Video assisted digital audio watermarking
A system and method for embedding digital audio watermarks in audio source information based at least upon identified video content are described. An audio/video processing system receives audiovisual data. A video content analyzer within the system analyzes video source information of the audiovisual data, determines video content depicted by data in the video source information, and generates an indication of the video content. An audio watermark embedder of the system receives the indication, and based at least in part on the indication, adjusts watermark embedding parameters used for embedding the audio watermark in the audio source information.
1. An audio watermarking embedder comprising: an interface configured to receive an identification of video content represented by data in a video frame; and control logic configured to: select a watermark embedding parameter used for embedding an audio watermark in an audio frame based at least in part on the identification of video content; embed the audio watermark in an audio frame corresponding to the video frame based at least in part on the selected watermark embedding parameter; embed a first amount of data of the audio watermark in the audio frame based at least in part on detecting the identification of video content represents a first scene; and embed a second amount of data different from the first amount of data of the audio watermark in the audio frame based at least in part on detecting the indication of video content represents a second scene different from the first scene.
2. The audio watermarking embedder as recited in claim 1 , wherein the control logic is further configured to:
embed the audio watermark in the audio frame with a first energy level based at least in part on detecting the identification of video content represents a first scene; and
embed the audio watermark in the audio frame with a second energy level different from the first energy level based at least in part on detecting the identification of video content represents a second scene different from the first scene.
3. The audio watermarking embedder as recited in claim 1 , wherein the control logic is further configured to:
embed the audio watermark in the audio frame at a first audio frequency based at least in part on detecting the identification of video content represents a first scene; and
embed the audio watermark in the audio frame at a second audio frequency different from the first audio frequency based at least in part on detecting the identification of video content represents a second scene different from the first scene.
4. The audio watermarking embedder as recited in claim 1 , wherein identifying the video content comprises:
analyzing the data in the video frame; and
determining the data depicts one or more video objects.
5. The audio watermarking embedder as recited in claim 4 , wherein identifying the video content further comprises associating each of the one or more video objects with a corresponding category of a plurality of categories.
6. The audio watermarking embedder as recited in claim 1 , wherein the control logic is further configured to combine the identification of video content with one or more audio decision parameters prior to embedding the audio watermark in the audio frame.
7. The audio watermarking embedder as recited in claim 6 , wherein the audio decision parameters comprise one or more of a frequency of a subband and an energy level of a subband.
8. A method comprising: receiving an indication identifying video content depicted by data in a video frame; selecting a watermark embedding parameter used for embedding an audio watermark in an audio frame based at least in part on the identification of video content; embedding the audio watermark in an audio frame corresponding to the video frame based at least in part on the selected watermark embedding parameter; embedding a first amount of data of the audio watermark in the audio frame based at least in part on detecting the identification of video content represents a first scene; and embedding a second amount of data different from the first amount of data of the audio watermark in the audio frame based at least in part on detecting the indication of video content represents a second scene different from the first scene.
9. The method as recited in claim 8 , further comprising:
embedding the audio watermark in the audio frame with a first energy level based at least in part on detecting the identification of video content represents a first scene; and
embedding the audio watermark in the audio frame with a second energy level different from the first energy level based at least in part on detecting the indication represents a second scene different from the first scene.
10. The method as recited in claim 8 , further comprising:
embedding the audio watermark in the audio frame at a first audio frequency based at least in part on detecting the identification of video content represents a first scene; and
embedding the audio watermark in the audio frame at a second audio frequency different from the first audio frequency based at least in part on detecting the identification of video content represents a second scene different from the first scene.
11. The method as recited in claim 8 , wherein the identifying the video content comprises:
analyzing the data in the video frame; and
determining the data depicts one or more video objects.
12. The method as recited in claim 11 , wherein identifying the video content further comprises associating each of the one or more video objects with a corresponding category of a plurality of categories.
13. The method as recited in claim 8 , wherein the control logic is further configured to combine the identification of video content with one or more audio decision parameters prior to embedding the audio watermark in the audio frame.
14. The method as recited in claim 13 , wherein the audio decision parameters comprise one or more of a frequency of a subband and an energy level of a subband.
15. An audio/video processing system comprising: a video content analyzer; and an audio watermarking embedder; wherein the video content analyzer is configured to: analyze data in a video frame; identify video content depicted by the data; and generate an indication of the video content; and wherein the audio watermarking embedder is configured to: receive the indication of the video content; select a watermark embedding parameter used for embedding an audio watermark in an audio frame based at least in part on the identification of video content; and embed the audio watermark in an audio frame corresponding to the video frame based at least in part on the selected watermark embedding parameter; embed a first amount of data of the audio watermark in the audio frame based at least in part on detecting the identification of video content represents a first scene; and embed a second amount of data different from the first amount of data of the audio watermark in the audio frame based at least in part on detecting the indication of video content represents a second scene different from the first scene.
16. The audio/video processing system as recited in claim 15 , wherein the audio watermarking embedder is further configured to:
embed the audio watermark in the audio frame with a first energy level based at least in part on detecting the identification of video content represents a first scene; and
embed the audio watermark in the audio frame with a second energy level different from the first energy level based at least in part on detecting the indication represents a second scene different from the first scene.
17. The audio/video processing system as recited in claim 15 , wherein the audio watermarking embedder is further configured to:
embed the audio watermark in the audio frame at a first audio frequency based at least in part on detecting the identification of video content represents a first scene; and
embed the audio watermark in the audio frame at a second audio frequency different from the first audio frequency based at least in part on detecting the identification of video content represents a second scene different from the first scene.