Hough Parameter Space Regularisation for Line Detection in 3D

Manuel Jeltsch, Christoph Dalitz, Regina Pohle-Fröhlich

2016

Abstract

The Hough transform is a well known technique for detecting lines or other parametric shapes in point clouds. When it is used for finding lines in a 3D-space, an appropriate line representation and quantisation of the parameter space is necessary. In this paper, we address the problem that a straightforward quantisation of the optimal four-parameter representation of a line after Roberts results in an inhomogeneous tessellation of the geometric space that introduces bias with respect to certain line orientations. We present a discretisation of the line directions via tessellation of an icosahedron that overcomes this problem whenever one parameter in the Hough space represents a direction in 3D (e.g. for lines or planes). The new method is applied to the detection of ridges and straight edges in laser scan data of buildings, where it performs better than a straightforward quantisation.

References

  1. Anderson, P. G. (1996). Advances in linear pixel shuffling. In Bergum, G., Philippou, A., and Horadam, A., editors, Applications of Fibonacci Numbers, pages 1-21. Springer, Netherlands.
  2. Bhattacharya, P., Liu, H., Rosenfeld, A., and Thompson, S. (2000). Hough-transform detection of lines in 3-D space. Pattern Recognition Letters, 21(9):843-849.
  3. Burger, W. and Burge, M. (2009). Principles of Digital Image Processing - Core Algorithms. Springer, London.
  4. González, A. (2010). Measurement of areas on a sphere using Fibonacci and latitude-longitude lattices. Mathematical Geosciences, 42(1):49-64.
  5. Hough, P. V. (1962). Method and means for recognizing complex patterns. US Patent 3,069,654.
  6. Ishida, Y., Izuoka, H., Chinthaka, H., Premachandra, N., and Kato, K. (2012). A study on plane extraction from distance images using 3D Hough transform. In Soft Computing and Intelligent Systems (SCIS) and International Symposium on Advanced Intelligent Systems (ISIS), pages 812-816.
  7. Moqiseh, A. and Nayebi, M. (2008). 3-D Hough transform for surveillance radar target detection. In IEEE Radar Conference RADAR 7808, pages 1-5.
  8. Mukhopadhyay, P. and Chaudhuri, B. B. (2015). A survey of Hough transform. Pattern Recognition, 48(3):993- 1010.
  9. Nvidia (2010). NVIDIA GF100: World's fastest GPU delivering great gaming performance with true geometric realism. http://www.nvidia.com/object/IO 86775.html.
  10. Qiu, W., Yuchi, M., Ding, M., Tessier, D., and Fenster, A. (2013). Needle segmentation using 3D Hough transform in 3D TRUS guided prostate transperineal therapy. Medical physics, 40(4):042902.
  11. Roberts, K. (1988). A new representation for a line. In Computer Vision and Pattern Recognition CVPR'88, pages 635-640.
  12. Schenk, T. (2004). From point-based to feature-based aerial triangulation. ISPRS Journal of Photogrammetry and Remote Sensing, 58(5):315-329.
  13. Zhou, H., Qiu, W., Ding, M., and Zhang, S. (2008). Automatic needle segmentation in 3D ultrasound images using 3D improved Hough transform. In Medical Imaging, page 691821.
Download


Paper Citation


in Harvard Style

Jeltsch M., Dalitz C. and Pohle-Fröhlich R. (2016). Hough Parameter Space Regularisation for Line Detection in 3D . In Proceedings of the 11th Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP, (VISIGRAPP 2016) ISBN 978-989-758-175-5, pages 345-352. DOI: 10.5220/0005679003450352


in Bibtex Style

@conference{visapp16,
author={Manuel Jeltsch and Christoph Dalitz and Regina Pohle-Fröhlich},
title={Hough Parameter Space Regularisation for Line Detection in 3D},
booktitle={Proceedings of the 11th Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP, (VISIGRAPP 2016)},
year={2016},
pages={345-352},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005679003450352},
isbn={978-989-758-175-5},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 11th Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP, (VISIGRAPP 2016)
TI - Hough Parameter Space Regularisation for Line Detection in 3D
SN - 978-989-758-175-5
AU - Jeltsch M.
AU - Dalitz C.
AU - Pohle-Fröhlich R.
PY - 2016
SP - 345
EP - 352
DO - 10.5220/0005679003450352