# US 2023/0056296 A1 · Image exposure adjustment method and apparatus, device, and storage medium

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

- Number: US 2023/0056296 A1
- Document ID: US20230056296A1
- Status: Published application
- Kind: A1
- Application number: 17/791,800
- Filed: 2020-09-25
- Published: 2023-02-23
- Earliest claimed: 2020-01-22
- Assignees: Zhejiang Uniview Technologies Co., Ltd.
- Applicants: Zhejiang Uniview Technologies Co., Ltd.
- Inventors: Zhewen WENG; Wenhui ZHANG
- Web page: https://patentgrep.com/patent/US20230056296A1

## CPC

- G06T 5/92: based on global image properties
- H04N 23/611: where the recognised objects include parts of the human body
- G06T 3/40: Scaling of whole images or parts thereof, e.g. expanding or contracting
- G06T 5/70: Denoising; Smoothing
- G06T 5/94: based on local image properties, e.g. for local contrast enhancement
- G06T 7/11: Region-based segmentation
- G06T 7/155: involving morphological operators
- G06T 7/194: involving foreground-background segmentation
- G06V 10/25: Determination of region of interest [ROI] or a volume of interest [VOI]
- G06V 10/267: {by performing operations on regions, e.g. growing, shrinking or watersheds}
- G06V 10/60: relating to illumination properties, e.g. using a reflectance or lighting model
- G06V 40/103: {Static body considered as a whole, e.g. static pedestrian or occupant recognition}
- G06V 40/161: {Detection; Localisation; Normalisation}
- G06V 40/166: {using acquisition arrangements}
- H04N 23/71: Circuitry for evaluating the brightness variation
- H04N 23/76: by influencing the image signals
- G06T 2207/30201: Face
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

Provided are an image exposure adjustment method and apparatus, a device, and a medium. The image exposure adjustment method includes performing human body detection on a collected image; in a case where a human body is detected, segmenting the image to determine a foreground region and a background region in the image; determining a mask image according to the foreground region and the background region; and determining an exposure weight table according to the mask image, and performing exposure value adjustment on the image according to the exposure weight table.

## Claims

### Claim 1

An image exposure adjustment method, comprising:
performing human body detection on a collected image;
in a case where a human body is detected, segmenting the image to determine a foreground region and a background region in the image;
determining a mask image according to the foreground region and the background region; and
determining an exposure weight table according to the mask image, and performing exposure value adjustment on the image according to the exposure weight table.

### Claim 2 (depends on 1)

The method according to claim 1, wherein segmenting the image to determine the foreground region and the background region in the image comprises:
segmenting the image according to a preset Gaussian mixture model to determine the foreground region and the background region in the image; and
wherein determining the mask image according to the foreground region and the background region comprises:
performing denoising processing and binarization processing on both the foreground region and the background region to obtain the mask image, wherein the denoising processing comprises filtering processing, erosion processing and dilation processing.

### Claim 3 (depends on 1)

The method according to claim 1, wherein determining the exposure weight table according to the mask image comprises:
scaling down or scaling up the mask image in equal proportion according to a data size of an image signal processor to obtain a new mask image;
in a case of scaling down the mask image in equal proportion, counting a number of first-type pixel points in each of pixel units in the new mask image, determining a number ratio of the number of first-type pixel points in each of the pixel units to a number of total pixel points in the each of the pixel units, and determining an exposure weight of each of the pixel units according to the number ratio, wherein each of the pixel units comprises at least two pixel points;
in a case of scaling up the mask image in equal proportion, determining an area of first-type pixel points in each of the pixel units in the new mask image, determining an area ratio of the area of first-type pixel points in each of the pixel units to an area of the each of the pixel units, and determining an exposure weight of each of the pixel units according to the area ratio; and
constructing the exposure weight table based on the exposure weight of each of the pixel units.

### Claim 4 (depends on 3)

The method according to claim 3, wherein determining the exposure weight of the each of the pixel units according to the number ratio comprises:
in a case where a number ratio of a number of first-type pixel points in one of the pixel units to a number of total pixel points in the one of pixel units is greater than a number ratio threshold, resetting an exposure weight of the one of the pixel units to a first value; and
in a case where a number ratio of a number of first-type pixel points in one of the pixel units to a number of total pixel points in the one of the pixel units is less than or equal to the number ratio threshold, resetting an exposure weight of the one of the pixel units to a second value.

