English   español  
Por favor, use este identificador para citar o enlazar a este item: http://hdl.handle.net/10261/133039
Compartir / Impacto:
Estadísticas
Add this article to your Mendeley library MendeleyBASE
Visualizar otros formatos: MARC | Dublin Core | RDF | ORE | MODS | METS | DIDL
Título

Dense segmentation-aware descriptors

AutorTrulls, Eduard; Kokkinos, Iasonas; Sanfeliu, Alberto; Moreno-Noguer, Francesc
Fecha de publicación2016
EditorSpringer
CitaciónDense Image Correspondences for Computer Vision: 83-107 (2016)
ResumenDense descriptors are becoming increasingly popular in a host of tasks, such as dense image correspondence, bag-of-words image classification, and label transfer. However, the extraction of descriptors on generic image points, rather than selecting geometric features, requires rethinking how to achieve invariance to nuisance parameters. In this work we pursue invariance to occlusions and background changes by introducing segmentation information within dense feature construction. The core idea is to use the segmentation cues to downplay the features coming from image areas that are unlikely to belong to the same region as the feature point. We show how to integrate this idea with dense SIFT, as well as with the dense scale- and rotation-invariant descriptor (SID). We thereby deliver dense descriptors that are invariant to background changes, rotation, and/or scaling. We explore the merit of our technique in conjunction with large displacement motion estimation and wide-baseline stereo, and demonstrate that exploiting segmentation information yields clear improvements.
DescripciónCapítulo 1.
Versión del editorhttp://dx.doi.org/10.1007/978-3-319-23048-1_5
URIhttp://hdl.handle.net/10261/133039
DOI10.1007/978-3-319-23048-1_5
ISBN978-3-319-23047-4
Aparece en las colecciones: (IRII) Libros y partes de libros
Ficheros en este ítem:
Fichero Descripción Tamaño Formato  
accesoRestringido.pdf15,38 kBAdobe PDFVista previa
Visualizar/Abrir
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.