Methods and apparatus for identifying media content using temporal signal characteristics
View Patent ↗Methods and apparatus to identify media content using temporal signal characteristics are disclosed. An example method to identify media content includes receiving a reference signal corresponding to known media content and generating a reference signature based on the reference signal. The method further includes generating a plurality of sums based on peaks in the media signal and identifying one or more signal peaks based on the generated sums. The method then generates a second signature based on a plurality of normalized curve features, wherein each normalized curve feature corresponds to a signal peak at the temporal location of the signal peak, and determines whether the media signal corresponds to the reference signal based a comparison of the reference signature and the second signature.
1. A method to identify media content, comprising:
receiving a reference signal corresponding to known media content and generating a reference signature based on the reference signal;
receiving a media signal corresponding to media content;
generating a plurality of sums based on peaks in the media signal;
identifying one or more signal peaks based on the generated sums;
generating a second signature based on a plurality of normalized curve features, wherein each normalized curve feature corresponds to one of the identified signal peaks at the temporal location of the signal peak; and
determining whether the media signal corresponds to the reference signal based a comparison of the reference signature and the second signature.
2. A method as defined in claim 1 , further comprising smoothing the plurality of sums.
3. A method as defined in claim 1 , wherein determining whether the media signal corresponds to the reference signal comprises performing a correlation of the second signature and the reference signature.
4. A method as defined in claim 1 , further comprising generating each of the normalized curve features by generating a peak having a height, a width, and a center location.
5. A method as defined in claim 4 , wherein the heights of the plurality of normalized curve features are equal and the widths of the plurality of normalized curve features are equal.
6. A method as defined in claim 4 , wherein the height of the second signature is substantially zero at temporal locations other than locations corresponding to the normalized curve features.
7. A method as defined in claim 1 , wherein determining whether the media signal corresponds to the reference signal comprises determining whether an index value is greater than a predetermined threshold.
8. A method as defined in claim 1 , wherein the media content is associated with at least one of a broadcast program or a local media source.
9. A method as defined in claim 1 , wherein the media content comprises at least one of audio content or video content.
10. A method as defined in claim 1 , wherein generating the reference signature comprises:
generating a second plurality of sums based on peaks in the reference signal;
identifying a second one or more signal peaks based on the generated sums; and
generating the reference signature based on a second plurality of normalized curve features, wherein each of the second plurality of normalized curve features corresponds to one of the second signal peaks at a temporal location of the signal peak.
11. A method to monitor exposure to media content, comprising:
monitoring an exposure site to collect a media signal;
generating a plurality of sums based on peaks in the media signal;
identifying one or more signal peaks based on the generated sums;
generating a signature based on a plurality of normalized curve features, wherein each of the normalized curve features corresponds to one of the signal peaks at a temporal location of the signal peak; and
identifying the media signal based on a comparison of the signature and one or more reference signatures representative of known media content.
12. A method as defined in claim 11 , further comprising smoothing the plurality of sums.
13. A method as defined in claim 11 , further comprising generating one or more reference signatures representative of the known media content, the generating comprising:
generating a second plurality of sums based on peaks in a known media content signal;
identifying second one or more signal peaks based on the second generated sums;
generating the reference signature based on a second plurality of normalized curve features, wherein each of the second normalized curve features corresponds to one of the second signal peaks at a temporal location of the signal peak.
14. A method as defined in claim 11 , further comprising identifying a second media signal based on a comparison of a third signature and one or more reference signatures representative of known media content.
15. A method as defined in claim 14 , wherein identifying the first and second media signals comprises comparing first and second index values with a first predetermined threshold.
16. A method as defined in claim 15 , further comprising identifying a third media signal, wherein exposure to the third media signal occurs between exposure to the first media signal and second media signal, and wherein identifying the third media signal comprises comparing a third index value with a second predetermined threshold lower than the first predetermined threshold.
17. An apparatus for identifying media content, comprising:
a memory; and
a processor in communication with the memory and programmed to:
receive a reference signal corresponding to known media content and generate a reference signature based on the reference signal;
generate a plurality of sums based on peaks in the media signal;
identify one or more signal peaks based on the generated sums;
generate a second signature based on a plurality of normalized curve features, wherein each normalized curve feature corresponds to one of the identified signal peaks at a temporal location of the signal peak; and
determine whether the media signal corresponds to the reference signal based a comparison of the reference signature and the second signature.
18. An apparatus as defined in claim 17 , wherein the processor is further programmed to smooth the plurality of sums.
19. An apparatus as defined in claim 17 , wherein determining whether the media signal corresponds to the reference signal comprises performing a correlation of the second signature and the reference signature.
20. An apparatus as defined in claim 17 , wherein the processor is further programmed to generate each of the normalized curve features by generating a peak having a height, a width, and a center location.
21. An apparatus as defined in claim 20 , wherein the heights of the plurality of normalized curve features are equal and the widths of the plurality of normalized curve features are equal.
22. An apparatus as defined in claim 20 , wherein the height of the second signature is substantially zero at temporal locations other than locations corresponding to the normalized curve features.
23. An apparatus as defined in claim 17 , wherein determining whether the media signal corresponds to the reference signal comprises determining whether an index value is greater than a predetermined threshold.
24. An apparatus as defined in claim 17 , wherein the media content is associated with at least one of a broadcast program or a local media source.
25. An apparatus as defined in claim 17 , wherein generating the reference signature comprises:
generating a second plurality of sums based on peaks in the media signal;
identifying second one or more signal peaks based on the second generated sums;
generating the reference signature based on a second plurality of normalized curve features, wherein each of the second normalized curve features corresponds to a signal peak at a temporal location of the signal peak.
26. A tangible machine readable medium having instructions stored thereon that, when executed, cause a machine to at least:
generate a reference signature based on a reference signal corresponding to known media content;
generate a plurality of sums based on peaks in the media signal;
identify one or more signal peaks based on the generated sums;
generate a second signature based on a plurality of normalized curve features, wherein each normalized curve feature corresponds to one of the identified signal peaks at a temporal location of the signal peak; and
determine whether the media signal corresponds to the reference signal based on a comparison of the reference signature and the second signature.
27. A machine readable medium as defined in claim 26 , wherein the instructions further cause the machine to smooth the plurality of sums.
28. A machine readable medium as defined in claim 26 , wherein the instructions cause the machine to determine whether the media signal corresponds to the reference signal by performing a correlation of the second signature and the reference signature.
29. A machine readable medium as defined in claim 26 , wherein the instructions further cause the machine to generate the normalized curve feature by generating a peak having a height, a width, and a center location.
30. A machine readable medium as defined in claim 29 , wherein the heights of the plurality of normalized curve features are equal and the widths of the plurality of normalized curve features are equal.
31. A machine readable medium as defined in claim 29 , wherein the height of the second signature is substantially zero at temporal locations other than locations corresponding to normalized curve features.
32. A machine readable medium as defined in claim 26 , wherein the instructions cause the machine to determine whether the media signal corresponds to the reference signal by determining whether an index value is greater than a predetermined threshold.
33. A machine readable medium as defined in claim 26 , wherein the media content is associated with at least one of a broadcast program or a local media source.
34. A machine readable medium as defined in claim 26 , wherein the instructions cause the machine to generate the reference signature by:
generating a second plurality of sums based on peaks in the reference signal;
identifying second one or more signal peaks based on the second generated sums; and
generating the reference signature based on a second plurality of normalized curve features, wherein each of the second normalized curve features corresponds to a signal peak at a temporal location of the signal peak.