Method and apparatus for recognizing objects in media content

• US 8,818,025 B2
• Filed: 08/23/2010
• Issued: 08/26/2014
• Est. Priority Date: 08/23/2010
• Status: Active Grant

• Current Assignee: Nokia Technologies Oy (Nokia Corporation)
• Original Assignee: Nokia Corporation
• Inventors: Salminen, Ilkka Tapani, Nurmi, Mikko Antero
• Primary Examiner(s): BHATNAGAR, ANAND P
• Application Number:
  US12/861,603
• Publication Number:
  US 20120045093A1
• Time in Patent Office: 1,464 Days
• Field of Search: 382/100, 382/103, 382/104, 382/115, 382/116, 382/117, 382/118, 382/181, 382/190, 382/195, 382/206, 348169-172
• US Class Current: 382/103
• CPC Class Codes: G06F 16/433 using audio data
• CPC Class Codes: G06F 16/583 using metadata automatically derived from the content
• CPC Class Codes: G06F 16/683 using metadata automatically derived from the content
• CPC Class Codes: G06F 16/7837 using objects detected or recognised in the video content
• CPC Class Codes: G06V 40/173 face re-identification, e.g. recognising unknown faces across different face tracks
• CPC Class Codes: G06V 40/179 metadata assisted face recognition
• CPC Class Codes: H04N 21/4332 by placing content in organized collections, e.g. local EPG data repository interfaces, Database management systems or updating for information retrieval G06F16/23; details of retrieval of video data and associated meta data in video database G06F16/739
• CPC Class Codes: H04N 21/44008 involving operations for analysing video streams, e.g. detecting features or characteristics in the video stream arrangements characterised by components specially adapted for monitoring, identification or recognition of video in broadcast systems H04H60/59
• CPC Class Codes: H04N 21/84 Generation or processing of descriptive data, e.g. content descriptors systems specially adapted for using meta-information in broadcast systems H04H60/73
• CPC Class Codes: H04N 21/8583 by creating hot-spots

Abstract

An approach is provided for recognizing objects in media content. The capture manager determines to detect, at a device, one or more objects in a content stream. Next, the capture manager determines to capture one or more representations of the one or more objects in the content stream. Then, the capture manager associates the one or more representations with one or more instances of the content stream.

Claims

1. A method comprising:

determining to detect, at a device, one or more objects in a content stream;

determining, by a processor, to capture one or more representations of the one or more objects in the content stream; and

associating the one or more representations with one or more instances of the content stream,

wherein one or more of the one or more objects are detected at least before the one or more instances of the content stream are captured.

2. A method of claim 1, further comprising:

determining to capture one or more other representations of the one or more objects in the content stream;

selecting either the one or more representations or the one or more other representations to associate with the one or more instances based, at least in part, on one or more criteria.

3. A method of claim 2, wherein the one or more representations or the one or more other representations are captured continuously, periodically, or at a predetermined schedule until either the one or more representations or the one or more other representations meet a predetermined quality threshold.

4. A method of claim 1, further comprising:

determining recognition information of the one or more objects based, at least in part, on the one or more representations; and

associating the recognition information with the one or more instances.

5. A method of claim 4, wherein the determination of the recognition information is further based, at least in part, on resources available at the device, another device, a server, a network component, or a combination thereof.

6. A method of claim 1, wherein the associating of the one or more representations comprises:

determining to store the one or more representations as metadata in the one or more instances, as metadata in a storage linked to the one or more instances, or a combination thereof.

7. A method of claim 1, further comprising:

associating the one or more representations with respective time stamps; and

associating the one or more representations with the one or more other instances based, at least in part, on the time stamps.

8. A method of claim 1, further comprising:

receiving at least one of the one or more representations from one or more other devices, one or more other content streams, or a combination thereof.

9. A method of claim 1, wherein the one or more representations correspond to one or more characteristics of the one or more objects.

10. A method of claim 1, further comprising:

determining tracking information of the one or more detected objects,

wherein the content stream is a live video stream, and the one or more instances are images, videos, audio recordings, or a combination thereof, and the tracking information includes information identifying at least a relative position of the object within the captured one or more instances.

11. An apparatus comprising:

at least one processor; and

at least one memory including computer program code for one or more programs,

the at least one memory and the computer program code configured to, with the at least one processor, cause the apparatus to perform at least the following,

determine to detect, at a device, one or more objects in a content stream;

determine to capture one or more representations of the one or more objects in the content stream; and

associate the one or more representations with one or more instances of the content stream,

wherein one or more of the one or more objects are detected at least before the one or more instances of the content stream are captured.

12. An apparatus of claim 11, wherein the apparatus is further caused to:

determine to capture one or more other representations of the one or more objects in the content stream;

select either the one or more representations or the one or more other representations to associate with the one or more instances based, at least in part, on one or more criteria.

13. An apparatus of claim 12, wherein the one or more representations or the one or more other representations are captured continuously, periodically, or at a predetermined schedule until either the one or more representations or the one or more other representations meet a predetermined quality threshold.

14. An apparatus of claim 11, wherein the apparatus is further caused to:

determining recognition information of the one or more objects based, at least in part, on the one or more representations; and

associating the recognition information with the one or more instances.

15. An apparatus of claim 14, wherein the determination of the recognition information is further based, at least in part, on resources available at the device, another device, a server, a network component, or a combination thereof.

16. An apparatus of claim 11, wherein the associating of the one or more representations comprises:

determining to store the one or more representations as metadata in the one or more instances, as metadata in a storage linked to the one or more instances, or a combination thereof.

17. An apparatus of claim 11, wherein the apparatus is further caused to:

associating the one or more representations with respective time stamps; and

associating the one or more representations with the one or more other instances based, at least in part, on the time stamps.

18. An apparatus of claim 11, wherein the apparatus is further caused to:

receiving at least one of the one or more representations from one or more other devices, one or more other content streams, or a combination thereof.

19. An apparatus of claim 11, wherein the one or more representations are captured before, after, and/or while the one or more instances of the content stream are captured, and wherein the one or more representations correspond to one or more characteristics of the one or more objects.

20. An apparatus of claim 11, wherein the content stream is a live video stream, and the one or more instances are images, videos, audio recordings, or a combination thereof.