Power Equipment Recognition Method based on Mask R-CNN and Bayesian Context Network

In order to improve the accuracy of power equipment recognition, an image recognition method based on Mask RCNN and Bayesian Context Network is proposed. The two-layer network contains Mask R-CNN as the first layer, which gives preliminary recognition results, and Bayesian Context Network as the sec...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:IEEE Power & Energy Society General Meeting s. 1 - 5
Hlavní autoři: Siheng, XIONG, Yadong, LIU, Rui, XU, Ying, DU, Zihan, CONG, Yingjie, YAN, Xiuchen, JIANG
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 02.08.2020
Témata:
Bayesian Context Network
Mask R-CNN
power equipment in substation
power equipment recognition
relationship between objects
ISSN:1944-9933
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract In order to improve the accuracy of power equipment recognition, an image recognition method based on Mask RCNN and Bayesian Context Network is proposed. The two-layer network contains Mask R-CNN as the first layer, which gives preliminary recognition results, and Bayesian Context Network as the second layer, which utilizes context information to correct the preliminary results. Bayesian Context Network is designed to take the relationship of type, size, and spatial location between objects into account. Experiments on images of power equipment in substation show that the proposed method outperforms Mask R-CNN, Multi-task Network Cascades and Fully Convolutional Instance-aware Semantic Segmentation. Since power equipment in a picture shows a strong correlation, the proposed method is quite suitable for power equipment recognition.
AbstractList In order to improve the accuracy of power equipment recognition, an image recognition method based on Mask RCNN and Bayesian Context Network is proposed. The two-layer network contains Mask R-CNN as the first layer, which gives preliminary recognition results, and Bayesian Context Network as the second layer, which utilizes context information to correct the preliminary results. Bayesian Context Network is designed to take the relationship of type, size, and spatial location between objects into account. Experiments on images of power equipment in substation show that the proposed method outperforms Mask R-CNN, Multi-task Network Cascades and Fully Convolutional Instance-aware Semantic Segmentation. Since power equipment in a picture shows a strong correlation, the proposed method is quite suitable for power equipment recognition.
Author Xiuchen, JIANG
Yingjie, YAN
Siheng, XIONG
Rui, XU
Ying, DU
Zihan, CONG
Yadong, LIU
Author_xml – sequence: 1
  givenname: XIONG
  surname: Siheng
  fullname: Siheng, XIONG
  email: xiongsiheng@sjtu.edu.cn
  organization: Shanghai Jiao Tong University,Department of Electronic Information and Electrical Engineering,Shanghai,China
– sequence: 2
  givenname: LIU
  surname: Yadong
  fullname: Yadong, LIU
  email: lyd@sjtu.edu.cn
  organization: Shanghai Jiao Tong University,Department of Electronic Information and Electrical Engineering,Shanghai,China
– sequence: 3
  givenname: XU
  surname: Rui
  fullname: Rui, XU
  organization: Shanghai Jiao Tong University,Department of Electronic Information and Electrical Engineering,Shanghai,China
– sequence: 4
  givenname: DU
  surname: Ying
  fullname: Ying, DU
  organization: Shanghai Jiao Tong University,Department of Electronic Information and Electrical Engineering,Shanghai,China
– sequence: 5
  givenname: CONG
  surname: Zihan
  fullname: Zihan, CONG
  organization: Shanghai Jiao Tong University,Department of Electronic Information and Electrical Engineering,Shanghai,China
– sequence: 6
  givenname: YAN
  surname: Yingjie
  fullname: Yingjie, YAN
  organization: Shanghai Jiao Tong University,Department of Electronic Information and Electrical Engineering,Shanghai,China
– sequence: 7
  givenname: JIANG
  surname: Xiuchen
  fullname: Xiuchen, JIANG
  organization: Shanghai Jiao Tong University,Department of Electronic Information and Electrical Engineering,Shanghai,China
