Identificador persistente para citar o vincular este elemento: http://hdl.handle.net/10553/15973
Título: Regularization strategies for discontinuity-preserving optical flow methods
Autores/as: Monzon, Nelson 
Salgado De La Nuez, Agustín 
Sanchez, Javier 
Clasificación UNESCO: 220990 Tratamiento digital. Imágenes
Palabras clave: Optical Flow
Discontinuity-preserving
Matrix-value Diffusion
Fecha de publicación: 2016
Publicación seriada: IEEE Transactions on Image Processing 
Resumen: The aim of this work is to study several strategies for the preservation of flow discontinuities in variational optical flow methods. We analyze the combination of robust functionals and diffusion tensors in the smoothness assumption. Our study includes the use of tensors based on decreasing functions, which has shown to provide good results. However, it presents several limitations and usually does not perform better than other basic approaches. It typically introduces instabilities in the computed motion fields in the form of independent \\\\textit{blobs} of vectors with large magnitude...
URI: http://hdl.handle.net/10553/15973
ISSN: 1057-7149
DOI: 10.1109/TIP.2016.2526903
Fuente: IEEE Transactions on Image Processing [ISSN 1057-7149],v. 25 (7401084), p. 1580-1591
Colección:Artículos
miniatura
Adobe PDF (9,22 MB)
Vista completa

Citas SCOPUSTM   

33
actualizado el 14-abr-2024

Citas de WEB OF SCIENCETM
Citations

28
actualizado el 25-feb-2024

Visitas

96
actualizado el 13-abr-2024

Descargas

324
actualizado el 13-abr-2024

Google ScholarTM

Verifica

Altmetric


Comparte



Exporta metadatos



Este elemento está sujeto a una licencia Licencia Creative Commons Creative Commons