SAEN-BGS: Energy-efficient spiking autoencoder network for background subtraction

Background subtraction (BGS) is utilized to detect moving objects in a video and is commonly employed at the onset of object tracking and human recognition processes. Nevertheless, existing BGS techniques utilizing deep learning still encounter challenges with various background noises in videos, in...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Pattern recognition Ročník 169; s. 111792
Hlavní autoři: Zhang, Zhixuan, Li, Xiao Peng, Liu, Qi
Médium: Journal Article
Jazyk:angličtina
Vydáno: Elsevier Ltd 01.01.2026
Témata:
ISSN:0031-3203
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract Background subtraction (BGS) is utilized to detect moving objects in a video and is commonly employed at the onset of object tracking and human recognition processes. Nevertheless, existing BGS techniques utilizing deep learning still encounter challenges with various background noises in videos, including variations in lighting, shifts in camera angles, and disturbances like air turbulence or swaying trees. To address this problem, we design a spiking autoencoder network, termed SAEN-BGS, based on noise resilience and time-sequence sensitivity of spiking neural networks (SNNs) to enhance the separation of foreground and background. To eliminate unnecessary background noise and preserve the important foreground elements, we begin by creating the continuous spiking conv-and-dconv block, which serves as the fundamental building block for the decoder in SAEN-BGS. Moreover, in striving for enhanced energy efficiency, we introduce a novel self-distillation spiking supervised learning method grounded in ANN-to-SNN frameworks, resulting in decreased power consumption. In extensive experiments conducted on CDnet-2014 and DAVIS-2016 datasets, our approach demonstrates superior segmentation performance relative to other baseline methods, even when challenged by complex scenarios with dynamic backgrounds. [Display omitted] •To address the background noise, a spiking autoencoder network is developed using the noise resilience and time-sequence sensitivity of SNNs.•This is the first instance of solving background subtraction from a spike-based perspective, where a continuous spiking convolutional and deconvolutional block is employed to enhance foreground features and diminish background noise within the decoder.•To achieve energy efficiency, a novel self-distillation spiking supervised learning method is proposed within ANN-to-SNN framework.•The empirical evaluations on CDnet-2014 and DAVIS-2016 demonstrate the superiority of the proposed method.
AbstractList Background subtraction (BGS) is utilized to detect moving objects in a video and is commonly employed at the onset of object tracking and human recognition processes. Nevertheless, existing BGS techniques utilizing deep learning still encounter challenges with various background noises in videos, including variations in lighting, shifts in camera angles, and disturbances like air turbulence or swaying trees. To address this problem, we design a spiking autoencoder network, termed SAEN-BGS, based on noise resilience and time-sequence sensitivity of spiking neural networks (SNNs) to enhance the separation of foreground and background. To eliminate unnecessary background noise and preserve the important foreground elements, we begin by creating the continuous spiking conv-and-dconv block, which serves as the fundamental building block for the decoder in SAEN-BGS. Moreover, in striving for enhanced energy efficiency, we introduce a novel self-distillation spiking supervised learning method grounded in ANN-to-SNN frameworks, resulting in decreased power consumption. In extensive experiments conducted on CDnet-2014 and DAVIS-2016 datasets, our approach demonstrates superior segmentation performance relative to other baseline methods, even when challenged by complex scenarios with dynamic backgrounds. [Display omitted] •To address the background noise, a spiking autoencoder network is developed using the noise resilience and time-sequence sensitivity of SNNs.•This is the first instance of solving background subtraction from a spike-based perspective, where a continuous spiking convolutional and deconvolutional block is employed to enhance foreground features and diminish background noise within the decoder.•To achieve energy efficiency, a novel self-distillation spiking supervised learning method is proposed within ANN-to-SNN framework.•The empirical evaluations on CDnet-2014 and DAVIS-2016 demonstrate the superiority of the proposed method.
