Object detection and tracking under Complex environment using deep learning-based LPM

Object detection and tracking under complex environment are challenging because of the disturbances induced by background clutter, illumination changes, occlusions and other factors. The bulk of traditional algorithms basically rely on hand-crafted features, which are not sufficiently robust to a co...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:IET computer vision Ročník 13; číslo 2; s. 157 - 164
Hlavní autoři: Li, Yundong, Zhang, Xueyan, Li, Hongguang, Zhou, Qichen, Cao, Xianbin, Xiao, Zhifeng
Médium: Journal Article
Jazyk:angličtina
Vydáno: The Institution of Engineering and Technology 01.03.2019
Wiley
Témata:
ISSN:1751-9632, 1751-9640, 1751-9640
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract Object detection and tracking under complex environment are challenging because of the disturbances induced by background clutter, illumination changes, occlusions and other factors. The bulk of traditional algorithms basically rely on hand-crafted features, which are not sufficiently robust to a complex environment. Moreover, the processes of detection and tracking are separated, which leads to the overall efficiency not high. In this study, a novel local probability model (LPM)-based mean shift (MS) algorithm is proposed to integrate object detection and tracking. The main contributions include: (i) a new framework based on the combination of LPM and MS is established for the integration of object tracking and detection. (ii) For object detection, the training and prediction of LPM are built by stacked denoising autoencoders based deep learning. (iii) For object tracking, an MS tracking algorithm leveraging LPM is modified to improve the tracking efficiency under a complex environment. Experimental results demonstrate that the proposed method is superior to the colour histograms based MS and histograms of oriented gradients based MS in terms of robustness and tracking accuracy.
AbstractList Object detection and tracking under complex environment are challenging because of the disturbances induced by background clutter, illumination changes, occlusions and other factors. The bulk of traditional algorithms basically rely on hand‐crafted features, which are not sufficiently robust to a complex environment. Moreover, the processes of detection and tracking are separated, which leads to the overall efficiency not high. In this study, a novel local probability model (LPM)‐based mean shift (MS) algorithm is proposed to integrate object detection and tracking. The main contributions include: (i) a new framework based on the combination of LPM and MS is established for the integration of object tracking and detection. (ii) For object detection, the training and prediction of LPM are built by stacked denoising autoencoders based deep learning. (iii) For object tracking, an MS tracking algorithm leveraging LPM is modified to improve the tracking efficiency under a complex environment. Experimental results demonstrate that the proposed method is superior to the colour histograms based MS and histograms of oriented gradients based MS in terms of robustness and tracking accuracy.
Author Zhou, Qichen
Cao, Xianbin
Li, Yundong
Zhang, Xueyan
Li, Hongguang
Xiao, Zhifeng
Author_xml – sequence: 1
  givenname: Yundong
  surname: Li
  fullname: Li, Yundong
  organization: 1School of Electronic and Information Engineering, North China University of Technology, Beijing, People's Republic of China
– sequence: 2
  givenname: Xueyan
  surname: Zhang
  fullname: Zhang, Xueyan
  organization: 1School of Electronic and Information Engineering, North China University of Technology, Beijing, People's Republic of China
– sequence: 3
  givenname: Hongguang
  surname: Li
  fullname: Li, Hongguang
  email: lihongguang@buaa.edu.cn
  organization: 2Unmanned Systems Research Institute, Beihang University, Beijing, People's Republic of China
– sequence: 4
  givenname: Qichen
  surname: Zhou
  fullname: Zhou, Qichen
  organization: 1School of Electronic and Information Engineering, North China University of Technology, Beijing, People's Republic of China
