# US 2023/0276125 A1 · Photographing method and electronic device

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

- Number: US 2023/0276125 A1
- Document ID: US20230276125A1
- Status: Published application
- Kind: A1
- Application number: 18/005,397
- Filed: 2021-07-08
- Published: 2023-08-31
- Earliest claimed: 2020-07-16
- Assignees: Huawei Technologies Co., Ltd.
- Applicants: Huawei Technologies Co., Ltd.
- Inventors: Dongsheng JIANG
- Web page: https://patentgrep.com/patent/US20230276125A1

## CPC

- H04N 5/2624: {for obtaining an image which is composed of whole input images, e.g. splitscreen}
- H04N 23/667: Camera operation mode switching, e.g. between still and video, sport and normal or high- and low-resolution modes
- G06F 3/017: {Gesture based interaction, e.g. based on a set of recognized hand gestures (interaction based on gestures traced on a digitiser G06F3/04883)}
- G06T 7/62: of area, perimeter, diameter or volume
- G06V 10/44: Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
- G06V 10/761: {Proximity, similarity or dissimilarity measures}
- H04N 23/61: based on recognised objects
- H04N 23/631: {Graphical user interfaces [GUI] specially adapted for controlling image capture or setting capture parameters}
- H04N 23/632: {for displaying or modifying preview images prior to image capturing, e.g. variety of image resolutions or capturing parameters}
- H04N 23/633: {for displaying additional information relating to control or operation of the camera}
- H04N 23/80: Camera processing pipelines; Components thereof
- H04N 23/90: Arrangement of cameras or camera modules, e.g. multiple cameras in TV studios or sports stadiums
- G06N 3/0895: Weakly supervised learning, e.g. semi-supervised or self-supervised learning
- H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

A photographing method and an electronic device are disclosed. The electronic device may determine feature information of each of at least one photographed object included in a photographing scene, and then determine at least one target photographing mode based on the feature information. Then, the electronic device obtains at least one image of the photographing scene in response to a first photographing instruction entered by a user. An imaging effect of the at least one image corresponds to the at least one target photographing mode. The electronic device may autonomously determine a photographing mode that better matches the photographing scene. This achieves high intelligence, and can obtain a plurality of images with different imaging effects by performing photographing once, thereby saving photographing resources and improving user experience.

## Claims

### Claim 1

A photographing method, comprising:
determining feature information of each of at least one photographed object comprised in a photographing scene, wherein the feature information comprises one or a combination of more of: a confidence level of the photographed object, a distance between the photographed object and a camera, or an image size of the photographed object;
determining at least one target photographing mode based on the feature information of each of the at least one photographed object; and
obtaining at least one image of the photographing scene in response to a first photographing instruction entered by a user, wherein an imaging effect of the at least one image corresponds to the at least one target photographing mode.

### Claim 2 (depends on 1)

The method according to claim 1, wherein the determining at least one target photographing mode based on the feature information of each of the at least one photographed object comprises:
performing calculation on the feature information of each of the at least one photographed object to obtain a calculation result corresponding to the photographed object; and
sequentially selecting a quantity of photographing modes in descending order of the calculation results to obtain the at least one target photographing mode.

### Claim 3 (depends on 2)

The method according to claim 2, wherein
the performing calculation on the feature information of each of the at least one photographed object to obtain a calculation result corresponding to the photographed object comprises:
calculating a comprehensive score E of the feature information of each photographed object according to an algorithm E=αx+βy+γz, wherein X is the confidence level of the photographed object, Y is the image size of the photographed object, Z is the distance between the photographed object and the camera, α is a first weight of the confidence level of the photographed object, β is a first weight of the image size of the photographed object, γ is a first weight of the distance between the photographed object and the camera, and α, β, and γ are values greater than 0 and less than 1; and
the sequentially selecting a quantity of photographing modes in descending order of the calculation results to obtain the at least one target photographing mode comprises:
sequentially selecting a quantity of confidence levels in descending order of the comprehensive scores E to obtain at least one target confidence level; and
determining a photographing mode corresponding to the at least one target confidence level as a target photographing mode, to obtain the at least one target photographing mode.

