Image selection from captured video sequence based on social components

Patent metadata

Field	Value
Publication number	US-9762956-B2
Application number	US-201313857075-A
Country	US
Kind code	B2
Filing date	Apr 4, 2013
Priority date	Oct 19, 2011
Publication date	Sep 12, 2017
Grant date	Sep 12, 2017

Abstract

In one embodiment, a mobile device analyzes frames before and after a particular frame of a real-time video to identify one or more social network objects, and selects one or more frames before and after the particular frame based on social network information for further storage in the mobile device.

First claim

What is claimed is:

1. A method comprising:
by a computing device, receiving one or more signals from an input device of a client computing device, the one or more signals comprising user input of an identifier of a selected one of a plurality of video frames within a video sequence;
by the computing device, analyzing the selected one of the plurality of video frames and a number of video frames occurring within a particular number of seconds before the selected video frame and a number of video frames occurring within a particular number of seconds after the selected video frame to identify one or more social network objects;
for each frame within the selected one of the plurality of video frames and the number of video frames occurring within the particular number of seconds before the selected video frame and the number of video frames occurring within the particular number of seconds after the selected video frame, computing a value based on the identified social network objects in each frame;
by the computing device, selecting, based on respective values of the frames, one or more top ranked frames of the selected one of the plurality of video frames and the number of video frames occurring within the particular number of seconds before the selected video frame and the number of video frames occurring within the particular number of seconds after the selected video frame; and
transmitting, to a display of the client computing device, the one or more top ranked frames.

2. The method of claim 1 , wherein, by the computing device, computing the value of each frame in the plurality of video frames of the video sequence further comprises:
by the computing device, for each frame of the sequence, assigning the value based on a number of social network objects identified in the each frame.

3. The method of claim 1 , wherein, by the computing device, computing the value of each frame in the plurality of video frames of the video sequence is further based on an affinity associated with each of the identified social network objects.

4. The method of claim 1 , wherein the video sequence is a real-time video.

5. The method of claim 1 , wherein at least part of the video sequence is stored in a buffer.

6. The method of claim 1 , wherein the user input comprises an indication for persistent storage received by the computing device.

7. One or more computer-readable non-transitory storage media embodying software that is operable when executed by a processor to:
receive one or more signals from an input device of a client computing device, the one or more signals comprising user input of an identifier of a selected one of a plurality of video frames in a video sequence;
analyze the selected one of the plurality of video frames and a number of video frames occurring within a particular number of seconds before the selected video frame and a number of video frames occurring within a particular number of seconds after the selected video frame to identify one or more social network objects;
for each frame within the selected one of the plurality of video frames and the number of video frames occurring within the particular number of seconds before the selected video frame and the number of video frames occurring within the particular number of seconds after the selected video frame, compute a value based on the identified social network objects in each frame;
select, based on respective values of the frames, one or more top ranked frames of the selected one of the plurality of video frames and the number of video frames occurring within the particular number of seconds before the selected video frame and the number of video frames occurring within the particular number of seconds after the selected video frame; and
transmit, to a display of the computing device, the one or more top ranked frames.

8. The media of claim 7 , wherein to compute the value of each frame in the plurality of video frames of the video sequence, the software is further operable when executed to:
for each frame of the video sequence, assign the value based on a number of social network objects identified in the each frame.

9. The media of claim 7 , wherein computing the value of each frame in the plurality of video frames of the video sequence is further based on an affinity associated with each of the identified social network objects.

10. The media of claim 7 , wherein the video sequence is a real-time video.

11. The media of claim 7 , wherein at least part of the video sequence is stored in a buffer.

12. The media of claim 7 , wherein the user input comprises an indication for persistent storage received by the computing device.

13. A system comprising:
one or more processors; and
a memory coupled to the processors comprising instructions executable by the processors, the processors being operable when executing the instructions to:
receive one or more signals from an input device of a client computing device, the one or more signals comprising user input of an identifier of a selected one of a plurality of video frames of a video sequence;
analyze the selected one of the plurality of video frames and a number of video frames occurring within a particular number of seconds before the selected video frame and a number of video frames occurring within a particular number of seconds after the selected video frame to identify one or more social network objects;
for each frame within the selected one of the plurality of video frames and the number of video frames occurring within the particular number of seconds before the selected video frame and the number of video frames occurring within the particular number of seconds after the selected video frame, compute a value based on the identified social network objects in each frame;
select, based on respective values of the frames, one or more top ranked frames of the selected one of the plurality of video frames and the number of video frames occurring within the particular number of seconds before the selected video frame and the number of video frames occurring within the particular number of seconds after the selected video frame; and
transmit, to a display of the client computing device, the one or more top ranked frames.

14. The system of claim 13 , wherein to compute the value of each frame in the plurality of video frames of the video sequence, the processors are further operable when executing the instructions to:
for each frame of the video sequence, assign the value based on a number of social network objects identified in the each frame.

15. The system of claim 13 , wherein computing the value of each frame in the plurality of video frames of the video sequence is further based on an affinity associated with each of the identified social network objects.

16. The system of claim 13 , wherein the video sequence is a real-time video.

17. The system of claim 13 , wherein at least part of the video sequence is stored in a buffer.

18. The system of claim 13 , wherein user input comprises an indication for persistent storage received by the computing device.

Assignees

• Bosworth Andrew Garrod
• Garcia David Harry
• Cuervo Oswald Soleio
• Facebook Inc

Inventors

• Bosworth Andrew Garrod
• Garcia David Harry
• Cuervo Oswald Soleio

Classifications

• G06V20/30 Primary

  in albums, collections or shared content, e.g. social network photos or video · CPC title

• H04N21/44

  Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream or rendering scenes according to encoded video stream scene graphs · CPC title

• H04N2201/212

  Selecting different recording or reproducing modes, e.g. high or low resolution, field or frame · CPC title

• G06K9/00677

  Physics · mapped topic

• G06F17/3079

  Physics · mapped topic