Identifying video content via fingerprint matching
View Patent ↗Methods and systems to identify video content based on video fingerprint matching are described. In some example embodiments, the methods and systems generate a query fingerprint of a frame of video content captured at a client device, query a database of reference fingerprints, determine the query fingerprint of the frame of captured video content matches a reference fingerprint, and identify the video content based on the match of fingerprints.
1. A computer-implemented method, comprising:
accessing a query fingerprint of a single video frame of video content captured at a client device, the query fingerprint being generated based on a first value of a first spatial region within the single video frame of video content, the first value of the first spatial region being calculated by subtracting a spatial sub-region of the first spatial region from one or more other spatial sub-regions of the first spatial region;
querying a database of reference fingerprints associated with video frames of known video content, each of the reference fingerprints being generated based on spatial regions within a different single video frame of the known video content;
determining that the query fingerprint matches at least one of the reference fingerprints; and
identifying the video content captured at the client device based on the determination that the query fingerprint matches at least one of the reference fingerprints.
2. The computer-implemented method of claim 1 , wherein the query fingerprint is generated based on a second value of a second spatial region within the single frame of video content, the second spatial region being distinct from the first spatial region, the second value of the second spatial region being calculated by subtracting a spatial sub-region of the second spatial region from one or more other spatial sub-regions of the second spatial region.
3. The computer-implemented method of claim 2 , wherein the query fingerprint is generated based on different weights applied to the first and second values according to different sizes of the first and second spatial regions of the single frame of video content.
4. The computer-implemented method of claim 1 , wherein the query fingerprint is generated based on a second value of a second spatial region within the single frame of video content, the second spatial region overlapping the first spatial region, the second value of the second spatial region being calculated by subtracting a spatial sub-region of the second spatial region from one or more other spatial sub-regions of the second spatial region.
5. The computer-implemented method of claim 4 , wherein the second spatial region coincides with the first spatial region.
6. The computer-implemented method of claim 4 , wherein the spatial sub-regions of the second spatial region are oriented perpendicular to the spatial sub-regions of the first spatial region.
7. The computer-implemented method of claim 1 , wherein the subtracting of the spatial sub-region of the first spatial region from the one or more other spatial sub-regions of the first spatial region includes subtracting an inner sub-region of the first spatial region from multiple outer sub-regions of the first spatial region.
8. The computer-implemented method of claim 1 , further comprising:
returning an identifier to the client device for the video content that is associated with metadata to be presented along with the video content via the client device.
9. The computer-implemented method of claim 1 , further comprising:
returning an identifier to the client device for the video content that is associated with event-based information to be presented along with the video content via the client device.
10. The method of claim 1 , wherein:
the subtracting of the spatial sub-region of the first spatial region from the one or more other spatial sub-regions of the first spatial region includes subtracting an inner sub-region of the first spatial region from multiple outer sub-regions of the first spatial region.
11. A system, comprising:
a query fingerprint generator configured to generate a query fingerprint of a single video frame of video content captured at a client device, the query fingerprint being generated based on our first value of a first spatial region within the single video frame of the video content, the first value of the first spatial region being calculated by subtracting a spatial sub-region of the first spatial region from one or more other spatial sub-regions of the first spatial region;
an index module that comprises one or more processors and is configured to query a database of reference fingerprints associated with video frames of known video content, each of the reference fingerprints being generated based on spatial regions within a different single video frame of the known video content;
a fingerprint match module that comprises one or more processors and is configured to determine that the query fingerprint matches at least one of the reference fingerprints; and
an identification module that comprises one or more processors and is configured to identify the video content captured at the client device based on the determination that the query fingerprint matches at least one of the reference fingerprints.
12. The system of claim 11 , wherein the query fingerprint is generated based on a second value of a second spatial region within the single frame of video content, the second spatial region being distinct from the first spatial region, the second value of the second spatial region being calculated by subtracting a spatial sub-region of the second spatial region from one or more other spatial sub-regions of the second spatial region.
13. The system of claim 11 , wherein the query fingerprint is generated based on different weights applied to the first and second values according to different sizes of the first and second spatial regions of the single frame of video content.
14. The system of claim 11 , wherein the query fingerprint is generated based on a second value of a second spatial region within the single frame of video content, the second spatial region overlapping the first spatial region, the second value of the second spatial region being calculated by subtracting a spatial sub-region of the second spatial region from one or more other spatial sub-regions of the second spatial region.
15. The system of claim 14 , wherein the spatial sub-regions of the second spatial region are oriented perpendicular to the spatial sub-regions of the first spatial region.
16. A computer-readable storage medium whose contents, when executed by a computing system, cause the computing system to perform operations, comprising:
accessing a query fingerprint of a single video frame of video content captured at a client device, the query fingerprint being generated based on a first value of a first spatial region within the single video frame of video content, the first value of the first spatial region being calculated by subtracting a spatial sub-region of the first spatial region from one or more other spatial sub-regions of the first spatial region;
querying a database of reference fingerprints associated with video frames of known video content, each of the reference fingerprints being generated based on spatial regions within a different single video frame of the known video content;
determining that the query fingerprint matches at least one of the reference fingerprints; and
identifying the video content captured at the client device based on the determination that the query fingerprint matches at least one of the reference fingerprints.
17. The computer-readable storage medium of claim 16 , wherein the query fingerprint is generated based on a second value of a second spatial region within the single frame of video content, the second spatial region being distinct from the first spatial region, the second value of the second spatial region being calculated by subtracting a spatial sub-region of the second spatial region from one or more other spatial sub-regions of the second spatial region.
18. The computer-readable storage medium of claim 16 , wherein the query fingerprint is generated based on a second value of a second spatial region within the single frame of video content, the second spatial region overlapping the firsts spatial region, the second value of the second spatial region being calculated by subtracting a spatial sub-region of the second spatial region from one or more other spatial sub-regions of the second spatial region.
19. The computer-readable storage medium of claim 16 , wherein:
the querying of the database of reference fingerprints associated with video frames of known video content includes querying a database of reference fingerprints with two or more accessed query fingerprints; and
the determining that the query fingerprint matches at least one of the reference fingerprints includes determining the two or more accessed query fingerprints matches at least two or more reference fingerprints.
20. The computer-readable storage medium of claim 16 , wherein:
the querying of the database of reference fingerprints includes querying an index of quantized region values calculated for the reference fingerprints.