Show simple item record

dc.contributor.authorRoss, Michael G.
dc.contributor.authorKaelbling, Leslie P.
dc.date.accessioned2003-12-13T20:13:43Z
dc.date.available2003-12-13T20:13:43Z
dc.date.issued2004-01
dc.identifier.urihttp://hdl.handle.net/1721.1/3870
dc.description.abstractThis paper describes the initial results of a project to create a self-supervised algorithm for learning object segmentation from video data. Developmental psychology and computational experience have demonstrated that the motion segmentation of objects is a simpler, more primitive process than the detection of object boundaries by static image cues. Therefore, motion information provides a plausible supervision signal for learning the static boundary detection task and for evaluating performance on a test set. A video camera and previously developed background subtraction algorithms can automatically produce a large database of motion-segmented images for minimal cost. The purpose of this work is to use the information in such a database to learn how to detect the object boundaries in novel images using static information, such as color, texture, and shape.en
dc.description.sponsorshipSingapore-MIT Alliance (SMA)en
dc.format.extent1234090 bytes
dc.format.mimetypeapplication/pdf
dc.language.isoen_US
dc.relation.ispartofseriesComputer Science (CS);
dc.subjectmachine learningen
dc.subjectself-supervised algorithmen
dc.subjectmotion segmentationen
dc.subjectobject boundary detectionen
dc.titleLearning object boundary detection from motion dataen
dc.typeArticleen


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record