantic and depth cues are used jointly to infer the scene representation in a sound global energy minimization formulation.
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. This work presents and evaluates a novel compact scene representation based on Stixels that infers geometric and semantic information.
0 kommentar(er)
