Show simple item record

dc.contributor.authorHuttenlocher, Daniel P.en_US
dc.contributor.authorNoh, Jae J.en_US
dc.contributor.authorRucklidge, William J.en_US
dc.description.abstractWe consider the problem of tracking non-rigid objects moving in a complex scene. We describe a model-based tracking method, in which two-dimensional geometric models are used to localize an object in each frame of an image sequence. The basic idea is to decompose the image of a solid object moving in space into two components: a two-dimensional motion and a two-dimensional shape change. The motion component is factored out, and the shape change is represented by explicitly storing a sequence of two-dimensional models, one corresponding to each image frame. The major assumption underlying the method is that the two-dimensional shape of an object will change slowly from one frame to the next. There is no assumption, however, that the two-dimensional image motion in successive frames will be small. Thus, the method can track objects that move arbitrarily far in the image from one frame to the next.en_US
dc.format.extent5777458 bytes
dc.format.extent2909379 bytes
dc.format.extent4354761 bytes
dc.publisherCornell Universityen_US
dc.subjectcomputer scienceen_US
dc.subjecttechnical reporten_US
dc.titleTracking Non-Rigid Objects in Complex Scenesen_US
dc.typetechnical reporten_US

Files in this item


This item appears in the following Collection(s)

Show simple item record