# US 2018/0322670 A1 · Automated Action Shot Generation in a Digital Medium Environment

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

- Number: US 2018/0322670 A1
- Document ID: US20180322670A1
- Status: Published application
- Kind: A1
- Application number: 15/586,133
- Filed: 2017-05-03
- Published: 2018-11-08
- Earliest claimed: 2017-05-03
- Assignees: Adobe Systems Incorporated
- Applicants: Adobe Systems Incorporated
- Inventors: Vibha Tanda; Sagar Tandon; Abhishek Shah
- Web page: https://patentgrep.com/patent/US20180322670A1

## CPC

- G06V 40/25: {Recognition of walking or running movements, e.g. gait recognition}
- G06T 11/60: Creating or editing images; Combining images with text
- G06V 20/47: {Detecting features for summarising video content}
- G11B 27/031: Electronic editing of digitised analogue information signals, e.g. audio or video signals
- G11B 27/28: by using information signals recorded by the same method as the main recording {(G11B27/22 takes precedence)}
- G11B 27/34: Indicating arrangements {(indicating means incorporated in magazine or cassette G11B23/046 and G11B23/0875; indicating measured values in general G01D)}
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G11B: INFORMATION STORAGE BASED ON RELATIVE MOVEMENT BETWEEN RECORD CARRIER AND TRANSDUCER (recording measured values in a way that does not require playback through a transducer G01D9/00; recording or playback apparatus using mechanically marked tape, e.g. punched paper tape, or using unit records, e.g. punched or magnetically marked cards G06K; transferring data from one type of record carrier to another G06K1/18; circuits for coupling output of reproducer to radio receiver H04B1/20; gramophone pick-ups or like acoustic electromechanical transducers or circuits therefor H04R)

## Abstract

Automatic frame selection and action shot generation techniques in a digital medium environment are described. A computing device identifies an object in a foreground of video data. A determination is then made by the computing device as to motion of the object exhibited between frames of the video data. A subset of frames is then selected by the computing device based on a determined motion of the identified object depicting an action sequence. An action shot is generated by the computing device by overlaying the identified objects in the selected frames on a background

## Claims

### Claim 1

In a digital medium environment to select frames from video data describing object motion, a method implemented by a computing device, the method comprising:
identifying, by the computing device, an object in a foreground of the video data;
determining, by the computing device, motion of the object exhibited between a plurality of frames of the video data;
selecting, by the computing device, a subset of the plurality of frames based on the determined motion of the object as depicting an action sequence of the object; and
outputting, by the computing device, the selected subset of the plurality of frames.

### Claim 2 (depends on 1)

The method as described in claim 1, further comprising overlaying the identified object from each of the selected subset of the plurality of frames onto a background to generate an action shot frame.

### Claim 3 (depends on 2)

The method as described in claim 2, wherein the background is a background taken from one frame of the selected subset of the plurality of frames.

### Claim 4 (depends on 1)

The method as described in claim 1, wherein the determining is based at least in part on determining a change in dimension of the object exhibited between the plurality of frames.

### Claim 5 (depends on 1)

The method as described in claim 1, wherein the determining is based at least in part on determining a change in an angle of the object exhibited between the plurality of frames, the angle of the object defined based on a plane parallel to the plurality of frames.

### Claim 6 (depends on 1)

The method as described in claim 1, wherein the determining is based at least in part on determining a change in an angle of the object exhibited between the plurality of frames, the angle of the object defined based on a plane perpendicular to the plurality of frames.

### Claim 7 (depends on 1)

The method as described in claim 1, wherein the determining is based at least in part on determining a change in a position of a center of the object exhibited between the plurality of frames.

### Claim 8 (depends on 1)

The method as described in claim 1, wherein the determined motion of the object is a weighted summation of at least two of the following:
a change in dimension of the object;
a change in a first angle of the object, the first angle of the object defined based on a plane parallel to the plurality of frames;
a change in a second angle of the object, the second angle of the object defined based on a plane perpendicular to the plurality of frames; or
a change in a position of a center of the object.

### Claim 9 (depends on 8)

The method as described in claim 8, wherein weights of the weighted summation are defined based on a user input.

### Claim 10 (depends on 1)

The method as described in claim 1, wherein the determining further comprises determining a total motion of the object exhibited by the plurality of frames in the video data.

### Claim 11 (depends on 10)

The method as described in claim 10, wherein the selecting further comprises selecting a frame from the plurality of frames based on the frame having a cumulative score greater than a threshold, the cumulative score based on a fraction of the determined total motion of the object.

### Claim 12 (depends on 1)

The method as described in claim 1, wherein the selected subset of frames comprises non-overlapping instances of the object.

### Claim 13

In a digital medium environment to select frames from video data describing object motion, a system comprising:
an object tracking module implemented at least partially in hardware of a computing device to identify an object in a foreground of the video data;
a motion module implemented at least partially in hardware of a computing device to determine motion of the object exhibited between a plurality of frames of the video data;
a frame selection module implemented at least partially in hardware of a computing device to select a subset of the plurality of frames based on the determined motion of the object as depicting an action sequence of the object; and
an action shot module implemented at least partially in hardware of a computing device to overlay the identified object from each of the selected subset of the plurality of frames onto a background to generate an action shot.

### Claim 14 (depends on 13)

The system as described in claim 13, wherein the determined motion of the object is based on at least two of the following:
a change in dimension of the object;
a change in a first angle of the object, the first angle of the object defined based on a plane parallel to the plurality of frames;
a change in a second angle of the object, the second angle of the object defined based on a plane perpendicular to the plurality of frames; or
a change in a position of a center of the object.

### Claim 15 (depends on 13)

The system as described in claim 13, wherein:
the motion module is further configured to determine a total motion of the object exhibited by the plurality of frames in the video data; and
the frame selection module is further configured to select a frame from the plurality of frames as part of the subset based on the frame having a cumulative score greater than a threshold, the cumulative score based on a fraction of a determined total motion of the object.

### Claim 16 (depends on 13)

The system as described in claim 13, wherein the background is taken from a single frame of the selected subset of the plurality of frames.

### Claim 17

In a digital medium environment to select frames from video data describing object motion, a system comprising:
means for identifying an object in a foreground of the video data;
means for determining motion of the object exhibited between a plurality of frames of the video data;
means for selecting a subset of the plurality of frames based on the determined motion of the object as depicting an action sequence of the object; and
means for outputting the selected subset of the plurality of frames.

### Claim 18 (depends on 17)

The system as described in claim 17, further comprising means for overlaying the identified object in each of the selected subset of the plurality of frames onto a background to generate an action shot frame.

### Claim 19 (depends on 18)

The system as described in claim 18, wherein the overlaying of the identified object includes changing an opacity of the identified object in each of the selected subset of the plurality of frames.

### Claim 20 (depends on 17)

The system as described in claim 17, wherein the determined motion of the object comprises a weighted summation of at least two of the following:
a change in dimension of the object;
a change in a first angle of the object, the first angle of the object defined based on a plane parallel to the plurality of frames;
a change in a second angle of the object, the second angle of the object defined based on a plane perpendicular to the plurality of frames; or
a change in a position of a center of the object.
