Bilinear interpolation algorithm based on gradient-weighted optimization

To address the problems of instantaneous field of view (IFoV) error and blurred details of infrared division of focal plane (DoFP) polarization images, this paper proposes a Bilinear interpolation algorithm based on gradient-weight optimization. The improvement of the algorithm mainly involves the f...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:2022 International Conference on Image Processing, Computer Vision and Machine Learning (ICICML) s. 634 - 639
Hlavní autori: Zhao, LinTong, Che, Kai, Lv, Jian, Zhou, Yun
Médium: Konferenčný príspevok..
Jazyk:English
Vydavateľské údaje: IEEE 28.10.2022
Predmet:
Bilinear interpolation
Correlation
division of focal plane polarization images
Image edge detection
Interpolation
Machine learning
Machine learning algorithms
Polarization
real-time
Real-time systems
the degree of polarization
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Abstract To address the problems of instantaneous field of view (IFoV) error and blurred details of infrared division of focal plane (DoFP) polarization images, this paper proposes a Bilinear interpolation algorithm based on gradient-weight optimization. The improvement of the algorithm mainly involves the following aspects: (1) the interpolation image pixels are extended for the characteristics of infrared DoFP polarization images, and the gradient correlation between the image elements is effectively used, to improve the interpolation accuracy; (2) the weighting factor is introduced to reconstruct the image pixels with weighting ratios, which improves the self-adaptive ability of the algorithm. The experimental results show that the algorithm in this paper effectively solves the problem of IFoV error of infrared polarization images, significantly enhances the contrast and sharpness of the degree of polarization images and meet the real-time hardware processing requirements. Experimental results showed that the PSNR of light intensity image increased by 4.4949dB, 3.5762dB and 1.5059dB compared with Nearest, Bilinear and Bicubic algorithms; the PSNR of the degree of polarization image by improved interpolation algorithm in this paper was increased by 2.3652dB, 2.2304dB and 2.0945dB, and the SSIM was increased by 0.0824, 0.1131 and 0.0881, compared with the Nearest, Bilinear and Bicubic algorithms; the operation speed of polarization image by improved interpolation algorithm in this paper was increased by 19.57fps and 21.68fps compared with Bicubic convolution and Gaussian interpolation algorithms.
AbstractList To address the problems of instantaneous field of view (IFoV) error and blurred details of infrared division of focal plane (DoFP) polarization images, this paper proposes a Bilinear interpolation algorithm based on gradient-weight optimization. The improvement of the algorithm mainly involves the following aspects: (1) the interpolation image pixels are extended for the characteristics of infrared DoFP polarization images, and the gradient correlation between the image elements is effectively used, to improve the interpolation accuracy; (2) the weighting factor is introduced to reconstruct the image pixels with weighting ratios, which improves the self-adaptive ability of the algorithm. The experimental results show that the algorithm in this paper effectively solves the problem of IFoV error of infrared polarization images, significantly enhances the contrast and sharpness of the degree of polarization images and meet the real-time hardware processing requirements. Experimental results showed that the PSNR of light intensity image increased by 4.4949dB, 3.5762dB and 1.5059dB compared with Nearest, Bilinear and Bicubic algorithms; the PSNR of the degree of polarization image by improved interpolation algorithm in this paper was increased by 2.3652dB, 2.2304dB and 2.0945dB, and the SSIM was increased by 0.0824, 0.1131 and 0.0881, compared with the Nearest, Bilinear and Bicubic algorithms; the operation speed of polarization image by improved interpolation algorithm in this paper was increased by 19.57fps and 21.68fps compared with Bicubic convolution and Gaussian interpolation algorithms.
Author Che, Kai
Zhao, LinTong
Zhou, Yun
Lv, Jian
Author_xml – sequence: 1
  givenname: LinTong
  surname: Zhao
  fullname: Zhao, LinTong
  email: 2895402884@qq.com
  organization: University of Electronic Science and Technology of China,College of Optoelectronic Science and Engineering,Chengdu,China
– sequence: 2
  givenname: Kai
  surname: Che