### Claim 5 (depends on 3)

The method according to claim 3, wherein determining the exposure weight of the each of the pixel units according to the area ratio comprises:
in a case where an area of first-type pixel points in one of the pixel units to an area of the one of the pixel units is greater than an area ratio threshold, resetting an exposure weight of the one of the pixel units to a first value; and
in a case where an area of first-type pixel points in one of the pixel units to an area of the one of the pixel units is less than or equal to the area ratio threshold, resetting an exposure weight of the one of the pixel units to a second value.

### Claim 6 (depends on 1)

The method according to claim 1, wherein performing the exposure value adjustment on the image according to the exposure weight table comprises:
segmenting the image according to a size of the exposure weight table to obtain a processed image;
determining a metering region according to a correspondence between the exposure weight table and the processed image; and
determining a first exposure adjustment parameter according to the metering region, and performing the exposure value adjustment on the image according to the first exposure adjustment parameter.

### Claim 7 (depends on 6)

The method according to claim 6, wherein determining the metering region according to the correspondence between the exposure weight table and the processed image comprises:
determining a pixel unit whose exposure weight is a first value in the processed image according to the correspondence between the exposure weight table and the processed image, and using a region where the pixel unit whose exposure weight is the first value is located as the metering region.

### Claim 8 (depends on 1)

The method according to claim 1, after performing the exposure value adjustment on the image according to the exposure weight table, further comprising:
performing face detection on an adjusted image;
in a case where a face is detected, using a region where the face is located as a metering region, and determining a second exposure adjustment parameter according to the metering region; and
performing the exposure value adjustment on the adjusted image according to the second exposure adjustment parameter.

### Claim 9

(canceled)

### Claim 10

An electronic device, comprising:
at least one processor; and
a storage apparatus, configured to store at least one program;
wherein the at least one program is configured to execute instructions causing the at least one processor to:
perform human body detection on a collected image;
in a case where a human body is detected, segment the image to determine a foreground region and a background region in the image;
determine a mask image according to the foreground region and the background region; and
determine an exposure weight table according to the mask image, and perform exposure value adjustment on the image according to the exposure weight table.

### Claim 11

A non-transitory computer-readable storage medium comprising instructions stored thereon to cause at least one processor to:
perform human body detection on a collected image;
in a case where a human body is detected, segment the image to determine a foreground region and a background region in the image;
determine a mask image according to the foreground region and the background region; and
determine an exposure weight table according to the mask image, and performing exposure value adjustment on the image according to the exposure weight table.

### Claim 12 (depends on 10)

The electronic device according to claim 10, wherein the at least one program is configured to execute the instructions causing the at least one processor to segment the image to determine the foreground region and the background region in the image in the following way:
segmenting the image according to a preset Gaussian mixture model to determine the foreground region and the background region in the image; and
wherein the at least one program is configured to execute the instructions causing the at least one processor to determine the mask image according to the foreground region and the background region in the following way:
performing denoising processing and binarization processing on both the foreground region and the background region to obtain the mask image, wherein the denoising processing comprises filtering processing, erosion processing and dilation processing.

### Claim 13 (depends on 10)

The electronic device according to claim 10, wherein the at least one program is configured to execute the instructions causing the at least one processor to determine the exposure weight table according to the mask image in the following way:
scaling down or scaling up the mask image in equal proportion according to a data size of an image signal processor to obtain a new mask image;
in a case of scaling down the mask image in equal proportion, counting a number of first-type pixel points in each of pixel units in the new mask image, determining a number ratio of the number of first-type pixel points in each of the pixel units to a number of total pixel points in the each of the pixel units, and determining an exposure weight of each of the pixel units according to the number ratio, wherein each of the pixel units comprises at least two pixel points;
in a case of scaling up the mask image in equal proportion, determining an area of first-type pixel points in each of the pixel units in the new mask image, determining an area ratio of the area of first-type pixel points in each of the pixel units to an area of the each of the pixel units, and determining an exposure weight of each of the pixel units according to the area ratio; and
constructing the exposure weight table based on the exposure weight of each of the pixel units.

### Claim 14 (depends on 13)

The electronic device according to claim 13, wherein the at least one program is configured to execute the instructions causing the at least one processor to determine the exposure weight of the each of the pixel units according to the number ratio in the following way:
in a case where a number ratio of a number of first-type pixel points in one of the pixel units to a number of total pixel points in the one of pixel units is greater than a number ratio threshold, resetting an exposure weight of the one of the pixel units to a first value; and
in a case where a number ratio of a number of first-type pixel points in one of the pixel units to a number of total pixel points in the one of the pixel units is less than or equal to the number ratio threshold, resetting an exposure weight of the one of the pixel units to a second value.