ArticleNumber 111792
Author Zhang, Zhixuan
Li, Xiao Peng
Liu, Qi
Author_xml – sequence: 1
  givenname: Zhixuan
  orcidid: 0000-0002-3933-5401
  surname: Zhang
  fullname: Zhang, Zhixuan
  email: zhangzhixuan77@gmail.com
  organization: School of Future Technology, South China University of Technology, Guangzhou, 511442, Guangdong, China
– sequence: 2
  givenname: Xiao Peng
  orcidid: 0000-0002-5448-7219
  surname: Li
  fullname: Li, Xiao Peng
  email: x.p.li@szu.edu.cn
  organization: State Key Laboratory of Radio Frequency Heterogeneous Integration, Shenzhen University, Shenzhen, 518060, Guangdong, China
– sequence: 3
  givenname: Qi
  orcidid: 0000-0001-5378-6404
  surname: Liu
  fullname: Liu, Qi
  email: drliuqi@scut.edu.cn
  organization: School of Future Technology, South China University of Technology, Guangzhou, 511442, Guangdong, China
BookMark eNp9kM1OAjEcxHvAREDfwENfYNd-7FrWgwkSRBOiMei56bb_bgrakrZoeHvYrGdPc5mZzPwmaOSDB4RuKCkpoXe323Kvsg5dyQirS0qpaNgIjQnhtOCM8Es0SWlLCBW0YmP0vpkvX4vH1eYeLz3E7liAtU478Bmnvds532F1yAG8DgYi9pB_Q9xhGyJuld51MRy8wenQ5qh0dsFfoQurvhJc_-kUfT4tPxbPxfpt9bKYrwvNapELXVWac2uEAtNyqwy1QA23tWA1bZiYAakFcKLOvhYIr5vKtM0MKqVNy2aKT1E19OoYUopg5T66bxWPkhLZo5BbOaCQPQo5oDjHHoYYnLf9OIgy9W81GBdBZ2mC-7_gBHMIbq0
Cites_doi 10.1109/TIP.2014.2378053
10.1016/j.patcog.2023.109891
10.1016/j.patrec.2016.09.014
10.1016/j.patrec.2018.08.002
10.1016/j.imavis.2008.11.007
10.1109/JPROC.2024.3429360
10.1109/TNNLS.2021.3095724
10.1109/JSAIT.2020.3039170
10.1109/TFUZZ.2020.3030498
10.1016/j.patcog.2019.05.015
10.1109/ACCESS.2019.2899348
10.1109/LSP.2019.2952253
10.1109/ACCESS.2021.3071163
10.1109/TPAMI.2020.3008413
10.1016/j.patcog.2024.111035
10.1117/1.JEI.27.2.023002
10.1016/j.patcog.2024.110879
10.1109/TEVC.2017.2694160
10.1016/j.cviu.2014.01.004
10.1109/JPROC.2002.801448
10.1109/TMM.2014.2353772
10.1109/TIP.2010.2101613
10.1109/TIP.2015.2419084
10.1016/j.patcog.2017.09.040
10.1109/LSP.2012.2205380
ContentType Journal Article
Copyright 2025 Elsevier Ltd
Copyright_xml – notice: 2025 Elsevier Ltd
DBID AAYXX
CITATION
DOI 10.1016/j.patcog.2025.111792
DatabaseName CrossRef
DatabaseTitle CrossRef
DatabaseTitleList
DeliveryMethod fulltext_linktorsrc
Discipline Computer Science
ExternalDocumentID 10_1016_j_patcog_2025_111792
S0031320325004522
GroupedDBID --K
--M
-D8
-DT
-~X
.DC
.~1
0R~
123
1B1
1RT
1~.
1~5
29O
4.4
457
4G.
53G
5VS
7-5
71M
8P~
9JN
AABNK
AAEDT
AAEDW
AAIKJ
AAKOC
AALRI
AAOAW
AAQFI
AAQXK
AATTM
AAXKI
AAXUO
AAYFN
AAYWO
ABBOA
ABDPE
ABEFU
ABFNM
ABFRF
ABHFT
ABJNI
ABMAC
ABWVN
ABXDB
ACBEA
ACDAQ
ACGFO
ACGFS
ACNNM
ACRLP
ACRPL
ACVFH
ACZNC
ADBBV
ADCNI
ADEZE
ADJOM
ADMUD
ADMXK
ADNMO
ADTZH
AEBSH
AECPX
AEFWE
AEIPS
AEKER
AENEX
AEUPX
AFJKZ
AFPUW
AFTJW
AGCQF
AGHFR
AGQPQ
AGUBO
AGYEJ
AHHHB
AHJVU
AHZHX
AIALX
AIEXJ
AIGII
AIIUN
AIKHN
AITUG
AKBMS
AKRWK
AKYEP
ALMA_UNASSIGNED_HOLDINGS
AMRAJ
ANKPU
AOUOD
APXCP
ASPBG
AVWKF
AXJTR
AZFZN
BJAXD
BKOJK
BLXMC
CS3
DU5
EBS
EFJIC
EFKBS
EFLBG
EJD
EO8
EO9
EP2
EP3
F0J
F5P
FD6
FDB
FEDTE
FGOYB
FIRID
FNPLU
FYGXN
G-Q
GBLVA
GBOLZ
HLZ
HVGLF
HZ~
H~9
IHE
J1W
JJJVA
KOM
KZ1
LG9
LMP
LY1
M41
MO0
N9A
O-L
O9-
OAUVE
OZT
P-8
P-9
P2P
PC.
Q38
R2-
RNS
ROL
RPZ
SBC
SDF
SDG
SDP
SDS
SES
SEW
SPC
SPCBC
SST
SSV
SSZ
T5K
TN5
UNMZH
VOH
WUQ
XJE
XPP
ZMT
ZY4
~G-
9DU
AAYXX
ACLOT
CITATION
~HD
ID FETCH-LOGICAL-c257t-c44c33fd7aedb3fad1fe1d3f572519278e057e30a44cbe03594db98e4acdb28a3
ISICitedReferencesCount 0
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001505826900005&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 0031-3203
IngestDate Sat Nov 29 06:57:27 EST 2025
Sat Sep 13 17:01:52 EDT 2025
IsPeerReviewed true
IsScholarly true
Keywords Deep learning
Energy efficiency
Background subtraction
Autoencoder
Spiking neural network
Language English
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c257t-c44c33fd7aedb3fad1fe1d3f572519278e057e30a44cbe03594db98e4acdb28a3
ORCID 0000-0001-5378-6404
0000-0002-5448-7219
0000-0002-3933-5401
ParticipantIDs crossref_primary_10_1016_j_patcog_2025_111792
elsevier_sciencedirect_doi_10_1016_j_patcog_2025_111792
PublicationCentury 2000
PublicationDate January 2026
2026-01-00
PublicationDateYYYYMMDD 2026-01-01
PublicationDate_xml – month: 01
  year: 2026
  text: January 2026
PublicationDecade 2020
PublicationTitle Pattern recognition
PublicationYear 2026
Publisher Elsevier Ltd
Publisher_xml – name: Elsevier Ltd
References Lim, Jang, Kim (b20) 2017
