English   español  
Please use this identifier to cite or link to this item: http://hdl.handle.net/10261/97514
Share/Impact:
Statistics
logo share SHARE   Add this article to your Mendeley library MendeleyBASE

Visualizar otros formatos: MARC | Dublin Core | RDF | ORE | MODS | METS | DIDL
Exportar a otros formatos:

Title

Efficient 3D object detection using multiple pose-specific classifiers

AuthorsVillamizar, Michael ; Grabner, Helmut; Moreno-Noguer, Francesc ; Andrade-Cetto, Juan ; Gool, Luc van; Sanfeliu, Alberto
Issue Date2011
PublisherBritish Machine Vision Association
CitationProceedings of the British Machine Vision Conference: 20.1-20.10 (2011)
AbstractWe propose an efficient method for object localization and 3D pose estimation. A two-step approach is used. In the first step, a pose estimator is evaluated in the input images in order to estimate potential object locations and poses. These candidates are then validated, in the second step, by the corresponding pose-specific classifier. The result is a detection approach that avoids the inherent and expensive cost of testing the complete set of specific classifiers over the entire image. A further speedup is achieved by feature sharing. Features are computed only once and are then used for evaluating the pose estimator and all specific classifiers. The proposed method has been validated on two public datasets for the problem of detecting of cars under several views. The results show that the proposed approach yields high detection rates while keeping efficiency.
DescriptionPresentado al 22nd BMVC celebrado en University of Dundee (Escocia) en septiembre de 2011.
Publisher version (URL)http://dx.doi.org/10.5244/C.25.20
URIhttp://hdl.handle.net/10261/97514
DOI10.5244/C.25.20
ISBN1-901725-43-X
Identifiersdoi: 10.5244/C.25.20
Appears in Collections:(IRII) Libros y partes de libros
Files in This Item:
File Description SizeFormat 
Efficient 3D Object.pdf2,26 MBUnknownView/Open
Show full item record
Review this work
 

Related articles:


WARNING: Items in Digital.CSIC are protected by copyright, with all rights reserved, unless otherwise indicated.