Computational Large Field-of-View RGB-D Integral Imaging System

The integral imaging system has received considerable research attention because it can be applied to real-time three-dimensional image displays with a continuous view angle without supplementary devices. Most previous approaches place a physical micro-lens array in front of the image, where each le...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Geunho Jung, Yong-Yuk Won, Sang Min Yoon
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	light field imaging monocular depth map estimation computational integral imaging Chemical technology TP1-1185
Acceso en línea:	https://doaj.org/article/2b0f650be9c84e888e1b491cf8de421c
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:2b0f650be9c84e888e1b491cf8de421c
record_format	dspace
spelling	oai:doaj.org-article:2b0f650be9c84e888e1b491cf8de421c2021-11-11T19:19:42ZComputational Large Field-of-View RGB-D Integral Imaging System10.3390/s212174071424-8220https://doaj.org/article/2b0f650be9c84e888e1b491cf8de421c2021-11-01T00:00:00Zhttps://www.mdpi.com/1424-8220/21/21/7407https://doaj.org/toc/1424-8220The integral imaging system has received considerable research attention because it can be applied to real-time three-dimensional image displays with a continuous view angle without supplementary devices. Most previous approaches place a physical micro-lens array in front of the image, where each lens looks different depending on the viewing angle. A computational integral imaging system with a virtual micro-lens arrays has been proposed in order to provide flexibility for users to change micro-lens arrays and focal length while reducing distortions due to physical mismatches with the lens arrays. However, computational integral imaging methods only represent part of the whole image because the size of virtual lens arrays is much smaller than the given large-scale images when dealing with large-scale images. As a result, the previous approaches produce sub-aperture images with a small field of view and need additional devices for depth information to apply to integral imaging pickup systems. In this paper, we present a single image-based computational RGB-D integral imaging pickup system for a large field of view in real time. The proposed system comprises three steps: deep learning-based automatic depth map estimation from an RGB input image without the help of an additional device, a hierarchical integral imaging system for a large field of view in real time, and post-processing for optimized visualization of the failed pickup area using an inpainting method. Quantitative and qualitative experimental results verify the proposed approach’s robustness.Geunho JungYong-Yuk WonSang Min YoonMDPI AGarticlelight field imagingmonocular depth map estimationcomputational integral imagingChemical technologyTP1-1185ENSensors, Vol 21, Iss 7407, p 7407 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	light field imaging monocular depth map estimation computational integral imaging Chemical technology TP1-1185
spellingShingle	light field imaging monocular depth map estimation computational integral imaging Chemical technology TP1-1185 Geunho Jung Yong-Yuk Won Sang Min Yoon Computational Large Field-of-View RGB-D Integral Imaging System
description	The integral imaging system has received considerable research attention because it can be applied to real-time three-dimensional image displays with a continuous view angle without supplementary devices. Most previous approaches place a physical micro-lens array in front of the image, where each lens looks different depending on the viewing angle. A computational integral imaging system with a virtual micro-lens arrays has been proposed in order to provide flexibility for users to change micro-lens arrays and focal length while reducing distortions due to physical mismatches with the lens arrays. However, computational integral imaging methods only represent part of the whole image because the size of virtual lens arrays is much smaller than the given large-scale images when dealing with large-scale images. As a result, the previous approaches produce sub-aperture images with a small field of view and need additional devices for depth information to apply to integral imaging pickup systems. In this paper, we present a single image-based computational RGB-D integral imaging pickup system for a large field of view in real time. The proposed system comprises three steps: deep learning-based automatic depth map estimation from an RGB input image without the help of an additional device, a hierarchical integral imaging system for a large field of view in real time, and post-processing for optimized visualization of the failed pickup area using an inpainting method. Quantitative and qualitative experimental results verify the proposed approach’s robustness.
format	article
author	Geunho Jung Yong-Yuk Won Sang Min Yoon
author_facet	Geunho Jung Yong-Yuk Won Sang Min Yoon
author_sort	Geunho Jung
title	Computational Large Field-of-View RGB-D Integral Imaging System
title_short	Computational Large Field-of-View RGB-D Integral Imaging System
title_full	Computational Large Field-of-View RGB-D Integral Imaging System
title_fullStr	Computational Large Field-of-View RGB-D Integral Imaging System
title_full_unstemmed	Computational Large Field-of-View RGB-D Integral Imaging System
title_sort	computational large field-of-view rgb-d integral imaging system
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/2b0f650be9c84e888e1b491cf8de421c
work_keys_str_mv	AT geunhojung computationallargefieldofviewrgbdintegralimagingsystem AT yongyukwon computationallargefieldofviewrgbdintegralimagingsystem AT sangminyoon computationallargefieldofviewrgbdintegralimagingsystem
_version_	1718431517067182080

Computational Large Field-of-View RGB-D Integral Imaging System

Ejemplares similares