(left) Museum dataset: point cloud consisting of 179,744 samples obtained from a set of photographs using SynthExport and Photosynth. (center) Our spherical accumulator. (right) Planes automatically detected by our technique in just 0.025 seconds on a 3.4 GHz PC. They were manually resized to better represent the original model.

Real-Time Detection of Planar Regions in Unorganized Point Clouds
Frederico A. Limberger
falimberger@inf.ufrgs.br

Manuel M. Oliveira
oliveira@inf.ufrgs.br

Instituto de Informática, UFRGS

Logo INF Logo UFRGS

Pattern Recognition.
Volume 48, Number 6, June 2015, pp. 2043-2053. [DOI]

Contents

Abstract Downloads Reference Acknowledgments

Abstract

Automatic detection of planar regions in point clouds is an important step for many graphics, image processing, and computer vision applications. While laser scanners and digital photography have allowed us to capture increasingly larger datasets, previous techniques are computationally expensive, being unable to achieve real-time performance for datasets containing tens of thousands of points, even when detection is performed in a non-deterministic way. We present a deterministic technique for plane detection in unorganized point clouds whose cost is O ( n log n ) in the number of input samples. It is based on an efficient Hough-transform voting scheme and works by clustering approximately co-planar points and by casting votes for these clusters on a spherical accumulator using a trivariate Gaussian kernel. A comparison with competing techniques shows that our approach is considerably faster and scales significantly better than previous ones, being the first practical solution for deterministic plane detection in large unorganized point clouds.

Downloads

Paper


Full Paper (pre-print)

The final publication is available at ScienceDirect - Elsevier

Code


Source Code
(please see the included readme.txt file for instructions)


Datasets


Datasets
(please see the included readme.txt file for instructions)


Reference

Citation

Limberger, Frederico A. and Manuel M. Oliveira. "Real-Time Detection of Planar Regions in Unorganized Point Clouds"Pattern Recognition. Volume 48, Number 6, June 2015, pp. 2043–2053.

BibTeX

@article {LimbergerOliveira2015HT3D,
  author = {Frederico A. Limberger and Manuel M. Oliveira},
  title = {Real-Time Detection of Planar Regions in Unorganized Point Clouds},
  journal = {Pattern Recognition},
  year = {2015},
  volume = {48},
  number = {6},
  pages = {2043-2053},
  doi = {http://dx.doi.org/10.1016/j.patcog.2014.12.020},
  issn = {0031-3203}
}

Keywords

Hough transform, Real-time plane detection, Unorganized point clouds, Spherical Accumulator, Trivariate Gaussian kernel.

Acknowledgments

CNPq-Brazil fellowships and grants #131002/2012-0, 482271/2012-4, and 308936/2010-8, and FAPERGS PQG 10/1322-0.