### Claim 4 (depends on 2)

The method according to claim 2, wherein
the performing calculation on the feature information of each of the at leas one photographed object to obtain a calculation result corresponding to the photographed object comprises:
calculating, according to an algorithm P=ax+by +cz, a probability value P that each photographed object is a photographed subject, wherein X is the confidence level of the photographed object, Y is the image size of the photographed object, Z is the distance between the photographed object and the camera, a is a second weight of the confidence level of the photographed object, b is a second weight of the image size of the photographed object, c is a second weight of the distance between the photographed object and the camera, and all of a, b, and c are values greater than 0 and less than 1; and
the sequentially selecting a quantity of photographing modes in descending order of the calculation results to obtain the at least one target photographing mode comprises:
sequentially selecting a quantity of photographing objects in descending order of the probability values P to obtain at least one target photographing object; and
determining a photographing mode matched upon determining that each of the at least one target photographing object is used as a photographing subject, to obtain the at least one target photographing mode.

### Claim 5 (depends on 1)

The method according to claim 1, wherein the obtaining at least one image of the photographing scene in response to a first photographing instruction entered by a user comprises:
when the at least one target photographing mode comprises at least two target photographing modes, and the at least two target photographing modes are different, obtaining an image of the photographing scene by using each of the at least two target photographing modes, to obtain at least two images of the photographing scene.

### Claim 6 (depends on 5)

The method according to claim 5, wherein the obtaining an image of the photographing scene by using each of the at least two target photographing modes comprises:
determining whether framing parameter differences between the at least two target photographing modes are all less than thresholds corresponding to corresponding framing parameters; and
upon determining that the framing parameter differences between the at least two target photographing modes are all less than the thresholds corresponding to the corresponding framing parameters, performing framing based on framing parameters of any one of the at least two target photographing modes to obtain framed image data, and separately processing the image data according to image processing algorithms of the at least two target photographing modes to obtain at least two images of the photographing scene; or
upon determining that any framing parameter difference between the at least two target photographing modes is greater than a threshold corresponding to a corresponding framing parameter, separately performing framing based on framing parameters of the at least two target photographing modes to obtain two pieces of image data, and processing corresponding image data according to image processing algorithms of the at least two target photographing modes to obtain at least two images of the photographing scene.

### Claim 7 (depends on 1)

The method according to claim 1, wherein the obtaining at least one image of the photographing scene in response to a first photographing instruction entered by a user comprises:
when the at least one target photographing mode is a portrait mode, sequentially selecting at least two photographed objects from the at least one photographed object in ascending order of distances;
obtaining framed image data of the photographing scene by using the portrait mode; and
processing the image data based on the portrait mode by using each of the at least two photographed objects as a photographed subject separately, to obtain at least two images of the photographing scene.

### Claim 8 (depends on 5)

The method according to claim 5, further comprising:
invoking at least two cameras to perform photographing in the at least one target photographing mode.

### Claim 9 (depends on 1)

The method according to claim 1, wherein after the obtaining at least one image of the photographing scene, the method further comprises:
receiving a first preview instruction input by the user; and
displaying the at least one image in a stacking mode, wherein, in the stacking mode, a first image in the at least one image is displayed over a second image in the at least one image and the first image is completely displayed.

### Claim 10 (depends on 9)

The method according to claim 9, further comprising:
receiving a first dynamic display instruction input by the user;
controlling the at least one image to be cyclically displayed at a frontmost end of a display;
receiving a first dynamic display stop instruction input by the user; and
controlling an image corresponding to the first dynamic display stop instruction to be statically displayed at the frontmost end.

### Claim 11 (depends on 9)

The method according to claim 9, further comprising:
receiving a second dynamic display instruction input by the user;
controlling the at least one image to be cyclically displayed at a frontmost end of a display;
receiving a second dynamic display stop instruction input by the user; and
controlling an image corresponding to the second dynamic display stop instruction to be statically displayed at the frontmost end.

