# US 2015/0103189 A1 · Applying Video Stabilization to a Multimedia Clip

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2015/0103189 A1
- Document ID: US20150103189A1
- Status: Published application
- Kind: A1
- Application number: 14/052,001
- Filed: 2013-10-11
- Published: 2015-04-16
- Earliest claimed: 2013-10-11
- Assignees: Facebook, Inc.
- Applicants: Facebook, Inc.
- Inventors: Alexandre Karpenko
- Web page: https://patentgrep.com/patent/US20150103189A1

## CPC

- H04N 23/683: {performed by a processor, e.g. controlling the readout of an image memory}
- H04N 23/6812: {based on additional sensors, e.g. acceleration sensors}
- H04N 23/682: {Vibration or motion blur correction}
- H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION

## Abstract

In one embodiment, a method includes determining one or more motions of a camera, where the motions correspond to movements of the camera during recording of a multimedia clip. The method also includes determining one or more amounts of light present during the recording, and from the determined motions and amounts of light, determining a motion-blur metric for the multimedia clip. The method further includes determining whether to apply a video-stabilization routine to the multimedia clip based on the motion-blur metric.

## Claims

### Claim 1

A method comprising:
by a computing device, determining one or more motions of a camera, where the motions correspond to movements of the camera during recording of a multimedia clip;
by the computing device, determining one or more amounts of light present during the recording;
by the computing device, from the determined motions and amounts of light, determining a motion-blur metric for the multimedia clip; and
by the computing device, determining whether to apply a video-stabilization routine to the multimedia clip based on the motion-blur metric.

### Claim 2 (depends on 1)

The method of claim 1, wherein:
determining one or more of the motions of the camera comprises:
by the computing device, receiving information from a motion sensor; and
by the computing device, from the motion-sensor information, determining one or more angular orientation changes of the camera; and
the motion sensor is a gyroscope.

### Claim 3 (depends on 1)

The method of claim 1, wherein the movements of the camera during recording are due at least in part to camera shake.

### Claim 4 (depends on 1)

The method of claim 1, wherein the computing device is a smartphone comprising a gyroscope and the camera.

### Claim 5 (depends on 1)

The method of claim 1, wherein determining one or more of the amounts of light present during the recording comprises, by the computing device, determining an exposure time for one or more image frames of the multimedia clip.

### Claim 6 (depends on 1)

The method of claim 1, wherein determining the motion-blur metric for the multimedia clip comprises, by the computing device, determining a product of an exposure time and a camera orientation change for a plurality of frames of the multimedia clip.

### Claim 7 (depends on 6)

The method of claim 6, wherein determining the motion-blur metric for the multimedia clip further comprises, by the computing device, determining an average value of the product of the exposure time and the camera orientation change for the plurality of frames.

### Claim 8 (depends on 1)

The method of claim 1, wherein determining whether to apply the video-stabilization routine comprises, by the computing device, determining whether the motion-blur metric is less than a predetermined threshold value.

### Claim 9 (depends on 1)

The method of claim 1, wherein determining whether to apply the video-stabilization routine comprises, by the computing device, determining whether approximately 95% or more of the multimedia clip would be substantially free of motion-blur artifacts after applying the video-stabilization routine to the multimedia clip.

### Claim 10 (depends on 1)

The method of claim 1, wherein determining whether to apply the video-stabilization routine comprises, by the computing device, determining whether approximately less than 5% of the multimedia clip would comprise motion-blur artifacts after applying the video-stabilization routine to the multimedia clip.

### Claim 11

One or more computer-readable non-transitory storage media embodying software that is operable when executed to:
determine one or more motions of a camera, where the motions correspond to movements of the camera during recording of a multimedia clip;
determine one or more amounts of light present during the recording;
from the determined motions and amounts of light, determine a motion-blur metric for the multimedia clip; and
determine whether to apply a video-stabilization routine to the multimedia clip based on the motion-blur metric.

### Claim 12 (depends on 11)

The media of claim 11, wherein:
the software is further operable when executed to:
receive information from a motion sensor; and
from the motion-sensor information, determine one or more angular orientation changes of the camera; and
the motion sensor is a gyroscope.

### Claim 13 (depends on 11)

The media of claim 11, wherein the movements of the camera during recording are due at least in part to camera shake.

### Claim 14 (depends on 11)

The media of claim 11, wherein the computing device is a smartphone comprising a gyroscope and the camera.

### Claim 15 (depends on 11)

The media of claim 11, wherein the software is further operable when executed to determine an exposure time for one or more image frames of the multimedia clip.

### Claim 16 (depends on 11)

The media of claim 11, wherein the software is further operable when executed to determine a product of an exposure time and a camera orientation change for a plurality of frames of the multimedia clip.

### Claim 17 (depends on 16)

The media of claim 16, wherein the software is further operable when executed to determine an average value of the product of the exposure time and the camera orientation change for the plurality of frames.

### Claim 18 (depends on 11)

The media of claim 11, wherein the software is further operable when executed to determine whether the motion-blur metric is less than a predetermined threshold value.

### Claim 19 (depends on 11)

The media of claim 11, wherein the software is further operable when executed to determine whether approximately 95% or more of the multimedia clip would be substantially free of motion-blur artifacts after applying the video-stabilization routine to the multimedia clip.

### Claim 20

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:
determine one or more motions of a camera, where the motions correspond to movements of the camera during recording of a multimedia clip;
determine one or more amounts of light present during the recording;
from the determined motions and amounts of light, determine a motion-blur metric for the multimedia clip; and
determine whether to apply a video-stabilization routine to the multimedia clip based on the motion-blur metric.
