Show simple item record

The Smoothest Velocity Field and Token Matching

dc.date.accessioned2004-10-01T20:18:14Z
dc.date.accessioned2018-11-24T10:09:56Z
dc.date.available2004-10-01T20:18:14Z
dc.date.available2018-11-24T10:09:56Z
dc.date.issued1983-08-01en_US
dc.identifier.urihttp://hdl.handle.net/1721.1/5652
dc.identifier.urihttp://repository.aust.edu.ng/xmlui/handle/1721.1/5652
dc.description.abstractThis paper presents some mathematical results concerning the measurement of motion of contours. A fundamental problem of motion measurement in general is that the velocity field is not determined uniquely from the changing intensity patterns. Recently Hildreth & Ullman have studied a solution to this problem based on an Extremum Principle [Hildreth (1983), Ullman & Hildreth (1983)]. That is, they formulate the measurement of motion as the computation of the smoothest velocity field consistent with the changing contour. We analyse this Extremum principle and prove that it is closely related to a matching scheme for motion measurement which matches points on the moving contour that have similar tangent vectors. We then derive necessary and sufficient conditions for the principle to yield the correct velocity field. These results have possible implications for the design of computer vision systems, and for the study of human vision.en_US
dc.format.extent10 p.en_US
dc.format.extent1408443 bytes
dc.format.extent1077372 bytes
dc.language.isoen_US
dc.subjectmotion measurementen_US
dc.subjectvelocity fielden_US
dc.subjectoptical flowen_US
dc.subjectszero crossingsen_US
dc.subjectmotion perceptionen_US
dc.titleThe Smoothest Velocity Field and Token Matchingen_US


Files in this item

FilesSizeFormatView
AIM-724.pdf1.077Mbapplication/pdfView/Open
AIM-724.ps1.408Mbapplication/postscriptView/Open

This item appears in the following Collection(s)

Show simple item record