– sequence: 5
  givenname: Xianbin
  surname: Cao
  fullname: Cao, Xianbin
  organization: 3School of Electronic and Information Engineering, Beihang University, Beijing, People's Republic of China
– sequence: 6
  givenname: Zhifeng
  surname: Xiao
  fullname: Xiao, Zhifeng
  organization: 4State Key Laboratory of Information Engineering in Surveying, Wuhan University, Wuhan, People's Republic of China
BookMark eNqFkctuGyEUhlGVSonTPkB3vMC43OZCd61VN5YcOVKbbBGXQ4Q7BosZO83bh4mjLLJIVwcOfP8RHzN0FlMEhL5QMqdEyK8Bxsoew5wR2s1ryuQHdEHbmlayEeTsdc3ZOZoNw5aQupFSXKDbjdmCHbGDsZSQItbR4TFr-zfEe3yIDjJepN2-h38Y4jHkFHcQR3wYpnMHsMc96BzLrjJ6AIfXN9ef0Eev-wE-v9RL9Hv588_iqlpvfq0W39eVFYSwinpBvRVetp0H6KimxAqja2gM16JrnOx402guhGGGtZL62kpWHme8p5xfotUp1SW9Vfscdjo_qqSDem6kfK90HoPtQRHjuNWeOyqtaFyniWvrzlEOtYEOTMmipyyb0zBk8K95lKjJsCqGVTGsJsNqMlyY9g1jw6gnicVf6N8lv53Ih9DD4_9HqcXdiv1Yll-rWYGrEzxd26ZDjkXxO8OeAKX5ptI
CitedBy_id crossref_primary_10_1016_j_asoc_2023_110176
crossref_primary_10_1007_s00521_024_10853_4
crossref_primary_10_1007_s13369_021_06275_2
crossref_primary_10_1186_s12938_022_01001_x
crossref_primary_10_1109_TIE_2020_3021640
crossref_primary_10_1109_TITS_2022_3156267
crossref_primary_10_1080_10447318_2024_2327197
Cites_doi 10.1109/CVPRW.2014.126
10.1109/TIP.2017.2718189
10.1007/s00371-014-1014-6
10.1109/ICCV.2007.4408954
10.1109/ICCV.1999.790416
10.1007/s11760-014-0612-0
10.1109/CVPR.2009.5206502
10.1109/TIP.2007.914150
10.1109/TASE.2016.2520955
10.1109/ICIP.2010.5653525
10.1016/j.patcog.2017.03.030
10.1145/1390156.1390294
10.1007/s00371-014-1044-0
10.1016/j.neucom.2013.07.014
10.2174/18744443015070101022
10.1109/TMM.2013.2266634
10.1049/iet-cvi.2016.0156
10.1109/TITS.2016.2614548
10.1007/978-3-642-35289-8_26
10.1109/TIP.2011.2182521
10.1109/TIP.2017.2775060
10.1109/TPAMI.2002.1017623
10.1109/TCSVT.2014.2305514
10.1049/iet-cvi.2016.0238
10.1007/s11704-015-4246-3
10.1109/TITS.2013.2263281
10.1109/TIP.2015.2510583
10.1177/0142331214549409
10.1016/j.ijleo.2015.04.031
10.1109/TPAMI.2011.239
10.1049/iet-cvi.2014.0150
10.1109/TCSVT.2012.2226527
10.1109/TPAMI.2005.205
10.1109/TITS.2017.2726546
ContentType Journal Article
Copyright The Institution of Engineering and Technology
2019 The Institution of Engineering and Technology
Copyright_xml – notice: The Institution of Engineering and Technology
– notice: 2019 The Institution of Engineering and Technology
DBID AAYXX
CITATION
DOA
DOI 10.1049/iet-cvi.2018.5129
DatabaseName CrossRef
DOAJ Directory of Open Access Journals
DatabaseTitle CrossRef
DatabaseTitleList CrossRef



Database_xml – sequence: 1
  dbid: DOA
  name: DOAJ Directory of Open Access Journals
  url: https://www.doaj.org/
  sourceTypes: Open Website
DeliveryMethod fulltext_linktorsrc
Discipline Applied Sciences
EISSN 1751-9640
EndPage 164
ExternalDocumentID oai_doaj_org_article_0bd3caf3d19c46d8a0d758d13e5be8eb
10_1049_iet_cvi_2018_5129
CVI2BF00552
Genre article
GrantInformation_xml – fundername: Open Fund of State Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University
  funderid: 17E01
– fundername: Beijing Natural Science Foundation
  funderid: 4182020
GroupedDBID 0R
24P
29I
3V.
5GY
6IK
8AL
8FE
8FG
8VB
AAJGR
ABJCF
ABPTK
ABUWG
ACGFS
ACIWK
AENEX
AFKRA
ALMA_UNASSIGNED_HOLDINGS
ARAPS
AZQEC
BENPR
BFFAM
BGLVJ
BPHCQ
CS3
DU5
DWQXO
EBS
EJD
ESX
GNUQQ
HCIFZ
HZ
IFIPE
IPLJI
J9A
JAVBF
K6V
K7-
L6V
LAI
LOTEE
LXI
LXU
M0N
M43
M7S
MS
NADUK
NXXTH
O9-
OCL
P62
PQEST
PQQKQ
PQUKI
PROAC
PTHSS
QWB
RIE
RNS
RUI
S0W
UNMZH
UNR
ZL0
ZZ
.DC
0R~
0ZK
1OC
AAHHS
AAHJG
ABQXS
ACCFJ
ACCMX
ACESK
ACGFO
ACXQS
ADEYR
ADZOD
AEEZP
AEGXH
AEQDE
AIWBW
AJBDE
ALUQN
AVUZU
CCPQU
GROUPED_DOAJ
HZ~
IAO
ITC
K1G
MCNEO
MS~
OK1
~ZZ
AAMMB
AAYXX
AEFGJ
AFFHD
AGXDD
AIDQK
AIDYY
CITATION
IDLOA
PHGZM
PHGZT
PQGLB
WIN
ID FETCH-LOGICAL-c4002-1f41fc4f978fee81a10c4ba5e6b3a486d98366a344b2b2791f5c92129bff133
IEDL.DBID 24P
ISICitedReferencesCount 10
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000459454900010&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1751-9632
1751-9640
IngestDate Fri Oct 03 12:49:47 EDT 2025
Tue Nov 18 22:00:25 EST 2025
Wed Oct 29 21:08:24 EDT 2025
