3D Scene Reconstruction Improvement Based on Image Enhancement with Conditional Adversarial Networks

Nowadays, the development of automatic driving technology is well-improved the object segmentation with the point cloud data, furthermore will build up the environment model with the color image. However, the analysis of color image will still face lots of bottlenecks. This paper proposed using a ge...

Full description

Saved in:
Bibliographic Details
Published in2018 IEEE 7th Global Conference on Consumer Electronics (GCCE) pp. 367 - 368
Main Authors Li, Yen-Ju, Cheng, Hao-Wen, Liu, Kai-Ting, Bai, Yun-Hao, Huang, Chun-Ju, Fan, Yu-Cheng
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.10.2018
Subjects
3D model reconstruction
image enhancement
neural network
Online AccessGet full text

Cover

Abstract Nowadays, the development of automatic driving technology is well-improved the object segmentation with the point cloud data, furthermore will build up the environment model with the color image. However, the analysis of color image will still face lots of bottlenecks. This paper proposed using a generative adversarial network to achieve intrinsic image decomposition faster and then applying a new interpolation algorithm to enhance the shadow layer to increase the contrast of color image. The results show that this method improved the accuracy and immediacy of the image enhancement, go a step further, improving the accuracy and immediacy of the environment reconstruction.
AbstractList Nowadays, the development of automatic driving technology is well-improved the object segmentation with the point cloud data, furthermore will build up the environment model with the color image. However, the analysis of color image will still face lots of bottlenecks. This paper proposed using a generative adversarial network to achieve intrinsic image decomposition faster and then applying a new interpolation algorithm to enhance the shadow layer to increase the contrast of color image. The results show that this method improved the accuracy and immediacy of the image enhancement, go a step further, improving the accuracy and immediacy of the environment reconstruction.
Author Huang, Chun-Ju
Cheng, Hao-Wen
Li, Yen-Ju
Bai, Yun-Hao
Liu, Kai-Ting
Fan, Yu-Cheng
Author_xml – sequence: 1
  givenname: Yen-Ju
  surname: Li
  fullname: Li, Yen-Ju
  organization: Department of Electronic Engineering, National Taipei University of Technology, Taipei, Taiwan
– sequence: 2
  givenname: Hao-Wen
  surname: Cheng
  fullname: Cheng, Hao-Wen
  organization: Department of Electronic Engineering, National Taipei University of Technology, Taipei, Taiwan
– sequence: 3
  givenname: Kai-Ting
  surname: Liu
  fullname: Liu, Kai-Ting
  organization: Department of Electronic Engineering, National Taipei University of Technology, Taipei, Taiwan
– sequence: 4
  givenname: Yun-Hao
  surname: Bai
  fullname: Bai, Yun-Hao
  organization: Department of Electronic Engineering, National Taipei University of Technology, Taipei, Taiwan
– sequence: 5
  givenname: Chun-Ju
  surname: Huang
  fullname: Huang, Chun-Ju
  organization: Department of Electronic Engineering, National Taipei University of Technology, Taipei, Taiwan
– sequence: 6
  givenname: Yu-Cheng
  surname: Fan
  fullname: Fan, Yu-Cheng
  organization: Department of Electronic Engineering, National Taipei University of Technology, Taipei, Taiwan
