Tree-Structured Models for Efficient Multi-Cue Scene Labeling

@article{Cordts2017TreeStructuredMF,
  title={Tree-Structured Models for Efficient Multi-Cue Scene Labeling},
  author={Marius Cordts and Timo Rehfeld and M. Enzweiler and Uwe Franke and S. Roth},
  journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year={2017},
  volume={39},
  pages={1444-1454}
}
  • Marius Cordts, Timo Rehfeld, +2 authors S. Roth
  • Published 2017
  • Computer Science, Medicine
  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • We propose a novel approach to semantic scene labeling in urban scenarios, which aims to combine excellent recognition performance with highest levels of computational efficiency. To that end, we exploit efficient tree-structured models on two levels: pixels and superpixels. At the pixel level, we propose to unify pixel labeling and the extraction of semantic texton features within a single architecture, so-called encode-and-classify trees. At the superpixel level, we put forward a multi-cue… CONTINUE READING
    11 Citations
    Instance Stixels: Segmenting and Grouping Stixels into Objects
    • 1
    Look and Listen: A Multi-modality Late Fusion Approach to Scene Classification for Autonomous Machines
    • 3
    • PDF
    End-to-End Learning of Decision Trees and Forests
    • 10
    • PDF
    Fast 3D Scene Alignment with Stereo Images using a Stixel-based 3D Model
    • 2
    • PDF
    Survey on Multi-Output Learning
    • 26
    • PDF
    Rearview Camera-Based Stixel Generation for Backing Crash Prevention
    • Jae Kyu Suhr, H. Jung
    • Computer Science
    • IEEE Transactions on Intelligent Transportation Systems
    • 2020
    • 3
    Split Bregman Algorithm for Structured Sparse Reconstruction
    • 3

    References

    SHOWING 1-10 OF 53 REFERENCES
    Learning Hierarchical Features for Scene Labeling
    • 2,166
    • PDF
    Low-level fusion of color, texture and depth for robust road scene understanding
    • 26
    Describing the scene as a whole: Joint object detection, scene classification and semantic segmentation
    • 368
    • PDF
    Semantic segmentation of street scenes by superpixel co-occurrence and 3D geometry
    • B. Micusík, J. Kosecka
    • Mathematics, Computer Science
    • 2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops
    • 2009
    • 77
    • PDF
    Figure-ground segmentation using a hierarchical conditional random field
    • J. Reynolds, K. Murphy
    • Mathematics, Computer Science
    • Fourth Canadian Conference on Computer and Robot Vision (CRV '07)
    • 2007
    • 61
    • PDF
    Harmony potentials for joint classification and segmentation
    • 176
    • PDF
    Efficient 3D Scene Labeling Using Fields of Trees
    • O. Kähler, I. Reid
    • Computer Science
    • 2013 IEEE International Conference on Computer Vision
    • 2013
    • 45
    • PDF
    Deep hierarchical parsing for semantic segmentation
    • Abhishek Sharma, Oncel Tuzel, D. Jacobs
    • Computer Science
    • 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
    • 2015
    • 97
    • PDF
    On Parameter Learning in CRF-Based Approaches to Object Class Image Segmentation
    • 94
    • PDF