Carregant...
Carregant...

Vés al contingut (premeu Retorn)

DaLI: deformation and light invariant descriptor

Autor
Simo, E.; Torras, C.; Moreno-Noguer, F.
Tipus d'activitat
Article en revista
Revista
International journal of computer vision
Data de publicació
2015-11-01
Volum
115
Número
2
Pàgina inicial
136
Pàgina final
154
DOI
https://doi.org/10.1007/s11263-015-0805-1 Obrir en finestra nova
Projecte finançador
IntellAct: Intelligent observation and execution of Actions and manipulations
Perception and Action in Robotics Problems with Large State Spaces DPI2011-27510 National Project
Visual Sense, Tagging visual data with semantic descriptions PCIN-2013-047
Repositori
http://hdl.handle.net/2117/83179 Obrir en finestra nova
http://www.iri.upc.edu/files/scidoc/1657-DaLI:-Deformation-and-Light-Invariant-Descriptor.pdf Obrir en finestra nova
URL
http://link.springer.com/article/10.1007/s11263-015-0805-1 Obrir en finestra nova
Resum
Recent advances in 3D shape analysis and recognition have shown that heat diffusion theory can be effectively used to describe local features of deforming and scaling surfaces. In this paper, we show how this description can be used to characterize 2D image patches, and introduce DaLI, a novel feature point descriptor with high resilience to non-rigid image transformations and illumination changes. In order to build the descriptor, 2D image patches are initially treated as 3D surfaces. Patches a...
Citació
Simo, E., Torras, C., Moreno-Noguer, F. DaLI: deformation and light invariant descriptor. "International journal of computer vision", 01 Novembre 2015, vol. 115, núm. 2, p. 136-154.
Paraules clau
Deformation and illumination invariance, Diffusion equation, Features, Framework, Heat kernel descriptors, Local image descriptors, Recognition, Segmentation, Surfaces, image
Grup de recerca
ROBiri - Grup de Robòtica de l'IRI

Participants