Video highlights with auto trimming

Patent metadata

Field	Value
Publication number	US-11538499-B1
Application number	US-201916730872-A
Country	US
Kind code	B1
Filing date	Dec 30, 2019
Priority date	Dec 30, 2019
Publication date	Dec 27, 2022
Grant date	Dec 27, 2022

Abstract

A server configured to receive video clips from a mobile device, such as eyewear. The server has an electronic processor enabled to execute computer instructions to process the video clips to identify one or more characteristics in the frames of the video clips. The processor selects the video clips having the identified characteristics in the frames and creates a set of the selected video clips having the identified characteristics in the frames. The processor automatically trims the video clips based on frames that have the identified characteristics to create trimmed video clip segments, and then sends the trimmed video clip segments to the mobile device.

First claim

What is claimed is:

1. A server having an electronic processor, the processor configured to execute computer instructions to:
a) automatically receive a plurality of video clips each comprised of frames from a mobile device during a first time period;
b) process the plurality of video clips to identify one or more characteristics in the frames of the plurality of video clips;
c) create a set of selected video clips having the identified characteristics in the frames, the one or more characteristics comprising whether the video frames contain segments depicting pets, a specified object, human emotions, or human speech;
d) automatically trim the set of selected video clips at the server responsive to a set of rules to create trimmed video clip segments, the set of rules specifying including portions of the selected video clips that include pets, the specified object, human emotions, or human speech, and delete other portions of the selected video clips that do not satisfy the set of rules and that have not been permanently saved by a user of the mobile device;
e) create video highlights from the trimmed video clip segments based on a number of trimmed video clip segments, a combined length in time of the trimmed video clip segments, and user determined variables including at least one of time of day, frequency, and length of trimmed video clip segments;
f) automatically send the video highlights created from the trimmed video clip segments to the mobile device at a selected time of day;
g) repeat the step a) during a second time period after the first time period, wherein the first time period and the second time period have approximately the same durations; and
h) repeat the steps b-f for the plurality of video clips received during the second time period.

2. The server as specified in claim 1 , wherein the mobile device comprises an electronic eyewear device.

3. The server as specified in claim 1 , wherein the trimmed video clip segments comprise a subset of the received plurality of video clips that is less than all the received plurality of video clips.

4. The server as specified in claim 3 , wherein the subset of the plurality of video clips are obtained within a selected time frame.

5. The server as specified in claim 4 , wherein the processor is configured to use computer vision (CV) to identify the one or more characteristics in the frames of the plurality of video clips.

6. The server as specified in claim 5 , wherein the identified characteristics comprise at least one of whether a camera from which the video clips were taken was obstructed or overexposed, a stability of the video frames of the video clip, or whether the video frames contain human speech.

7. A method of use of a server having an electronic processor and computer instructions, the processor:
a) automatically receiving a plurality of video clips each comprised of frames from a mobile device during a first time period;
b) processing the plurality of video clips to identify one or more characteristics in the frames of the plurality of video clips;
c) creating a set of selected video clips having the identified characteristics in the frames, the one or more characteristics comprising whether the video frames contain segments depicting pets, a specified object, human emotions, or human speech;
d) automatically trimming the set of selected video clips at the server responsive to a set of rules to create trimmed video clip segments, the set of rules specifying including portions of the selected video clips that include pets, the specified object, human emotions, or human speech, and deleting other portions of the selected video clips that do not satisfy the set of rules and that have not been permanently saved by a user of the mobile device;
e) creating video highlights from the trimmed video clip segments based on a number of trimmed video clip segments, a combined length in time of the trimmed video clip segments, and user determined variables including at least one of time of day, frequency, and length of trimmed video clip segments;
f) automatically sending the video highlights created from the trimmed video clip segments to the mobile device at a selected time of day;
g) repeating the step a) during a second time period after the first time period, wherein the first time period and the second time period have approximately the same durations; and
h) repeating the steps b-f for the plurality of video clips received during the second time period.

8. The method of claim 7 , wherein the mobile device comprises an electronic eyewear device.

9. The method as specified in claim 7 , wherein the trimmed video clip segments comprise a subset of the received plurality of video clips that is less than all the received plurality of video clips.

10. The method as specified in claim 9 , wherein the subset of the plurality of video clips are obtained within a selected time frame.

11. The method as specified in claim 10 , further comprising the processor using computer vision (CV) to identify the one or more characteristics in the frames of the plurality of video clips.

12. The method as specified in claim 11 , wherein the identified characteristics comprise at least one of whether a camera from which the video clips were taken was obstructed or overexposed, a stability of the video frames of the video clip, or whether the video frames contain human speech.

13. A non-transitory computer-readable medium storing program code which, when executed, is operative to cause a computing device to perform the steps of:
a) automatically receiving a plurality of video clips each comprised of frames from a mobile device during a first time period;
b) processing the plurality of video clips to identify one or more characteristics in the frames of the plurality of video clips;
c) creating a set of selected video clips having the identified characteristics in the frames, the one or more characteristics comprising whether the video frames contain segments depicting pets, a specified object, human emotions, or human speech;
d) automatically trimming the set of selected video clips at a server responsive to a set of rules to create trimmed video clip segments, the set of rules specifying including portions of the selected video clips that include pets, the specified object, human emotions, or human speech, and deleting other portions of the selected video clips that do not satisfy the set of rules and that have not been permanently saved by a user of the mobile device;
e) creating video highlights from the trimmed video clip segments based on a number of trimmed video clip segments, a combined length in time of the trimmed video clip segments, and user determined variables including at least one of time of day, frequency, and length of trimmed video clip segments;
f) automatically sending the video highlights created from the trimmed video clip segments to the mobile device at a selected time of day;
g) repeating the step a) during a second time period after the first time period, wherein the first time period and the second time period have approximately the same durations; and
h) repeating the steps b-f for the plurality of video clips received during the second time period.

14. The non-transitory computer readable medium as specified in claim 13 , wherein the mobile device comprises an electronic eyewear device.

15. The non-transitory computer readable medium as specified in claim 13 , wherein the trimmed video clip segments comprise a subset of the received plurality of video clips that is less than all the received plurality of video clips.

Assignees

• Snap Inc

Inventors

• Haim David Ben
• Huang Justin
• Litke Nathan
• Zak Eyal

Classifications

• G06V20/47

  Detecting features for summarising video content · CPC title

• G11B27/031 Primary

  Electronic editing of digitised analogue information signals, e.g. audio or video signals · CPC title