Object-Level Priors for Stixel Generation

Cordts, Marius; Schneider, Lukas; Enzweiler, Markus; Franke, Uwe; Roth, Stefan

doi:10.1007/978-3-319-11752-2_14

Cited by 19 publications

(20 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our proposal of using Stixels cuts is related to Cordts et al (2014): they use fast object detectors for different object classes, e.g. Viola-Jones cascade detector (Viola and Jones 2001), to produce top and bottom Stixel cuts that are used as prior information, which is then integrated into the Stixel algorithm.…”

Section: Related Workmentioning

confidence: 99%

“…walls or sidewalks, providing pixel-level information, instead of boxes around the objects. Also, semantic segmentation requires a single predictor, while the method proposed by Cordts et al (2014) needs a detector trained for each object class. In contrast, we define a Stixel cut prior to generate an over-segmentation of the optimal Stixel cuts in order to speed up the execution of the algorithm.…”

Section: Related Workmentioning

confidence: 99%

“…It has shown its potential particularly in the Bertha-Benz drive (Ziegler et al 2014b), where it has been successfully applied for visual scene understanding in autonomous driving. This success has led to increased interest in the model from the intelligent vehicles community over the past years (Schneider et al 2016; Hernandez-Juarez et al 2017a; Benenson et al 2011;Cordts et al 2014Cordts et al , 2017Ignat 2016;Levi et al 2015;Carrillo and Sutherland 2016;Hernandez-Juarez et al 2017b).…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Slanted Stixels: A Way to Represent Steep Streets

et al. 2019

Self Cite

View full text Add to dashboard Cite

This work presents and evaluates 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 in order to significantly reduce the computational complexity of the Stixel algorithm, and then achieve real-time computation capabilities. 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. This work presents a novel over-segmentation strategy based on a Fully Convolutional Network (FCN), which outperforms an approach based on using local extrema of the disparity map.We evaluate the proposed methods 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.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Slanted Stixels: A Way to Represent Steep Streets

et al. 2019

Self Cite

View full text Add to dashboard Cite

show abstract

“…However, in practice it is sufficient to restrict this prior to structural classes only and add exceptions for a few select classes depending on the actual application, e.g. [5]. The same holds for the weights of the data likelihoods, i.e.…”

Section: Algorithmic Simplificationmentioning

confidence: 99%

The Stixel World: A medium-level representation of traffic scenes

Cordts

Rehfeld

Schneider

et al. 2017

Image and Vision Computing

Self Cite

View full text Add to dashboard Cite

Recent progress in advanced driver assistance systems and the race towards autonomous vehicles is mainly driven by two factors: (1) increasingly sophisticated algorithms that interpret the environment around the vehicle and react accordingly, and (2) the continuous improvements of sensor technology itself. In terms of cameras, these improvements typically include higher spatial resolution, which as a consequence requires more data to be processed. The trend to add multiple cameras to cover the entire surrounding of the vehicle is not conducive in that matter. At the same time, an increasing number of special purpose algorithms need access to the sensor input data to correctly interpret the various complex situations that can occur, particularly in urban traffic.By observing those trends, it becomes clear that a key challenge for vision architectures in intelligent vehicles is to share computational resources. We believe this challenge should be faced by introducing a representation of the sensory data that provides compressed and structured access to all relevant visual content of the scene. The Stixel World discussed in this paper is such a representation. It is a medium-level model of the environment that is specifically designed to compress information about obstacles by leveraging the typical layout of outdoor traffic scenes. It has proven useful for a multi- * Corresponding author: marius.cordts@daimler.com tude of automotive vision applications, including object detection, tracking, segmentation, and mapping. In this paper, we summarize the ideas behind the model and generalize it to take into account multiple dense input streams: the image itself, stereo depth maps, and semantic class probability maps that can be generated, e.g., by deep convolutional neural networks. Our generalization is embedded into a novel mathematical formulation for the Stixel model. We further sketch how the free parameters of the model can be learned using structured SVMs.

show abstract

“…The Stixel World has been successfully used for representing traffic scenes, as introduced in [20]. The intelligent vehicles community has shown an increasing interest in this model over the last years [2,3,4,6,11,13,15,23]. It defines a compact medium-level representation of dense 3D disparity data obtained from stereo vision using rectangles (Stixels) as elements.…”

Section: Introductionmentioning

confidence: 99%

Slanted Stixels: Representing San Francisco's Steepest Streets

Hernandez-Juarez¹,

Schneider²,

Espinosa³

et al. 2017

Procedings of the British Machine Vision Conference 2017

Self Cite

View full text Add to dashboard Cite

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.

show abstract

Object-Level Priors for Stixel Generation

Cited by 19 publications

References 29 publications

Slanted Stixels: A Way to Represent Steep Streets

Slanted Stixels: A Way to Represent Steep Streets

The Stixel World: A medium-level representation of traffic scenes

Slanted Stixels: Representing San Francisco's Steepest Streets

Contact Info

Product

Resources

About