Elgammal, Duraiswami, Harwood, Davis (b26) 2002; 90
Ronan, Weston (b42) 2008
Zhong, Wu, Yu, Wang, Lu (b6) 2025; 158
Sakkos, Liu, Han, Shao (b34) 2017
Mozafari, Ganjtabesh, Nowzari-Dalini, Thorpe, Masquelier (b39) 2019; 94
Chiranjeevi, Sengupta (b11) 2012; 19
Zhang, Feng, Zhou, Yang, Zhang, Saleh, Donta, Dehury (b36) 2024
Horowitz (b55) 2014
An, Zhao, Yu, Guo, Zhao, Tang, Wang (b32) 2023
Tezcan, Ishwar, Konrad (b24) 2021; 9
Li, Deng, Tang, Pan, Tian, Roy, Maass (b35) 2024; 112
St-Charles, Bilodeau, Bergevin (b28) 2015
Elgammal, Harwood, Davis (b14) 2000
Kim, Panda (b54) 2020
St-Charles, Bilodeau, Bergevin (b50) 2014
Jabri, Duric, Wechsler, Rosenfeld (b13) 2000; vol. 4
Perazzi, Pont-Tuset, McWilliams, VanGool, Gross, Sorkine-Hornung (b45) 2016
Lee, Kwon, Shim, Yoo (b31) 2018
St-Charles, Bilodeau, Bergevin (b29) 2015; 24
Tezcan, Ishwar, Konrad (b23) 2020
Isik, Ozkan, Gunal, Gerek (b30) 2018; 27
Cheung, Chandrika (b7) 2005; 14
Wang, Luo, Jodoin (b53) 2017; 96
Arjovsky, Bottou (b41) 2017
Wang, Luo, Jodoin (b19) 2017; 96
Sun, Yao, Zhou, Zhao (b43) 2019
Liu, Zhao, Yao, Qi (b16) 2015; 24
Stauffer, Grimson (b25) 1999; vol. 2
Barnich, Droogenbroeck (b27) 2010; 20
Gregorio, Giordano (b47) 2014
Bianco, Ciocca, Schettini (b51) 2017; 21
Zeng, Chen, Zhu, Goesele, Kuijper (b52) 2019; 7
Ashraphijuo, Wang (b3) 2020; 1
Braham, Droogenbroeck (b18) 2016
Stauffer, Grimson (b15) 1999; vol. 2
Wang, Bunyak, Seetharaman, Palaniappan (b49) 2014
Ling, Pan, Ren, Wang, Geng (b5) 2023; 144
Babaee, Dinh, Rigoll (b33) 2018; 76
Jang, Wang, Kim (b4) 2025; 157
Seo, Kim (b8) 2014; 16
Braham, Pierard, Droogenbroeck (b17) 2017
Gallego, Delbrück, Orchard, Bartolozzi, Taba, Censi, Leutenegger, Davison, Conradt, Daniilidis, Scaramuzza (b37) 2022; 44
Liu, Li, Yang (b2) 2022; 30
Wu, Chua, Zhang, Li, Li, Tan (b40) 2021; 34
Mandal, Dhar, Mishra, Vipparthi (b21) 2019; 26
Xiao, Yu, Yan, Tang (b38) 2019; vol. 7
Sedky, Moniri, Chibelushi (b48) 2014
Zhang, Xu (b12) 2006
Paszke, Gross, Massa, Lerer, Chintala (b46) 2019; vol. 33
Chen, Ellis (b9) 2014; 122
Vinciarelli, Pantic, Bourlard (b10) 2009; 27
Liu, Li, Cao, Wu (b1) 2021
Wang, Jodoin, Porikli, Konrad, Benezeth, Ishwar (b44) 2014
Lim, Keles (b22) 2018; 112
Seo (10.1016/j.patcog.2025.111792_b8) 2014; 16
Arjovsky (10.1016/j.patcog.2025.111792_b41) 2017
Gregorio (10.1016/j.patcog.2025.111792_b47) 2014
Stauffer (10.1016/j.patcog.2025.111792_b25) 1999; vol. 2
Ashraphijuo (10.1016/j.patcog.2025.111792_b3) 2020; 1
Chiranjeevi (10.1016/j.patcog.2025.111792_b11) 2012; 19
Jang (10.1016/j.patcog.2025.111792_b4) 2025; 157
Zhang (10.1016/j.patcog.2025.111792_b12) 2006
Chen (10.1016/j.patcog.2025.111792_b9) 2014; 122
An (10.1016/j.patcog.2025.111792_b32) 2023
St-Charles (10.1016/j.patcog.2025.111792_b29) 2015; 24
Wang (10.1016/j.patcog.2025.111792_b53) 2017; 96
St-Charles (10.1016/j.patcog.2025.111792_b28) 2015
Kim (10.1016/j.patcog.2025.111792_b54) 2020
Isik (10.1016/j.patcog.2025.111792_b30) 2018; 27
Perazzi (10.1016/j.patcog.2025.111792_b45) 2016
Zhong (10.1016/j.patcog.2025.111792_b6) 2025; 158
Ling (10.1016/j.patcog.2025.111792_b5) 2023; 144
Babaee (10.1016/j.patcog.2025.111792_b33) 2018; 76
Lim (10.1016/j.patcog.2025.111792_b20) 2017
Wang (10.1016/j.patcog.2025.111792_b49) 2014
Bianco (10.1016/j.patcog.2025.111792_b51) 2017; 21
Li (10.1016/j.patcog.2025.111792_b35) 2024; 112
Braham (10.1016/j.patcog.2025.111792_b18) 2016
Wang (10.1016/j.patcog.2025.111792_b19) 2017; 96
Liu (10.1016/j.patcog.2025.111792_b16) 2015; 24
Paszke (10.1016/j.patcog.2025.111792_b46) 2019; vol. 33
Mandal (10.1016/j.patcog.2025.111792_b21) 2019; 26
Stauffer (10.1016/j.patcog.2025.111792_b15) 1999; vol. 2
Barnich (10.1016/j.patcog.2025.111792_b27) 2010; 20
Wu (10.1016/j.patcog.2025.111792_b40) 2021; 34
Sakkos (10.1016/j.patcog.2025.111792_b34) 2017
Ronan (10.1016/j.patcog.2025.111792_b42) 2008
Braham (10.1016/j.patcog.2025.111792_b17) 2017
Gallego (10.1016/j.patcog.2025.111792_b37) 2022; 44
Mozafari (10.1016/j.patcog.2025.111792_b39) 2019; 94
Sun (10.1016/j.patcog.2025.111792_b43) 2019
Horowitz (10.1016/j.patcog.2025.111792_b55) 2014
Wang (10.1016/j.patcog.2025.111792_b44) 2014
Sedky (10.1016/j.patcog.2025.111792_b48) 2014
Elgammal (10.1016/j.patcog.2025.111792_b14) 2000
St-Charles (10.1016/j.patcog.2025.111792_b50) 2014
Lim (10.1016/j.patcog.2025.111792_b22) 2018; 112
Cheung (10.1016/j.patcog.2025.111792_b7) 2005; 14
Tezcan (10.1016/j.patcog.2025.111792_b24) 2021; 9
Tezcan (10.1016/j.patcog.2025.111792_b23) 2020
Liu (10.1016/j.patcog.2025.111792_b1) 2021
