Normal estimation for pointcloud using GPU based sparse tensor voting - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2012

Normal estimation for pointcloud using GPU based sparse tensor voting

Ming Liu
Francis Colas

Résumé

Normal estimation is the basis for most applications using pointcloud, such as segmentation. However, it is still a challenging problem regarding computational complexity and observation noise. In this paper, we propose a normal estimation method for pointcloud using results from tensor voting. Comparing with other approaches, we show it has smaller estimation error. Moreover, by varying the voting kernel size, we find it is a flexible approach for structure extraction as well. The results show that the proposed method is robust to noisy observation and missing data points as well. We use a GPU based implementation of Sparse Tensor Voting, which enables realtime calculation.
Fichier principal
Vignette du fichier
2012_Liu_RoBio_Normal.pdf (2.26 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01142736 , version 1 (15-04-2015)

Identifiants

Citer

Ming Liu, François Pomerleau, Francis Colas, Roland Siegwart. Normal estimation for pointcloud using GPU based sparse tensor voting. IEEE International Conference on Robotics and Biomimetics (Robio), 2012, Guangzhou, China. ⟨10.1109/ROBIO.2012.6490949⟩. ⟨hal-01142736⟩
68 Consultations
944 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More