Video segmentation based on motion coherence of particles in a video sequence
Autor(a) principal: | |
---|---|
Data de Publicação: | 2010 |
Outros Autores: | |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Institucional da UFRGS |
Texto Completo: | http://hdl.handle.net/10183/27632 |
Resumo: | This work describes an approach for object-oriented video segmentation based on motion coherence. Using a tracking process based on adaptively sampled points (namely, particles), 2-D motion patterns are identified with an ensemble clustering approach. Particles are clustered to obtain a pixel-wise segmentation in space and time domains. The segmentation result is mapped to an image spatio-temporal feature space. Thus, the different constituent parts of the scene that move coherently along the video sequence are mapped to volumes in this spatio-temporal space. These volumes make the redundancy in the temporal sense more explicit, leading to potential gains in video coding applications. The proposed solution is robust and more generic than similar approaches for 2-D video segmentation found in the literature. In order to illustrate the potential advantages of using the proposed motion segmentation approach in video coding applications, the PSNR of the temporal predictions and the entropies of prediction errors obtained in our experiments are presented, and compared with other methods. Our experiments with real and synthetic sequences suggest that our method also could be used in other image processing and computer vision tasks, besides video coding, such as video information retrieval and video understanding. |
id |
UFRGS-2_5aef49cff215c0b4e0db0c3583f74184 |
---|---|
oai_identifier_str |
oai:www.lume.ufrgs.br:10183/27632 |
network_acronym_str |
UFRGS-2 |
network_name_str |
Repositório Institucional da UFRGS |
repository_id_str |
|
spelling |
Silva, Luciano Silva daScharcanski, Jacob2011-01-29T06:00:47Z20101057-7149http://hdl.handle.net/10183/27632000741894This work describes an approach for object-oriented video segmentation based on motion coherence. Using a tracking process based on adaptively sampled points (namely, particles), 2-D motion patterns are identified with an ensemble clustering approach. Particles are clustered to obtain a pixel-wise segmentation in space and time domains. The segmentation result is mapped to an image spatio-temporal feature space. Thus, the different constituent parts of the scene that move coherently along the video sequence are mapped to volumes in this spatio-temporal space. These volumes make the redundancy in the temporal sense more explicit, leading to potential gains in video coding applications. The proposed solution is robust and more generic than similar approaches for 2-D video segmentation found in the literature. In order to illustrate the potential advantages of using the proposed motion segmentation approach in video coding applications, the PSNR of the temporal predictions and the entropies of prediction errors obtained in our experiments are presented, and compared with other methods. Our experiments with real and synthetic sequences suggest that our method also could be used in other image processing and computer vision tasks, besides video coding, such as video information retrieval and video understanding.application/pdfengIEEE transactions on image processing. New York. Vol. 19, no 4 (Apr. 2010), p. 1036-1049Computação gráficaProcessamento de imagensEnsemble clusteringMotion segmentationObject- based video segmentationPoint trackingVideo codingVideo segmentation based on motion coherence of particles in a video sequenceEstrangeiroinfo:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/openAccessreponame:Repositório Institucional da UFRGSinstname:Universidade Federal do Rio Grande do Sul (UFRGS)instacron:UFRGSTEXT000741894.pdf.txt000741894.pdf.txtExtracted Texttext/plain79139http://www.lume.ufrgs.br/bitstream/10183/27632/2/000741894.pdf.txt69d178d231347cc277431bc5cf094a69MD52ORIGINAL000741894.pdf000741894.pdfTexto completo (inglês)application/pdf907673http://www.lume.ufrgs.br/bitstream/10183/27632/1/000741894.pdfc9e84271e7bf39879a3c0a9234246b50MD51THUMBNAIL000741894.pdf.jpg000741894.pdf.jpgGenerated Thumbnailimage/jpeg2359http://www.lume.ufrgs.br/bitstream/10183/27632/3/000741894.pdf.jpg2cfe8229222934a8444c378934ed9e73MD5310183/276322021-05-26 04:44:51.970554oai:www.lume.ufrgs.br:10183/27632Repositório de PublicaçõesPUBhttps://lume.ufrgs.br/oai/requestopendoar:2021-05-26T07:44:51Repositório Institucional da UFRGS - Universidade Federal do Rio Grande do Sul (UFRGS)false |