Vinciarelli (10.1016/j.patcog.2025.111792_b10) 2009; 27
Jabri (10.1016/j.patcog.2025.111792_b13) 2000; vol. 4
Elgammal (10.1016/j.patcog.2025.111792_b26) 2002; 90
Zeng (10.1016/j.patcog.2025.111792_b52) 2019; 7
Liu (10.1016/j.patcog.2025.111792_b2) 2022; 30
Zhang (10.1016/j.patcog.2025.111792_b36) 2024
Xiao (10.1016/j.patcog.2025.111792_b38) 2019; vol. 7
Lee (10.1016/j.patcog.2025.111792_b31) 2018
References_xml – volume: 76
  start-page: 635
  year: 2018
  end-page: 649
  ident: b33
  article-title: A deep convolutional neural network for video sequence background subtraction
  publication-title: Pattern Recognit.
– volume: 20
  start-page: 1709
  year: 2010
  end-page: 1724
  ident: b27
  article-title: Vibe: A universal background subtraction algorithm for video sequences
  publication-title: IEEE Trans. Image Process.
– volume: 96
  start-page: 66
  year: 2017
  end-page: 75
  ident: b53
  article-title: Interactive deep learning method for segmenting moving objects
  publication-title: Pattern Recognit. Lett.
– start-page: 1
  year: 2017
  end-page: 19
  ident: b34
  article-title: End-to-end video background subtraction with 3d convolutional neural networks
  publication-title: Multimedia Tools Appl.
– start-page: 1
  year: 2024
  end-page: 9
  ident: b36
  article-title: Spiking neural networks in intelligent edge computing
  publication-title: IEEE Consum. Electron. Mag.
– volume: 1
  start-page: 632
  year: 2020
  end-page: 644
  ident: b3
  article-title: Structured alternating minimization for union of nested low-rank subspaces data completion
  publication-title: IEEE J. Sel. AREA. Inf. Theory
– volume: vol. 7
  start-page: 1445
  year: 2019
  end-page: 1451
  ident: b38
  article-title: Fast and accurate classification with a multi-spike learning algorithm for spiking neurons
  publication-title: Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence
– volume: 34
  start-page: 446
  year: 2021
  end-page: 460
  ident: b40
  article-title: A tandem learning rule for effective training and rapid inference of deep spiking neural networks
  publication-title: IEEE Trans. Neural Netw. Learn. Syst.
– year: 2018
  ident: b31
  article-title: Wisenetmd: Motion detection using dynamic background region analysis
– volume: 24
  start-page: 2502
  year: 2015
  end-page: 2514
  ident: b16
  article-title: Background subtraction based on low-rank and structured sparse decomposition
  publication-title: IEEE Trans. Image Process.
– year: 2017
  ident: b41
  article-title: Towards principled methods for training generative adversarial networks
– volume: 16
  start-page: 2333
  year: 2014
  end-page: 2344
  ident: b8
  article-title: Recursive on-line 2D PCA and its application to long-term background subtraction
  publication-title: IEEE Trans. Multimed.
– volume: vol. 2
  start-page: 246
  year: 1999
  end-page: 252
  ident: b15
  article-title: Adaptive background mixture models for real-time tracking
  publication-title: Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit.
– volume: 90
  start-page: 1151
  year: 2002
  end-page: 1163
  ident: b26
  article-title: Background and foreground modeling using nonparametric kernel density estimation for visual surveillance
  publication-title: Proc. IEEE
– start-page: 1
  year: 2016
  end-page: 4
  ident: b18
  article-title: Deep background subtraction with scene-specific convolutional neural networks
  publication-title: Proc. Int. Conf. Syst. Signals Image Process.
– start-page: 4552
  year: 2017
  end-page: 4556
  ident: b17
  article-title: Semantic background subtraction
  publication-title: Proc. Int. Conf. Image Process.
– volume: 112
  start-page: 544
  year: 2024
  end-page: 584
  ident: b35
  article-title: Brain-inspired computing: A systematic survey and future trends
  publication-title: Proc. IEEE
– volume: vol. 2
  start-page: 2246
  year: 1999
  ident: b25
  article-title: Adaptive background mixture models for real-time tracking
  publication-title: Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit.
– volume: 96
  start-page: 66
  year: 2017
  end-page: 75
  ident: b19
  article-title: Interactive deep learning method for segmenting moving objects
  publication-title: Pattern Recognit.
– volume: 30
  start-page: 287
  year: 2022
  end-page: 292
  ident: b2
  article-title: Optimum codesign for image denoising between type-2 fuzzy identifier and matrix completion denoiser
  publication-title: IEEE Trans. Fuzzy Syst.
