Semantic Stixels: Depth is not enough

@article{Schneider2016SemanticSD,
  title={Semantic Stixels: Depth is not enough},
  author={L. Schneider and Marius Cordts and Timo Rehfeld and D. Pfeiffer and M. Enzweiler and U. Franke and M. Pollefeys and S. Roth},
  journal={2016 IEEE Intelligent Vehicles Symposium (IV)},
  year={2016},
  pages={110-117}
}
  • L. Schneider, Marius Cordts, +5 authors S. Roth
  • Published 2016
  • Computer Science
  • 2016 IEEE Intelligent Vehicles Symposium (IV)
  • In this paper we present Semantic Stixels, a novel vision-based scene model geared towards automated driving. Our model jointly infers the geometric and semantic layout of a scene and provides a compact yet rich abstraction of both cues using Stixels as primitive elements. Geometric information is incorporated into our model in terms of pixel-level disparity maps derived from stereo vision. For semantics, we leverage a modern deep learning-based scene labeling approach that provides an object… CONTINUE READING
    65 Citations
    Slanted Stixels: A Way to Represent Steep Streets
    • Highly Influenced
    • PDF
    Slanted Stixels: Representing San Francisco's Steepest Streets
    • 42
    • PDF
    Improved Semantic Stixels via Multimodal Sensor Fusion
    • 3
    • PDF
    Mono-Stixels: Monocular Depth Reconstruction of Dynamic Street Scenes
    • 5
    • Highly Influenced
    • PDF
    A Stixel Approach for Enhancing Semantic Image Segmentation Using Prior Map Information
    Instance Stixels: Segmenting and Grouping Stixels into Objects
    • Highly Influenced
    Multi view stereo with semantic priors
    • 4
    • PDF
    SDNet: Semantically Guided Depth Estimation Network
    • 12
    • PDF
    Exploiting Single Image Depth Prediction for Mono-stixel Estimation
    • 1
    • PDF
    Semantic segmentation-based stereo reconstruction with statistically improved long range accuracy
    • 7
    • PDF

    References

    SHOWING 1-10 OF 47 REFERENCES
    Low-level fusion of color, texture and depth for robust road scene understanding
    • 26
    • Highly Influential
    Joint Semantic Segmentation and 3D Reconstruction from Monocular Video
    • 204
    • Highly Influential
    • PDF
    Object-Level Priors for Stixel Generation
    • 18
    • PDF
    Extending the Stixel World with online self-supervised color modeling for road-versus-obstacle segmentation
    • 19
    • PDF
    Towards a Global Optimal Multi-Layer Stixel Representation of Dense 3D Data
    • 93
    • PDF
    3D Traffic Scene Understanding From Movable Platforms
    • 333
    • PDF
    Nonparametric semantic segmentation for 3D street scenes
    • Hu He, B. Upcroft
    • Computer Science
    • 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems
    • 2013
    • 34
    • PDF
    Joint 2D-3D temporally consistent semantic segmentation of street scenes
    • G. Floros, B. Leibe
    • Computer Science
    • 2012 IEEE Conference on Computer Vision and Pattern Recognition
    • 2012
    • 91
    • PDF
    Efficient Piecewise Training of Deep Structured Models for Semantic Segmentation
    • 688
    • PDF