  fullname: Che, Kai
  email: kaicheyc@163.com
  organization: University of Electronic Science and Technology of China,College of Optoelectronic Science and Engineering,Chengdu,China
– sequence: 3
  givenname: Jian
  surname: Lv
  fullname: Lv, Jian
  email: lvjian@uestc.edu.cn
  organization: University of Electronic Science and Technology of China,College of Optoelectronic Science and Engineering,Chengdu,China
– sequence: 4
  givenname: Yun
  surname: Zhou
  fullname: Zhou, Yun
  email: 175875284@qq.com
  organization: University of Electronic Science and Technology of China,College of Optoelectronic Science and Engineering,Chengdu,China
BookMark eNo1z81KxDAUBeAIutBx3sBFfYDW3Ns0aZZa1ClUZjOuhySNnQttWjIB0ad3_Fsd-OAcOFfsPMzBM3YLvADg-q5t2ualq1QpsECOWADnXKuKn7G1VjVIWQkpZM0v2eaBRgrexIxC8nGZR5NoDpkZhzlSOkyZNUffZycaounJh5S_exoO6RuXRBN9_jSu2cWbGY9-_Zcr9vr0uGs2ebd9bpv7LicoRcqtU4AoK-XAGUSvBQjHuZKobK9roUGd1DpTy9oI3Tu0ViJaEKCF7EW5Yje_u-S93y-RJhM_9v8Hyy8sGku2
ContentType Conference Proceeding
DBID 6IE
6IL
CBEJK
RIE
RIL
DOI 10.1109/ICICML57342.2022.10009750
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Xplore POP ALL
IEEE Xplore All Conference Proceedings
IEEE Electronic Library (IEL)
IEEE Proceedings Order Plans (POP All) 1998-Present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
EISBN 9781665464680
1665464682
EndPage 639
ExternalDocumentID 10009750
Genre orig-research
GrantInformation_xml – fundername: Chinese Academy of Sciences
  funderid: 10.13039/501100002367
GroupedDBID 6IE
6IL
CBEJK
RIE
RIL
ID FETCH-LOGICAL-i134t-bc7122657c1ca22e9414c007627bd98491722ebca868a49dc2bb622b141946d43
IEDL.DBID RIE
ISICitedReferencesCount 1
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000932798900117&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
IngestDate Thu Jan 18 11:14:36 EST 2024
IsPeerReviewed false
IsScholarly false
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i134t-bc7122657c1ca22e9414c007627bd98491722ebca868a49dc2bb622b141946d43
PageCount 6
ParticipantIDs ieee_primary_10009750
PublicationCentury 2000
PublicationDate 2022-Oct.-28
PublicationDateYYYYMMDD 2022-10-28
PublicationDate_xml – month: 10
  year: 2022
  text: 2022-Oct.-28
  day: 28
PublicationDecade 2020
PublicationTitle 2022 International Conference on Image Processing, Computer Vision and Machine Learning (ICICML)
PublicationTitleAbbrev ICICML
PublicationYear 2022
Publisher IEEE
Publisher_xml – name: IEEE
Score 1.8185059
Snippet To address the problems of instantaneous field of view (IFoV) error and blurred details of infrared division of focal plane (DoFP) polarization images, this...
SourceID ieee
SourceType Publisher
StartPage 634
SubjectTerms Bilinear interpolation
Correlation
division of focal plane polarization images
Image edge detection
Interpolation
Machine learning
Machine learning algorithms
Polarization
real-time
Real-time systems
the degree of polarization
Title Bilinear interpolation algorithm based on gradient-weighted optimization
URI https://ieeexplore.ieee.org/document/10009750
WOSCitedRecordID wos000932798900117&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/eLvHCXMwlV1LSwMxEA5aRDypuOKbFbym3WSnm-zVYmmhlh5Ueit5jHXBtrJu9e-bZLeKBw9CDuEjEJjAvDLfDCE3SWpS4RYFlQAFZyKp0hlSIxTLnpVOeZix9DQS47GcTvNJQ1YPXBhEDMVn2Pbb8JdvV2btU2UdFmgHPkLfFiKryVq75Lrpm9kZ9oa9-1FXpOAZVpy3N-d_TU4JhqO__88rD0j0Q8GLJ9_G5ZBs4fKIDG4L7xWqMi7q8Vh1IVusXucrF-S_LGJvlGzsoHkZarkq-hlynx50ymHRsC4j8ti_e-gNaDMKgRYshYpqI5hzlLrCMKM4xxwYGP-LxoW2uQQXdDlUGyUzqSC3hmudca4ZsBwyC-kxaS1XSzwhMUPleTtCokVw_oRKrOJS5wg-tLLylEReDLO3utvFbCOBsz_wc7Lnhe31OZcXpFWVa7wkO-ajKt7Lq_BGX2Ozk6Y
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LSwMxEA5SRT2pWPHtCl7TbrLTTfZqsbS4LT1U6a3kZV1ou7Ju9e-bZLeKBw9CDuGDEJjAvDLfDEJ3YaQiZhcGEQIGayKxkLHBigkSvwgZUT9j6TlloxGfTpNxTVb3XBhjjC8-My239X_5OldrlyprE087cBH6dgeAhhVdaxfd1p0z24PuoDtMOywCx7GitLU58Wt2ijcdvYN_XnqImj8kvGD8bV6O0JZZHaP-feb8QlEEWTUgqyplC8Rintsw_3UZOLOkAwvNC1_NVeJPn_10oFUPy5p32URPvYdJt4_rYQg4IxGUWCpGrKvUYYooQalJgIBy_2iUSZ1wsGGXRaUSPOYCEq2olDGlkgBJINYQnaDGKl-ZUxQQIxxzh3GjDViPQoRaUC4TAy640vwMNZ0YZm9Vv4vZRgLnf-A3aK8_GaazdDB6vED7TvBOu1N-iRplsTZXaEd9lNl7ce3f6wtCW5bt
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=2022+International+Conference+on+Image+Processing%2C+Computer+Vision+and+Machine+Learning+%28ICICML%29&rft.atitle=Bilinear+interpolation+algorithm+based+on+gradient-weighted+optimization&rft.au=Zhao%2C+LinTong&rft.au=Che%2C+Kai&rft.au=Lv%2C+Jian&rft.au=Zhou%2C+Yun&rft.date=2022-10-28&rft.pub=IEEE&rft.spage=634&rft.epage=639&rft_id=info:doi/10.1109%2FICICML57342.2022.10009750&rft.externalDocID=10009750