SVD-Based Tensor-Completion Technique for Background Initialization
Extracting the background from a video in the presence of various moving patterns is the focus of several background-initialization approaches. To model the scene background using rank-one matrices, this paper proposes a background-initialization technique that relies on the singular-value decomposi...
Saved in:
Main Authors: | , , , |
---|---|
Format: | Article |
Published: |
Institute of Electrical and Electronics Engineers Inc.
2018
|
Online Access: | https://www.scopus.com/inward/record.uri?eid=2-s2.0-85044044731&doi=10.1109%2fTIP.2018.2817045&partnerID=40&md5=56caf57c232f6ddd50c175199cdc9746 http://eprints.utp.edu.my/20898/ |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
id |
my.utp.eprints.20898 |
---|---|
record_format |
eprints |
spelling |
my.utp.eprints.208982019-02-26T02:42:13Z SVD-Based Tensor-Completion Technique for Background Initialization Kajo, I. Kamel, N. Ruichek, Y. Malik, A.S. Extracting the background from a video in the presence of various moving patterns is the focus of several background-initialization approaches. To model the scene background using rank-one matrices, this paper proposes a background-initialization technique that relies on the singular-value decomposition (SVD) of spatiotemporally extracted slices from the video tensor. The proposed method is referred to as spatiotemporal slice-based SVD (SS-SVD). To determine the SVD components that best model the background, a depth analysis of the computation of the left/right singular vectors and singular values is performed, and the relationship with tensor-tube fibers is determined. The analysis proves that a rank-1 matrix extracted from the first left and right singular vectors and singular value represents an efficient model of the scene background. The performance of the proposed SS-SVD method is evaluated using 93 complex video sequences of different challenges, and the method is compared with state-of-the-art tensor/matrix completion-based methods, statistical-based methods, search-based methods, and labeling-based methods. The results not only show better performance over most of the tested challenges, but also demonstrate the capability of the proposed technique to solve the background-initialization problem in a less computational time and with fewer frames. © 1992-2012 IEEE. Institute of Electrical and Electronics Engineers Inc. 2018 Article NonPeerReviewed https://www.scopus.com/inward/record.uri?eid=2-s2.0-85044044731&doi=10.1109%2fTIP.2018.2817045&partnerID=40&md5=56caf57c232f6ddd50c175199cdc9746 Kajo, I. and Kamel, N. and Ruichek, Y. and Malik, A.S. (2018) SVD-Based Tensor-Completion Technique for Background Initialization. IEEE Transactions on Image Processing, 27 (6). pp. 3114-3126. http://eprints.utp.edu.my/20898/ |
institution |
Universiti Teknologi Petronas |
building |
UTP Resource Centre |
collection |
Institutional Repository |
continent |
Asia |
country |
Malaysia |
content_provider |
Universiti Teknologi Petronas |
content_source |
UTP Institutional Repository |
url_provider |
http://eprints.utp.edu.my/ |
description |
Extracting the background from a video in the presence of various moving patterns is the focus of several background-initialization approaches. To model the scene background using rank-one matrices, this paper proposes a background-initialization technique that relies on the singular-value decomposition (SVD) of spatiotemporally extracted slices from the video tensor. The proposed method is referred to as spatiotemporal slice-based SVD (SS-SVD). To determine the SVD components that best model the background, a depth analysis of the computation of the left/right singular vectors and singular values is performed, and the relationship with tensor-tube fibers is determined. The analysis proves that a rank-1 matrix extracted from the first left and right singular vectors and singular value represents an efficient model of the scene background. The performance of the proposed SS-SVD method is evaluated using 93 complex video sequences of different challenges, and the method is compared with state-of-the-art tensor/matrix completion-based methods, statistical-based methods, search-based methods, and labeling-based methods. The results not only show better performance over most of the tested challenges, but also demonstrate the capability of the proposed technique to solve the background-initialization problem in a less computational time and with fewer frames. © 1992-2012 IEEE. |
format |
Article |
author |
Kajo, I. Kamel, N. Ruichek, Y. Malik, A.S. |
spellingShingle |
Kajo, I. Kamel, N. Ruichek, Y. Malik, A.S. SVD-Based Tensor-Completion Technique for Background Initialization |
author_facet |
Kajo, I. Kamel, N. Ruichek, Y. Malik, A.S. |
author_sort |
Kajo, I. |
title |
SVD-Based Tensor-Completion Technique for Background Initialization |
title_short |
SVD-Based Tensor-Completion Technique for Background Initialization |
title_full |
SVD-Based Tensor-Completion Technique for Background Initialization |
title_fullStr |
SVD-Based Tensor-Completion Technique for Background Initialization |
title_full_unstemmed |
SVD-Based Tensor-Completion Technique for Background Initialization |
title_sort |
svd-based tensor-completion technique for background initialization |
publisher |
Institute of Electrical and Electronics Engineers Inc. |
publishDate |
2018 |
url |
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85044044731&doi=10.1109%2fTIP.2018.2817045&partnerID=40&md5=56caf57c232f6ddd50c175199cdc9746 http://eprints.utp.edu.my/20898/ |
_version_ |
1738656248220352512 |
score |
13.160551 |