Wed Jan 22 16:31:57 EST 2025
Tue Jan 05 21:44:11 EST 2021
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 2
Keywords stacked denoising autoencoders
local probability model-based mean shift algorithm
probability
deep learning-based LPM
colour histograms
object detection
MS tracking algorithm
LPM-based mean shift algorithm
local probability model
feature extraction
histograms of oriented gradients
hand-crafted features
object tracking
image colour analysis
learning (artificial intelligence)
neural nets
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c4002-1f41fc4f978fee81a10c4ba5e6b3a486d98366a344b2b2791f5c92129bff133
OpenAccessLink https://doaj.org/article/0bd3caf3d19c46d8a0d758d13e5be8eb
PageCount 8
ParticipantIDs crossref_citationtrail_10_1049_iet_cvi_2018_5129
iet_journals_10_1049_iet_cvi_2018_5129
doaj_primary_oai_doaj_org_article_0bd3caf3d19c46d8a0d758d13e5be8eb
crossref_primary_10_1049_iet_cvi_2018_5129
wiley_primary_10_1049_iet_cvi_2018_5129_CVI2BF00552
ProviderPackageCode RUI
PublicationCentury 2000
PublicationDate 20190300
March 2019
2019-03-00
2019-03-01
PublicationDateYYYYMMDD 2019-03-01
PublicationDate_xml – month: 3
  year: 2019
  text: 20190300
PublicationDecade 2010
PublicationTitle IET computer vision
PublicationYear 2019
Publisher The Institution of Engineering and Technology
Wiley
Publisher_xml – name: The Institution of Engineering and Technology
– name: Wiley
References Shehzad, M.I.; Shah, Y.A.; Mehmood, Z. (C3) 2017; 11
Zoidi, O.; Tefas, A.; Pitas, I.. (C4) 2013; 23
Dou, J.; Li, J. (C21) 2015; 126
Ali, A.; Jalil, A.; Niu, J.W. (C2) 2016; 10
Li, Y.; Zhao, W.; Jiahao, P. (C24) 2017; 14
Li, H.; Li, Y.; Porikli, F.M. (C27) 2015; 25
Yigit, A.; Temizel, A.. (C33) 2017; 11
Chu, C.-T.; Hwang, J.-N.; Pai, H.-I. (C19) 2013; 15
Cao, X.; Gao, C.; Lan, J. (C20) 2014; 124
Kalal, Z.; Krystian, M.; Matas, J. (C28) 2012; 34
Collins, R.T; Liu, Y. (C11) 2003; 27
Wang, L.F.; Yan, H.P.; Wu, H.Y. (C15) 2013; 14
Ali, A.; Jalil, A.; Ahmed, J. (C18) 2015; 9
Song, Y.; Li, S.X.; Zhu, C.F. (C34) 2015; 9
Baochang, Z.; Luan, S.; Chen, C. (C22) 2018; 27
Yuan, Y.; Xiong, Z.; Wang, Q. (C32) 2017; 18
Yang, X.; Di, T.. (C42) 2015; 7
Junyu, G.; Zhang, T.; Yang, X. (C38) 2017; 26
Li, Z.; Yu, X.; Li, P. (C14) 2015; 31
Wang, Q.; Gao, J.; Yuan, Y. (C25) 2018; 19
Wang, J.; Yagi, Y. (C12) 2008; 17
Li, Z.; He, S.; Hashem, M. (C13) 2015; 31
Kim, D.-H.; Kim, H.-K.; Lee, S.J. (C17) 2014; 24
Bengio, Y. (C43) 2012; 7700
Mazinan, A.H. (C35) 2015; 37
Wu, Y.; Cheng, J.; Wang, J. (C9) 2012; 21
Wang, Q.; Wan, J.; Yuan, Y.. (C29) 2017
Tan, X.; Triggs, B. (C8) 2007; 19
Wang, Q.; Wan, J.; Yuan, J. (C30) 2018; 75
Baochang, Z.; Yang, Y.; Chen, C. (C23) 2017; 26
2007; 19
2015; 37
2015; 126
2017; 26
2012
2010
2013; 23
2015; 31
2012; 7700
2008; 17
2016; 10
2009
2008
2007
2006
2014; 24
2005
2002
2015; 9
2012; 34
2015; 7
2018; 27
1999
2018; 19
2015; 25
2013; 15
2013; 14
2017; 14
2017; 11
2003; 27
2017
2017; 18
2014
2013
2018; 75
2012; 21
2014; 124
Yang M.‐H. (e_1_2_6_38_2) 2009
Li H. (e_1_2_6_27_2) 2014
e_1_2_6_31_2
Tan X. (e_1_2_6_9_2) 2007; 19
Wang Q. (e_1_2_6_30_2) 2017
e_1_2_6_18_2
e_1_2_6_19_2
e_1_2_6_12_2
e_1_2_6_35_2
Grabner H. (e_1_2_6_11_2) 2006
e_1_2_6_13_2
e_1_2_6_34_2
e_1_2_6_10_2
e_1_2_6_33_2
Bai Y. (e_1_2_6_37_2) 2012
e_1_2_6_32_2
e_1_2_6_16_2
Junyu G. (e_1_2_6_39_2) 2017; 26
e_1_2_6_17_2
e_1_2_6_14_2
e_1_2_6_15_2
e_1_2_6_36_2
Triggs B. (e_1_2_6_6_2) 2005
e_1_2_6_42_2
e_1_2_6_20_2
e_1_2_6_41_2
e_1_2_6_40_2
e_1_2_6_8_2
e_1_2_6_7_2
e_1_2_6_29_2
e_1_2_6_4_2
e_1_2_6_3_2
e_1_2_6_5_2
e_1_2_6_24_2
e_1_2_6_23_2
e_1_2_6_22_2
e_1_2_6_21_2
e_1_2_6_28_2
e_1_2_6_43_2
Yang M. (e_1_2_6_2_2) 2013
e_1_2_6_44_2
e_1_2_6_26_2
e_1_2_6_25_2
References_xml – volume: 31
  start-page: 1319
  issue: 10
  year: 2015
  end-page: 1337
  ident: C13
  article-title: Robust object tracking via multi-feature adaptive fusion based on stability: contrast analysis
  publication-title: Vis. Comput.
– volume: 24
  start-page: 1288
  issue: 8
  year: 2014
  end-page: 1300
  ident: C17
  article-title: Kernel-based structural binary pattern tracking
  publication-title: IEEE Trans. Circuits Syst. Video Technol.
