SHOG - Spherical HOG Descriptors for Rotation Invariant 3D Object Detection

@inproceedings{Skibbe2011SHOGS,
  title={SHOG - Spherical HOG Descriptors for Rotation Invariant 3D Object Detection},
  author={Henrik Skibbe and Marco Reisert and Hans Burkhardt},
  booktitle={DAGM-Symposium},
  year={2011}
}
We present a method for densely computing local spherical histograms of oriented gradients (SHOG) in volumetric images. The descriptors are based on the continuous representation of the orientation histograms in the harmonic domain, which we compute very efficiently via spherical tensor products and the Fast Fourier Transformation. Building upon these local spherical histogram representations, we utilize the Harmonic Filter to create a generic rotation invariant object detection system that… CONTINUE READING
BETA

Figures, Tables, and Topics from this paper.

Similar Papers

Citations

Publications citing this paper.
SHOWING 1-10 OF 15 CITATIONS

Spherical Tensor Algebra: A Toolkit for 3D Image Processing

  • Journal of Mathematical Imaging and Vision
  • 2017
VIEW 5 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Image clustering based on hermetian positive definite matrix and radial Jacobi moments

  • 2018 International Conference on Intelligent Systems and Computer Vision (ISCV)
  • 2018
VIEW 3 EXCERPTS
CITES BACKGROUND
HIGHLY INFLUENCED

Radial invariant of 2D and 3D Racah moments

  • Multimedia Tools and Applications
  • 2017
VIEW 1 EXCERPT
CITES METHODS

3D radial invariant of dual Hahn moments

  • Neural Computing and Applications
  • 2016
VIEW 1 EXCERPT
CITES BACKGROUND

3D rotation invariants by complex moments

  • Pattern Recognition
  • 2015
VIEW 1 EXCERPT
CITES METHODS

Multi-features association-based local HOG description for image matching

  • International Symposium on Multispectral Image Processing and Pattern Recognition
  • 2015
VIEW 1 EXCERPT
CITES METHODS