– volume: 94
  start-page: 87
  year: 2019
  end-page: 95
  ident: b39
  article-title: Bio-inspired digit recognition using reward-modulated spike-timing-dependent plasticity in deep convolutional networks
  publication-title: Pattern Recognit.
– volume: 19
  start-page: 603
  year: 2012
  end-page: 606
  ident: b11
  article-title: New fuzzy texture features for robust detection of moving objects
  publication-title: IEEE Signal Process. Lett.
– volume: 122
  start-page: 35
  year: 2014
  end-page: 46
  ident: b9
  article-title: A self-adaptive Gaussian mixture model
  publication-title: Comput. Vis. Image Understand.
– volume: 44
  start-page: 154
  year: 2022
  end-page: 180
  ident: b37
  article-title: Event-based vision: A survey
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
– start-page: 160
  year: 2008
  end-page: 167
  ident: b42
  article-title: A unified architecture for natural language processing: deep neural networks with multitask learning
  publication-title: Machine Learning, Proceedings of the Twenty-Fifth International Conference
– volume: 112
  start-page: 256
  year: 2018
  end-page: 262
  ident: b22
  article-title: Foreground segmentation using convolutional neural networks for multiscale feature encoding
  publication-title: Pattern Recognit.
– volume: vol. 4
  start-page: 627
  year: 2000
  end-page: 630
  ident: b13
  article-title: Detection and location of people in video images using adaptive fusion of color and edge information
  publication-title: Proceedings 15th International Conference on Pattern Recognition
– start-page: 6997
  year: 2019
  end-page: 7006
  ident: b43
  article-title: Deeply-supervised knowledge synergy
  publication-title: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition
– year: 2017
  ident: b20
  article-title: Background subtraction using encoder–decoder structured convolutional neural network
  publication-title: Proc. IEEE Int. Conf. Adv. Video Signal Based-Surveill
– year: 2020
  ident: b54
  article-title: Revisiting batch normalization for training low-latency deep spiking neural networks from scratch
– volume: 157
  year: 2025
  ident: b4
  article-title: Fcgnet: Foreground and class guided network for human parsing
  publication-title: Pattern Recognit.
– start-page: 724
  year: 2016
  end-page: 732
  ident: b45
  article-title: A benchmark dataset and evaluation methodology for video object segmentation
  publication-title: Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit.
– start-page: 414
  year: 2014
  end-page: 419
  ident: b50
  article-title: Flexible background subtraction with self-balanced local sensitivity
  publication-title: Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit.
– year: 2021
  ident: b1
  article-title: From simulated to visual data: A robust low-rank tensor completion approach using lp-regression for outlier resistance
  publication-title: IEEE Trans. Circuits Syst. Video Technol.
– volume: 21
  start-page: 914
  year: 2017
  end-page: 928
  ident: b51
  article-title: Combination of video change detection algorithms by genetic programming
  publication-title: IEEE Trans. Evol. Comput.
– start-page: 10
  year: 2014
  end-page: 14
  ident: b55
  article-title: 1.1 Computing’s energy problem (and what we can do about it)
  publication-title: 2014 IEEE International Solid-State Circuits Conference Digest of Technical Papers
– start-page: 990
  year: 2015
  end-page: 997
  ident: b28
  article-title: A self-adjusting approach to change detection based on background word consensus
  publication-title: Proc. IEEE Winter Conf. Applicat. Comput. Vis
– start-page: 2763
  year: 2020
  end-page: 2772
  ident: b23
  article-title: Bsuv-net: A fully-convolutional neural network for background subtraction of unseen videos
  publication-title: Proc. IEEE Winter Conf. Applicat. Comput. Vis
– start-page: 409
  year: 2014
  end-page: 413
  ident: b47
  article-title: Change detection with weightless neural networks
  publication-title: Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit.
– volume: 27
  start-page: 1
  year: 2018
  ident: b30
  article-title: Swcd: a sliding window and self-regulated learning-based background updating method for change detection in videos
  publication-title: J. Electron. Imaging.
– start-page: 420
  year: 2014
  end-page: 424
  ident: b49
  article-title: Static and moving object detection using flux tensor with split Gaussian models
  publication-title: Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit.
– start-page: 887
  year: 2006
  end-page: 893
  ident: b12
  article-title: Fusing color and texture features for background model
  publication-title: International Conference on Fuzzy Systems and Knowledge Discovery
– start-page: 6355
  year: 2023
  end-page: 6364
  ident: b32
  article-title: Zbs: Zero-shot background subtraction via instance-level background modeling and foreground selection
  publication-title: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition
– volume: 27
  start-page: 1743
  year: 2009
  end-page: 1759
  ident: b10
  article-title: Social signal processing: Survey of an emerging domain
  publication-title: Image Vis. Comput.
– volume: 26
  start-page: 1882
  year: 2019
  end-page: 1886
  ident: b21
  article-title: 3Dfr: A swift 3d feature reductionist framework for scene independent change detection
  publication-title: IEEE Signal Process. Lett.
– volume: 9
  start-page: 53849
  year: 2021
  end-page: 53860
  ident: b24
  article-title: Bsuv-net2.0: Spatio-temporal data augmentations for video-agnostic supervised background subtraction
  publication-title: IEEE Access.
– volume: 14
  start-page: 2330
  year: 2005
  end-page: 2340
  ident: b7
  article-title: Robust background subtraction with foreground validation for urban traffic video
  publication-title: EURASIP J. Adv. Signal Process.
– volume: 24
  start-page: 359
  year: 2015
  end-page: 373
  ident: b29
  article-title: Subsense: A universal change detection method with local adaptive sensitivity
  publication-title: IEEE Trans. Image Process.
