Semantic Classification of 3D Point Clouds with Multiscale Spherical Neighborhoods

Abstract : This paper introduces a new definition of multiscale neighborhoods in 3D point clouds. This definition, based on spherical neighborhoods and proportional subsampling, allows the computation of features with a consistent geometrical meaning, which is not the case when using k-nearest neighbors. With an appropriate learning strategy, the proposed features can be used in a random forest to classify 3D points. In this semantic classification task, we show that our multiscale features outperform state-of-the-art features using the same experimental conditions. Furthermore, their classification power competes with more elaborate classification approaches including Deep Learning methods.
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-01985640
Contributor : Hugues Thomas <>
Submitted on : Friday, January 18, 2019 - 10:48:44 AM
Last modification on : Sunday, January 20, 2019 - 1:09:51 AM

Links full text

Identifiers

Citation

Yann Le Gall, Hugues Thomas, François Goulette, Jean-Emmanuel Deschaud, Beatriz Marcotegui. Semantic Classification of 3D Point Clouds with Multiscale Spherical Neighborhoods. 2018 International Conference on 3D Vision (3DV), Sep 2018, Verone, Italy. ⟨10.1109/3DV.2018.00052⟩. ⟨hal-01985640⟩

Share

Metrics

Record views

34