Publicado em: 28/04/2014

Dissertação de Mestrado em Processamento Gráfico

UNIVERSIDADE FEDERAL DO RIO GRANDE DO SUL
INSTITUTO DE INFORMÁTICA
PROGRAMA DE POS-GRADUAÇÃO EM COMPUTAÇÃO

———————————————————

DEFESA DE DISSERTAÇÃO DE MESTRADO

Aluno: Frederico Artur Limberger
Orientador: Prof. Dr. Manuel Menezes de Oliveira Neto
Título: Real-Time Detection of Planar Regions in Unorganized Point Clouds

Linha de Pesquisa: Processamento Gráfico
Data: 30/04/2014
Hora: 10:30h

Local: Prédio 43413 – Auditório Inferior , Instituto de Informática

Banca Examinadora:

Prof. Dr. Cláudio Rosito Jung (UFRGS)
Prof. Dr. João Luiz Dihl Comba (UFRGS)
Prof. Dr. Leandro Augusto Frata Fernandes (UFF)

Presidente da Banca: Prof. Dr. Manuel Menezes de Oliveira Neto

Resumo:

Automatic detection of planar regions in point clouds is an important (preprocessing) step for many graphics, image processing, and computer vision applications. While the availability of laser scanners and digital photography has allowed us to capture increasingly larger datasets, existing techniques for plane detection are computationally expensive, being unable to achieve real-time performance for datasets containing tens of thousands of points, even when detection is performed in a non-deterministic way. We present an O(n log n) technique for plane detection in unorganized point clouds. It is based on an efficient Hough-transform voting scheme and works by clustering groups of approximately co-planar points and by casting votes for these clusters on a spherical accumulator using a trivariate Gaussian kernel. A comparison with competing techniques shows that our approach is considerably faster and scales significantly better than existing ones, being the only practical solution available for deterministic plane detection in large unorganized point clouds.

Palavras-chave:  plane detection, Hough transform, unorganized point clouds

_____________

Divulgação PPGC