Visual Privacy Protection Method Based on YOLOv8 and ControlNet

To achieve a balance between visual privacy protection and visual information integrity, we propose a visual privacy protection method based on YOLOv8 and ControlNet. In the privacy recognition process, we realize the targeted selection of redrawing area by recognizing privacy features and effective...

Full description

Saved in:
Bibliographic Details
Published in2024 5th International Conference on Computer Vision, Image and Deep Learning (CVIDL) pp. 1023 - 1029
Main Authors Li, Kesong, Yang, Guanci
Format Conference Proceeding
LanguageEnglish
Published IEEE 19.04.2024
Subjects
Accuracy
Computational modeling
ControlNet
Data privacy
Diffusion models
Privacy
Stable diffusion
Target recognition
Visualization
YOLOv8
Online AccessGet full text

Cover

Abstract To achieve a balance between visual privacy protection and visual information integrity, we propose a visual privacy protection method based on YOLOv8 and ControlNet. In the privacy recognition process, we realize the targeted selection of redrawing area by recognizing privacy features and effectively segmenting the people and backgrounds that leak privacy. In the privacy preservation process, individuals undergo virtual dressing through the ControlNet-guided Stable Diffusion model, resulting in visually protected images. Empirical studies demonstrate promising results, with an average accuracy of 94.7 \% in privacy identification. Additionally, the average Structural Similarity Index (SSIM) value between privacy-protected images and original images stands at 0.843
AbstractList To achieve a balance between visual privacy protection and visual information integrity, we propose a visual privacy protection method based on YOLOv8 and ControlNet. In the privacy recognition process, we realize the targeted selection of redrawing area by recognizing privacy features and effectively segmenting the people and backgrounds that leak privacy. In the privacy preservation process, individuals undergo virtual dressing through the ControlNet-guided Stable Diffusion model, resulting in visually protected images. Empirical studies demonstrate promising results, with an average accuracy of 94.7 \% in privacy identification. Additionally, the average Structural Similarity Index (SSIM) value between privacy-protected images and original images stands at 0.843
Author Yang, Guanci
Li, Kesong
Author_xml – sequence: 1
  givenname: Kesong
  surname: Li
  fullname: Li, Kesong
  organization: Guizhou University,Key Laboratory of Advanced Manufacturing Technology of the Ministry of Education,Guiyang,China
– sequence: 2
  givenname: Guanci
  surname: Yang
  fullname: Yang, Guanci
  email: gcyang@gzu.edu.cn
  organization: Guizhou University,Key Laboratory of Advanced Manufacturing Technology of the Ministry of Education,Guiyang,China
BookMark eNqFjb0KwjAYACPo4E_fwCEvYM1PbdNJsCoK1TpIwamE9hMDNZE0Fvr2dtDZ6ThuuAkaaqMBIUyJTymJl0l-3KYho0HkM8ICn5KQBIyJAfLiKBZ8RXjEBSNjtM5V85Y1vljVyrLraRyUThmNT-AepsIb2UCFe79ladYKLHWFE6OdNfUZ3AyN7rJuwPtyiub73TU5LBQAFC-rntJ2xe_P_-QP_iQ4Xg
ContentType Conference Proceeding
DBID 6IE
6IL
CBEJK
RIE
RIL
DOI 10.1109/CVIDL62147.2024.10604228
