# US 2021/0342978 A1 · Systems and methods for noise reduction

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

- Number: US 2021/0342978 A1
- Document ID: US20210342978A1
- Status: Published application
- Kind: A1
- Application number: 17/305,668
- Filed: 2021-07-13
- Published: 2021-11-04
- Earliest claimed: 2019-01-17
- Assignees: Zhejiang Dahua Technology Co., Ltd.
- Applicants: Zhejiang Dahua Technology Co., Ltd.
- Inventors: Keqiang YU
- Web page: https://patentgrep.com/patent/US20210342978A1

## CPC

- G06T 5/70: Denoising; Smoothing
- G06T 5/50: using two or more images, e.g. averaging or subtraction
- G06T 2207/10016: Video; Image sequence
- G06T 2207/20182: Noise reduction or smoothing in the temporal domain; Spatio-temporal filtering
- G06T 2207/20224: Image subtraction
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL

## Abstract

The present disclosure is related to systems and methods for noise reduction. The method includes determining a first image block in each of a group of continuous frames including a current frame and a plurality of reference frames based on coordinates of a target pixel in the current frame. The method includes determining at least one second image block corresponding to the first image block in each of the group of continuous frames. The method includes determining an average offset between the at least one second image block in the current frame and the second image blocks in the plurality of reference frames. The method includes determining a spatial domain filtering intensity and a temporal domain filtering intensity for the target pixel in the current frame.

## Claims

### Claim 1

A method for noise reduction implemented on a computing device having at least one processor and at least one storage device, the method comprising:
determining a first image block in each of a group of continuous frames including a current frame and a plurality of reference frames based on coordinates of a target pixel in the current frame;
determining at least one second image block corresponding to the first image block in each of the group of continuous frames, wherein the at least one second image block is similar with the corresponding first image block;
determining, based on coordinates of the second image blocks in the group of continuous frames, an average offset between the at least one second image block in the current frame and the second image blocks in the plurality of reference frames; and
determining, based on the average offset, a spatial domain filtering intensity and a temporal domain filtering intensity for the target pixel in the current frame.

### Claim 2 (depends on 1)

The method of claim 1, wherein a larger average offset-corresponds to a larger spatial domain filtering intensity and a smaller temporal domain filtering intensity for the target pixel in the current frame.

### Claim 3 (depends on 1)

The method of claim 1, further comprising:
performing a spatial domain filtering operation and a temporal domain filtering operation on the target pixel in the current frame based on the spatial domain filtering intensity, the temporal domain filtering intensity, and a spatial domain filter size.

### Claim 4 (depends on 3)

The method of claim 3, wherein performing the spatial domain filtering operation and the temporal domain filtering operation on the target pixel in the current frame based on the spatial domain filtering intensity, the temporal domain filtering intensity, and the spatial domain filter size, comprises:
performing, based on the spatial domain filtering intensity and the spatial domain filter size, the spatial domain filtering operation on the target pixel in the current frame to determine a first value of the target pixel in the current frame; and
performing, based on the temporal domain filtering intensity, the first value of the target pixel in the current frame, and a first value of a reference pixel in each reference frame of the plurality of reference frames, the temporal domain filtering operation on the target pixel in the current frame to determine a second value of the target pixel in the current frame, wherein the coordinates of the target pixel in the current image are the same as coordinates of the reference pixel in the each reference frame, and the first value of the reference pixel in the each reference frame is determined by performing a spatial domain filtering operation on the reference pixel in the each reference frame.

### Claim 5 (depends on 4)

The method of claim 4, wherein performing, based on the temporal domain filtering intensity, the first value of the target pixel in the current frame, and the first value of the reference pixel in the each reference frame of the plurality of reference frames, the temporal domain filtering operation on the target pixel in the current frame to determine the second value of the target pixel in the current frame, further comprises:
determining, based on a weight of the temporal domain filtering operation associated with the reference pixel in the each reference frame of the plurality of reference frames, a weight of the temporal domain filtering operation associated with the target pixel in the current frame, and the temporal domain filtering intensity, a target temporal domain filtering intensity for the reference pixel in the each reference frame of the plurality of reference frames and the target pixel in the current frame; and
performing, based on the first value of the reference pixel in the each reference frame of the plurality of reference frames, the first value of the target pixel in the current frame, and the target temporal domain filtering intensity for the reference pixel in the each reference frame of the plurality of reference frames and the target pixel in the current frame, the temporal domain filtering operation on the target pixel in the current frame to determine the second value of the target pixel in the current frame.

