Method and system for combining video sequences with spatio-temporal alignment
AssigneeEcole Polytechnique Fédérale
InventorsSerge Ayer, Martin Vetterli
Life of this patent
Estimating the term…
Abstract
Given two video sequences, a composite video sequence can be generated which includes visual elements from each of the given sequences, suitably synchronized and represented in a chosen focal plane. For example, given two video sequences with each showing a different contestant individually racing the same down-hill course, the composite sequence can include elements from each of the given sequences to show the contestants as if racing simultaneously. A composite video sequence can be made also by similarly combining a video sequence with an audio sequence.
Claims24
A method for generating a composite video sequence from a plurality of given video sequences, wherein each of the given video sequences comprises a first representation of a respective foreground object and a representation of at least a portion of spatially contiguous background, the method comprising:
- (a) synchronizing the given video sequences;
- (b) spatially aligning the synchronized sequences;
- and
- (c) forming the composite sequence from the aligned sequences, comprising a second representation of each of the foreground objects as projected into a local plane chosen for composite simultaneous visualization.
A system for generating a composite video sequence from a plurality of given video sequences, wherein each of the given video sequences comprises a first representation of a respective foreground object and a representation of at least a portion of a spatially contiguous background, the method comprising:
- (a) means for synchronizing the given video sequences;
- (b) means for spatially aligning the synchronized sequences;
- and
- (c) means for forming the composite sequence from the aligned sequences, comprising a second representation of each of the foreground objects as projected into a focal plane chosen for composite simultaneous visualization.
A system for generating a composite video sequence from a plurality of given video sequences, wherein each of the given video sequences comprises a first representation of respective foreground object and a representation of at least a portion of a spatially contiguous background, the method comprising:
- (a) means for synchronizing the given video sequences and
- (b) a processor which is instructed for
- (i) spatially aligning the synchronized sequences and
- (ii) forming the composite sequence from the aligned sequences, comprising a second representation of each of the foreground objects as projected into a focal plane chosen for composite simultaneous visualization.
A method for generating a composite image, comprising:
- (a) synchronizing a plurality of video sequences wherein each of the video sequences comprises a first representation of a respective foreground object and a representation of at least a portion of a spatially contiguous background;
- (b) spatially aligning the synchronized sequences;
- and
- (c) forming the composite image from corresponding frames of the aligned sequences, comprising a second representation of each of the foreground objects as projected into a focal plane chosen for composite simultaneous visualization.
A broadcast service comprising:
- (a) synchronizing a plurality of given video sequences wherein each of the given video sequences comprises a first representation of a respective foreground object and a representation of at least a portion of a spatially contiguous background;
- (b) spatially aligning the synchronized sequences;
- (c) forming a composite sequence from the aligned sequences, comprising a second representation of each of the foreground objects as projected into a focal plane chosen for composite simultaneous visualization;
- and
- (d) broadcasting the composite sequence.
A method for determining differential time between two contestants at a specified location in a race, the method comprising:
- (a) synchronizing two given video sequences, each comprising a first respective representation of a respective contestant as a respective foreground object, wherein each of the given video sequences further comprises at least a portion of a spatially contiguous background which comprises the specified location;
- (b) spatially aligning the synchronized sequences;
- (c) forming a composite sequence from the aligned sequences, comprising a second representation of each of the contestants as projected into a focal plane chosen for composite simultaneous visualization;
- and
- (d) counting the number of frames between the contestants passing the location.
Dependencies are inferred from the claim text.