3D model-based sematic labeling of 2D objects

Raluca Diana Petre, Titus Zaharia

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

This paper tackles the issue of still image object categorization. The objective is to infer the semantics of 2D objects present in natural images. The principle of the proposed approach consists of exploiting categorized 3D synthetic models in order to identify unknown 2D objects, based on 2D/3D matching techniques. Notably, we use 2D/3D shape indexing methods, where 3D models are described through a set of 2D views. Experimental results carried out on both MPEG-7 and Princeton 3D mesh test sets show recognition rates of up to 89%.

Original languageEnglish
Title of host publicationProceedings - 2011 International Conference on Digital Image Computing
Subtitle of host publicationTechniques and Applications, DICTA 2011
Pages152-157
Number of pages6
DOIs
Publication statusPublished - 1 Dec 2011
Externally publishedYes
Event2011 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2011 - Noosa, QLD, Australia
Duration: 6 Dec 20118 Dec 2011

Publication series

NameProceedings - 2011 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2011

Conference

Conference2011 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2011
Country/TerritoryAustralia
CityNoosa, QLD
Period6/12/118/12/11

Keywords

  • 2D/3D shape descriptors
  • 3D mesh
  • indexing and retrieval
  • object classification

Fingerprint

Dive into the research topics of '3D model-based sematic labeling of 2D objects'. Together they form a unique fingerprint.

Cite this