A joint 3D image semantic segmentation and scalable coding scheme with ROI approach

Along with the digital evolution, image post-production and indexing have become one of the most advanced and desired services in the lossless 3D image domain. The 3D context provides a significant gain in terms of semantics for scene representation. However, it also induces many drawbacks including...

Full description

Saved in:
Bibliographic Details
Published in:2014 IEEE Visual Communications and Image Processing Conference pp. 270 - 273
Main Authors: Samrouth, Khouloud, Deforges, Olivier, Yi Liu, Falou, Wassim, Khalil, Mohamad
Format: Conference Proceeding
Language:English
Published: IEEE 01.12.2014
Subjects:
3D scalable compression
Context
Image coding
Image color analysis
Image resolution
Image segmentation
RoI extraction and refinement
segmentation
Semantics
Three-dimensional displays
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract Along with the digital evolution, image post-production and indexing have become one of the most advanced and desired services in the lossless 3D image domain. The 3D context provides a significant gain in terms of semantics for scene representation. However, it also induces many drawbacks including monitoring visual degradation of compressed 3D image (especially upon edges), and increased complexity for scene representation. In this paper, we propose a semantic region representation and a scalable coding scheme. First, the semantic region representation scheme is based on a low resolution version of the 3D image. It provides the possibility to segment the image according to a desirable balance between 2D and depth. Second, the scalable coding scheme consists in selecting a number of regions as a Region of Interest (RoI), based on the region representation, in order to be refined at a higher bitrate. Experiments show that the proposed scheme provides a high coherence between texture, depth and regions and ensures an efficient solution to the problems of compression and scene representation in the 3D image domain.
AbstractList Along with the digital evolution, image post-production and indexing have become one of the most advanced and desired services in the lossless 3D image domain. The 3D context provides a significant gain in terms of semantics for scene representation. However, it also induces many drawbacks including monitoring visual degradation of compressed 3D image (especially upon edges), and increased complexity for scene representation. In this paper, we propose a semantic region representation and a scalable coding scheme. First, the semantic region representation scheme is based on a low resolution version of the 3D image. It provides the possibility to segment the image according to a desirable balance between 2D and depth. Second, the scalable coding scheme consists in selecting a number of regions as a Region of Interest (RoI), based on the region representation, in order to be refined at a higher bitrate. Experiments show that the proposed scheme provides a high coherence between texture, depth and regions and ensures an efficient solution to the problems of compression and scene representation in the 3D image domain.
Author Falou, Wassim
Khalil, Mohamad
Yi Liu
Deforges, Olivier
Samrouth, Khouloud
Author_xml – sequence: 1
  givenname: Khouloud
  surname: Samrouth
  fullname: Samrouth, Khouloud
  email: khouloud.samrouthI@insa-rennes.fr
  organization: IETR Lab., UEB, Rennes, France
– sequence: 2
  givenname: Olivier
  surname: Deforges
  fullname: Deforges, Olivier
  email: olivier.deforges@insa-rennes.fr
  organization: IETR Lab., UEB, Rennes, France
– sequence: 3
  surname: Yi Liu
  fullname: Yi Liu
  email: yi.liu@insa-rennes.fr
