Return to Research

Plane-extraction from depth-data

Plane-extraction from depth-data using a Gaussian mixture regression model

Richard Marriott, Alexander Pashevich, and Radu Horaud

Pattern Recognition Letters, volume 110, pages 44-50, July 2018 | arXiv | HAL | BibTeX |Matlab code


Segmentation into elliptical planar patches based on piecewise linear Gaussian mixture regression

Final result after merging of Gaussian components into a collection of planes that best fit the depth data

Abstract: We propose a novel algorithm for unsupervised extraction of piecewise planar models from depth data. Among other applications, such models are a good way of enabling autonomous agents (robots, cars, drones, etc.) to effectively perceive their surroundings and to navigate in three dimensions.  We propose to do this by fitting the data with a piecewise-linear Gaussian mixture regression model whose components are  skewed over planes, making them flat in appearance rather than being ellipsoidal, by embedding an outlier-trimming process that is formally incorporated into the proposed expectation-maximization algorithm, and by selectively fusing contiguous, coplanar components. Part of our motivation is an attempt to estimate more accurate plane-extraction by allowing each model component to make use of all available data through probabilistic clustering. The algorithm is thoroughly evaluated against a standard benchmark and is shown to rank among the best of the existing state-of-the-art methods.

  TITLE = {{Plane-extraction from depth-data using a Gaussian mixture regression model}},
  AUTHOR = {Marriott, Richard T and Pashevich, Alexander and Horaud, Radu},
  JOURNAL = {Pattern Recognition Letters},
  PUBLISHER = {Elsevier},
  VOLUME = {110},
  PAGES = {44-50},
  YEAR = {2018},
  MONTH = {July},