BookMark eNotkM1OAjEcxKvRRECewIN9gcV-btujbgBNYCWgZ9Ld_lcr0uJuDfL2YmQuM7_LZDJ9dBFiAIRuKRlRSszdYryazgU1UowYYWRkmKZKyjPUp-oYpSRan6MeNUJkxnB-hYZd90GOkkLlOeuh1SLuocXjr2-_20JIeAl1fAs--RjwHNJ7dLiyHTj8x7bb4GVWlCW2weEHe4DO24CLGBL8JFxC2sd2c40uG_vZwfDkA_Q6Gb8Uj9nsefpU3M8yzwhPWZ3TWlNeOeKMEkblx7GN1bISyoAzvKmUJTWlFZNOkbwhAozTrOJO57XmhA_QzX-vB4D1rvVb2x7Wpw_4L23AUlI
ContentType Conference Proceeding
DBID 6IE
6IH
CBEJK
RIE
RIO
DOI 10.1109/PESGM41954.2020.9281755
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Proceedings Order Plan (POP) 1998-present by volume
IEEE Xplore All Conference Proceedings
IEEE/IET Electronic Library
IEEE Proceedings Order Plans (POP) 1998-present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE/IET Electronic Library
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISBN 1728155088
9781728155081
EISSN 1944-9933
EndPage 5
ExternalDocumentID 9281755
Genre orig-research
GroupedDBID 29O
6IE
6IF
6IH
6IL
6IM
6IN
AAJGR
AAWTH
ABLEC
ACGFS
ADZIZ
ALMA_UNASSIGNED_HOLDINGS
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CBEJK
CHZPO
IEGSK
IJVOP
M43
OCL
RIE
RIL
RIO
ID FETCH-LOGICAL-i203t-c61c813bd0d974976088fa85b479ed93fb7a0c11b25d706f04e9d82b3d86c8303
IEDL.DBID RIE
ISICitedReferencesCount 0
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000679246601114&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
IngestDate Wed Aug 27 02:33:53 EDT 2025
IsPeerReviewed false
IsScholarly true
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i203t-c61c813bd0d974976088fa85b479ed93fb7a0c11b25d706f04e9d82b3d86c8303
PageCount 5
ParticipantIDs ieee_primary_9281755
PublicationCentury 2000
PublicationDate 2020-Aug.-2
PublicationDateYYYYMMDD 2020-08-02
PublicationDate_xml – month: 08
  year: 2020
  text: 2020-Aug.-2
  day: 02
PublicationDecade 2020
PublicationTitle IEEE Power & Energy Society General Meeting
PublicationTitleAbbrev PESGM
PublicationYear 2020
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0000547662
Score 2.1773632
Snippet In order to improve the accuracy of power equipment recognition, an image recognition method based on Mask RCNN and Bayesian Context Network is proposed. The...
SourceID ieee
SourceType Publisher
StartPage 1
SubjectTerms Bayesian Context Network
Mask R-CNN
power equipment in substation
power equipment recognition
relationship between objects
Title Power Equipment Recognition Method based on Mask R-CNN and Bayesian Context Network
URI https://ieeexplore.ieee.org/document/9281755
WOSCitedRecordID wos000679246601114&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
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3LS8MwHP4xhwe9-NjENzl4tFuatnlcHZteVsamsNtI84AhdLp1ov-9SVanghdvTaEUfmnz5fE9AG4Ep-6rYDSyEpso5TaJuIqp-_E4TbnKlMY6hE2wPOfTqRg14HarhTHGBPKZ6fjLcJavF2rtt8q6gnCHdtkO7DDGNlqt7X6Km3owSklN4Yqx6I76k_th6h3N3DKQ4E799K8YlYAig4P_vf8Q2t9yPDTaAs0RNEx5DPs_nARbMBn5tDPUf13PAwEIjb-IQYsSDUNKNPKApZFvy9UzGke9PEey1OhOfhgvpUTBqeq9QvmGGt6Gp0H_sfcQ1XkJ0ZzgpIoUjRWPk8KV160S3DzDjSBW8qxImTBaJLZgEqs4LkimGaYWp0ZoTopEc6q4w7ITaJaL0pwCsm78FDaz3iw-tZaIwrBMKutltkrS4gxavjyzl40lxqyuzPnfty9gz_dA4M2RS2hWy7W5gl31Vs1Xy-vQj5_ox52J
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3LT8IwHG4QTdSLDzS-7cGjg67ruvYqATHCQgATbqTrIyEmQ2EY_e9ty0RNvHhblyxZft369fE9ALjhjNqvIqGBEUgHhJkoYDKk9sdjlDAZS4WUD5tI0pSNx7xfAbdrLYzW2pPPdN1d-rN8NZNLt1XW4JhZtIs3wGZMCA5Xaq31joqdfCSU4pLEFSLe6LeG9z3iPM3sQhCjevn8ryAVjyPtvf-9wT44-hbkwf4aag5AReeHYPeHl2ANDPsu7wy2XpdTTwGCgy9q0CyHPZ8TDR1kKejaYvEMB0EzTaHIFbwTH9qJKaH3qnovYLoihx-Bp3Zr1OwEZWJCMMUoKgJJQ8nCKLMFtusEO9OwY4gRLM5IwrXikckSgWQYZjhWCaIGEc0Vw1mkGJXMotkxqOazXJ8AaOwIyk1snF08MQbzTCexkMYJbaWg2SmoufJMXlamGJOyMmd_374G251RrzvpPqSP52DH9YZn0eELUC3mS30JtuRbMV3Mr3yffgJKxKDQ
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=proceeding&rft.title=IEEE+Power+%26+Energy+Society+General+Meeting&rft.atitle=Power+Equipment+Recognition+Method+based+on+Mask+R-CNN+and+Bayesian+Context+Network&rft.au=Siheng%2C+XIONG&rft.au=Yadong%2C+LIU&rft.au=Rui%2C+XU&rft.au=Ying%2C+DU&rft.date=2020-08-02&rft.pub=IEEE&rft.eissn=1944-9933&rft.spage=1&rft.epage=5&rft_id=info:doi/10.1109%2FPESGM41954.2020.9281755&rft.externalDocID=9281755