Identificador persistente para citar o vincular este elemento: http://hdl.handle.net/10553/72522
Título: Complementary optic flow
Autores/as: Zimmer, Henning
Bruhn, Andres
Weickert, Joachim
Valgaerts, Levi
Salgado De la Nuez, Agustín 
Rosenhahn, Bodo
Seidel, Hans-Peter
Clasificación UNESCO: 120304 Inteligencia artificial
Palabras clave: Computation
Motion
Fecha de publicación: 2009
Publicación seriada: Lecture Notes in Computer Science 
Conferencia: 7th International Conference on Energy Minimization Methods in Computer Vision and Pattern Recognition 
Resumen: We introduce the concept of complementarity between data and smoothness term in modern variational optic flow methods. First we design a sophisticated data term that incorporates HSV colour representation with higher order constancy assumptions, completely separate robust penalisation, and constraint normalisation. Our anisotropic smoothness term reduces smoothing in the data constraint direction instead of the image edge direction, while enforcing a strong filling-in effect orthogonal to it. This allows optimal complementarity between both terms and avoids undesirable interference. The high quality of our complementary optic flow (COF) approach is demonstrated by the current top ranking result at the Middlebury benchmark.
URI: http://hdl.handle.net/10553/72522
ISBN: 978-3-642-03640-8
ISSN: 0302-9743
DOI: 10.1007/978-3-642-03641-5_16
Fuente: Cremers D., Boykov Y., Blake A., Schmidt F.R. (eds), Energy Minimization Methods In Computer Vision And Pattern Recognition, Proceedings [ISSN 0302-9743], v. 5681, p. 207-220, (2009)
Colección:Actas de congresos
Vista completa

Google ScholarTM

Verifica

Altmetric


Comparte



Exporta metadatos



Los elementos en ULPGC accedaCRIS están protegidos por derechos de autor con todos los derechos reservados, a menos que se indique lo contrario.