– volume: 15
  start-page: 1602
  issue: 7
  year: 2013
  end-page: 1615
  ident: C19
  article-title: Tracking human under occlusion based on adaptive multiple kernels with projected gradients
  publication-title: IEEE Trans. Multimed.
– volume: 19
  start-page: 1457
  issue: 5
  year: 2018
  end-page: 1470
  ident: C25
  article-title: A joint convolutional neural networks and context transfer for street scenes labeling
  publication-title: IEEE Trans. Intell. Transp. Syst. (T–ITS)
– year: 2017
  ident: C29
  article-title: Deep metric learning for crowdedness regression
  publication-title: IEEE Trans. Circuits Syst. Video Technol. (T-CSVT)
– volume: 37
  start-page: 921
  issue: 8
  year: 2015
  end-page: 931
  ident: C35
  article-title: Performance improvement in artificial intelligence-based objects tracking via probabilistic estimation approach
  publication-title: Trans. Inst. Meas. Control
– volume: 7700
  start-page: 437
  issue: 1–3
  year: 2012
  end-page: 478
  ident: C43
  article-title: Practical recommendations for gradient-based training of deep architectures
  publication-title: Neural Netw., Tricks Trade
– volume: 9
  start-page: 489
  issue: 4
  year: 2015
  end-page: 499
  ident: C34
  article-title: Invariant foreground occupation ratio for scale adaptive mean shift tracking
  publication-title: IET Comput. Vis.
– volume: 7
  start-page: 1022
  issue: 1
  year: 2015
  end-page: 1028
  ident: C42
  article-title: Research on mean-shift target tracking based on image HOG feature
  publication-title: Open Autom. Control Syst.
– volume: 26
  start-page: 1845
  issue: 99
  year: 2017
  end-page: 1858
  ident: C38
  article-title: Deep relative tracking
  publication-title: IEEE Trans. Image Process.
– volume: 19
  start-page: 1635
  year: 2007
  end-page: 1650
  ident: C8
  article-title: Enhanced local texture feature sets for face recognition under difficult lighting conditions
  publication-title: IEEE Trans. Image Process.
– volume: 10
  start-page: 167
  issue: 1
  year: 2016
  end-page: 188
  ident: C2
  article-title: Visual object tracking–classical and contemporary approaches
  publication-title: Frontiers Comput. Sci. Sel. Publ. Chin. Univ.
– volume: 27
  start-page: 1631
  issue: 10
  year: 2003
  end-page: 1643
  ident: C11
  article-title: Online selection of discriminative tracking features
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
– volume: 23
  start-page: 870
  issue: 5
  year: 2013
  end-page: 882
  ident: C4
  article-title: Visual object tracking based on local steering kernels and color histograms
  publication-title: IEEE Trans. Circuits Syst. Video Technol.
– volume: 34
  start-page: 1409
  issue: 7
  year: 2012
  end-page: 1422
  ident: C28
  article-title: Tracking–learning–detection
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
– volume: 11
  start-page: 255
  issue: 3
  year: 2017
  end-page: 263
  ident: C33
  article-title: Individual and group tracking with the evaluation of social interactions
  publication-title: IET Comput. Vis.
– volume: 124
  start-page: 168
  issue: SI
  year: 2014
  end-page: 177
  ident: C20
  article-title: Ego motion guided particle filter for vehicle tracking in airborne videos
  publication-title: Neurocomputing
– volume: 75
  start-page: 272
  year: 2018
  end-page: 281
  ident: C30
  article-title: Locality constraint distance metric learning for traffic congestion detection
  publication-title: Pattern Recognit. (PR)
– volume: 126
  start-page: 1449
  issue: 15–16
  year: 2015
  end-page: 1456
  ident: C21
  article-title: Robust visual tracking based on joint multi–feature histogram by integrating particle filter and mean shift
  publication-title: Optik, Int. J. Light Electron. Opt.
– volume: 18
  start-page: 1918
  issue: 7
  year: 2017
  end-page: 1929
  ident: C32
  article-title: An incremental framework for video-based traffic sign detection, tracking and recognition
  publication-title: IEEE Trans. Intell. Transp. Syst. (T–ITS)
– volume: 9
  start-page: 1567
  issue: 7
  year: 2015
  end-page: 1585
  ident: C18
  article-title: Correlation, Kalman filter and adaptive fast mean shift based heuristic approach for robust visual tracking
  publication-title: Signal Image Video Process.
– volume: 26
  start-page: 4648
  issue: 10
  year: 2017
  end-page: 4660
  ident: C23
  article-title: Action recognition using 3D histograms of texture and a multi–class boosting classifier
  publication-title: IEEE Trans. Image Process.
– volume: 14
  start-page: 1480
  issue: 3
  year: 2013
  end-page: 1489
  ident: C15
  article-title: Forward-backward mean-shift for visual tracking with local-background-weighted histogram
  publication-title: IEEE Trans. Intell. Transp. Syst.
– volume: 27
  start-page: 1038
  year: 2018
  end-page: 1048
  ident: C22
  article-title: Latent constrained correlation filter
  publication-title: IEEE Trans. Image Process.
– volume: 14
  start-page: 1256
  issue: 2
  year: 2017
  end-page: 1264
  ident: C24
  article-title: Deformable patterned fabric defect detection with fisher criterion based deep learning
  publication-title: IEEE Trans. Autom. Sci. Eng.
– volume: 11
  start-page: 68
  issue: 1
  year: 2017
  end-page: 77
  ident: C3
  article-title: –means based multiple objects tracking with long-term occlusion handling
  publication-title: IET Comput. Vis.