dc.title.pt_BR.fl_str_mv |
Video segmentation based on motion coherence of particles in a video sequence |
title |
Video segmentation based on motion coherence of particles in a video sequence |
spellingShingle |
Video segmentation based on motion coherence of particles in a video sequence Silva, Luciano Silva da Computação gráfica Processamento de imagens Ensemble clustering Motion segmentation Object- based video segmentation Point tracking Video coding |
title_short |
Video segmentation based on motion coherence of particles in a video sequence |
title_full |
Video segmentation based on motion coherence of particles in a video sequence |
title_fullStr |
Video segmentation based on motion coherence of particles in a video sequence |
title_full_unstemmed |
Video segmentation based on motion coherence of particles in a video sequence |
title_sort |
Video segmentation based on motion coherence of particles in a video sequence |
author |
Silva, Luciano Silva da |
author_facet |
Silva, Luciano Silva da Scharcanski, Jacob |
author_role |
author |
author2 |
Scharcanski, Jacob |
author2_role |
author |
dc.contributor.author.fl_str_mv |
Silva, Luciano Silva da Scharcanski, Jacob |
dc.subject.por.fl_str_mv |
Computação gráfica Processamento de imagens |
topic |
Computação gráfica Processamento de imagens Ensemble clustering Motion segmentation Object- based video segmentation Point tracking Video coding |
dc.subject.eng.fl_str_mv |
Ensemble clustering Motion segmentation Object- based video segmentation Point tracking Video coding |
description |
This work describes an approach for object-oriented video segmentation based on motion coherence. Using a tracking process based on adaptively sampled points (namely, particles), 2-D motion patterns are identified with an ensemble clustering approach. Particles are clustered to obtain a pixel-wise segmentation in space and time domains. The segmentation result is mapped to an image spatio-temporal feature space. Thus, the different constituent parts of the scene that move coherently along the video sequence are mapped to volumes in this spatio-temporal space. These volumes make the redundancy in the temporal sense more explicit, leading to potential gains in video coding applications. The proposed solution is robust and more generic than similar approaches for 2-D video segmentation found in the literature. In order to illustrate the potential advantages of using the proposed motion segmentation approach in video coding applications, the PSNR of the temporal predictions and the entropies of prediction errors obtained in our experiments are presented, and compared with other methods. Our experiments with real and synthetic sequences suggest that our method also could be used in other image processing and computer vision tasks, besides video coding, such as video information retrieval and video understanding. |
publishDate |
2010 |
dc.date.issued.fl_str_mv |
2010 |
dc.date.accessioned.fl_str_mv |
2011-01-29T06:00:47Z |
dc.type.driver.fl_str_mv |
Estrangeiro info:eu-repo/semantics/article |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
format |
article |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
http://hdl.handle.net/10183/27632 |
dc.identifier.issn.pt_BR.fl_str_mv |
1057-7149 |
dc.identifier.nrb.pt_BR.fl_str_mv |
000741894 |
identifier_str_mv |
1057-7149 000741894 |
url |
http://hdl.handle.net/10183/27632 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.ispartof.pt_BR.fl_str_mv |
IEEE transactions on image processing. New York. Vol. 19, no 4 (Apr. 2010), p. 1036-1049 |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
application/pdf |
dc.source.none.fl_str_mv |
reponame:Repositório Institucional da UFRGS instname:Universidade Federal do Rio Grande do Sul (UFRGS) instacron:UFRGS |
instname_str |
Universidade Federal do Rio Grande do Sul (UFRGS) |
instacron_str |
UFRGS |
institution |
UFRGS |
reponame_str |
Repositório Institucional da UFRGS |
collection |
Repositório Institucional da UFRGS |
bitstream.url.fl_str_mv |
http://www.lume.ufrgs.br/bitstream/10183/27632/2/000741894.pdf.txt http://www.lume.ufrgs.br/bitstream/10183/27632/1/000741894.pdf http://www.lume.ufrgs.br/bitstream/10183/27632/3/000741894.pdf.jpg |
bitstream.checksum.fl_str_mv |
69d178d231347cc277431bc5cf094a69 c9e84271e7bf39879a3c0a9234246b50 2cfe8229222934a8444c378934ed9e73 |
bitstream.checksumAlgorithm.fl_str_mv |
MD5 MD5 MD5 |
repository.name.fl_str_mv |
Repositório Institucional da UFRGS - Universidade Federal do Rio Grande do Sul (UFRGS) |
repository.mail.fl_str_mv |
|
_version_ |
1801224725089746944 |