### Claim 15 (depends on 13)

The electronic device according to claim 13, wherein the at least one program is configured to execute the instructions causing the at least one processor to determine the exposure weight of the each of the pixel units according to the area ratio in the following way:
in a case where an area of first-type pixel points in one of the pixel units to an area of the one of the pixel units is greater than an area ratio threshold, resetting an exposure weight of the one of the pixel units to a first value; and
in a case where an area of first-type pixel points in one of the pixel units to an area of the one of the pixel units is less than or equal to the area ratio threshold, resetting an exposure weight of the one of the pixel units to a second value.

### Claim 16 (depends on 10)

The electronic device according to claim 10, wherein the at least one program is configured to execute the instructions causing the at least one processor to perform the exposure value adjustment on the image according to the exposure weight table in the following way:
segmenting the image according to a size of the exposure weight table to obtain a processed image;
determining a metering region according to a correspondence between the exposure weight table and the processed image; and
determining a first exposure adjustment parameter according to the metering region, and performing the exposure value adjustment on the image according to the first exposure adjustment parameter.

### Claim 17 (depends on 16)

The electronic device according to claim 16, wherein the at least one program is configured to execute the instructions causing the at least one processor to determine the metering region according to the correspondence between the exposure weight table and the processed image in the following way:
determining a pixel unit whose exposure weight is a first value in the processed image according to the correspondence between the exposure weight table and the processed image, and using a region where the pixel unit whose exposure weight is the first value is located as the metering region.

### Claim 18 (depends on 10)

The electronic device according to claim 10, after performing the exposure value adjustment on the image according to the exposure weight table, the at least one program being configured to execute the instructions causing the at least one processor further to:
perform face detection on an adjusted image;
in a case where a face is detected, use a region where the face is located as a metering region, and determine a second exposure adjustment parameter according to the metering region; and
perform the exposure value adjustment on the adjusted image according to the second exposure adjustment parameter.

### Claim 19 (depends on 11)

The non-transitory computer-readable storage medium according to claim 11, wherein the instructions cause the at least one processor to segment the image to determine the foreground region and the background region in the image in the following way:
segmenting the image according to a preset Gaussian mixture model to determine the foreground region and the background region in the image; and
wherein the program, when executed by a processor, performs determining the mask image according to the foreground region and the background region in the following way:
performing denoising processing and binarization processing on both the foreground region and the background region to obtain the mask image, wherein the denoising processing comprises filtering processing, erosion processing and dilation processing.

### Claim 20 (depends on 11)

The non-transitory computer-readable storage medium according to claim 11, wherein the instructions cause the at least one processor to determine the exposure weight table according to the mask image in the following way:
scaling down or scaling up the mask image in equal proportion according to a data size of an image signal processor to obtain a new mask image;
in a case of scaling down the mask image in equal proportion, counting a number of first-type pixel points in each of pixel units in the new mask image, determining a number ratio of the number of first-type pixel points in each of the pixel units to a number of total pixel points in the each of the pixel units, and determining an exposure weight of each of the pixel units according to the number ratio, wherein each of the pixel units comprises at least two pixel points;
in a case of scaling up the mask image in equal proportion, determining an area of first-type pixel points in each of the pixel units in the new mask image, determining an area ratio of the area of first-type pixel points in each of the pixel units to an area of the each of the pixel units, and determining an exposure weight of each of the pixel units according to the area ratio; and
constructing the exposure weight table based on the exposure weight of each of the pixel units.

### Claim 21 (depends on 20)

The non-transitory computer-readable storage medium according to claim 20, wherein the instructions cause the at least one processor to determine the exposure weight of the each of the pixel units according to the number ratio in the following way:
in a case where a number ratio of a number of first-type pixel points in one of the pixel units to a number of total pixel points in the one of pixel units is greater than a number ratio threshold, resetting an exposure weight of the one of the pixel units to a first value; and
in a case where a number ratio of a number of first-type pixel points in one of the pixel units to a number of total pixel points in the one of the pixel units is less than or equal to the number ratio threshold, resetting an exposure weight of the one of the pixel units to a second value.
