Method and system for audio-video signal processing
Both fingerprinting and watermark decoding processes are applied to received items of audio-visual content. Further processing is applied as well. This further processing depends on output data from the watermark decoding process, and can cause two items of seemingly-identical audio-visual content to be further-processed in different ways.
1. A method of signal processing that includes processing a received item of audio-visual content to derive both fingerprint and steganographic watermark data, the method comprising the acts:
processing the received item of audio-visual content to derive watermark data therefrom, said watermark data having been previously steganographically encoded in said content;
obtaining metadata for the received item of audio-visual content, based on the derived watermark data;
also processing the received item of audio-visual content to derive fingerprint data therefrom, the derived fingerprint data being different than the derived watermark data;
searching a database of reference fingerprint data for a match with the derived fingerprint data, to thereby determine identity information for a piece of pre-existing audio-visual work included in the received item of audio-visual content;
determining an amount of said piece of pre-existing audio-visual work that is included in the received item of audio-visual content, based on said derived fingerprint data or said derived watermark data, said amount comprising a certain percentage, or a certain duration, of the pre-existing audio-visual work; and
governing use of said item of received audio-visual content based on (1) the determined identity information for the pre-existing audio-visual work; (2) the determined amount of the pre-existing audio-visual work that is included in the received item of content; and (3) the obtained metadata;
wherein use of two items of received audio-visual content that appear identical to a human observer, having the same determined identity information and the same determined amount of the pre-existing audio-visual work, are nonetheless governed in two different ways, due to a difference in the obtained metadata for said two items of received content.
2. The method of claim 1 wherein said obtained metadata indicates that a first party was included in a chain of distribution of a first of said two items of received content, and was not included in a chain of distribution of the a second of said two items of received content.
3. The method of claim 1 wherein said first party is different than a party from whom the first item of audio-visual content was received.
4. A non-transitory computer readable medium containing software instructions for configuring a computer system to perform a method that includes processing a received item of audio-visual content to derive both fingerprint and steganographic watermark data, said method comprising the acts:
processing the received item of audio-visual content to derive watermark data therefrom that was previously steganographically encoded in said content;
obtaining metadata for the received item of audio-visual content, based on the derived watermark data;
also processing the received item of audio-visual content to derive fingerprint data therefrom, the derived fingerprint data being different than the derived watermark data;
searching a database of reference fingerprint data for a match with the derived fingerprint data, to thereby determine identity information for a piece of pre-existing audio-visual work included in the received item of audio-visual content;
determining an amount of said piece of pre-existing audio-visual work that is included in the received item of audio-visual content, based on said derived fingerprint data or said derived watermark data, said amount comprising a certain percentage, or a certain duration, of the pre-existing audio-visual work; and
governing use of said item of received audio-visual content based on (1) the determined identity information for the pre-existing audio-visual work; (2) the determined amount of the pre-existing audio-visual work that is included in the received item of content; and (3) the obtained metadata;
wherein use of two items of received audio-visual content that appear identical to a human observer, having the same determined identity information and the same determined amount of the pre-existing audio-visual work, are nonetheless governed in two different ways, due to a difference in the obtained metadata for said two items of received content.
5. A computer system for ingesting and re-distributing a received item of audio-visual content, comprising:
watermark decoder means for deriving watermark data from a received item of audio-visual content uploaded by a user, the watermark data having been previously steganographically encoded in said content;
fingerprint derivation means for deriving fingerprint data from said received item of audio-visual content, the derived fingerprint data being different than the derived watermark data;
one or more processors and memory, the memory containing software instructions for configuring the computer system to perform acts including:
obtaining metadata for said received item of audio-visual content, based on the derived watermark data;
searching a database of reference fingerprint data for a match with the derived fingerprint data, to thereby determine identity information for a piece of pre-existing audio-visual work included in the received item of audio-visual content;
determining an amount of said piece of pre-existing audio-visual work that is included in the received item of audio-visual content, based on said derived fingerprint data or said derived watermark data, said amount comprising a certain percentage, or a certain duration, of the pre-existing audio-visual work; and
governing use of said received item of audio-visual content based on (1) the determined identity information for the pre-existing audio-visual work; (2) the determined amount of the pre-existing audio-visual work that is included in the received item of audio-visual content; and (3) the obtained metadata;
wherein use of two items of received audio-visual content that appear identical to a human observer, having the same determined identity information and the same determined amount of the pre-existing audio-visual work, are nonetheless governed in two different ways, due to a difference in the obtained metadata for said two items of received content.