BookMark eNotkMlOwzAYhI0EElDyAIiLXyDBu51jCWmpVIHEcq4c5w81NE5lh1a8PUt7mtF8mjnMJToNQwCErikpKCXl7byq6oIRagojtZBUnaCs1IZKbpTipNTnKEvpgxDClOGGqgvU8nv84iAAfgY3hDTGLzf6IeBFv43DDnoII76zCVr8H9p3wHVY2-AOaO_HNa6G0Pq_lt3gabuDmGz0v_4Rxv0QP9MVOuvsJkF21Al6m9Wv1UO-fJovquky91TLMRfGSOpYqUkrmegkdNoK6xrpSg6WgBOOKyWBNkoq5iwXTpuO2g6arikl4xN0c9j1ALDaRt_b-L06fsF_AHzsV-0
ContentType Conference Proceeding
DBID 6IE
6IL
CBEJK
RIE
RIL
DOI 10.1109/GCCE.2018.8574516
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 Xplore
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 9781538663097
1538663082
1538663090
9781538663080
EndPage 368
ExternalDocumentID 8574516
Genre orig-research
GroupedDBID 6IE
6IF
6IL
6IN
AAJGR
ABLEC
ALMA_UNASSIGNED_HOLDINGS
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CBEJK
IEGSK
OCL
RIE
RIL
ID FETCH-LOGICAL-i175t-48851c2970d524f5ef7a4acb5c93ea0ec4c3665e1b6562ca34c78f1afebfb9523
IEDL.DBID RIE
IngestDate Thu Jun 29 18:39:25 EDT 2023
IsPeerReviewed false
IsScholarly false
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i175t-48851c2970d524f5ef7a4acb5c93ea0ec4c3665e1b6562ca34c78f1afebfb9523
PageCount 2
ParticipantIDs ieee_primary_8574516
PublicationCentury 2000
PublicationDate 2018-Oct.
PublicationDateYYYYMMDD 2018-10-01
PublicationDate_xml – month: 10
  year: 2018
  text: 2018-Oct.
PublicationDecade 2010
PublicationTitle 2018 IEEE 7th Global Conference on Consumer Electronics (GCCE)
PublicationTitleAbbrev GCCE
PublicationYear 2018
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0002683816
Score 1.7242496
Snippet Nowadays, the development of automatic driving technology is well-improved the object segmentation with the point cloud data, furthermore will build up the...
SourceID ieee
SourceType Publisher
StartPage 367
SubjectTerms 3D model reconstruction
image enhancement
neural network
Title 3D Scene Reconstruction Improvement Based on Image Enhancement with Conditional Adversarial Networks
URI https://ieeexplore.ieee.org/document/8574516
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV3NS8MwFA_bTp5UNvGbHDzarmmbNL06N4ewIehgt9EkLziETth22V_vS1I3FA_eSkpJea_N-73f-yLkjimJKCE1kRYI33LObKQqYSKJ4BUBgjTMOGpgMhXjWf485_MWud_XwgCATz6D2F36WL5Z6a2jyvqSF26ubJu0i7IMtVp7PiUV0sXAmsAlS8r-02AwdLlbMm6e-zFAxduP0TGZfO8c0kY-4u1GxXr3qynjf1_thPQOlXr0ZW-DTkkL6i4x2SN91XiIUedcHlrE0sAgeEKQPqD5MtQv4pFCh_W707-_5bhZihuYZSAKqZ_avK7ct0qnIW983SOz0fBtMI6aaQrREiHCJsI_lTOdlkVieJpbDrao8korrssMqgR0rjMhODDllKerLNeFtKyyoKwq0V89I516VcM5oamARBllpBUK3etSAlo4oTNZgLFKmAvSdRJafIaGGYtGOJd_L1-RI6elkCF3TTooFLhBS79Rt17FX3hgquA
link.rule.ids 310,311,783,787,792,793,799,27938,55087
linkProvider IEEE
linkToHtml http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV07T8MwED6VMsAEqEW88cBI0rzsOCulJUBbIdFK3ar4JSqkFKntwq_n7IRWIAa2yJHl6M7xfff5HgA3oeCIEiLlSYbwLaGh8UTBlMcRvCJA4CpUlhoYjlg-SZ6mdNqA200ujNbaBZ9p3z66u3y1kGtLlXU4TW1f2R3YRVzN0ypba8OoRIzbW7D66jIMss5Dt9uz0Vvcr2f-aKHiLEj_AIbfa1eBI-_-eiV8-fmrLON_P-4Q2ttcPfKysUJH0NBlC1R8T14lHmPEupfbIrGk4hAcJUju0IAp4gbxUCG98s3uAPfKsrMEF1Dziiokrm_zsrC7lYyqyPFlGyb93ribe3U_BW-OIGHl4b9KQxllaaBolBiqTVokhRRUZrEuAi0TGTNGdSis-mQRJzLlJiyMFkZk6LEeQ7NclPoESMR0IJRQ3DCBDnbGNdo4JmOeamUEU6fQshKafVQlM2a1cM7-Hr6GvXw8HMwGj6Pnc9i3Gqvi5S6giQLSl2j3V-LKqfsLlOWuLA
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=2018+IEEE+7th+Global+Conference+on+Consumer+Electronics+%28GCCE%29&rft.atitle=3D+Scene+Reconstruction+Improvement+Based+on+Image+Enhancement+with+Conditional+Adversarial+Networks&rft.au=Li%2C+Yen-Ju&rft.au=Cheng%2C+Hao-Wen&rft.au=Liu%2C+Kai-Ting&rft.au=Bai%2C+Yun-Hao&rft.date=2018-10-01&rft.pub=IEEE&rft.spage=367&rft.epage=368&rft_id=info:doi/10.1109%2FGCCE.2018.8574516&rft.externalDocID=8574516