Media content identification on mobile devices
A mobile device responds in real time to media content presented on a media device, such as a television. The mobile device captures temporal fragments of audio-video content on its microphone, camera, or both and generates corresponding audio-video query fingerprints. The query fingerprints are transmitted to a search server located remotely or used with a search function on the mobile device for content search and identification. Audio features are extracted and audio signal global onset detection is used for input audio frame alignment. Additional audio feature signatures are generated from local audio frame onsets, audio frame frequency domain entropy, and maximum change in the spectral coefficients. Video frames are analyzed to find a television screen in the frames, and a detected active television quadrilateral is used to generate video fingerprints to be combined with audio fingerprints for more reliable content identification.
1. A computer-implemented method comprising:
obtaining, by a portable computing device, a first fragment of media content using an input device of the portable computing device, wherein the first fragment of media content is a representation of a sequence of media content that is presented by a playback device;
generating, by the portable computing device, a first query fingerprint using the first fragment of media content;
transmitting, by the portable computing device to a server device, the first query fingerprint;
receiving, by the portable computing device from the server device, a set of reference fingerprints corresponding to the sequence of media content, wherein the set of reference fingerprints includes a particular reference fingerprint having associated action data;
storing, by the portable computing device, the set of reference fingerprints and the action data in a memory of the portable computing device;
obtaining, by the portable computing device, a second fragment of media content using the input device of the portable computing device;
generating, by the portable computing device, a second query fingerprint using the second fragment of media content;
determining, by the portable computing device, that the second query fingerprint matches the particular reference fingerprint; and
based on the determining that the second query fingerprint matches the particular reference fingerprint:
obtaining, by the portable computing device from the memory of the portable computing device, the action data associated with the particular reference fingerprint, and
triggering one or more action events on the portable computing device, wherein the one or more action events is based on the action data, wherein the action data is based on the media content that is presented by the playback device, and wherein triggering the one or more action events comprises allowing a user of the portable computing device to report consumption of the sequence of media content online in real time by performing a social media check-in to the sequence of media content with a registration server that is separate from the server device.
2. The computer-implemented method of claim 1 , wherein triggering the one or more action events comprises presenting an identity of the sequence of media content.
3. The computer-implemented method of claim 1 , wherein triggering the one or more action events comprises retrieving related information based on an identity of the sequence of media content.
4. The computer-implemented method of claim 1 , wherein triggering the one or more action events comprises presenting an advertisement.
5. The computer-implemented method of claim 1 , wherein the input device comprises a microphone, wherein the first fragment of media content comprises an audio fragment, and wherein the first query fingerprint comprises an audio fingerprint.
6. The computer-implemented method of claim 5 , further comprising resampling the audio fragment or down-mixing the audio fragment prior to generating the audio fingerprint.
7. The computer-implemented method of claim 1 , wherein the input device comprises a camera, wherein the first fragment of media content comprises a video fragment, and wherein the first query fingerprint comprises a video fingerprint.
8. The computer-implemented method of claim 7 , further comprising selecting a video frame of the video fragment, wherein generating the first query fingerprint comprises generating the video fingerprint using the video frame.
9. The computer-implemented method of claim 1 , wherein the playback device comprises a television.
10. A portable computing device comprising:
an input device;
one or more processors; and
a computer-readable medium having stored therein instructions that are executable by the one or more processors to cause the portable computing device to perform functions comprising:
obtaining a first fragment of media content using the input device, wherein the first fragment of media content is a representation of a sequence of media content that is presented by a playback device,
generating a first query fingerprint using the first fragment of media content,
transmitting, to a server device, the first query fingerprint,
receiving, from the server device, a set of reference fingerprints corresponding to the sequence of media content, wherein the set of reference fingerprints includes a particular reference fingerprint having associated action data,
storing the set of reference fingerprints and the action data in a memory of the portable computing device,
obtaining a second fragment of media content using the input device,
generating a second query fingerprint using the second fragment of media content,
determining that the second query fingerprint matches the particular reference fingerprint, and
based on the determining that the second query fingerprint matches the particular reference fingerprint:
obtaining, from the memory of the portable computing device, the action data associated with the particular reference fingerprint; and
triggering one or more action events on the portable computing device, wherein the one or more action events is based on the action data, wherein the action data is based on the media content that is presented by the playback device, and wherein triggering the one or more action events comprises allowing a user of the portable computing device to report consumption of the sequence of media content online in real time by performing a social media check-in to the sequence of media content in with a registration server that is separate from the server device.
11. The portable computing device of claim 10 , wherein triggering the one or more action events comprises presenting an identity of the sequence of media content.
12. The portable computing device of claim 10 , wherein triggering the one or more action events comprises presenting an advertisement.
13. The portable computing device of claim 10 , wherein the input device comprises a microphone, wherein the first fragment of media content comprises an audio fragment, and wherein the first query fingerprint comprises an audio fingerprint.
14. The portable computing device of claim 10 , wherein the input device comprises a camera, wherein the first fragment of media content comprises a video fragment, and wherein the first query fingerprint comprises a video fingerprint.
15. A non-transitory computer-readable medium having stored therein instructions that are executable by one or more processors to cause a portable computing device to perform functions comprising:
obtaining a first fragment of media content using an input device of the portable computing device, wherein the first fragment of media content is a representation of a sequence of media content that is presented by a playback device;
generating a first query fingerprint using the first fragment of media content;
transmitting, to a server device, the first query fingerprint;
receiving, from the server device, a set of reference fingerprints corresponding to the sequence of media content, wherein the set of reference fingerprints includes a particular reference fingerprint having associated action data;
storing the set of reference fingerprints and the action data in a memory of the portable computing device;
obtaining a second fragment of media content using the input device;
generating a second query fingerprint using the second fragment of media content;
determining that the second query fingerprint matches the particular reference fingerprint; and
based on the determining that the second query fingerprint matches the particular reference fingerprint:
obtaining, from the memory of the portable computing device, the action data associated with the particular reference fingerprint, and
triggering one or more action events on the portable computing device, wherein the one or more action events is based on the action data, wherein the action data is based on the media content that is presented by the playback device, and wherein triggering the one or more action events comprises allowing a user of the portable computing device to report consumption of the sequence of media content online in real time by performing a social media check-in to the sequence of media content with a registration server that is separate from the server device.