Learning depth-sensitive conditional random fields for semantic segmentation of RGB-D images

@article{Mller2014LearningDC,
  title={Learning depth-sensitive conditional random fields for semantic segmentation of RGB-D images},
  author={Andreas C. M{\"u}ller and Sven Behnke},
  journal={2014 IEEE International Conference on Robotics and Automation (ICRA)},
  year={2014},
  pages={6232-6237}
}
We present a structured learning approach to semantic annotation of RGB-D images. Our method learns to reason about spatial relations of objects and fuses low-level class predictions to a consistent interpretation of a scene. Our model incorporates color, depth and 3D scene features, on which an energy function is learned to directly optimize object class prediction using the loss-based maximum-margin principle of structural support vector machines. We evaluate our approach on the NYU V2… CONTINUE READING
Highly Cited
This paper has 98 citations. REVIEW CITATIONS
36 Extracted Citations
22 Extracted References
Similar Papers

Citing Papers

Publications influenced by this paper.
Showing 1-10 of 36 extracted citations

98 Citations

0204020142015201620172018
Citations per Year
Semantic Scholar estimates that this publication has 98 citations based on the available data.

See our FAQ for additional information.

Referenced Papers

Publications referenced by this paper.
Showing 1-10 of 22 references

Similar Papers

Loading similar papers…