Abstract: A system and method is presented that segregates portions of a video file into distinct sections based on whether the sections contain original content or modified content. For each segment, portion, section or scene with modified content, a compressed file is created which includes at least one instance of a set of frames which includes modified content. For some sections there may be two or more versions of modifications. These alternative versions may be compressed as a single distinct file. This permits efficient edge caching of video files with modified content, for example for selective provision of alternative versions of the video file to various end users in a transmission efficient manner.

Abstract: A system and method is presented that segregates portions of a video file into distinct sections based on whether the sections contain original content or modified content. For each segment, portion, section or scene with modified content, a compressed file is created which includes at least one instance of a set of frames which includes modified content. For some sections there may be two or more versions of modifications. These alternative versions may be compressed as a single distinct file. This permits efficient edge caching of video files with modified content, for example for selective provision of alternative versions of the video file to various end users in a transmission efficient manner.

Abstract: A method of identifying distinctive objects or images within a digital video comprises the use of one or more pixel (pel) based “pattern” or “feature” recognition protocols.

Abstract: A method and system to identify and locate images/objects which may be characterized as non-distinctive or “featureless” and which would be difficult to locate by conventional means comprises a plurality of steps including identifying first and second frame markers, increasing granularity between the frame markers, identifying at least one dominant object between the frame markers, normalizing its shape and identifying its edges, dissecting the dominant object into at least two equally sized sections; identifying shape and characteristics of at least one section (the analyzed section) of the dominant object thereby creating section data; applying geometric modeling such that section data from the analyzed section is used to determine overall shape, facets and configuration of the dominant object, thereby forming a geometric model; comparing geometric model to a known reference database of objects like the non-distinctive object (the reference object); and assessing the probability that the geometric model so

Abstract: A method and system to identify and locate images/objects which may be characterized as non-distinctive or “feature-less” and which would be difficult to locate by conventional means comprises a plurality of steps including identifying first and second frame markers, increasing granularity between the frame markers, identifying at least one dominant object between the frame markers, normalizing its shape and identifying its edges, dissecting the dominant object into at least two equally sized sections; identifying shape and characteristics of at least one section (the analyzed section) of the dominant object thereby creating section data; applying geometric modeling such that section data from the analyzed section is used to determine overall shape, facets and configuration of the dominant object, thereby forming a geometric model; comparing geometric model to a known reference data-base of objects like the non-distinctive object (the reference object); and assessing the probability that the geometric model s

Abstract: A method of tracking and collating items being added to and removed from a shopping receptacle comprises receiving a cue that an item is in motion, upon such cue, receiving at least one collected colour image of the item, analyzing the image to identify the item, and creating a ledger of items in the shopping receptacle, said ledger comprising the identity of each item in the shopping receptacle.

Abstract: A method of inserting a new image into a dynamic digital video file comprises identifying a target digital video segment into which the new image is to be inserted, projectively transforming the digital video segment from a first state to a second state, the second state being one which defines a substantially undistorted background, primed for new image insertion, and wherein any feature differences as between the first state and the second state are adjustment features; recording segment into data related to the adjustment features; selecting a point of insertion of new image; and blending the new image with the second state of the target digital video segment, weighing the adjustment features against each such that any visual cues which would mark placement of the new images as incongruous are adjusted.

Abstract: A method of identifying distinctive objects or images within a digital video comprises the use of one or more pixel (pel) based “pattern” or “feature” recognition protocols.