Media channel identification and action with multi-match detection and disambiguation based on matching with differential reference-fingerprint feature
A computing system compares various reference fingerprints each representing a reference media stream broadcast on a different respective known channel, and the computing system determines that a plurality of the reference fingerprints match each other, thus defining a multi-match group of the matching reference fingerprints. In response, the computing system identifies a fingerprint feature that could define a distinction between the reference fingerprints, and the computing system resolves the multi-match based on the identified feature, thereby determining the channel carrying the media stream being rendered by the media presentation device. And the computing system could then take channel-specific action based on the determined channel.
1. A system comprising:
a network communication interface;
a processing unit;
non-transitory data storage; and
program instructions stored in the non-transitory data storage and executable by the processing unit to carry out operations including:
receiving, from a media presentation device, first query fingerprint data representing video content being received by the media presentation device, wherein the video content includes video frames having video frame regions, the video frame regions comprising a center, an edge, and a corner;
determining that the first query fingerprint data matches multiple instances of reference fingerprint data corresponding with multiple channels; and
responsive to at least determining that the first query fingerprint data matches the multiple instances of reference fingerprint data corresponding with the multiple channels, performing disambiguation by (i) identifying a video frame region, of the video frame regions of the video content, that defines a difference between the multiple channels with which the multiple instance of reference fingerprint data correspond, (ii) requesting and receiving, from the media presentation device, second query fingerprint data specifically focused on the identified video frame region, and (iii) determining that the second query fingerprint data matches reference fingerprint data representing the video frame region of just one channel of the multiple channels, whereby the disambiguation establishes that the media presentation device is receiving the video content on the one channel.
2. The system of claim 1 , wherein the operations further include, for each channel of the multiple channels, establishing respective reference fingerprint data of the identified video frame region,
wherein determining that the second query fingerprint data matches the reference fingerprint data of the video frame region of the one channel of the multiple channels comprises determining that the second query fingerprint data matches the established respective reference fingerprint data of the identified video frame region of the one channel of the multiple channels.
3. The system of claim 1 , wherein the operations further include taking action based on the establishing that the media presentation device is receiving the video content on the one channel.
4. The system of claim 3 , wherein taking action based on the establishing that the media presentation device is receiving the video content on the one channel comprises causing supplemental channel-specific content to be presented by the media presentation device in conjunction with the video content being received by the media presentation device.
5. The system of claim 3 , wherein taking action based on the establishing that the media presentation device is receiving the video content on the one channel comprises causing presentation of a replacement advertisement in place of an advertisement on the channel.
6. The system of claim 3 , wherein taking action based on the establishing that the media presentation device is receiving the video content on the one channel comprises recording channel ratings data.
7. The system of claim 1 , wherein the multiple instances of reference fingerprint data are selected from a plurality of instances of reference fingerprint data in reference data, and wherein determining that the first query fingerprint data matches the multiple instances of reference fingerprint data comprises:
comparing the first query fingerprint data with the plurality of instances of reference fingerprint data in the reference data, and
based on the comparing, determining that the first query fingerprint data matches the multiple instances of reference fingerprint data.
8. The system of claim 1 , wherein the system has access to data that indicates, for the multiple channels with which the multiple instances of reference fingerprint data correspond, the video frame region that defines the difference between the multiple channels, and wherein identifying the video frame region comprises referring to the data to identify the video frame region.
9. The system of claim 1 , wherein the identified video frame region comprises a region at a video frame edge.
10. The system of claim 1 , wherein the identified video frame region comprises a video frame region where channel identification is presented.
11. Non-transitory data storage having stored thereon instructions executable by a processing unit to carry out operations comprising:
receiving, from a media presentation device, a first query fingerprint of video content being rendered by the media presentation device, wherein the video content includes video frames having video frame regions, the video frame regions comprising a center, an edge, and a corner;
determining that the first query fingerprint matches multiple reference fingerprints corresponding with multiple channels; and
responsive to at least determining that the first query fingerprint matches the multiple reference fingerprints corresponding with the multiple channels, performing disambiguation by (i) identifying a video frame region, of the video frame regions of the video content, that defines a difference between the channels corresponding with the multiple reference fingerprints, (ii) requesting and receiving, from the media presentation device, a second query fingerprint specifically focused on the identified video frame region, and (iii) determining that the second query fingerprint matches a reference fingerprint of the video frame region of just one channel of the multiple channels, whereby the disambiguation establishes that the media presentation device is receiving the video content on the one channel.
12. The non-transitory data storage of claim 11 , wherein the operations further include, for each channel of the multiple channels, establishing respective reference fingerprint data of the identified video frame region,
wherein determining that the second query fingerprint data matches the reference fingerprint data of the video frame region of the one channel of the multiple channels comprises determining that the second query fingerprint data matches the established respective reference fingerprint data of the identified video frame region of the one channel of the multiple channels.
13. The non-transitory data storage of claim 11 , wherein the operations further include taking action based on the establishing that the media presentation device is receiving the video content on the one channel.
14. The non-transitory data storage of claim 13 , wherein taking action based on the establishing that the media presentation device is receiving the video content on the one channel comprises causing supplemental channel-specific content to be presented by the media presentation device in conjunction with the video content being received by the media presentation device.
15. The non-transitory data storage of claim 13 , wherein taking action based on the establishing that the media presentation device is receiving the video content on the one channel comprises causing presentation of a replacement advertisement in place of an advertisement on the channel.
16. The non-transitory data storage of claim 13 , wherein taking action based on the establishing that the media presentation device is receiving the video content on the one channel comprises recording channel ratings data.
17. The non-transitory data storage of claim 11 , wherein the multiple instances of reference fingerprint data are selected from a plurality of instances of reference fingerprint data in reference data, and wherein determining that the first query fingerprint data matches the multiple instances of reference fingerprint data comprises:
comparing the first query fingerprint data with the plurality of instances of reference fingerprint data in the reference data, and
based on the comparing, determining that the first query fingerprint data matches the multiple instances of reference fingerprint data.
18. The non-transitory data storage of claim 11 , wherein the processing unit has access to data that indicates, for the multiple channels with which the multiple instances of reference fingerprint data correspond, the video frame region that defines the difference between the multiple channels, and wherein identifying the video frame region comprises referring to the data to identify the video frame region.
19. The non-transitory data storage of claim 11 , wherein the identified video frame region comprises a region at a video frame edge.
20. The non-transitory data storage of claim 11 , wherein the identified video frame region comprises a video frame region where channel identification is presented.