Show simple item record

dc.contributor.authorHaridasan, Radhakrishanen_US
dc.date.accessioned2007-05-23T10:04:54Z
dc.date.available2007-05-23T10:04:54Z
dc.date.issued1997en_US
dc.identifier.urihttp://hdl.handle.net/1903/5908
dc.description.abstractThe goal of motion-based segmentation is to partition the image into regions that have different characteristics or properties. The paper establishes feasibility of using computer vision algorithms for real-time segmentation and compression of motion video sequences. A convex formulation, using Huber's regularizer, in a robust estimation framework has significant advantages over previous approaches. Unlike previous techniques, our approach guarantees stable, repeatable (or reproducible) segmentations which make real-time applications in segmenting video possible. <BR>en_US
dc.format.extent206286 bytes
dc.format.mimetypeapplication/pdf
dc.language.isoen_USen_US
dc.relation.ispartofseriesISR; TR 1997-17en_US
dc.relation.ispartofseriesCSHCN; TR 1997-6en_US
dc.subjectoptical flowen_US
dc.subjectmotion-based image segmentation regulationen_US
dc.subjectrobust estimationen_US
dc.subjectobject-based video codingen_US
dc.subjectIntelligent Signal Processing en_US
dc.subjectCommunications Systemsen_US
dc.titleA Convex Model for the Robust Estimation of Optical Flow for, Motion-Based Image Segmentationen_US
dc.typeTechnical Reporten_US
dc.contributor.departmentISRen_US
dc.contributor.departmentCSHCNen_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record