Real-time Background Subtraction via L1 Norm Tensor Decomposition

Taehyeon Kim, Yoonsik Choe

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Currently, background subtraction is being actively studied in many image processing applications. Nuclear Norm Minimization (NNM) and Weighted Nuclear Norm Minimization (WNNM) are commonly used background subtraction methods based on Robust Principal Component Analysis (RPCA). However, these techniques approximate the RPCA rank function and take the form of an iterative optimization algorithm. Therefore, due to the approximation, the NNM solution can not converge if the number of frames is small. In addition, the NNM and WNNM processing times are delayed because of their iterative optimization schemes. Thus, NNM and WNNM are not suitable for real-time background subtraction. In order to overcome these limitations, this paper presents a real-time background subtraction method using tensor decomposition in accordance with the recent tensor analysis research trend. In this study, we used the closed form TUCKER2 decomposition solution to omit the iterative process while retaining the L1 norm of the RPCA rank function. This proposed method allows for convergence even when the number of frames is small. Compared to NNM and WNNM, the proposed method reduces the processing time by more than 80 times and has a higher precision even when the number of frames are less than 10.

Original languageEnglish
Title of host publication2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2018 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1963-1967
Number of pages5
ISBN (Electronic)9789881476852
DOIs
Publication statusPublished - 2019 Mar 4
Event10th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2018 - Honolulu, United States
Duration: 2018 Nov 122018 Nov 15

Publication series

Name2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2018 - Proceedings

Conference

Conference10th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2018
CountryUnited States
CityHonolulu
Period18/11/1218/11/15

Fingerprint

Tensors
Decomposition
Principal component analysis
Processing
Image processing

All Science Journal Classification (ASJC) codes

  • Information Systems

Cite this

Kim, T., & Choe, Y. (2019). Real-time Background Subtraction via L1 Norm Tensor Decomposition. In 2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2018 - Proceedings (pp. 1963-1967). [8659727] (2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2018 - Proceedings). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.23919/APSIPA.2018.8659727
Kim, Taehyeon ; Choe, Yoonsik. / Real-time Background Subtraction via L1 Norm Tensor Decomposition. 2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2018 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2019. pp. 1963-1967 (2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2018 - Proceedings).
@inproceedings{00cd2aa50f7446be924656939db90561,
title = "Real-time Background Subtraction via L1 Norm Tensor Decomposition",
abstract = "Currently, background subtraction is being actively studied in many image processing applications. Nuclear Norm Minimization (NNM) and Weighted Nuclear Norm Minimization (WNNM) are commonly used background subtraction methods based on Robust Principal Component Analysis (RPCA). However, these techniques approximate the RPCA rank function and take the form of an iterative optimization algorithm. Therefore, due to the approximation, the NNM solution can not converge if the number of frames is small. In addition, the NNM and WNNM processing times are delayed because of their iterative optimization schemes. Thus, NNM and WNNM are not suitable for real-time background subtraction. In order to overcome these limitations, this paper presents a real-time background subtraction method using tensor decomposition in accordance with the recent tensor analysis research trend. In this study, we used the closed form TUCKER2 decomposition solution to omit the iterative process while retaining the L1 norm of the RPCA rank function. This proposed method allows for convergence even when the number of frames is small. Compared to NNM and WNNM, the proposed method reduces the processing time by more than 80 times and has a higher precision even when the number of frames are less than 10.",
author = "Taehyeon Kim and Yoonsik Choe",
year = "2019",
month = "3",
day = "4",
doi = "10.23919/APSIPA.2018.8659727",
language = "English",
series = "2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2018 - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "1963--1967",
booktitle = "2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2018 - Proceedings",
address = "United States",

}

Kim, T & Choe, Y 2019, Real-time Background Subtraction via L1 Norm Tensor Decomposition. in 2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2018 - Proceedings., 8659727, 2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2018 - Proceedings, Institute of Electrical and Electronics Engineers Inc., pp. 1963-1967, 10th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2018, Honolulu, United States, 18/11/12. https://doi.org/10.23919/APSIPA.2018.8659727

Real-time Background Subtraction via L1 Norm Tensor Decomposition. / Kim, Taehyeon; Choe, Yoonsik.

2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2018 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2019. p. 1963-1967 8659727 (2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2018 - Proceedings).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Real-time Background Subtraction via L1 Norm Tensor Decomposition

AU - Kim, Taehyeon

AU - Choe, Yoonsik

PY - 2019/3/4

Y1 - 2019/3/4

N2 - Currently, background subtraction is being actively studied in many image processing applications. Nuclear Norm Minimization (NNM) and Weighted Nuclear Norm Minimization (WNNM) are commonly used background subtraction methods based on Robust Principal Component Analysis (RPCA). However, these techniques approximate the RPCA rank function and take the form of an iterative optimization algorithm. Therefore, due to the approximation, the NNM solution can not converge if the number of frames is small. In addition, the NNM and WNNM processing times are delayed because of their iterative optimization schemes. Thus, NNM and WNNM are not suitable for real-time background subtraction. In order to overcome these limitations, this paper presents a real-time background subtraction method using tensor decomposition in accordance with the recent tensor analysis research trend. In this study, we used the closed form TUCKER2 decomposition solution to omit the iterative process while retaining the L1 norm of the RPCA rank function. This proposed method allows for convergence even when the number of frames is small. Compared to NNM and WNNM, the proposed method reduces the processing time by more than 80 times and has a higher precision even when the number of frames are less than 10.

AB - Currently, background subtraction is being actively studied in many image processing applications. Nuclear Norm Minimization (NNM) and Weighted Nuclear Norm Minimization (WNNM) are commonly used background subtraction methods based on Robust Principal Component Analysis (RPCA). However, these techniques approximate the RPCA rank function and take the form of an iterative optimization algorithm. Therefore, due to the approximation, the NNM solution can not converge if the number of frames is small. In addition, the NNM and WNNM processing times are delayed because of their iterative optimization schemes. Thus, NNM and WNNM are not suitable for real-time background subtraction. In order to overcome these limitations, this paper presents a real-time background subtraction method using tensor decomposition in accordance with the recent tensor analysis research trend. In this study, we used the closed form TUCKER2 decomposition solution to omit the iterative process while retaining the L1 norm of the RPCA rank function. This proposed method allows for convergence even when the number of frames is small. Compared to NNM and WNNM, the proposed method reduces the processing time by more than 80 times and has a higher precision even when the number of frames are less than 10.

UR - http://www.scopus.com/inward/record.url?scp=85063549315&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85063549315&partnerID=8YFLogxK

U2 - 10.23919/APSIPA.2018.8659727

DO - 10.23919/APSIPA.2018.8659727

M3 - Conference contribution

AN - SCOPUS:85063549315

T3 - 2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2018 - Proceedings

SP - 1963

EP - 1967

BT - 2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2018 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Kim T, Choe Y. Real-time Background Subtraction via L1 Norm Tensor Decomposition. In 2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2018 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2019. p. 1963-1967. 8659727. (2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2018 - Proceedings). https://doi.org/10.23919/APSIPA.2018.8659727