Classification of Outdoor 3D Lidar Data Based on Unsupervised Gaussian Mixture Models - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2015

Classification of Outdoor 3D Lidar Data Based on Unsupervised Gaussian Mixture Models

Résumé

3D point clouds acquired with lidars are an important source of data for the classification of outdoor environments by autonomous terrestrial robots. We propose here a two-layer classification system. The first layer consists of a Gaussian mixture model, issued from unsupervised training, which defines a large set of data-oriented classes. The second layer consists of a supervised, manual grouping of the unsupervised classes into a smaller set of task-oriented classes. Because it uses unsupervised learning at its core, the system does not require any manual labeling of datasets. We evaluate the system on two datasets of different nature, and the results show its capacity to adapt to different data while providing classes which are exploitable in a target task.
Fichier principal
Vignette du fichier
MALIGO-SSRR-2015.pdf (2.27 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01232096 , version 1 (22-11-2015)

Identifiants

  • HAL Id : hal-01232096 , version 1

Citer

Artur Maligo, Simon Lacroix. Classification of Outdoor 3D Lidar Data Based on Unsupervised Gaussian Mixture Models. IEEE International Symposium on Safety, Security, and Rescue Robotics, Oct 2015, West Lafayette, United States. ⟨hal-01232096⟩
376 Consultations
320 Téléchargements

Partager

Gmail Facebook X LinkedIn More