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

  title={SHOG - Spherical HOG Descriptors for Rotation Invariant 3D Object Detection},
  author={H. Skibbe and M. Reisert and H. Burkhardt},
  • H. Skibbe, M. Reisert, H. Burkhardt
  • Published in DAGM-Symposium 2011
  • Mathematics, Computer Science
  • 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
    25 Citations

    Figures, Tables, and Topics from this paper.

    Rotation-Invariant HOG Descriptors Using Fourier Analysis in Polar and Spherical Coordinates
    • 112
    • PDF
    An effective local feature descriptor for object detection in real scenes
    • 16
    Multi-features association-based local HOG description for image matching
    • B. Wu, Shilin Zhou, L. Lei, K. Ji
    • Engineering, Mathematics
    • International Symposium on Multispectral Image Processing and Pattern Recognition
    • 2015
    Circular Fourier-HOG features for rotation invariant object detection in biomedical images
    • H. Skibbe, M. Reisert
    • Mathematics, Computer Science
    • 2012 9th IEEE International Symposium on Biomedical Imaging (ISBI)
    • 2012
    • 20
    • PDF
    Spherical Tensor Algebra: A Toolkit for 3D Image Processing
    • H. Skibbe, M. Reisert
    • Mathematics, Computer Science
    • Journal of Mathematical Imaging and Vision
    • 2017
    • 9
    Radial Hahn Moment Invariants for 2D and 3D Image Recognition
    • 11
    • PDF


    Histograms of oriented gradients for human detection
    • N. Dalal, B. Triggs
    • Computer Science
    • 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05)
    • 2005
    • 26,052
    • PDF
    Harmonic Filters for Generic Feature Detection in 3D
    • 14
    Spherical Bessel Filter for 3D object detection
    • 4
    • PDF
    Harmonic Filters for 3D Multichannel Data: Rotation Invariant Detection of Mitoses in Colorectal Cancer
    • 20
    • PDF
    Distinctive Image Features from Scale-Invariant Keypoints
    • 23,911
    • PDF
    Elementary Theory of Angular Momentum
    • 3,071