Placing sponsored-content based on images in video content

• US 9,043,828 B1
• Filed: 12/28/2007
• Issued: 05/26/2015
• Est. Priority Date: 12/28/2007
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Jing, Yushi, Baluja, Shumeet
• Primary Examiner(s): TAYLOR, JOSHUA D
• Application Number:
  US11/966,587
• Time in Patent Office: 2,706 Days
• US Class Current: 725/32
• CPC Class Codes: G06Q 30/0241 Advertisements
• CPC Class Codes: H04N 21/23418 involving operations for analysing video streams, e.g. detecting features or characteristics television picture signal circuitry for scene change detection H04N5/147; filtering for image enhancement G06T5/00; methods or arrangements for recognising scenes G06V20/00; arrangements characterised by components specially adapted for monitoring, identification or recognition of video in broadcast systems H04H60/59
• CPC Class Codes: H04N 21/258 Client or end-user data management, e.g. managing client capabilities, user preferences or demographics, processing of multiple end-users preferences to derive collaborative data arrangements for services using the result on the distributing side of broadcast systems H04H60/66; profiles in network data switching protocols H04L67/30
• CPC Class Codes: H04N 21/2668 Creating a channel for a dedicated end-user group, e.g. insertion of targeted commercials based on end-user profiles information retrieval from the Internet by querying with filtering and personalisation G06F16/9535; arrangements for replacing or switching information during the broadcast H04H20/10; push services over packet-switching network H04L12/1859; adaptation of message content in packet-switching networks H04L51/063
• CPC Class Codes: H04N 21/812 involving advertisement data advertising per se G06Q30/02

Abstract

Sponsored-content may be placed based on images in video content. A first image in a frame of a video content item is identified. The first image is matched with a second stored image. A sponsored-content item to be presented is selected based on an association between the second stored image and the sponsored-content item.

Claims

1. A method comprising:

selecting, from a buffer, a first frame of a video content item;

selecting a region of interest of the video content item visible in the first frame;

identifying a first image in the region of interest;

using object recognition techniques to match, by a computer, the first image received in a request for an advertisement with a second stored image, the second stored image being directly associated with one or more sponsored-content items;

selecting, by the computer, a sponsored-content item from the one or more sponsored-content items to be presented based on an association between the second stored image and the sponsored-content item;

selecting, based on a dynamic sampling rate that depends on a number of frames in the buffer, a second frame of the video content item;

comparing the second frame of the video content item with the first frame of the video content item to determine whether the first and second frames are statistically similar; and

upon determining that the first and second frames are statistically similar, associating the first image from the first frame with the second frame and selecting an advertisement based on the first image from the first frame.

2. The method of claim 1 further comprising storing the sponsored-content item in association with the video content item for later retrieval and display while the video content item is being played.

3. The method of claim 1 further comprising:

playing the video content item; and

displaying the sponsored-content item within or adjacent to the video content item.

4. The method of claim 1 wherein matching comprises identifying that the first image that is identical to the second image.

5. The method of claim 1 wherein matching comprises identifying that the first image that is substantially similar to the second image.

6. The method of claim 1 wherein matching the first image comprises matching a sub-image of the first image with a second sub-image of the second image.

7. The method of claim 6 wherein matching the sub-image of the first image comprises:

using object recognition techniques to generate a likelihood that the second sub-image includes the first sub-image of the first image; and

wherein selecting a sponsored-content item comprises selecting a sponsored-content item to be presented based on a comparison between the likelihood and a threshold.

8. The method of claim 1 wherein selecting a sponsored-content item comprises selecting a sponsored-content item to be presented based on both a bid associated with the sponsored-content item and the association between the second stored image and the sponsored-content item.

9. The method of claim 1 wherein selecting a sponsored-content item comprises selecting a sponsored-content item to be presented based on both a maximum bid associated with the sponsored-content item and the association between the second stored image and the sponsored-content item.

10. The method of claim 1, wherein the association between the second stored image and the sponsored-content item comprises a pointer.

11. The method of claim 1, wherein the association between the second stored image and the sponsored-content item comprises a link.

12. The method of claim 1, wherein the association between the second stored image and the sponsored-content item comprises an association stored in a data store between the sponsored-content item and the image.

13. The method of claim 1, wherein matching the first image with the second stored image comprises matching the first image with the second stored image while the video is playing.

14. The method of claim 1, further comprising:

playing the video; and

displaying the advertisement while the video is playing.

15. A computer system comprising instructions, that when executed by the computer system, cause the computer system to perform operations comprising:

selecting, from a buffer, a first frame of a video content item;

selecting a region of interest of the video content item visible in the first frame;

identifying a first image in the region of interest;

using object recognition techniques to match the first image received in a request for an advertisement with a second stored image, the second stored image being directly associated with one or more sponsored-content items;

selecting a sponsored-content item from the one or more sponsored-content items to be presented based on an association between the second stored image and the sponsored-content item;

selecting, based on a dynamic sampling rate that depends on a number of frames in the buffer, a second frame of the video content item;

comparing the second frame of the video content item with the first frame of the video content item to determine whether the first and second frames are statistically similar; and

upon determining that the first and second frames are statistically similar, associating the first image from the first frame with the second frame and selecting an advertisement based on the first image from the first frame.

16. The computer system of claim 15 further comprising instructions to cause the computer to store the sponsored-content item in association with the video content item for later retrieval and display while the video content item is being played.

17. The computer system of claim 15 further comprising instructions to cause the computer to:

play the video content item; and

display the sponsored-content item within or adjacent to the video content item.

18. The computer system of claim 15 wherein matching comprises identifying that the first image that is identical to the second image.

19. The computer system of claim 15 wherein matching comprises identifying that the first image that is substantially similar to the second image.

20. The computer system of claim 15 wherein matching the first image comprises matching a sub-image of the first image with a second sub-image of the second image.

21. The computer system of claim 20 wherein matching the sub-image of the first image comprises:

using object recognition techniques to generate a likelihood that the second sub-image includes the first sub-image of the first image; and

wherein selecting a sponsored-content item comprises selecting a sponsored-content item to be presented based on a comparison between the likelihood and a threshold.

22. The computer system of claim 15 wherein selecting a sponsored-content item comprises selecting a sponsored-content item to be presented based on both a bid associated with the sponsored-content item and the association between the second stored image stored and the sponsored-content item.