### Claim 6 (depends on 5)

The method of claim 5, further comprising:
determining, based on an original value of the target pixel, the first value of the target pixel, the weight of the temporal domain filtering operation associated with the target pixel, and a weight of the spatial domain filtering operation associated with the target pixel, an updated first value of the target pixel in the current frame, wherein a sum of the weight of the temporal domain filtering operation associated with the target pixel and the weight of the spatial domain filtering operation associated with the target pixel is 1.

### Claim 7 (depends on 6)

The method of claim 6, wherein determining, based on the original value of the target pixel, the first value of the target pixel, the weight of the temporal domain filtering operation associated with the target pixel, and the weight of the spatial domain filtering operation associated with the target pixel, the updated first value of the target pixel in the current frame, comprises:
determining a product of the original value of the target pixel and the weight of the temporal domain filtering operation associated with the target pixel;
determining a product of the first value of the target pixel and the weight of the spatial domain filtering operation associated with the target pixel; and
determining, based on a sum of the product of the original value of the target pixel and the weight of the temporal domain filtering operation associated with the target pixel, and the product of the first value of the target pixel and the weight of the spatial domain filtering operation associated with the target pixel, the updated first value of the target pixel in the current frame.

### Claim 8 (depends on 5)

The method of claim 5, wherein the weight of the temporal domain filtering operation associated with the reference pixel in the each reference frame of the plurality of reference frames is determined according to a process, the process comprising:
determining an absolute value of a difference between a filtered value of the reference pixel in the each reference frame and a filtered value of the target pixel in the current frame; and
determining, based on the absolute value of the difference and a preset relationship between the absolute value of the difference and the weight of the temporal domain filtering operation associated with the reference pixel in the each reference frame, the weight of the temporal domain filtering operation associated with the reference pixel in the each reference frame, wherein the weight of the temporal domain filtering operation associated with the reference pixel in the each reference frame is in a range of [0, 1], and a larger absolute value of the difference corresponding to a smaller weight of the temporal domain filtering operation associated with the reference pixel in the each reference frame.

### Claim 9 (depends on 3)

The method of claim 3, wherein the spatial domain filter size includes a radius of the spatial domain filter, and the radius of the spatial domain filter is determined according to a process, the process comprising:
determining, based on a filtered value of the reference pixel in the each reference frame of the plurality of reference frames and a filtered value of the target pixel in the current frame, a noise value; and
determining, based on the noise value and a preset relationship between the noise value and the radius of the spatial domain filter, the radius of the spatial domain filter, wherein a larger noise value corresponds to a larger radius of the spatial domain filter.

### Claim 10 (depends on 9)

The method of claim 9, wherein determining, based on the filtered value of the reference pixel in the each reference frame of the plurality of reference frame and the filtered value of the target pixel in the current frame, the noise value, further comprises:
determining, based on a difference between an average value of the filtered values of the reference pixels and the target pixels, and the filtered value of the target pixel in the current frame, the noise value.

### Claim 11 (depends on 10)

The method of claim 10, wherein at least one of the filtered value of the reference pixel in the each reference frame of the plurality of reference frame or the filtered value of the target pixel in the current frame is determined by using a Gauss filter.

### Claim 12 (depends on 1)

The method of claim 1, wherein the at least one second image block corresponding to the first image block in each of the group of continuous frames is determined according to a sum of absolute differences (SAD) algorithm.

### Claim 13

A system for noise reduction, comprising:
at least one storage medium storing a set of instructions; and
at least one processor in communication with the at least one storage medium, wherein when executing the stored set of instructions, the at least one processor causes the system to:
determine a first image block in each of a group of continuous frames including a current frame and a plurality of reference frames based on of a target pixel in the current frame;
determine at least one second image block corresponding to the first image block in each of the group of continuous frames, wherein the at least one second image block is similar with the corresponding first image block;
determine, based on coordinates of the second image blocks in the group of continuous frames, an average offset between the at least one second image block in the current frame and the second image blocks in the plurality of reference frames; and
determine, based on the average offset, a spatial domain filtering intensity and a temporal domain filtering intensity for the target pixel in the current frame.

### Claim 14

(canceled)

### Claim 15 (depends on 13)

The system of claim 13, wherein the at least one processor causes the system to:
perform a spatial domain filtering operation and a temporal domain filtering operation on the target pixel in the current frame based on the spatial domain filtering intensity, the temporal domain filtering intensity, and a spatial domain filter size.