– volume: 21
  start-page: 2824
  issue: 5
  year: 2012
  end-page: 2837
  ident: C9
  article-title: Real–time probabilistic covariance tracking with efficient model update
  publication-title: IEEE Trans. Image Process.
– volume: 17
  start-page: 235
  issue: 2
  year: 2008
  end-page: 240
  ident: C12
  article-title: Integrating color and shape-texture features for adaptive real-time object tracking
  publication-title: IEEE Trans. Image Process.
– volume: 31
  start-page: 1633
  issue: 12
  year: 2015
  end-page: 1651
  ident: C14
  article-title: Moving object tracking based on multi-independent features distribution fields with comprehensive spatial feature similarity
  publication-title: Vis. Comput.
– volume: 25
  start-page: 1834
  issue: 4
  year: 2015
  end-page: 1848
  ident: C27
  article-title: Deeptrack: learning discriminative feature representations online for robust visual tracking
  publication-title: IEEE Trans. Image Process.
– volume: 31
  start-page: 1633
  issue: 12
  year: 2015
  end-page: 1651
  article-title: Moving object tracking based on multi‐independent features distribution fields with comprehensive spatial feature similarity
  publication-title: Vis. Comput.
– volume: 126
  start-page: 1449
  issue: 15–16
  year: 2015
  end-page: 1456
  article-title: Robust visual tracking based on joint multi–feature histogram by integrating particle filter and mean shift
  publication-title: Optik, Int. J. Light Electron. Opt.
– start-page: 971
  year: 2002
  end-page: 987
– start-page: 1
  year: 2007
  end-page: 8
– volume: 31
  start-page: 1319
  issue: 10
  year: 2015
  end-page: 1337
  article-title: Robust object tracking via multi‐feature adaptive fusion based on stability: contrast analysis
  publication-title: Vis. Comput.
– volume: 15
  start-page: 1602
  issue: 7
  year: 2013
  end-page: 1615
  article-title: Tracking human under occlusion based on adaptive multiple kernels with projected gradients
  publication-title: IEEE Trans. Multimed.
– volume: 124
  start-page: 168
  issue: SI
  year: 2014
  end-page: 177
  article-title: Ego motion guided particle filter for vehicle tracking in airborne videos
  publication-title: Neurocomputing
– start-page: 1854
  year: 2012
  end-page: 1861
– volume: 21
  start-page: 2824
  issue: 5
  year: 2012
  end-page: 2837
  article-title: Real–time probabilistic covariance tracking with efficient model update
  publication-title: IEEE Trans. Image Process.
– volume: 7
  start-page: 1022
  issue: 1
  year: 2015
  end-page: 1028
  article-title: Research on mean‐shift target tracking based on image HOG feature
  publication-title: Open Autom. Control Syst.
– volume: 24
  start-page: 1288
  issue: 8
  year: 2014
  end-page: 1300
  article-title: Kernel‐based structural binary pattern tracking
  publication-title: IEEE Trans. Circuits Syst. Video Technol.
– start-page: 393
  year: 2014
  end-page: 400
– volume: 10
  start-page: 167
  issue: 1
  year: 2016
  end-page: 188
  article-title: Visual object tracking–classical and contemporary approaches
  publication-title: Frontiers Comput. Sci. Sel. Publ. Chin. Univ.
– start-page: 886
  year: 2005
  end-page: 893
– start-page: 194
  year: 2014
  end-page: 209
– volume: 19
  start-page: 1635
  year: 2007
  end-page: 1650
  article-title: Enhanced local texture feature sets for face recognition under difficult lighting conditions
  publication-title: IEEE Trans. Image Process.
– start-page: 3789
  year: 2010
  end-page: 3792
– volume: 23
  start-page: 870
  issue: 5
  year: 2013
  end-page: 882
  article-title: Visual object tracking based on local steering kernels and color histograms
  publication-title: IEEE Trans. Circuits Syst. Video Technol.
– volume: 9
  start-page: 489
  issue: 4
  year: 2015
  end-page: 499
  article-title: Invariant foreground occupation ratio for scale adaptive mean shift tracking
  publication-title: IET Comput. Vis.
– volume: 25
  start-page: 1834
  issue: 4
  year: 2015
  end-page: 1848
  article-title: Deeptrack: learning discriminative feature representations online for robust visual tracking
  publication-title: IEEE Trans. Image Process.
– volume: 27
  start-page: 1631
  issue: 10
  year: 2003
  end-page: 1643
  article-title: Online selection of discriminative tracking features
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
– volume: 11
  start-page: 255
  issue: 3
  year: 2017
  end-page: 263
  article-title: Individual and group tracking with the evaluation of social interactions
  publication-title: IET Comput. Vis.
– volume: 11
  start-page: 68
  issue: 1
  year: 2017
  end-page: 77
  article-title: –means based multiple objects tracking with long‐term occlusion handling
  publication-title: IET Comput. Vis.
– start-page: 2411
  year: 2013
  end-page: 2418
– year: 2017
  article-title: Deep metric learning for crowdedness regression
  publication-title: IEEE Trans. Circuits Syst. Video Technol. (T‐CSVT)
– start-page: 983
  year: 2009
  end-page: 990
– volume: 18
  start-page: 1918
  issue: 7
  year: 2017
  end-page: 1929
  article-title: An incremental framework for video‐based traffic sign detection, tracking and recognition
  publication-title: IEEE Trans. Intell. Transp. Syst. (T–ITS)
– start-page: 47
  year: 2006
  end-page: 56
– volume: 17
  start-page: 235
  issue: 2
  year: 2008
  end-page: 240
  article-title: Integrating color and shape‐texture features for adaptive real‐time object tracking
  publication-title: IEEE Trans. Image Process.
