Cargando…

Reconstruction-Based Change Detection with Image Completion for a Free-Moving Camera

Reconstruction-based change detection methods are robust for camera motion. The methods learn reconstruction of input images based on background images. Foreground regions are detected based on the magnitude of the difference between an input image and a reconstructed input image. For learning, only...

Descripción completa

Detalles Bibliográficos
Autores principales: Minematsu, Tsubasa, Shimada, Atsushi, Uchiyama, Hideaki, Charvillat, Vincent, Taniguchi, Rin-ichiro
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2018
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5948507/
https://www.ncbi.nlm.nih.gov/pubmed/29673193
http://dx.doi.org/10.3390/s18041232
_version_ 1783322565161254912
author Minematsu, Tsubasa
Shimada, Atsushi
Uchiyama, Hideaki
Charvillat, Vincent
Taniguchi, Rin-ichiro
author_facet Minematsu, Tsubasa
Shimada, Atsushi
Uchiyama, Hideaki
Charvillat, Vincent
Taniguchi, Rin-ichiro
author_sort Minematsu, Tsubasa
collection PubMed
description Reconstruction-based change detection methods are robust for camera motion. The methods learn reconstruction of input images based on background images. Foreground regions are detected based on the magnitude of the difference between an input image and a reconstructed input image. For learning, only background images are used. Therefore, foreground regions have larger differences than background regions. Traditional reconstruction-based methods have two problems. One is over-reconstruction of foreground regions. The other is that decision of change detection depends on magnitudes of differences only. It is difficult to distinguish magnitudes of differences in foreground regions when the foreground regions are completely reconstructed in patch images. We propose the framework of a reconstruction-based change detection method for a free-moving camera using patch images. To avoid over-reconstruction of foreground regions, our method reconstructs a masked central region in a patch image from a region surrounding the central region. Differences in foreground regions are enhanced because foreground regions in patch images are removed by the masking procedure. Change detection is learned from a patch image and a reconstructed image automatically. The decision procedure directly uses patch images rather than the differences between patch images. Our method achieves better accuracy compared to traditional reconstruction-based methods without masking patch images.
format Online
Article
Text
id pubmed-5948507
institution National Center for Biotechnology Information
language English
publishDate 2018
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-59485072018-05-17 Reconstruction-Based Change Detection with Image Completion for a Free-Moving Camera Minematsu, Tsubasa Shimada, Atsushi Uchiyama, Hideaki Charvillat, Vincent Taniguchi, Rin-ichiro Sensors (Basel) Article Reconstruction-based change detection methods are robust for camera motion. The methods learn reconstruction of input images based on background images. Foreground regions are detected based on the magnitude of the difference between an input image and a reconstructed input image. For learning, only background images are used. Therefore, foreground regions have larger differences than background regions. Traditional reconstruction-based methods have two problems. One is over-reconstruction of foreground regions. The other is that decision of change detection depends on magnitudes of differences only. It is difficult to distinguish magnitudes of differences in foreground regions when the foreground regions are completely reconstructed in patch images. We propose the framework of a reconstruction-based change detection method for a free-moving camera using patch images. To avoid over-reconstruction of foreground regions, our method reconstructs a masked central region in a patch image from a region surrounding the central region. Differences in foreground regions are enhanced because foreground regions in patch images are removed by the masking procedure. Change detection is learned from a patch image and a reconstructed image automatically. The decision procedure directly uses patch images rather than the differences between patch images. Our method achieves better accuracy compared to traditional reconstruction-based methods without masking patch images. MDPI 2018-04-17 /pmc/articles/PMC5948507/ /pubmed/29673193 http://dx.doi.org/10.3390/s18041232 Text en © 2018 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Minematsu, Tsubasa
Shimada, Atsushi
Uchiyama, Hideaki
Charvillat, Vincent
Taniguchi, Rin-ichiro
Reconstruction-Based Change Detection with Image Completion for a Free-Moving Camera
title Reconstruction-Based Change Detection with Image Completion for a Free-Moving Camera
title_full Reconstruction-Based Change Detection with Image Completion for a Free-Moving Camera
title_fullStr Reconstruction-Based Change Detection with Image Completion for a Free-Moving Camera
title_full_unstemmed Reconstruction-Based Change Detection with Image Completion for a Free-Moving Camera
title_short Reconstruction-Based Change Detection with Image Completion for a Free-Moving Camera
title_sort reconstruction-based change detection with image completion for a free-moving camera
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5948507/
https://www.ncbi.nlm.nih.gov/pubmed/29673193
http://dx.doi.org/10.3390/s18041232
work_keys_str_mv AT minematsutsubasa reconstructionbasedchangedetectionwithimagecompletionforafreemovingcamera
AT shimadaatsushi reconstructionbasedchangedetectionwithimagecompletionforafreemovingcamera
AT uchiyamahideaki reconstructionbasedchangedetectionwithimagecompletionforafreemovingcamera
AT charvillatvincent reconstructionbasedchangedetectionwithimagecompletionforafreemovingcamera
AT taniguchirinichiro reconstructionbasedchangedetectionwithimagecompletionforafreemovingcamera