Plane-extraction from depth-data using a Gaussian mixture regression model - Archive ouverte HAL Access content directly
Journal Articles Pattern Recognition Letters Year : 2018

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

(1) , (1) , (1)
1

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.
Fichier principal
Vignette du fichier
Mariott-arXiv-v2.pdf (506.91 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01663984 , version 1 (14-12-2017)
hal-01663984 , version 2 (29-03-2018)

Identifiers

Cite

Richard T Marriott, Alexander Pashevich, Radu Horaud. Plane-extraction from depth-data using a Gaussian mixture regression model. Pattern Recognition Letters, 2018, 110, pp.44-50. ⟨10.1016/j.patrec.2018.03.024⟩. ⟨hal-01663984v2⟩
322 View
180 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More