English   español  
Por favor, use este identificador para citar o enlazar a este item: http://hdl.handle.net/10261/127652
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:

LETHA: Learning from high quality inputs for 3D pose estimation in low quality images

AutorPeñate-Sánchez, Adrián; Moreno-Noguer, Francesc; Andrade-Cetto, Juan ; Fleuret, François
Palabras claveBoosting
Low resolution
Pose estimation
Fecha de publicación2014
EditorInstitute of Electrical and Electronics Engineers
CitaciónProceedings 2nd International Conference on 3D Vision: 517-524 (2014)
ResumenWe introduce LETHA (Learning on Easy data, Test on Hard), a new learning paradigm consisting of building strong priors from high quality training data, and combining them with discriminative machine learning to deal with low- quality test data. Our main contribution is an implementation of that concept for pose estimation. We first automatically build a 3D model of the object of interest from high-definition images, and devise from it a pose-indexed feature extraction scheme. We then train a single classifier to process these feature vectors. Given a low quality test image, we visit many hypothetical poses, extract features consistently and evaluate the response of the classifier. Since this process uses locations recorded during learning, it does not require matching points anymore. We use a boosting procedure to train this classifier common to all poses, which is able to deal with missing features, due in this context to self-occlusion. Our results demonstrate that the method combines the strengths of global image representations, discriminative even for very tiny images, and the robustness to occlusions of approaches based on local feature point descriptors.
DescripciónTrabajo presentado a la 2nd International Conference on 3D Vision (3DV), celebrada en Tokyo (Japón) del 8 al 11 de diciembre de 2014.
Versión del editorhttp://dx.doi.org/10.1109/3DV.2014.18
Identificadoresisbn: 978-1-4799-7001-8
Aparece en las colecciones: (IRII) Libros y partes de libros
Ficheros en este ítem:
Fichero Descripción Tamaño Formato  
LETHA.pdf8,02 MBAdobe PDFVista previa
Mostrar el registro completo

NOTA: Los ítems de Digital.CSIC están protegidos por copyright, con todos los derechos reservados, a menos que se indique lo contrario.