DocumentCode
2998481
Title
3D Model-Based Sematic Labeling of 2D Objects
Author
Petre, Raluca-Diana ; Zaharia, Titus
Author_Institution
ARTEMIS Dept., TELECOM SudParis, Evry, France
fYear
2011
fDate
6-8 Dec. 2011
Firstpage
152
Lastpage
157
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%.
Keywords
image matching; object detection; 2D matching techniques; 2D objects; 3D matching techniques; 3D model based sematic labeling; image object categorization; Image recognition; Indexing; Shape; Solid modeling; Three dimensional displays; Transform coding; 2D/3D shape descriptors; 3D mesh; indexing and retrieval; object classification;
fLanguage
English
Publisher
ieee
Conference_Titel
Digital Image Computing Techniques and Applications (DICTA), 2011 International Conference on
Conference_Location
Noosa, QLD
Print_ISBN
978-1-4577-2006-2
Type
conf
DOI
10.1109/DICTA.2011.32
Filename
6128674
Link To Document