US 7,734,070 B1 · Method and system for immersing face images into a video sequence

Abstract

The present invention is a system and method for immersing facial images of people captured automatically from an image or a sequence of images into a live video playback sequence. This method allows viewers to perceive a participation in the viewed “movie” segment. A format is defined for storing the video such that this live playback of the video sequence is possible. A plurality of Computer Vision algorithms in the invention processes a plurality of input image sequences from the means for capturing images, which is pointed at the users in the vicinity of the system and performs the head detection and tracking. The interaction in the invention can be performed either in real-time or off-line depending on the embodiment of the invention in an uncontrolled background.

Claims31

Dependent claims

A method, comprising:

receiving a plurality of input images;
extracting one or more facial images from the plurality of input images using a computer system;
generating, at the computer system, demographic classifications using the plurality of input images;
replacing at least one replaceable actor image in a video sequence with at least one of the plurality of input images based on the demographic classifications;
and
creating a movie based on the replaced at least one replaceable actor image.

3 more elements

Dependencies are inferred from the claim text.

Facts

Application

10/738,453Filed 16 Dec 2003 · us provisional application

Priority

31 Dec 2002

Granted

8 Jun 2010

Term ends

Not estimatedThe source records don’t support an estimate.

Classification6 codes

G06V 20/46
In video content: extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames
G06V 40/16
Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands: human faces, e.g. facial parts, sketches or expressions
G11B 27/036
Electronic editing of digitised analogue information signals, e.g. audio or video signals: insert-editing
G11B 27/28
By using information detectable on the record carrier: by using information signals recorded by the same method as the main recording

Method and system for immersing face images into a video sequence

Life of this patent

Method and system for immersing face images into a video sequence

Life of this patent

Abstract

Claims31