Variable bandwidth QMDPE and its application in robust optic flow estimation

Simple item page
dc.contributor.authorWang, H.
dc.contributor.authorSuter, D.
dc.contributor.conferenceIEEE International Conference on Computer Vision (9th : 2003 : Nice, France)
dc.date.issued2003
dc.description.abstractRobust estimators, such as least median of squared (LMedS) residuals, M-estimators, the least trimmed squares (LTS) etc., have been employed to estimate optical flow from image sequences in recent years. However, these robust estimators have a breakdown point of no more than 50%. We propose a novel robust estimator, called variable bandwidth quick maximum density power estimator (vbQMDPE), which can tolerate more than 50% outliers. We apply the novel proposed estimator to robust optical flow estimation. Our method yields better results than most other recently proposed methods, and it has the potential to better handle multiple motion effects.
dc.description.statementofresponsibilityHanzi Wang and David Suter
dc.description.urihttp://dx.doi.org/10.1109/ICCV.2003.1238337
dc.identifier.citation9th IEEE International Conference on Computer Vision (ICCV) 2003: pp.178-183
dc.identifier.doi10.1109/iccv.2003.1238337
dc.identifier.isbn0769519504
dc.identifier.orcidSuter, D. [0000-0001-6306-3023]
dc.identifier.urihttp://hdl.handle.net/2440/55409
dc.language.isoen
dc.publisherIEEE
dc.publisher.placeOnline
dc.source.urihttp://dx.doi.org/10.1109/iccv.2003.1238337
dc.titleVariable bandwidth QMDPE and its application in robust optic flow estimation
dc.typeConference paper
pubs.publication-statusPublished

Files

Collections

Computer Science publications