– volume: 158
  year: 2025
  ident: b6
  article-title: A benchmark dataset and semantics-guided detection network for spatial–temporal human actions in urban driving scenes
  publication-title: Pattern Recognit.
– volume: vol. 33
  year: 2019
  ident: b46
  article-title: Pytorch: An imperative style, high-performance deep learning library
  publication-title: Advances in Neural Information Processing Systems
– volume: 144
  year: 2023
  ident: b5
  article-title: Motional foreground attention-based video crowd counting
  publication-title: Pattern Recognit.
– volume: 7
  start-page: 153869
  year: 2019
  end-page: 153884
  ident: b52
  article-title: Background subtraction with real-time semantic segmentation
  publication-title: IEEE Access
– start-page: 751
  year: 2000
  end-page: 767
  ident: b14
  article-title: Non-parametric model for background subtraction
  publication-title: Proc. European Conf. Computer Vision
– start-page: 393
  year: 2014
  end-page: 400
  ident: b44
  article-title: CDnet 2014: An expanded change detection benchmark dataset
  publication-title: Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit.
– start-page: 405
  year: 2014
  end-page: 408
  ident: b48
  article-title: Spectral-360: A physics-based technique for change detection
  publication-title: Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit.
– volume: 24
  start-page: 359
  issue: 1
  year: 2015
  ident: 10.1016/j.patcog.2025.111792_b29
  article-title: Subsense: A universal change detection method with local adaptive sensitivity
  publication-title: IEEE Trans. Image Process.
  doi: 10.1109/TIP.2014.2378053
– volume: 144
  year: 2023
  ident: 10.1016/j.patcog.2025.111792_b5
  article-title: Motional foreground attention-based video crowd counting
  publication-title: Pattern Recognit.
  doi: 10.1016/j.patcog.2023.109891
– volume: 96
  start-page: 66
  year: 2017
  ident: 10.1016/j.patcog.2025.111792_b19
  article-title: Interactive deep learning method for segmenting moving objects
  publication-title: Pattern Recognit.
  doi: 10.1016/j.patrec.2016.09.014
– volume: 112
  start-page: 256
  year: 2018
  ident: 10.1016/j.patcog.2025.111792_b22
  article-title: Foreground segmentation using convolutional neural networks for multiscale feature encoding
  publication-title: Pattern Recognit.
  doi: 10.1016/j.patrec.2018.08.002
– start-page: 160
  year: 2008
  ident: 10.1016/j.patcog.2025.111792_b42
  article-title: A unified architecture for natural language processing: deep neural networks with multitask learning
– volume: 27
  start-page: 1743
  issue: 12
  year: 2009
  ident: 10.1016/j.patcog.2025.111792_b10
  article-title: Social signal processing: Survey of an emerging domain
  publication-title: Image Vis. Comput.
  doi: 10.1016/j.imavis.2008.11.007
– start-page: 6997
  year: 2019
  ident: 10.1016/j.patcog.2025.111792_b43
  article-title: Deeply-supervised knowledge synergy
– volume: 112
  start-page: 544
  issue: 6
  year: 2024
  ident: 10.1016/j.patcog.2025.111792_b35
  article-title: Brain-inspired computing: A systematic survey and future trends
  publication-title: Proc. IEEE
  doi: 10.1109/JPROC.2024.3429360
– volume: 34
  start-page: 446
  issue: 1
  year: 2021
  ident: 10.1016/j.patcog.2025.111792_b40
  article-title: A tandem learning rule for effective training and rapid inference of deep spiking neural networks
  publication-title: IEEE Trans. Neural Netw. Learn. Syst.
  doi: 10.1109/TNNLS.2021.3095724
– start-page: 2763
  year: 2020
  ident: 10.1016/j.patcog.2025.111792_b23
  article-title: Bsuv-net: A fully-convolutional neural network for background subtraction of unseen videos
– start-page: 4552
  year: 2017
  ident: 10.1016/j.patcog.2025.111792_b17
  article-title: Semantic background subtraction
– volume: vol. 2
  start-page: 2246
  year: 1999
  ident: 10.1016/j.patcog.2025.111792_b25
  article-title: Adaptive background mixture models for real-time tracking
– volume: vol. 33
  year: 2019
  ident: 10.1016/j.patcog.2025.111792_b46
  article-title: Pytorch: An imperative style, high-performance deep learning library
– start-page: 10
  year: 2014
  ident: 10.1016/j.patcog.2025.111792_b55
  article-title: 1.1 Computing’s energy problem (and what we can do about it)
– volume: 1
  start-page: 632
  issue: 3
  year: 2020
  ident: 10.1016/j.patcog.2025.111792_b3
  article-title: Structured alternating minimization for union of nested low-rank subspaces data completion
  publication-title: IEEE J. Sel. AREA. Inf. Theory
  doi: 10.1109/JSAIT.2020.3039170
– start-page: 1
  year: 2016
  ident: 10.1016/j.patcog.2025.111792_b18
  article-title: Deep background subtraction with scene-specific convolutional neural networks
– start-page: 420
  year: 2014
  ident: 10.1016/j.patcog.2025.111792_b49
  article-title: Static and moving object detection using flux tensor with split Gaussian models
– volume: 30
  start-page: 287
  issue: 1
  year: 2022
  ident: 10.1016/j.patcog.2025.111792_b2
  article-title: Optimum codesign for image denoising between type-2 fuzzy identifier and matrix completion denoiser
  publication-title: IEEE Trans. Fuzzy Syst.
  doi: 10.1109/TFUZZ.2020.3030498
– start-page: 1
  year: 2017
  ident: 10.1016/j.patcog.2025.111792_b34
  article-title: End-to-end video background subtraction with 3d convolutional neural networks
  publication-title: Multimedia Tools Appl.
