Selection of Key Frames for 3D Reconstruction in Real Time

Cameras play a prominent role in the context of 3D data, as they can be designed to be very cheap and small and can therefore be used in many 3D reconstruction systems. Typical cameras capture video at 20 to 60 frames per second, resulting in a high number of frames to select from for 3D reconstruct...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Alan Koschel, Christoph Müller, Alexander Reiterer
Formato: article
Lenguaje:EN
Publicado: MDPI AG 2021
Materias:
Acceso en línea:https://doaj.org/article/ab1ea1935e9a46388bbaa8e3c6a19c3e
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:ab1ea1935e9a46388bbaa8e3c6a19c3e
record_format dspace
spelling oai:doaj.org-article:ab1ea1935e9a46388bbaa8e3c6a19c3e2021-11-25T16:12:52ZSelection of Key Frames for 3D Reconstruction in Real Time10.3390/a141103031999-4893https://doaj.org/article/ab1ea1935e9a46388bbaa8e3c6a19c3e2021-10-01T00:00:00Zhttps://www.mdpi.com/1999-4893/14/11/303https://doaj.org/toc/1999-4893Cameras play a prominent role in the context of 3D data, as they can be designed to be very cheap and small and can therefore be used in many 3D reconstruction systems. Typical cameras capture video at 20 to 60 frames per second, resulting in a high number of frames to select from for 3D reconstruction. Many frames are unsuited for reconstruction as they suffer from motion blur or show too little variation compared to other frames. The camera used within this work has built-in inertial sensors. What if one could use the built-in inertial sensors to select a set of key frames well-suited for 3D reconstruction, free from motion blur and redundancy, in real time? A random forest classifier (RF) is trained by inertial data to determine frames without motion blur and to reduce redundancy. Frames are analyzed by the fast Fourier transformation and Lucas–Kanade method to detect motion blur and moving features in frames to label those correctly to train the RF. We achieve a classifier that omits successfully redundant frames and preserves frames with the required quality but exhibits an unsatisfied performance with respect to ideal frames. A 3D reconstruction by Meshroom shows a better result with selected key frames by the classifier. By extracting frames from video, one can comfortably scan objects and scenes without taking single pictures. Our proposed method automatically extracts the best frames in real time without using complex image-processing algorithms.Alan KoschelChristoph MüllerAlexander ReitererMDPI AGarticlesupervised learningclassificationkey frame selectionreal timeinertial sensingIndustrial engineering. Management engineeringT55.4-60.8Electronic computers. Computer scienceQA75.5-76.95ENAlgorithms, Vol 14, Iss 303, p 303 (2021)
institution DOAJ
collection DOAJ
language EN
topic supervised learning
classification
key frame selection
real time
inertial sensing
Industrial engineering. Management engineering
T55.4-60.8
Electronic computers. Computer science
QA75.5-76.95
spellingShingle supervised learning
classification
key frame selection
real time
inertial sensing
Industrial engineering. Management engineering
T55.4-60.8
Electronic computers. Computer science
QA75.5-76.95
Alan Koschel
Christoph Müller
Alexander Reiterer
Selection of Key Frames for 3D Reconstruction in Real Time
description Cameras play a prominent role in the context of 3D data, as they can be designed to be very cheap and small and can therefore be used in many 3D reconstruction systems. Typical cameras capture video at 20 to 60 frames per second, resulting in a high number of frames to select from for 3D reconstruction. Many frames are unsuited for reconstruction as they suffer from motion blur or show too little variation compared to other frames. The camera used within this work has built-in inertial sensors. What if one could use the built-in inertial sensors to select a set of key frames well-suited for 3D reconstruction, free from motion blur and redundancy, in real time? A random forest classifier (RF) is trained by inertial data to determine frames without motion blur and to reduce redundancy. Frames are analyzed by the fast Fourier transformation and Lucas–Kanade method to detect motion blur and moving features in frames to label those correctly to train the RF. We achieve a classifier that omits successfully redundant frames and preserves frames with the required quality but exhibits an unsatisfied performance with respect to ideal frames. A 3D reconstruction by Meshroom shows a better result with selected key frames by the classifier. By extracting frames from video, one can comfortably scan objects and scenes without taking single pictures. Our proposed method automatically extracts the best frames in real time without using complex image-processing algorithms.
format article
author Alan Koschel
Christoph Müller
Alexander Reiterer
author_facet Alan Koschel
Christoph Müller
Alexander Reiterer
author_sort Alan Koschel
title Selection of Key Frames for 3D Reconstruction in Real Time
title_short Selection of Key Frames for 3D Reconstruction in Real Time
title_full Selection of Key Frames for 3D Reconstruction in Real Time
title_fullStr Selection of Key Frames for 3D Reconstruction in Real Time
title_full_unstemmed Selection of Key Frames for 3D Reconstruction in Real Time
title_sort selection of key frames for 3d reconstruction in real time
publisher MDPI AG
publishDate 2021
url https://doaj.org/article/ab1ea1935e9a46388bbaa8e3c6a19c3e
work_keys_str_mv AT alankoschel selectionofkeyframesfor3dreconstructioninrealtime
AT christophmuller selectionofkeyframesfor3dreconstructioninrealtime
AT alexanderreiterer selectionofkeyframesfor3dreconstructioninrealtime
_version_ 1718413275825176576