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume
IEEE Xplore All Conference Proceedings
IEEE/IET Electronic Library
IEEE Proceedings Order Plans (POP All) 1998-Present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Xplore
  url: https://proxy.k.utb.cz/login?url=https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
EISBN 9798350373820
EndPage 1029
ExternalDocumentID 10604228
Genre orig-research
GrantInformation_xml – fundername: National Natural Science Foundation of China
  funderid: 10.13039/501100001809
GroupedDBID 6IE
6IL
CBEJK
RIE
RIL
ID FETCH-ieee_primary_106042283
IEDL.DBID RIE
IngestDate Wed Jul 31 06:02:00 EDT 2024
IsPeerReviewed false
IsScholarly false
Language English
LinkModel DirectLink
MergedId FETCHMERGED-ieee_primary_106042283
ParticipantIDs ieee_primary_10604228
PublicationCentury 2000
PublicationDate 2024-April-19
PublicationDateYYYYMMDD 2024-04-19
PublicationDate_xml – month: 04
  year: 2024
  text: 2024-April-19
  day: 19
PublicationDecade 2020
PublicationTitle 2024 5th International Conference on Computer Vision, Image and Deep Learning (CVIDL)
PublicationTitleAbbrev CVIDL
PublicationYear 2024
Publisher IEEE
Publisher_xml – name: IEEE
Score 3.836379
Snippet To achieve a balance between visual privacy protection and visual information integrity, we propose a visual privacy protection method based on YOLOv8 and...
SourceID ieee
SourceType Publisher
StartPage 1023
SubjectTerms Accuracy
Computational modeling
ControlNet
Data privacy
Diffusion models
Privacy
Stable diffusion
Target recognition
Visualization
YOLOv8
Title Visual Privacy Protection Method Based on YOLOv8 and ControlNet
URI https://ieeexplore.ieee.org/document/10604228
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV3dS8NADA9uTz6pOPFjyj342tqP2-36JFgdU7bOBx3zaVyvKQylG9oO9K83d7WKouDbfYRLCISQyy8JwKmXKxX1c-1IxT2Hoy8cKVSPQhVB9GGa-dpkdMeJGN7zm1lv9lGsbmthENGCz9A1S5vLz5a6Ml9lZOHCtqxqQUt6QV2s1aBzvOgsnl5fjoQZvENxX8Ddhvzb4BTrNwZbkDQca7jIo1uVqavffjRj_LdI29D5KtFjt5_OZwc2sNiF8-nipVJPdLFYK_1qCEoLtSrY2E6KZhfktDJG-4fJaLKWTBUZi2u0eoJlB7qDq7t46BgJ5qu6EcW8YR7uQbtYFrhPulA8JSNVoY-SKxP8KUTel6jJMIM8P4DOr08c_nF-BJtGlyZ_4kddaJfPFR6TGy7TE6v-d0ArjCo
link.rule.ids 310,311,786,790,795,796,802,27958,55109
linkProvider IEEE
linkToHtml http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV3NS8MwFH_oPOhJxYofU3Pw2tquWdaeBKuj07bzMMc8lTR9haF0ou1A_3qT1CqKgrd8JyQ8fry833sP4NQuOPcHhTA9Tm2TosNMj_G-VFWYHO9muSOURTdOWHhHr2f92YezuvaFQURNPkNLFbUtP1-IWn2VSQlnOmTVKqxJoLf9xl2r5efY_lkwHV1GTKXekZpfj1rthG-pUzRyDDchafdsCCMPVl1llnj7EY7x34faAuPLSY_cfsLPNqxguQPn0_lLzR9lx3zJxasaUGmyVUlinSuaXEjYyoms34-j8dIjvMxJ0PDVE6wM6A6vJkFoqhOkT00oirTd3N2FTrkocU_eBaeZFFPuOuhRrtQ_jkgHHgopmr2i2Afj1yUO_mg_gfVwEkdpNEpuDmFD3auypjh-FzrVc41HEpSr7Fg_xTvXC4-A
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%3Abook&rft.genre=proceeding&rft.title=2024+5th+International+Conference+on+Computer+Vision%2C+Image+and+Deep+Learning+%28CVIDL%29&rft.atitle=Visual+Privacy+Protection+Method+Based+on+YOLOv8+and+ControlNet&rft.au=Li%2C+Kesong&rft.au=Yang%2C+Guanci&rft.date=2024-04-19&rft.pub=IEEE&rft.spage=1023&rft.epage=1029&rft_id=info:doi/10.1109%2FCVIDL62147.2024.10604228&rft.externalDocID=10604228