### Claim 12 (depends on 1)

The method according to claim 1, wherein after the obtaining at least one image of the photographing scene, the method further comprises:
receiving a second preview instruction input by the user; and
displaying the at least one image in a stacking mode on a first screen, wherein, in the stacking mode, a first image in the at least one image is displayed over a second image in the at least one image and the first image is completely displayed on the first screen.

### Claim 13 (depends on 12)

The method according to claim 12, further comprising:
receiving a first gesture instruction input by the user; and
controlling an image corresponding to the first gesture instruction to be displayed on a second screen, and controlling an image under the image corresponding to the first gesture instruction to be displayed on the first screen.

### Claim 14 (depends on 12)

The method according to claim 12, further comprising:
receiving a third dynamic display instruction input by the user;
controlling the at least one image to be cyclically displayed at a frontmost end of the first screen;
receiving a second gesture instruction input by the user; and
controlling an image corresponding to the second gesture instruction to be displayed on a second screen.

### Claim 15 (depends on 9)

The method according to claim 9, wherein
the image displayed at a frontmost end of a display is marked with a photographing mode corresponding to the image.

### Claim 16 (depends on 15)

The method according to claim 15, further comprising:
receiving a second photographing instruction input by the user; and
performing photographing in the photographing scene by using a photographing mode corresponding to the second photographing instruction.

### Claim 17 (depends on 1)

The method according to claim 1, wherein before the determining feature information of each of at least one photographed object comprised in a photographing scene, the method further comprises:
receiving a first setting instruction input by the user;
displaying an image quantity setting entry in response to the first setting instruction; and
receive, by using the image quantity setting entry, a quantity of target images that are obtained by performing photographing and input by the user, wherein a quantity of the at least one image is greater than or equal to the quantity of target images.

### Claim 18

An electronic device, comprising a memory and one or more processors, the memory is configured to store computer program code including computer instructions that, when executed by the one or more processors, enable the electronic device to perform operations comprising:
determining feature information of each of at least one photographed object comprised in a photographing scene, wherein the feature information comprises one or a combination of more of: a confidence level of the photographed object, a distance between the photographed object and a camera, or an image size of the photographed object;
determining at least one target photographing mode based on the feature information of each of the at least one photographed object; and
obtaining at least one image of the photographing scene in response to a first photographing, instruction entered by a user, wherein an imaging effect of the at least one image corresponds to the at least one target photographing mode.

### Claim 19

(canceled)

### Claim 20

(canceled)

### Claim 21 (depends on 18)

The electronic device according to claim 18, wherein the obtaining at least one image of the photographing scene in response to a first photographing instruction entered by a user comprises:
when the at least one target photographing mode comprises at least two target photographing modes, and the at least two target photographing modes are different, obtaining an image of the photographing scene by using each of the at least two target photographing modes, to obtain at least two images of the photographing scene.

### Claim 22 (depends on 21)

The electronic device according to claim 21, wherein the obtaining an image of the photographing scene by using each of the at least two target photographing modes comprises:
determining whether framing parameter differences between the at least two target photographing modes are all less than thresholds corresponding to corresponding framing parameters; and
upon determining that the framing parameter differences between the at least two target photographing modes are all less than the thresholds corresponding to the corresponding framing parameters, performing framing based on framing parameters of any one of the at least two target photographing modes to obtain framed image data, and separately processing the image data according to image processing algorithms of the at least two target photographing modes to obtain at least two images of the photographing scene; or
upon determining that any framing parameter difference between the at least two target photographing modes is greater than a threshold corresponding to a corresponding framing parameter, separately performing framing based on framing parameters of the at least two target photographing modes to obtain two pieces of image data, and processing corresponding image data according to image processing algorithms of the at least two target photographing modes to obtain at least two images of the photographing scene.

### Claim 23 (depends on 18)

The electronic device according to claim 18, wherein the obtaining at least one image of the photographing scene in response to a first photographing instruction entered by a user comprises:
when the at least one target photographing mode is a portrait mode, sequentially selecting at least two photographed objects from the at least one photographed object in ascending order of distances;
obtaining framed image data of the photographing scene by using the portrait mode; and
processing the image data based on the portrait mode by using each of the at least two photographed objects as a photographed subject separately, to obtain at least two images of the photographing scene.
