Contextual advertising

• US 8,549,556 B2
• Filed: 01/08/2009
• Issued: 10/01/2013
• Est. Priority Date: 04/15/2008
• Status: Active Grant

• Current Assignee: Novafora, Inc.
• Original Assignee: Novafora, Inc.
• Inventors: Rakib, Shlomo Selim, Devictor, Gilles Bruno Marie
• Primary Examiner(s): Kumar, Pankaj
• Assistant Examiner(s): Tilahun, Alazar
• Application Number:
  US12/350,869
• Publication Number:
  US 20100005488A1
• Time in Patent Office: 1,727 Days
• Field of Search: 725/9, 725 32- 36, 725 86- 88, 725/102, 386/249
• US Class Current: 725/34
• CPC Class Codes: G06F 16/748 Hypervideo linking data to content, e.g. by linking an URL to a video object in the context of video distribution systems H04N21/858
• CPC Class Codes: G06F 16/7847 using low-level visual features of the video content
• CPC Class Codes: G06V 20/48 Matching video sequences

Abstract

A contextual advertising system and method receives video data and multiple advertisements associated with the video data. The system and method identify object content in the received video data and generates a video signal representing the video data. The video signal is communicated to a display device which displays a video image. User interaction with the displayed video image is monitored by the system and method. An advertisement is selected from the multiple received advertisements for display to the user. The advertisement is selected based on the user interaction with the displayed video image and the identified object content in the video data.

Claims

1. A method comprising:

receiving video data on a device equipped with at least one computer processor;

said video data comprising a plurality of 2D images without identified object content;

identifying object content in the received video data by using said at least one processor and computer vision algorithms to analyze said video data into a three dimensional structure of features and associated objects;

said three dimensional structure of video features and associated video objects comprising two spatial dimensions and one time dimension;

separately receiving a plurality of objects that are associated with advertisements,

wherein at least some of the objects that are associated with advertisements comprise objects that are similar to the associated video objects that are contained in said three dimensional structure;

generating a video signal representing the video data;

communicating the video signal to a display device, wherein the display device displays a video image;

monitoring user interaction with the displayed video image by monitoring user selection of said associated video objects and/or user control of video playback; and

using the plurality of received objects that are associated with advertisements, the monitored user interaction with the displayed video image, the video associated objects in the video data, and the similarity between the video associated objects in the video data and at least one object associated with advertisements to select an advertisement for display to the user.

2. The method of claim 1, wherein monitoring user interaction with the displayed video image includes monitoring user selection of an object in the displayed video image.

3. The method of claim 1, wherein monitoring user interaction with the displayed video image includes monitoring user control of playback of the displayed video image.

4. The method of claim 3, wherein the user control of playback includes pausing, fast forwarding, or rewinding playback of the displayed video image.

5. The method of claim 1, wherein selecting an advertisement for display includes offering the user an option to view the selected advertisement immediately.

6. The method of claim 5, further comprising deleting future advertisements associated with the video data if the user chooses to view the selected advertisement immediately.

7. The method of claim 1, wherein identifying object content in the received video data includes identifying an object position within the displayed video image.

8. The method of claim 1, wherein identifying object content in the received video data includes retrieving metadata associated with the video data, wherein the metadata identifies objects and associated object positions within the video data.

9. The method of claim 1, wherein said features comprise the coordinates of an image point of interest and a descriptor which describes the local image content or environment around said point of interest, said features and descriptors being chosen for their ability to persist when an image is rotated, presented with altered resolution, or presented with different lighting.

10. The method of claim 1, wherein said three dimensional structure comprises two spatial dimensions and one time dimension.

11. The method of claim 1, wherein user privacy is enhanced by further receiving and storing said plurality of objects that are associated with advertisements, and said advertisements, prior to monitoring user interaction with the displayed video image.