– volume: 9
  start-page: 1567
  issue: 7
  year: 2015
  end-page: 1585
  article-title: Correlation, Kalman filter and adaptive fast mean shift based heuristic approach for robust visual tracking
  publication-title: Signal Image Video Process.
– volume: 14
  start-page: 1256
  issue: 2
  year: 2017
  end-page: 1264
  article-title: Deformable patterned fabric defect detection with fisher criterion based deep learning
  publication-title: IEEE Trans. Autom. Sci. Eng.
– start-page: 1208
  year: 2009
  end-page: 1215
– volume: 34
  start-page: 1409
  issue: 7
  year: 2012
  end-page: 1422
  article-title: Tracking–learning–detection
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
– volume: 75
  start-page: 272
  year: 2018
  end-page: 281
  article-title: Locality constraint distance metric learning for traffic congestion detection
  publication-title: Pattern Recognit. (PR)
– volume: 37
  start-page: 921
  issue: 8
  year: 2015
  end-page: 931
  article-title: Performance improvement in artificial intelligence‐based objects tracking via probabilistic estimation approach
  publication-title: Trans. Inst. Meas. Control
– volume: 27
  start-page: 1038
  year: 2018
  end-page: 1048
  article-title: Latent constrained correlation filter
  publication-title: IEEE Trans. Image Process.
– volume: 26
  start-page: 4648
  issue: 10
  year: 2017
  end-page: 4660
  article-title: Action recognition using 3D histograms of texture and a multi–class boosting classifier
  publication-title: IEEE Trans. Image Process.
– volume: 19
  start-page: 1457
  issue: 5
  year: 2018
  end-page: 1470
  article-title: A joint convolutional neural networks and context transfer for street scenes labeling
  publication-title: IEEE Trans. Intell. Transp. Syst. (T–ITS)
– start-page: 1096
  year: 2008
  end-page: 1103
– volume: 7700
  start-page: 437
  issue: 1–3
  year: 2012
  end-page: 478
  article-title: Practical recommendations for gradient‐based training of deep architectures
  publication-title: Neural Netw., Tricks Trade
– volume: 26
  start-page: 1845
  issue: 99
  year: 2017
  end-page: 1858
  article-title: Deep relative tracking
  publication-title: IEEE Trans. Image Process.
– volume: 14
  start-page: 1480
  issue: 3
  year: 2013
  end-page: 1489
  article-title: Forward‐backward mean‐shift for visual tracking with local‐background‐weighted histogram
  publication-title: IEEE Trans. Intell. Transp. Syst.
– year: 1999
– start-page: 194
  volume-title: Asian Conference on Computer Vision (ACCV)
  year: 2014
  ident: e_1_2_6_27_2
– ident: e_1_2_6_42_2
  doi: 10.1109/CVPRW.2014.126
– ident: e_1_2_6_24_2
  doi: 10.1109/TIP.2017.2718189
– ident: e_1_2_6_14_2
  doi: 10.1007/s00371-014-1014-6
– ident: e_1_2_6_7_2
  doi: 10.1109/ICCV.2007.4408954
– ident: e_1_2_6_40_2
  doi: 10.1109/ICCV.1999.790416
– start-page: 47
  volume-title: Proceedings of British Machine Vision Conference (BMVC)
  year: 2006
  ident: e_1_2_6_11_2
– ident: e_1_2_6_19_2
  doi: 10.1007/s11760-014-0612-0
– ident: e_1_2_6_17_2
  doi: 10.1109/CVPR.2009.5206502
– ident: e_1_2_6_13_2
  doi: 10.1109/TIP.2007.914150
– ident: e_1_2_6_25_2
  doi: 10.1109/TASE.2016.2520955
– ident: e_1_2_6_32_2
  doi: 10.1109/ICIP.2010.5653525
– volume: 19
  start-page: 1635
  year: 2007
  ident: e_1_2_6_9_2
  article-title: Enhanced local texture feature sets for face recognition under difficult lighting conditions
  publication-title: IEEE Trans. Image Process.
