Abstract: A method for estimating a motion field from a first image with a corresponding first shape to a second image with a corresponding second shape, wherein a hypothesis motion field is given and the motion fields have one motion vector for each valid pixel or valid block of pixels in the first image.

Abstract: A method and apparatus for indirect quantitative assessment or determination and modelling of the depth dimension of moving objects in signal streams where the depth information is not directly avaible, but where occlusion information can be derived.

Abstract: The present invention concerns improved motion estimation in signal records.

Abstract: The invention discloses an apparatus for decoding a video sequence, compressed according to a known data modeling method suitable for transmission or storage, into decompressed frames, suitable for viewing, the data model comprising a plurality of spatial intensity changes patterns, called intensity loads, a plurality of spatial address change patterns, called address loads, and a plurality of values, called scores, specifying for each frame how much of each load should be present. Each of the loads includes respective hardware components for storing and processing it. The respective components are connected in a pipeline consisting of parallel synchronous data paths, through which pipeline the intermediate image and motion field are continuously transmitted.