– start-page: 6355
  year: 2023
  ident: 10.1016/j.patcog.2025.111792_b32
  article-title: Zbs: Zero-shot background subtraction via instance-level background modeling and foreground selection
– volume: 94
  start-page: 87
  year: 2019
  ident: 10.1016/j.patcog.2025.111792_b39
  article-title: Bio-inspired digit recognition using reward-modulated spike-timing-dependent plasticity in deep convolutional networks
  publication-title: Pattern Recognit.
  doi: 10.1016/j.patcog.2019.05.015
– volume: 7
  start-page: 153869
  year: 2019
  ident: 10.1016/j.patcog.2025.111792_b52
  article-title: Background subtraction with real-time semantic segmentation
  publication-title: IEEE Access
  doi: 10.1109/ACCESS.2019.2899348
– volume: 26
  start-page: 1882
  issue: 12
  year: 2019
  ident: 10.1016/j.patcog.2025.111792_b21
  article-title: 3Dfr: A swift 3d feature reductionist framework for scene independent change detection
  publication-title: IEEE Signal Process. Lett.
  doi: 10.1109/LSP.2019.2952253
– volume: 9
  start-page: 53849
  year: 2021
  ident: 10.1016/j.patcog.2025.111792_b24
  article-title: Bsuv-net2.0: Spatio-temporal data augmentations for video-agnostic supervised background subtraction
  publication-title: IEEE Access.
  doi: 10.1109/ACCESS.2021.3071163
– volume: 44
  start-page: 154
  issue: 1
  year: 2022
  ident: 10.1016/j.patcog.2025.111792_b37
  article-title: Event-based vision: A survey
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
  doi: 10.1109/TPAMI.2020.3008413
– volume: 158
  year: 2025
  ident: 10.1016/j.patcog.2025.111792_b6
  article-title: A benchmark dataset and semantics-guided detection network for spatial–temporal human actions in urban driving scenes
  publication-title: Pattern Recognit.
  doi: 10.1016/j.patcog.2024.111035
– start-page: 414
  year: 2014
  ident: 10.1016/j.patcog.2025.111792_b50
  article-title: Flexible background subtraction with self-balanced local sensitivity
– volume: 14
  start-page: 2330
  year: 2005
  ident: 10.1016/j.patcog.2025.111792_b7
  article-title: Robust background subtraction with foreground validation for urban traffic video
  publication-title: EURASIP J. Adv. Signal Process.
– volume: 96
  start-page: 66
  year: 2017
  ident: 10.1016/j.patcog.2025.111792_b53
  article-title: Interactive deep learning method for segmenting moving objects
  publication-title: Pattern Recognit. Lett.
  doi: 10.1016/j.patrec.2016.09.014
– start-page: 751
  year: 2000
  ident: 10.1016/j.patcog.2025.111792_b14
  article-title: Non-parametric model for background subtraction
– volume: 27
  start-page: 1
  issue: 2
  year: 2018
  ident: 10.1016/j.patcog.2025.111792_b30
  article-title: Swcd: a sliding window and self-regulated learning-based background updating method for change detection in videos
  publication-title: J. Electron. Imaging.
  doi: 10.1117/1.JEI.27.2.023002
– volume: vol. 7
  start-page: 1445
  year: 2019
  ident: 10.1016/j.patcog.2025.111792_b38
  article-title: Fast and accurate classification with a multi-spike learning algorithm for spiking neurons
– volume: 157
  year: 2025
  ident: 10.1016/j.patcog.2025.111792_b4
  article-title: Fcgnet: Foreground and class guided network for human parsing
  publication-title: Pattern Recognit.
  doi: 10.1016/j.patcog.2024.110879
– start-page: 887
  year: 2006
  ident: 10.1016/j.patcog.2025.111792_b12
  article-title: Fusing color and texture features for background model
– volume: 21
  start-page: 914
  issue: 6
  year: 2017
  ident: 10.1016/j.patcog.2025.111792_b51
  article-title: Combination of video change detection algorithms by genetic programming
  publication-title: IEEE Trans. Evol. Comput.
  doi: 10.1109/TEVC.2017.2694160
– start-page: 409
  year: 2014
  ident: 10.1016/j.patcog.2025.111792_b47
  article-title: Change detection with weightless neural networks
– start-page: 724
  year: 2016
  ident: 10.1016/j.patcog.2025.111792_b45
  article-title: A benchmark dataset and evaluation methodology for video object segmentation
– year: 2018
  ident: 10.1016/j.patcog.2025.111792_b31
– year: 2020
  ident: 10.1016/j.patcog.2025.111792_b54
– volume: 122
  start-page: 35
  year: 2014
  ident: 10.1016/j.patcog.2025.111792_b9
  article-title: A self-adaptive Gaussian mixture model
  publication-title: Comput. Vis. Image Understand.
  doi: 10.1016/j.cviu.2014.01.004
– volume: vol. 2
  start-page: 246
  year: 1999
  ident: 10.1016/j.patcog.2025.111792_b15
  article-title: Adaptive background mixture models for real-time tracking
– start-page: 990
  year: 2015
  ident: 10.1016/j.patcog.2025.111792_b28
  article-title: A self-adjusting approach to change detection based on background word consensus
– start-page: 1
  year: 2024
  ident: 10.1016/j.patcog.2025.111792_b36
  article-title: Spiking neural networks in intelligent edge computing
  publication-title: IEEE Consum. Electron. Mag.
