Comcast: Infrared Cameras Could Drive Customized Programming

Comcast may be able to deliver customized programming by relying on infrared cameras in subscriber homes to determine which household member is holding the remote control, the MSO disclosed in a recent patent application.

Bryan Yurasits, front-end Web developer at Comcast Interactive Media, and Maurice Gaston, Web developer at CIM, are named as inventors on the patent application. The “Command Source User Identification” invention was published by the U.S. Patent & Trademark Office on Dec. 24.

Abstract: A sensor-based system may detect users in a space who are consuming content, such as watching a television program. The system may capture images of the users, recognize features such as their faces and bodies to identify them, and capture a control signal, such as an infrared flash from a remote control device. The system may determine which user was manipulating the remote control, and may then associate the remote control command with the identified user. In this manner, users may be provided with a customized interactive experience.

Patent Application

Related:
Comcast Device Could Power Video Calls, Facial Recognition, ITV 

Claims: 

1. A method, comprising: capturing image information of a scene containing a plurality of users and a remote control signal using an imaging device; determining a location of the remote control signal in the scene based on the captured information; comparing the location of the remote control signal in the scene with the users based on the captured information; and determining which of the users initiated the remote control signal.

2. The method of claim 1, wherein the remote control signal is an infrared remote control signal.

3. The method of claim 1, wherein the comparing the location comprises determining distances between the location of the remote control signal and locations of identified body portions of the users.

4. The method of claim 3, wherein the identified body portions of the users comprise faces and at least a hand, arm, shoulder, or neck.

5. The method of claim 1, wherein the comparing the location comprises identifying an appendage connection between the location of the remote control signal and the location of a face of one of the plurality of users.

6. The method of claim 1, wherein the captured image information comprises three-dimensional image information.

7. The method of claim 1, comprising: identifying a face of each user; performing facial recognition on the face to identify each user; and responsive to determining a user initiated the remote control signal, displaying the user’s personal preferences.

8. A method, comprising: processing image information of a scene containing a plurality of users and a signal being transmitted; comparing a location of the signal in the image with locations of the users; and determining which of the users initiated the signal.

9. The method of claim 8, wherein the processing the image of the scene containing the plurality of users being transmitted to obtain a location of the signal and locations of the users in the image comprises: determining the location of the signal in the image; determining a number of users in the image; identifying a body part of each user in the image; and determining a location of the each identified body part in the image.

10. The method of claim 9, wherein the comparing the location of the signal in the image with the locations of the users comprises: determining a distance between the signal and each identified body part.

11. The method of claim 10, wherein the using results of the comparing to determine which of the users initiated the signal comprises: identifying the user associated with a smallest distance between the signal and an identified body part as an initiator of the signal.

12. The method of claim 8, wherein the image of the scene is a three-dimensional image.

13. The method of claim 8, comprising: capturing the image responsive to detecting transmission of the signal.

14. The method of claim 8, wherein the signal is an infrared remote control signal.

15. The method of claim 8, comprising: performing a recognition function to identify a body part of each user, wherein the comparing the location of the signal in the image with the locations of the users comprises determining whether an identified body part of a first user connects the first user to the signal, wherein the using results of the comparing to determine which of the users initiated the signal comprises responsive to determining that the identified body part of the first user connects the first user to the signal, associating the signal with the first user.

16-20. (canceled)

21. A non-transitory computer-readable medium storing computer-executable instructions that when executed cause an apparatus to perform at least the following: capturing image information of a scene containing a plurality of users and a remote control signal using an imaging device; determining a location of the remote control signal in the scene based on the captured information; comparing the location of the remote control signal in the scene with the users based on the captured information; and determining which of the users initiated the remote control signal.

22. The non-transitory computer-readable medium of claim 21, wherein the comparing the location comprises determining distances between the location of the remote control signal and locations of identified body portions of the users.

23. The non-transitory computer-readable medium of claim 22, wherein the identified body portions of the users comprise faces and at least a hand, arm, shoulder, or neck.

24. The non-transitory computer-readable medium of claim 21, wherein the comparing the location comprises identifying an appendage connection between the location of the remote control signal and the location of a face of one of the plurality of users

25. The non-transitory computer-readable medium of claim 21, wherein the computer-readable medium stores computer-executable instructions that when executed cause an apparatus to perform at least the following: identifying a face of each user; performing facial recognition on the face to identify each user; and responsive to determining a user initiated the remote control signal, displaying the user’s personal preferences.