专利名称：Methods and systems for motion estimation
with nonlinear motion-field smoothing
发明人：Petrus J. L. Van Beek申请号：US12554809申请日：20090904公开号：US08711938B2公开日：20140429
专利附图：
摘要：Aspects of the present invention are related to low complexity systems andmethods for nonlinear diffusion filtering of a motion-vector field. Local weights in thenonlinear diffusion filter may be data-adaptive, and, according to one aspect of the
present invention, may be determined such that spatial coherency may not be enforcedat object boundaries although the object boundaries have not been explicitly detected.Thus, the methods and systems of the present invention may smooth a motion-vectorfield without smoothing the motion-vector field across an object boundary. According toa second aspect of the present invention, motion vectors with a low confidence value maybe suppressed, while motion vectors with a high confidence value may be propagated.According to another aspect of the present invention, motion estimation methods andsystems may incorporate the methods and systems of the nonlinear diffusion filteringaccording to the present invention.
申请人：Petrus J. L. Van Beek
地址：Camas WA US
国籍：US
代理人：Kristine Elizabeth Matthews,David C. Ripma
更多信息请下载全文后查看
因篇幅问题不能全部显示，请点此查看更多更全内容