ABSTRACT
Spherical harmonic cross-correlation is a robust registration algorithm that brings two point-clouds of the same scene into coarse rotational alignment. The found rotation however may not give the desired alignment, as misalignments can occur if there is not enough overlap between point-clouds, or if they contain a form of symmetry. We propose a verification method whose purpose is to determine if registration has failed for a priori unknown registration. The rotational transformation between multiple clouds must satisfy internal consistency, namely multiple rotational transformations are transitive. The rotation verification is performed using triplets of images, which are cross-referenced with each other to classify rotations individually. Testing is performed on a dataset of a priori known registrations. It is found that when the number of images or the percentage of correct rotations is increased, the number of correct rotation classifications improves. Even when tested with only four images and a correct rotation percentage of 17%, the rotation verification is still considered a viable method for classifying rotations. Spherical harmonic cross-correlation is benefited by rotation verification as it provides an additional approach for checking whether found rotations are correct.
- P. Baldi, S. Brunak, Y. Chauvin, C. A. F. Andersen, and H. Nielsen. Assessing the accuracy of prediction algorithms for classification: an overview. Bioinformatics, 16(5): 412--424, 2000.Google ScholarCross Ref
- F. Blais. Review of 20 years of range sensor development. Journal of Electronic Imaging, 13(1): 231--243, January 2004.Google Scholar
- G. E. Christensen and H. J. Johnson. Consistent image registration. IEEE Transactions on Medical Imaging, 20(7): 568--582, July 2001.Google ScholarCross Ref
- X. Geng, D. Kumar, and G. E. Christensen. Transitive inverse-consistent manifold registration. Lecture Notes in Computer Science: Information Processing in Medical Imaging, 3565: 468--479, July 2005. Google ScholarDigital Library
- B. Gutman, Y. Wang, T. Chan, P. M. Thompson, and A. W. Toga. Shape registration with spherical cross correlation. In Second MICCAI 2008 Workshop on Mathematical Foundations in Computational Anatomy (MFCA '08), pages 56--67, 2008.Google Scholar
- D. F. Huber and M. Hebert. Fully automatic registration of multiple 3D data sets. Image and Vision Computing, 21(7): 637--650, July 2003.Google ScholarCross Ref
- R. L. Larkins, M. J. Cree, and A. A. Dorrington. Analysis of ICP variants for the registration of partially overlapping time-of-flight range images. In Proceedings of the 25th International Image and Vision Computing New Zealand Conference (IVCNZ 2010), November 2010.Google ScholarCross Ref
- R. L. Larkins, M. J. Cree, and A. A. Dorrington. Analysis of binning of normals for spherical harmonic cross-correlation. In Proceedings of SPIE-IS&T Electronic Imaging, volume 8290, March 2012.Google ScholarCross Ref
- A. Pooja and V. M. Govindu. A multi-view extension of the ICP algorithm. In Proceedings of the Seventh Indian Conference on Computer Vision, Graphics and Image Processing, ICVGIP '10, pages 235--242, Chennai, India, December 2010. Google ScholarDigital Library
- J. Salvi, C. Matabosch, D. Fofi, and J. Forest. A review of recent range image registration methods with accuracy evaluation. Image and Vision Computing, 25(5): 578--596, 2007. Google ScholarDigital Library
Index Terms
- Verification of multi-view point-cloud registration for spherical harmonic cross-correlation
Recommendations
Evaluating Equiangle Binning for Spherical Harmonic Registration
IVCNZ '14: Proceedings of the 29th International Conference on Image and Vision Computing New ZealandSpherical harmonic correlation (SHC) is a robust registration algorithm that can bring two overlapping meshes into coarse rotational alignment. This is achieved by using the normals extracted from each mesh, as their relationship with each other is ...
Robust registration and learning using multi-radii spherical polar Fourier transform
AbstractThis paper presents effective methods using spherical polar Fourier transform data for two different applications, with active areas of research, one as a conventional volumetric registration algorithm and other as a machine learning ...
Highlights- Leverages spherical correlations and convolutions for registration and classification.
- Uses spectral spherical signals effectively in registration and machine learning.
- A general method for registration for volumes for up to 7 DOF ...
Spherical volume-preserving Demons registration
In order to analyze the brain shift situation accurately, we need to register the medical image and analyze its deformation. In this paper, we introduce a framework with volume-preserving registration for brain shift analysis. First, a volume-preserving ...
Comments