12. A method comprising:

receiving video data on a device equipped with at least one computer processor;

said video data comprising a plurality of 2D images without identified object content;

using said at least one processor and computer vision algorithms to analyze said video data into a three dimensional structure of video features and associated video objects;

said three dimensional structure of video features and associated video objects comprising two spatial dimensions and one time dimension;

wherein said features comprise the coordinates of a video image point of interest and a descriptor which describes the local video image content or environment around said video point of interest, said features and descriptors being chosen for their ability to persist when a video image is rotated, presented with altered resolution, or presented with different lighting;

separately receiving a plurality of objects that are associated with advertisements,

wherein at least some of the objects that are associated with advertisements comprise objects that are similar to the associated video objects that are contained in said three dimensional structure;

generating a video signal representing the video data;

communicating the video signal to a display device that displays a video image to a user;

monitoring user selection of an object displayed in the video image;

wherein if said user selects an object displayed in the video image, using the similarity between the user selected object and one more objects that are associated with advertisements to retrieve at least one advertisement associated with the selected object; and

display the retrieved advertisement to the user.

13. The method of claim 12, further comprising replacing an original advertisement contained in the received video data with the retrieved advertisement.

14. The method of claim 12, wherein user privacy is enhanced by further receiving and storing said plurality of objects that are associated with advertisements, and said advertisements, prior to monitoring user interaction with the displayed video image.

15. A method comprising:

receiving video data and general advertisement video data on a video player device equipped with at least one computer processor;

said video data and general advertisement video data comprising a plurality of 2D images without identified object content;

storing the received video data and general advertisement video data;

using said at least one processor and computer vision algorithms to analyze said video data and general advertisement video data into a three dimensional structure of video features and general advertisement features and associated video objects and general advertisement objects;

said three dimensional structure of the video features and general advertisement features and associated video objects and general advertisement objects comprising two spatial dimensions and one time dimension;

retrieving viewer potential interest advertisement data likely to be of interest to a viewer of the received video data and general advertisement video data;

said viewer potential interest advertisement data comprising viewer potential interest advertisements associated with various video objects or general advertisement objects that are contained in said three dimensional structure;

storing the retrieved viewer potential interest advertisement data;

identifying at least one preference associated with the viewer of the received video data and general advertisement video data by monitoring user selection of said video data and general advertisement objects and/or user control of video playback or general advertisement video playback;

selecting an viewer potential interest advertisement from the retrieved viewer potential interest advertisement data based on the identified preference associated with the viewer of the received video data and general advertisement video data; and

replacing one of the general advertisements contained in the received general advertisement video data with the selected viewer potential interest advertisement.

16. The method of claim 15, further comprising selecting additional viewer potential interest advertisements form the retrieved viewer potential interest advertisement data based on the identified preference associated with the viewer of the received video data and general advertisement video data, and replacing a plurality of the general advertisements contained in the received general advertisement video data with the selected additional viewer potential interest advertisements.

17. The method of claim 15, wherein identifying at least one preference associated with the viewer of the received video data and general advertisement video data includes monitoring the viewer'"'"'s interaction with the received video data and general advertisement video data.

18. The method of claim 17, wherein selecting a viewer potential interest advertisement from the retrieved viewer potential interest advertisement data is further based on the viewer'"'"'s interaction with the received video data and general advertisement video data.

19. The method of claim 17, wherein monitoring the viewer'"'"'s interaction with the received video data and general advertisement video data includes monitoring the viewer'"'"'s selection of an object in the received video data and general advertisement video data.

20. The method of claim 19, wherein monitoring the viewer'"'"'s selection of an object in the received video data and general advertisement video data includes identifying an object position within a frame of the received video data and general advertisement video data.

21. The method of claim 17, wherein monitoring the viewer'"'"'s interaction with the received video data and general advertisement video data includes monitoring the viewer'"'"'s control of playback of the received video data and general advertisement video data.

22. The method of claim 15, wherein selecting a viewer potential interest advertisement from the retrieved viewer potential interest advertisement data is further based on received metadata associated with the received viewer potential interest video data.

23. The method of claim 15, wherein said features comprise the coordinates of an image point of interest and a descriptor which describes the local image content or environment around said point of interest, said features and descriptors being chosen for their ability to persist when an image is rotated, presented with altered resolution, or presented with different lighting.

24. The method of claim 15, wherein said three dimensional structure comprises two spatial dimensions and one time dimension.