– ident: e_1_2_6_31_2
  doi: 10.1016/j.patcog.2017.03.030
– ident: e_1_2_6_41_2
  doi: 10.1145/1390156.1390294
– ident: e_1_2_6_15_2
  doi: 10.1007/s00371-014-1044-0
– ident: e_1_2_6_21_2
  doi: 10.1016/j.neucom.2013.07.014
– ident: e_1_2_6_43_2
  doi: 10.2174/18744443015070101022
– start-page: 2411
  volume-title: 2013 IEEE Conf. Computer Vision and Pattern Recognition (CVPR)
  year: 2013
  ident: e_1_2_6_2_2
– start-page: 886
  volume-title: 2005 IEEE Computer Society Conf. Computer Vision and Pattern Recognition (CVPR)
  year: 2005
  ident: e_1_2_6_6_2
– ident: e_1_2_6_20_2
  doi: 10.1109/TMM.2013.2266634
– ident: e_1_2_6_4_2
  doi: 10.1049/iet-cvi.2016.0156
– ident: e_1_2_6_33_2
  doi: 10.1109/TITS.2016.2614548
– ident: e_1_2_6_44_2
  doi: 10.1007/978-3-642-35289-8_26
– ident: e_1_2_6_10_2
  doi: 10.1109/TIP.2011.2182521
– ident: e_1_2_6_23_2
  doi: 10.1109/TIP.2017.2775060
– ident: e_1_2_6_8_2
  doi: 10.1109/TPAMI.2002.1017623
– ident: e_1_2_6_18_2
  doi: 10.1109/TCSVT.2014.2305514
– ident: e_1_2_6_34_2
  doi: 10.1049/iet-cvi.2016.0238
– start-page: 1854
  volume-title: 2012 IEEE Conf. Computer Vision and Pattern Recognition (CVPR)
  year: 2012
  ident: e_1_2_6_37_2
– ident: e_1_2_6_3_2
  doi: 10.1007/s11704-015-4246-3
– ident: e_1_2_6_16_2
  doi: 10.1109/TITS.2013.2263281
– ident: e_1_2_6_28_2
  doi: 10.1109/TIP.2015.2510583
– ident: e_1_2_6_36_2
  doi: 10.1177/0142331214549409
– ident: e_1_2_6_22_2
  doi: 10.1016/j.ijleo.2015.04.031
– ident: e_1_2_6_29_2
  doi: 10.1109/TPAMI.2011.239
– ident: e_1_2_6_35_2
  doi: 10.1049/iet-cvi.2014.0150
– ident: e_1_2_6_5_2
  doi: 10.1109/TCSVT.2012.2226527
– start-page: 983
  volume-title: 2009 IEEE Conf. Computer Vision and Pattern Recognition (CVPR)
  year: 2009
  ident: e_1_2_6_38_2
– year: 2017
  ident: e_1_2_6_30_2
  article-title: Deep metric learning for crowdedness regression
  publication-title: IEEE Trans. Circuits Syst. Video Technol. (T‐CSVT)
– ident: e_1_2_6_12_2
  doi: 10.1109/TPAMI.2005.205
– ident: e_1_2_6_26_2
  doi: 10.1109/TITS.2017.2726546
– volume: 26
  start-page: 1845
  issue: 99
  year: 2017
  ident: e_1_2_6_39_2
  article-title: Deep relative tracking
  publication-title: IEEE Trans. Image Process.
SSID ssj0056994
Score 2.220281
Snippet Object detection and tracking under complex environment are challenging because of the disturbances induced by background clutter, illumination changes,...
SourceID doaj
crossref
wiley
iet
SourceType Open Website
Enrichment Source
Index Database
Publisher
StartPage 157
SubjectTerms colour histograms
deep learning-based LPM
feature extraction
hand-crafted features
histograms of oriented gradients
image colour analysis
learning (artificial intelligence)
local probability model
local probability model-based mean shift algorithm
LPM-based mean shift algorithm
MS tracking algorithm
neural nets
object detection
object tracking
probability
Special Issue: Visual Domain Adaptation and Generalisation
stacked denoising autoencoders
SummonAdditionalLinks – databaseName: DOAJ Directory of Open Access Journals
  dbid: DOA
  link: http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1LS8QwEA4iHrz4FtcXOYgHodomabc56uKi4AsU9RbylAWpslvFoz_B3-gvcSaty3rRi9cyScOXmcwkmcxHyA7XDqKKIBLmuywRNjOJhmlOvLRpCfYkpWnIJroXF-X9vbyaoPrCnLCmPHAD3EFqHLc6cJdJKwpX6tRBiOsy7nPjS29w9U278nsz1azBeSEjBSL4xiwBFWPj-0x5MPB1Yl8HmNVV7qO7--GRYuF-8DMg9TNcjf6mv0Dm2kCRHjYDXCRTvloi823QSFuTHC2Tu0uDRynU-TpmVVVUV47WQ23xEJziG7EhRat_9G904lkbxYz3B2jmn2lLHfHw-f6BXs3Rs6vzFXLdP77pnSQtW0JiRWQoCSILVgTYFgbvy0xnqRVG574wXIuycLLkRaG5EIYZ1pVZyK0ExyVNCLBRXSXT1VPl1wg1UheGAeI5yHqmjZAhmDwU3Gmnc9Yh6TdeyraFxJHP4lHFC20hFYCnAGKFECuEuEP2xk2emyoavwkf4SSMBbEAdvwAaqFatVB_qUWH7GLHrUGOfvsbj7P897hU7_aUHfWxahlb_48xbpBZ6Fw2GW2bZLoevvgtMmNf68FouB0V-gs-Hvq8
  priority: 102
  providerName: Directory of Open Access Journals
Title Object detection and tracking under Complex environment using deep learning-based LPM