### Claim 16 (depends on 15)

The system of claim 15, wherein to perform the spatial domain filtering operation and the temporal domain filtering operation on the target pixel in the current frame based on the spatial domain filtering intensity, the temporal domain filtering intensity, and the spatial domain filter size, the at least one processor causes the system to:
perform, based on the spatial domain filtering intensity and the spatial domain filter size, the spatial domain filtering operation on the target pixel in the current frame to determine a first value of the target pixel in the current frame; and
perform, based on the temporal domain filtering intensity, the first value of the target pixel in the current frame, and a first value of a reference pixel in each reference frame of the plurality of reference frames, the temporal domain filtering operation on the target pixel in the current frame to determine a second value of the target pixel in the current frame, wherein the coordinates of the target pixel in the current image are the same as coordinates of the reference pixel in the each reference frame, and the first value of the reference pixel in the each reference frame is determined by performing a spatial domain filtering operation on the reference pixel in the each reference frame.

### Claim 17 (depends on 16)

The system of claim 16, wherein to perform, based on the temporal domain filtering intensity, the first value of the target pixel in the current frame, and the first value of the reference pixel in the each reference frame of the plurality of reference frame, the temporal domain filtering operation on the target pixel in the current frame to determine the second value of the target pixel in the current frame, the at least one processor causes the system to:
determine, based on a weight of the temporal domain filtering operation associated with the reference pixel in the each reference frame of the plurality of reference frames, a weight of the temporal domain filtering operation associated with the target pixel in the current frame, and the temporal domain filtering intensity, a target temporal domain filtering intensity for the reference pixel in the each reference frame of the plurality of reference frames and the target pixel in the current frame; and
perform, based on the first value of the reference pixel in the each reference frame of the plurality of reference frames, the first value of the target pixel in the current frame, and the target temporal domain filtering intensity for the reference pixel in the each reference frame of the plurality of reference frames and the target pixel in the current frame, the temporal domain filtering operation on the target pixel in the current frame to determine the second value of the target pixel in the current frame.

### Claim 18 (depends on 17)

The system of claim 17, wherein the at least one processor causes the system to:
determine, based on an original value of the target pixel, the first value of the target pixel, the weight of the temporal domain filtering operation associated with the target pixel, and a weight of the spatial domain filtering operation associated with the target pixel, an updated first value of the target pixel in the current frame, wherein a sum of the weight of the temporal domain filtering operation associated with the target pixel and the weight of the spatial domain filtering operation associated with the target pixel is 1.

### Claim 19 (depends on 18)

The system of claim 18, wherein to determine, based on the original value of the target pixel, the first value of the target pixel, the weight of the temporal domain filtering operation associated with the target pixel, and the weight of the spatial domain filtering operation associated with the target pixel, the updated first value of the target pixel in the current frame, the at least one processor causes the system to:
determine a product of the original value of the target pixel and the weight of the temporal domain filtering operation associated with the target pixel;
determine a product of the first value of the target pixel and the weight of the spatial domain filtering operation associated with the target pixel; and
determine, based on a sum of the product of the original value of the target pixel and the weight of the temporal domain filtering operation associated with the target pixel, and the product of the first value of the target pixel and the weight of the spatial domain filtering operation associated with the target pixel, the updated first value of the target pixel in the current frame.

### Claim 20

(canceled)

### Claim 21 (depends on 15)

The system of claim 15, wherein the spatial domain filter size includes a radius of the spatial domain filter, and the radius of the spatial domain filter is determined according to a method process, the process comprising:
determining, based on a filtered value of the reference pixel in the each reference frame of the plurality of reference frames and a filtered value of the target pixel in the current frame, a noise value; and
determining based on the noise value and a preset relationship between the noise value and the radius of the spatial domain filter, the radius of the spatial domain filter, wherein a larger noise value corresponding corresponds to a larger radius of the spatial domain filter.

### Claim at position 22

22-24. (canceled)

### Claim 25

A non-transitory computer readable medium storing instructions, the instructions, when executed by at least one processor, causing the at least one processor to implement a method comprising:
determining a first image block in each of a group of continuous frames including a current frame and a plurality of reference frames based on coordinates of a target pixel in the current frame;
determining at least one second image block corresponding to the first image block in each of the group of continuous frames, wherein the at least one second image block is similar with the corresponding first image block;
determining, based on coordinates of the second image blocks in the group of continuous frames, an average offset between the at least one second image block in the current frame and the second image blocks in the plurality of reference frames; and
determining, based on the average offset, a spatial domain filtering intensity and a temporal domain filtering intensity for the target pixel in the current frame.

### Claim 26

(canceled)

### Claim 27

(canceled)