– volume: 90
  start-page: 1151
  year: 2002
  ident: 10.1016/j.patcog.2025.111792_b26
  article-title: Background and foreground modeling using nonparametric kernel density estimation for visual surveillance
  publication-title: Proc. IEEE
  doi: 10.1109/JPROC.2002.801448
– start-page: 405
  year: 2014
  ident: 10.1016/j.patcog.2025.111792_b48
  article-title: Spectral-360: A physics-based technique for change detection
– year: 2017
  ident: 10.1016/j.patcog.2025.111792_b20
  article-title: Background subtraction using encoder–decoder structured convolutional neural network
– volume: 16
  start-page: 2333
  issue: 8
  year: 2014
  ident: 10.1016/j.patcog.2025.111792_b8
  article-title: Recursive on-line 2D PCA and its application to long-term background subtraction
  publication-title: IEEE Trans. Multimed.
  doi: 10.1109/TMM.2014.2353772
– volume: 20
  start-page: 1709
  issue: 6
  year: 2010
  ident: 10.1016/j.patcog.2025.111792_b27
  article-title: Vibe: A universal background subtraction algorithm for video sequences
  publication-title: IEEE Trans. Image Process.
  doi: 10.1109/TIP.2010.2101613
– year: 2021
  ident: 10.1016/j.patcog.2025.111792_b1
  article-title: From simulated to visual data: A robust low-rank tensor completion approach using lp-regression for outlier resistance
  publication-title: IEEE Trans. Circuits Syst. Video Technol.
– start-page: 393
  year: 2014
  ident: 10.1016/j.patcog.2025.111792_b44
  article-title: CDnet 2014: An expanded change detection benchmark dataset
– volume: 24
  start-page: 2502
  issue: 8
  year: 2015
  ident: 10.1016/j.patcog.2025.111792_b16
  article-title: Background subtraction based on low-rank and structured sparse decomposition
  publication-title: IEEE Trans. Image Process.
  doi: 10.1109/TIP.2015.2419084
– year: 2017
  ident: 10.1016/j.patcog.2025.111792_b41
– volume: 76
  start-page: 635
  year: 2018
  ident: 10.1016/j.patcog.2025.111792_b33
  article-title: A deep convolutional neural network for video sequence background subtraction
  publication-title: Pattern Recognit.
  doi: 10.1016/j.patcog.2017.09.040
– volume: 19
  start-page: 603
  issue: 10
  year: 2012
  ident: 10.1016/j.patcog.2025.111792_b11
  article-title: New fuzzy texture features for robust detection of moving objects
  publication-title: IEEE Signal Process. Lett.
  doi: 10.1109/LSP.2012.2205380
– volume: vol. 4
  start-page: 627
  year: 2000
  ident: 10.1016/j.patcog.2025.111792_b13
  article-title: Detection and location of people in video images using adaptive fusion of color and edge information
SSID ssj0017142
Score 2.4888396
Snippet Background subtraction (BGS) is utilized to detect moving objects in a video and is commonly employed at the onset of object tracking and human recognition...
SourceID crossref
elsevier
SourceType Index Database
Publisher
StartPage 111792
SubjectTerms Autoencoder
Background subtraction
Deep learning
Energy efficiency
Spiking neural network
Title SAEN-BGS: Energy-efficient spiking autoencoder network for background subtraction
URI https://dx.doi.org/10.1016/j.patcog.2025.111792
Volume 169
WOSCitedRecordID wos001505826900005&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVESC
  databaseName: ScienceDirect Freedom Collection
  issn: 0031-3203
  databaseCode: AIEXJ
  dateStart: 19950101
  customDbUrl:
  isFulltext: true
  dateEnd: 99991231
  titleUrlDefault: https://www.sciencedirect.com
  omitProxy: false
  ssIdentifier: ssj0017142
  providerName: Elsevier
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1Lb9QwELag5cCFN2opIB-4IVcb21sn3Ba0vIRWW7WgFZfIT0grZVe7Cdqf3_Eju2mpKnrgYkVW7FiZT-PxeOYbhN7owZEFM1gT5SiHA0rhSM6HkjBDlVZgkdNwXfDjm5hM8tmsmKZyqatQTkDUdb5eF4v_KmroA2H71NlbiHszKXTAMwgdWhA7tP8k-JPReELefzrxZ_1xyOwjNvBE-Fv_1aI6D2mJbTP3FJaeSaKOkeAxcFPqc5_o4b3prWqWMe2hb8FOAyGnT4JJkUfbe_yN8_nn72rd9oJ9QsTArJLzt1ObdsrQ3fr-46rveaB9z0PSpiwjjA7YJW0aK68kfZh5xjl6raqOXoOzwwVsOfNfcFKnw8Pt65eZsa_sWJs4wi5E7ayMs5R-ljLOchftUjEsQNPtjr6MZ183d0si45FDPq2-S6gMUX9_r-Z6g6VnhJw-Qg_S6QGPotQfozu2foIedpU5cFLUT9FxB4J3-CoEcIIA7kEAJwhggADeQgD3IPAMff84Pv3wmaTiGUSDFm6I5lwz5oyQ1ijmpMmczQxzQ-FzlanILVjqlg0kvKesJ3LkRhW55VIbRXPJnqOdel7bPYQLa5WhzuVMKK55Jp1RuhADTWXmR-4j0v2hchE5UsqbJLOPRPcby2TnRfutBGzcOPLFLb90gO5vgfsS7TTL1r5C9_SfplotXydgXADvdXbY
linkProvider Elsevier
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=SAEN-BGS%3A+Energy-efficient+spiking+autoencoder+network+for+background+subtraction&rft.jtitle=Pattern+recognition&rft.au=Zhang%2C+Zhixuan&rft.au=Li%2C+Xiao+Peng&rft.au=Liu%2C+Qi&rft.date=2026-01-01&rft.issn=0031-3203&rft.volume=169&rft.spage=111792&rft_id=info:doi/10.1016%2Fj.patcog.2025.111792&rft.externalDBID=n%2Fa&rft.externalDocID=10_1016_j_patcog_2025_111792
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0031-3203&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0031-3203&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0031-3203&client=summon