Cargando…

Event-Based 3D Motion Flow Estimation Using 4D Spatio Temporal Subspaces Properties

State of the art scene flow estimation techniques are based on projections of the 3D motion on image using luminance—sampled at the frame rate of the cameras—as the principal source of information. We introduce in this paper a pure time based approach to estimate the flow from 3D point clouds primar...

Descripción completa

Detalles Bibliográficos
Autores principales: Ieng, Sio-Hoi, Carneiro, João, Benosman, Ryad B.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2017
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5292574/
https://www.ncbi.nlm.nih.gov/pubmed/28220057
http://dx.doi.org/10.3389/fnins.2016.00596
_version_ 1782504949488287744
author Ieng, Sio-Hoi
Carneiro, João
Benosman, Ryad B.
author_facet Ieng, Sio-Hoi
Carneiro, João
Benosman, Ryad B.
author_sort Ieng, Sio-Hoi
collection PubMed
description State of the art scene flow estimation techniques are based on projections of the 3D motion on image using luminance—sampled at the frame rate of the cameras—as the principal source of information. We introduce in this paper a pure time based approach to estimate the flow from 3D point clouds primarily output by neuromorphic event-based stereo camera rigs, or by any existing 3D depth sensor even if it does not provide nor use luminance. This method formulates the scene flow problem by applying a local piecewise regularization of the scene flow. The formulation provides a unifying framework to estimate scene flow from synchronous and asynchronous 3D point clouds. It relies on the properties of 4D space time using a decomposition into its subspaces. This method naturally exploits the properties of the neuromorphic asynchronous event based vision sensors that allows continuous time 3D point clouds reconstruction. The approach can also handle the motion of deformable object. Experiments using different 3D sensors are presented.
format Online
Article
Text
id pubmed-5292574
institution National Center for Biotechnology Information
language English
publishDate 2017
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-52925742017-02-20 Event-Based 3D Motion Flow Estimation Using 4D Spatio Temporal Subspaces Properties Ieng, Sio-Hoi Carneiro, João Benosman, Ryad B. Front Neurosci Neuroscience State of the art scene flow estimation techniques are based on projections of the 3D motion on image using luminance—sampled at the frame rate of the cameras—as the principal source of information. We introduce in this paper a pure time based approach to estimate the flow from 3D point clouds primarily output by neuromorphic event-based stereo camera rigs, or by any existing 3D depth sensor even if it does not provide nor use luminance. This method formulates the scene flow problem by applying a local piecewise regularization of the scene flow. The formulation provides a unifying framework to estimate scene flow from synchronous and asynchronous 3D point clouds. It relies on the properties of 4D space time using a decomposition into its subspaces. This method naturally exploits the properties of the neuromorphic asynchronous event based vision sensors that allows continuous time 3D point clouds reconstruction. The approach can also handle the motion of deformable object. Experiments using different 3D sensors are presented. Frontiers Media S.A. 2017-02-06 /pmc/articles/PMC5292574/ /pubmed/28220057 http://dx.doi.org/10.3389/fnins.2016.00596 Text en Copyright © 2017 Ieng, Carneiro and Benosman. http://creativecommons.org/licenses/by/4.0/ This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
spellingShingle Neuroscience
Ieng, Sio-Hoi
Carneiro, João
Benosman, Ryad B.
Event-Based 3D Motion Flow Estimation Using 4D Spatio Temporal Subspaces Properties
title Event-Based 3D Motion Flow Estimation Using 4D Spatio Temporal Subspaces Properties
title_full Event-Based 3D Motion Flow Estimation Using 4D Spatio Temporal Subspaces Properties
title_fullStr Event-Based 3D Motion Flow Estimation Using 4D Spatio Temporal Subspaces Properties
title_full_unstemmed Event-Based 3D Motion Flow Estimation Using 4D Spatio Temporal Subspaces Properties
title_short Event-Based 3D Motion Flow Estimation Using 4D Spatio Temporal Subspaces Properties
title_sort event-based 3d motion flow estimation using 4d spatio temporal subspaces properties
topic Neuroscience
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5292574/
https://www.ncbi.nlm.nih.gov/pubmed/28220057
http://dx.doi.org/10.3389/fnins.2016.00596
work_keys_str_mv AT iengsiohoi eventbased3dmotionflowestimationusing4dspatiotemporalsubspacesproperties
AT carneirojoao eventbased3dmotionflowestimationusing4dspatiotemporalsubspacesproperties
AT benosmanryadb eventbased3dmotionflowestimationusing4dspatiotemporalsubspacesproperties