English   español  
Por favor, use este identificador para citar o enlazar a este item: http://hdl.handle.net/10261/96350
Compartir / Impacto:
Estadísticas
Add this article to your Mendeley library MendeleyBASE
Citado 7 veces en Web of Knowledge®  |  Ver citas en Google académico
Visualizar otros formatos: MARC | Dublin Core | RDF | ORE | MODS | METS | DIDL
Exportar otros formatos: Exportar EndNote (RIS)Exportar EndNote (RIS)Exportar EndNote (RIS)
Título

Dense segmentation-aware descriptors

Autor Trulls, Eduard; Kokkinos, Iasonas; Sanfeliu, Alberto; Moreno-Noguer, Francesc
Fecha de publicación 2013
EditorInstitute of Electrical and Electronics Engineers
Citación IEEE Computer Society Conference on Computer Vision and Pattern Recognition: 2890-2897 (2013)
ResumenIn this work we exploit segmentation to construct appearance descriptors that can robustly deal with occlusion and background changes. For this, we downplay measurements coming from areas that are unlikely to belong to the same region as the descriptor¿s center, as suggested by soft segmentation masks. Our treatment is applicable to any image point, i.e. dense, and its computational overhead is in the order of a few seconds. We integrate this idea with Dense SIFT, and also with Dense Scale and Rotation Invariant Descriptors (SID), delivering descriptors that are densely computable, invariant to scaling and rotation, and robust to background changes. We apply our approach to standard benchmarks on large displacement motion estimation using SIFT-flow and widebaseline stereo, systematically demonstrating that the introduction of segmentation yields clear improvements.
Descripción Trabajo presentado al CVPR celebrado en Portland del 23 al 28 de junio de 2013.
Versión del editorhttp://dx.doi.org/10.1109/CVPR.2013.372
URI http://hdl.handle.net/10261/96350
DOI10.1109/CVPR.2013.372
Identificadoresdoi: 10.1109/CVPR.2013.372
issn: 1063-6919
Aparece en las colecciones: (IRII) Artículos
Ficheros en este ítem:
Fichero Descripción Tamaño Formato  
Dense segmentation-aware.pdf4,3 MBAdobe 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.