Show simple item record

dc.contributor.authorXue, Tianfan
dc.contributor.authorRubinstein, Michael
dc.contributor.authorWadhwa, Neal
dc.contributor.authorLevin, Anat
dc.contributor.authorDurand, Fredo
dc.contributor.authorFreeman, William T.
dc.date.accessioned2015-11-24T13:10:48Z
dc.date.available2015-11-24T13:10:48Z
dc.date.issued2014
dc.identifier.isbn978-3-319-10577-2
dc.identifier.isbn978-3-319-10578-9
dc.identifier.issn0302-9743
dc.identifier.issn1611-3349
dc.identifier.urihttp://hdl.handle.net/1721.1/100013
dc.description.abstractWe present principled algorithms for measuring the velocity and 3D location of refractive fluids, such as hot air or gas, from natural videos with textured backgrounds. Our main observation is that intensity variations related to movements of refractive fluid elements, as observed by one or more video cameras, are consistent over small space-time volumes. We call these intensity variations “refraction wiggles”, and use them as features for tracking and stereo fusion to recover the fluid motion and depth from video sequences. We give algorithms for 1) measuring the (2D, projected) motion of refractive fluids in monocular videos, and 2) recovering the 3D position of points on the fluid from stereo cameras. Unlike pixel intensities, wiggles can be extremely subtle and cannot be known with the same level of confidence for all pixels, depending on factors such as background texture and physical properties of the fluid. We thus carefully model uncertainty in our algorithms for robust estimation of fluid motion and depth. We show results on controlled sequences, synthetic simulations, and natural videos. Different from previous approaches for measuring refractive flow, our methods operate directly on videos captured with ordinary cameras, do not require auxiliary sensors, light sources or designed backgrounds, and can correctly detect the motion and location of refractive fluids even when they are invisible to the naked eye.en_US
dc.description.sponsorshipShell Researchen_US
dc.description.sponsorshipMotion Sensing Wi-Fi Sensor Networks Co. (Grant 6925133)en_US
dc.description.sponsorshipNational Science Foundation (U.S.). Graduate Research Fellowship (Grant 1122374)en_US
dc.description.sponsorshipMicrosoft Research (PhD Fellowship)en_US
dc.language.isoen_US
dc.publisherSpringer-Verlagen_US
dc.relation.isversionofhttp://dx.doi.org/10.1007/978-3-319-10578-9_50en_US
dc.rightsCreative Commons Attribution-Noncommercial-Share Alikeen_US
dc.rights.urihttp://creativecommons.org/licenses/by-nc-sa/4.0/en_US
dc.sourceMIT web domainen_US
dc.titleRefraction Wiggles for Measuring Fluid Depth and Velocity from Videoen_US
dc.typeArticleen_US
dc.identifier.citationXue, Tianfan, Michael Rubinstein, Neal Wadhwa, Anat Levin, Fredo Durand, and William T. Freeman. “Refraction Wiggles for Measuring Fluid Depth and Velocity from Video.” Lecture Notes in Computer Science (2014): 767–782.en_US
dc.contributor.departmentMassachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratoryen_US
dc.contributor.departmentMassachusetts Institute of Technology. Department of Electrical Engineering and Computer Scienceen_US
dc.contributor.departmentMassachusetts Institute of Technology. Department of Mathematicsen_US
dc.contributor.mitauthorXue, Tianfanen_US
dc.contributor.mitauthorRubinstein, Michaelen_US
dc.contributor.mitauthorWadhwa, Nealen_US
dc.contributor.mitauthorDurand, Fredoen_US
dc.contributor.mitauthorFreeman, William T.en_US
dc.relation.journalComputer Vision – ECCV 2014en_US
dc.eprint.versionAuthor's final manuscripten_US
dc.type.urihttp://purl.org/eprint/type/ConferencePaperen_US
eprint.statushttp://purl.org/eprint/status/NonPeerRevieweden_US
dspace.orderedauthorsXue, Tianfan; Rubinstein, Michael; Wadhwa, Neal; Levin, Anat; Durand, Fredo; Freeman, William T.en_US
dc.identifier.orcidhttps://orcid.org/0000-0002-3707-3807
dc.identifier.orcidhttps://orcid.org/0000-0002-2902-6752
dc.identifier.orcidhttps://orcid.org/0000-0001-9919-069X
dc.identifier.orcidhttps://orcid.org/0000-0002-2231-7995
dc.identifier.orcidhttps://orcid.org/0000-0001-5031-6618
mit.licenseOPEN_ACCESS_POLICYen_US
mit.metadata.statusComplete


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record