  organization: IETR Lab., UEB, Rennes, France
– sequence: 4
  givenname: Wassim
  surname: Falou
  fullname: Falou, Wassim
  email: wassim.falou@ul.edu.lb
  organization: LaSTRe, Lebanese Univ., Tripoli, Lebanon
– sequence: 5
  givenname: Mohamad
  surname: Khalil
  fullname: Khalil, Mohamad
  email: mohamad.khalil@ul.edu.lb
  organization: LaSTRe, Lebanese Univ., Tripoli, Lebanon
BookMark eNotj81KxDAUhSPowhl9AHGTF2jNbdOfuxzqX2FgxBG3Q5rctJE2LW1AfHsLM6tzvs3HORt27UdPjD2AiAEEPn1X9UecCJBxITLIsvyKbUAWiDmkmN-y447_jM4Hnj5zN6iW-EKD8sHptbQD-aCCGz1X3vBFq141PXE9GufblTsaiP-60PHPQ83VNM2j0t0du7GqX-j-klt2fH35qt6j_eGtrnb7yKEIUaMahLJIFKIFsGUmEFEIk-mVUtRSl6WlBI0AAKOLLDeCEiulslYmkG7Z49nqiOg0zev6-e90eZn-A3N_S1I
ContentType Conference Proceeding
DBID 6IE
6IL
CBEJK
RIE
RIL
DOI 10.1109/VCIP.2014.7051556
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 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 1479961396
9781479961399
EndPage 273
ExternalDocumentID 7051556
Genre orig-research
GroupedDBID 6IE
6IL
CBEJK
RIE
RIL
ID FETCH-LOGICAL-i90t-bab91872a99f11f85099900d5c11f39c4c88fe29d0111dc756d0e2f44aff4213
IEDL.DBID RIE
IngestDate Thu Jun 29 18:37:55 EDT 2023
IsPeerReviewed false
IsScholarly false
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i90t-bab91872a99f11f85099900d5c11f39c4c88fe29d0111dc756d0e2f44aff4213
PageCount 4
ParticipantIDs ieee_primary_7051556
PublicationCentury 2000
PublicationDate 2014-Dec.
PublicationDateYYYYMMDD 2014-12-01
PublicationDate_xml – month: 12
  year: 2014
  text: 2014-Dec.
PublicationDecade 2010
PublicationTitle 2014 IEEE Visual Communications and Image Processing Conference
PublicationTitleAbbrev VCIP
PublicationYear 2014
Publisher IEEE
Publisher_xml – name: IEEE
Score 1.5570438
Snippet Along with the digital evolution, image post-production and indexing have become one of the most advanced and desired services in the lossless 3D image domain....
SourceID ieee
SourceType Publisher
StartPage 270
SubjectTerms 3D scalable compression
Context
Image coding
Image color analysis
Image resolution
Image segmentation
RoI extraction and refinement
segmentation
Semantics
Three-dimensional displays
Title A joint 3D image semantic segmentation and scalable coding scheme with ROI approach
URI https://ieeexplore.ieee.org/document/7051556
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LSwMxEB7a4sGTSiu-ycGj2ybZ7GZzlKpYkFqsSG8lTWZ1hd2VduvvN9muFcGLt7xI4AvJTDLzzQBcRlwyrTAJJEcZCM0x0Bpp4IS7pYY5HRrrIK4PcjxOZjM1acHVlguDiLXzGfZ9sbbl29Ks_VfZQNYJSeI2tKWMN1ytxlDJqBq8DEcT76sl-s24XwlTanlxt_e_lfah90O8I5OtSDmAFhZdmF6T9zIrKhLekCx355-sMHeAZMYVXvOGPFQQXViycpB7MhQxpZ_B1d8wR-J_W8nT44h8hxDvwfTu9nl4HzS5EIJM0SpY6IViieRaqZSxNIm8YkepjYyrhcoIkyQpcmV96nhrZBRbijwVQqep4Cw8hE5RFngExMhYUuOULul6Qqq0cHelQiXVAv375Bi6Ho75xybYxbxB4uTv5lPY9Yhv_DvOoFMt13gOO-azylbLi3qHvgA-0pL2
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3PT8IwFH5BNNGTGjD-tgePDrqto-vRoAQiIhFiuJHSvulMthk2_Pttx8SYePHWX2mTr0nfa_u-9wFcBx53pcDQ4R5yh0kPHSmROsa4a6pc40NjmcR1yEejcDYT4xrcbLgwiFgGn2HLFsu_fJ2plX0qa_NSkKSzBdtWOatia1VflS4V7ZfuYGyjtVirGvlLMqW0GL39_611AM0f6h0Zb4zKIdQwbcDklrxncVoQ_47EiTkBSI6JgSRWpvCaVPShlMhUk9yAbulQRGV2BlN_wwSJfW8lz08D8p1EvAmT3v2023cqNQQnFrRwFnIh3JB7UojIdaMwsK4dpTpQpuYLxVQYRugJbcXjteJBR1P0IsZkFDHP9Y-gnmYpHgNRvMOpMm4XNz0-FZKZ01Kg4GKB9oZyAg0Lx_xjne5iXiFx-nfzFez2p4_D-XAwejiDPYv-OtrjHOrFcoUXsKM-izhfXpa79QUX-5Y_
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=2014+IEEE+Visual+Communications+and+Image+Processing+Conference&rft.atitle=A+joint+3D+image+semantic+segmentation+and+scalable+coding+scheme+with+ROI+approach&rft.au=Samrouth%2C+Khouloud&rft.au=Deforges%2C+Olivier&rft.au=Yi+Liu&rft.au=Falou%2C+Wassim&rft.date=2014-12-01&rft.pub=IEEE&rft.spage=270&rft.epage=273&rft_id=info:doi/10.1109%2FVCIP.2014.7051556&rft.externalDocID=7051556