Characterization of 3-D Volumetric Probabilistic Scenes for Object Recognition

@article{Restrepo2012CharacterizationO3,
  title={Characterization of 3-D Volumetric Probabilistic Scenes for Object Recognition},
  author={Maria I. Restrepo and Brandon A. Mayer and Ali O. Ulusoy and Joseph L. Mundy},
  journal={IEEE Journal of Selected Topics in Signal Processing},
  year={2012},
  volume={6},
  pages={522-537}
}
This paper presents a new volumetric representation for categorizing objects in large-scale 3-D scenes reconstructed from image sequences. This work uses a probabilistic volumetric model (PVM) that combines the ideas of background modeling and volumetric multi-view reconstruction to handle the uncertainty inherent in the problem of reconstructing 3-D structures from 2-D images. The advantages of probabilistic modeling have been demonstrated by recent application of the PVM representation to… CONTINUE READING

Citations

Publications citing this paper.
SHOWING 1-10 OF 14 CITATIONS

Geo-localization using Volumetric Representations of Overhead Imagery

  • International Journal of Computer Vision
  • 2015
VIEW 5 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Fury of the Swarm: Efficient and Very Accurate Triangulation for Multi-view Scene Reconstruction

  • 2013 IEEE International Conference on Computer Vision Workshops
  • 2013
VIEW 2 EXCERPTS
CITES BACKGROUND
HIGHLY INFLUENCED

Threewise: a local variance algorithm for GPU

  • 2016 IEEE Intl Conference on Computational Science and Engineering (CSE) and IEEE Intl Conference on Embedded and Ubiquitous Computing (EUC) and 15th Intl Symposium on Distributed Computing and Applications for Business Engineering (DCABES)
  • 2016
VIEW 1 EXCERPT
CITES METHODS

3D Urban Reconstruction from Wide Area Aerial Surveillance Video

  • 2015 IEEE Winter Applications and Computer Vision Workshops
  • 2015
VIEW 1 EXCERPT
CITES METHODS

GPU-accelerated and efficient multi-view triangulation for scene reconstruction

  • IEEE Winter Conference on Applications of Computer Vision
  • 2014
VIEW 3 EXCERPTS
CITES METHODS & BACKGROUND

References

Publications referenced by this paper.
SHOWING 1-10 OF 66 REFERENCES

A Continuous probabilistic scene model for aerial imagery

D. E. Crispell
  • Ph.D. dissertation, School of Eng., Brown Univ., Providence, RI, 2010.
  • 2010
VIEW 6 EXCERPTS
HIGHLY INFLUENTIAL

Accurate, Dense, and Robust Multiview Stereopsis

  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • 2007
VIEW 7 EXCERPTS
HIGHLY INFLUENTIAL

Change Detection in a 3-d World

  • 2007 IEEE Conference on Computer Vision and Pattern Recognition
  • 2007
VIEW 10 EXCERPTS
HIGHLY INFLUENTIAL

Histograms of oriented gradients for human detection

  • 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05)
  • 2005
VIEW 6 EXCERPTS
HIGHLY INFLUENTIAL

A Combined Corner and Edge Detector

  • Alvey Vision Conference
  • 1988
VIEW 3 EXCERPTS
HIGHLY INFLUENTIAL

Similar Papers

Loading similar papers…