URI http://digital-library.theiet.org/content/journals/10.1049/iet-cvi.2018.5129
https://onlinelibrary.wiley.com/doi/abs/10.1049%2Fiet-cvi.2018.5129
https://doaj.org/article/0bd3caf3d19c46d8a0d758d13e5be8eb
Volume 13
WOSCitedRecordID wos000459454900010&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: PRVWIB
  databaseName: Wiley Online Library Free Content
  customDbUrl:
  eissn: 1751-9640
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0056994
  issn: 1751-9632
  databaseCode: WIN
  dateStart: 20130101
  isFulltext: true
  titleUrlDefault: https://onlinelibrary.wiley.com
  providerName: Wiley-Blackwell
– providerCode: PRVWIB
  databaseName: Wiley Online Library Open Access
  customDbUrl:
  eissn: 1751-9640
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0056994
  issn: 1751-9632
  databaseCode: 24P
  dateStart: 20130101
  isFulltext: true
  titleUrlDefault: https://authorservices.wiley.com/open-science/open-access/browse-journals.html
  providerName: Wiley-Blackwell
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV3daxQxEA-1-uCLrV94VUsexAdhdfOxuc2jPTws6Hmg2L6FfB4HZVv2tqWP_RP8G_1LnMnunS1CBfFlH8JMNkzyy0wmkxlCXgkbwKpIsuBxzAvpmSssTHMRtS9rwJPWri82MZ7N6uNjPd8ik_VbmD4_xMbhhsjI-zUC3Lq-CgkYtTCJy9gV_mKJ0Vn1W1Rbd8hdxsQYlzaX8_V2XCmdqyGCmmSFVvL31aZ-90cXN5RTzuEPKgeoblquWfVMd_7LoHfJg8HypO_7pfKQbMXmEdkZrFA6YHz1mBx9ceiboSF2OUyrobYJtGutR686xUdnLcVt5CRe0mvv5CiG0C-ALZ7RoRbF4ufVD1STgX6af35Cvk4_fJt8LIbyC4WXueRJkix5meCcmWKsmWWll85WUTlhZa2CroVSVkjpuONjzVLlNWhC7VKCk-9Tst2cNvEZoU5b5XgSoQLayK2TOiVXJSWCDbbiI1KupW78kJkcC2ScmHxDLrUBsRkQm0GxGRTbiLzZsJz1aTluIz7AqdwQYkbt3HDaLswAUFO6ILyFQTLtpQq1LQMcpQITsXKxjm5EXmPHA8JXt_1N5BXw93GZyfdDfjDFNGh875-4npP70K77mLgXZLtrz-NLcs9fdMtVu59xsJ-9DPA9Opz9AjjrDn0
linkProvider Wiley-Blackwell
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1Lb9QwEB6VFgkutLzE8ig-VD0gBRLb8cZHWli1YrtdiQp6s_xcrVSlVTZUHPkJ_EZ-CR4nu6VCKlLFNRo71tjjb2Y8D4Adpl3UKgLPqB_SjNvCZDpuc-alzasoT1KartnEcDKpTk_ldA0-LHNhuvoQK4cbSka6r1HA0SHdGZwci2TOfZvZyzmGZ1VvEbfuwAaPaIN9DCifLu_jUsjUDjHiZJFJwa_eNuW7v6a4hk6piH_EnEh1XXVN2DPa_D-r3oIHve5J3neH5SGs-foRbPZ6KOmlfPEYvh4b9M4Q59sUqFUTXTvSNtqiX51g2llD8CI589_JH5lyBIPoZ3GYvyB9N4rZrx8_ESgdGU-PnsDn0ceT_YOsb8CQWZ6angReBMtDtDSD91Whi9xyo0svDNO8Ek5WTAjNODfU0KEsQmllxEJpQoi271NYr89r_wyIkVoYGpgrI62n2nAZgimDYE47XdIB5Eu2K9vXJscWGWcqvZFzqSLbVGSbQrYpZNsA3qyGXHSFOW4i3sO9XBFiTe304byZqV5EVW4cszouspCWC1fp3EVjyhXMl8ZX3gxgFyfuZXxx099YOgL_Xpfa_3JI90ZYCI0-v9Wo13Dv4ORorMaHk08v4H6kkV2E3EtYb5tv_hXctZftfNFsJ6H4DXuUEFs
linkToPdf http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV3daxQxEB9qK-KL9ROvtZqH4oOwuptkc5tH23q02J4HivYt5PM4KNtjby199E_wb_QvaSa7d7UIFcTXZZINk8xXMvMbgF2mXfQqAs-oH9KM28JkOm5z5qXNqyhPUpqu2cRwPK5OT-VkDQ6WtTAdPsTqwg0lI-lrFHA_d6ELODmCZM58m9mLGaZnVW_Rbt2BDV5GXYv4znyy1MelkKkdYrSTRSYFv37blO_-mOKGdUog_tHmRKqbrmuyPaPN_7Pqh_Cg9z3J--6wPII1Xz-Gzd4PJb2UL57At08Gb2eI821K1KqJrh1pG23xXp1g2VlDUJGc-UvyW6UcwST6aRzm56TvRjH99eMnGkpHjicnT-Hz6MOX_cOsb8CQWZ6angReBMtDjDSD91Whi9xyo0svDNO8Ek5WTAjNODfU0KEsQmlltIXShBBj32ewXp_X_jkQI7UwNDBXRlpPteEyBFMGwZx2uqQDyJdsV7bHJscWGWcqvZFzqSLbVGSbQrYpZNsA3qyGzDtgjtuI93AvV4SIqZ0-nDdT1Yuoyo1jVsdFFtJy4SqduxhMuYL50vjKmwG8xol7GV_c9jeWjsDf16X2vx7RvRECodGtfxr1Cu5NDkbq-Gj8cRvuRxLZJci9gPW2-e534K69aGeL5mWSiSsK6w_f
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=Object+detection+and+tracking+under+Complex+environment+using+deep+learning%E2%80%90based+LPM&rft.jtitle=IET+computer+vision&rft.au=Li%2C+Yundong&rft.au=Zhang%2C+Xueyan&rft.au=Li%2C+Hongguang&rft.au=Zhou%2C+Qichen&rft.date=2019-03-01&rft.pub=The+Institution+of+Engineering+and+Technology&rft.issn=1751-9640&rft.eissn=1751-9640&rft.volume=13&rft.issue=2&rft.spage=157&rft.epage=164&rft_id=info:doi/10.1049%2Fiet-cvi.2018.5129&rft.externalDBID=10.1049%252Fiet-cvi.2018.5129&rft.externalDocID=CVI2BF00552
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1751-9632&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1751-9632&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1751-9632&client=summon