# US 2025/0157015 A1 · Video noise detection method and apparatus, and device and medium

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

- Number: US 2025/0157015 A1
- Document ID: US20250157015A1
- Status: Published application
- Kind: A1
- Application number: 18/725,617
- Filed: 2023-01-17
- Published: 2025-05-15
- Earliest claimed: 2022-01-27
- Applicants: Beijing Zitiao Network Technology Co., Ltd.
- Inventors: Qiubo CHEN
- Web page: https://patentgrep.com/patent/US20250157015A1

## CPC

- G06T 7/0002: {Inspection of images, e.g. flaw detection}
- G06T 3/02: Affine transformations (for image registration G06T3/147; for image mosaicing G06T3/4038)
- G06T 5/50: using two or more images, e.g. averaging or subtraction
- G06T 5/70: Denoising; Smoothing
- G06T 7/11: Region-based segmentation
- G06T 7/40: Analysis of texture (depth or shape recovery from texture G06T7/529)
- H04N 5/14: Picture signal circuitry for video frequency region (cameras or camera modules comprising electronic image sensors, or control thereof H04N23/00)
- H04N 17/00: Diagnosis, testing or measuring for television systems or their details
- G06T 2207/10016: Video; Image sequence
- G06T 2207/30168: Image quality inspection
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION

## Abstract

The present disclosure relates to a video noise detection method and apparatus, and a device and a medium. The video noise detection method includes: extracting a first video frame and a second video frame from a target video, wherein the first video frame and the second video frame are adjacent video frames; performing differential processing on the first video frame and the second video frame, so as to obtain an inter-frame differential image between the first video frame and the second video frame; performing flat area detection on the first video frame and the second video frame, to obtain an intersection of flat areas in the first video frame and the second video frame; and calculating a time-domain noise value corresponding to the first video frame by using pixel information of the intersection of the flat areas in the inter-frame differential image.

## Claims

### Claim 1

A video noise detection method, comprising:
extracting a first video frame and a second video frame from a target video, wherein the first video frame and the second video frame are adjacent video frames;
performing differential processing on the first video frame and the second video frame, to obtain an inter-frame differential image between the first video frame and the second video frame;
performing flat area detection on the first video frame and the second video frame, to obtain an intersection of flat areas in the first video frame and the second video frame; and
calculating a time-domain noise value corresponding to the first video frame by using pixel information of the intersection of the flat areas in the inter-frame differential image.

### Claim 2 (depends on 1)

The video noise detection method according to claim 1, wherein the pixel information comprises pixel values of pixels of the intersection of the flat areas in the inter-frame differential image, and the calculating a time-domain noise value corresponding to the first video frame by using pixel information of the intersection of the flat areas in the inter-frame differential image comprises:
calculating a weighted average of the pixel values of the pixels; and
taking the weighted average as the time-domain noise value corresponding to the first video frame.

### Claim 3 (depends on 2)

The video noise detection method according to claim 2, further comprising:
before the calculating a weighted average of the pixel values of the pixels, determining weights respectively corresponding to the pixel values based on a preset correspondence between the pixel value and the weight.

### Claim 4 (depends on 3)

The video noise detection method according to claim 3, wherein the calculating a weighted average of the pixel values of the pixels comprises:
for each pixel value, calculating a product of the pixel value and the weight corresponding to the pixel value, to obtain a weighted pixel value corresponding to the pixel value; and
performing weighted average calculation according to the weighted pixel values respectively corresponding to the pixel values, to obtain the weighted average.

### Claim 5 (depends on 1)

The video noise detection method according to claim 1, further comprising:
perform noise perception influence evaluation on at least one of the first video frame or the second video frame, to obtain a noise perception influence coefficient in at least one dimension.

### Claim 6 (depends on 5)

The video noise detection method according to claim 5, further comprising:
after the calculating a time-domain noise value corresponding to the first video frame by using pixel information of the intersection of the flat areas in the inter-frame differential image, obtaining a noise perception score of the first video frame according to the time-domain noise value and the noise perception influence coefficient of at least one dimension, the noise perception score being configured for evaluating visual perception of noise in the first video frame and/or whether to perform noise reduction processing on the first video frame.

### Claim 7 (depends on 5)

The video noise detection method according to claim 5, wherein:
the noise perception influence coefficient of at least one dimension comprises a detail richness influence coefficient, and the performing noise perception influence evaluation on the first video frame or the second video frame, to obtain a noise perception evaluation coefficient in at least one dimension, comprises: performing detail intensity detection on the first video frame or the second video frame, to obtain the detail richness influence coefficient; and/or
the evaluation coefficient of at least one dimension comprises a displacement rate influence coefficient, and the performing noise perception influence evaluation on the first video frame or the second video frame, to obtain a noise perception evaluation coefficient of at least one dimension, comprises: performing image displacement detection according to the first video frame and the second video frame, to obtain the displacement rate influence coefficient; and/or
the evaluation coefficient of at least one dimension comprises a luminance influence coefficient, and the performing noise perception influence evaluation on the first video frame or the second video frame, to obtain a noise perception evaluation coefficient of at least one dimension, comprises: performing highlight area detection on the first video frame or the second video frame, to obtain the luminance influence coefficient.

### Claim 8 (depends on 1)

The video noise detection method according to claim 1, wherein the performing flat area detection on the first video frame and the second video frame, to obtain an intersection of flat areas in the first video frame and the second video frame, comprises:
for any of the first video frame and the second video frame, performing flat area extraction on the video frame, to obtain the flat area of the video frame; and
performing an AND operation on the flat area of the first video frame and the flat area of the second video frame, to obtain the intersection of the flat areas.

### Claim 9 (depends on 8)

The video noise detection method according to claim 8, wherein the performing flat area extraction on the video frame, to obtain the flat area of the video frame, comprises:
performing image segmentation on the video frame, to obtain a plurality of image areas of the video frame;
determining a texture parameter of each of the image areas; and
taking an image area with the texture parameter less than a preset parameter threshold as the flat area of the video frame.

### Claim 10 (depends on 1)

The video noise detection method according to claim 1, further comprising:
before the performing differential processing on the first video frame and the second video frame, to obtain an inter-frame differential image between the first video frame and the second video frame, performing global alignment on the first video frame and the second video frame, to obtain aligned first video frame and second video frame.

### Claim 11 (depends on 10)

The video noise detection method according to claim 10, wherein the performing differential processing on the first video frame and the second video frame, to obtain an inter-frame differential image between the first video frame and the second video frame, comprises:
performing a differential operation on the aligned first video frame and second video frame, to obtain the inter-frame differential image.

### Claim 12 (depends on 10)

The video noise detection method according to claim 10, wherein the performing global alignment on the first video frame and the second video frame, to obtain aligned first video frame and second video frame, comprises:
performing luminance alignment processing on the first video frame and the second video frame, to obtain luminance-aligned first video frame and second video frame;
performing a phase alignment operation on the luminance-aligned first video frame and second video frame, to obtain a coordinate transformation relation between the first video frame and the second video frame;
performing affine transformation on the luminance-aligned first video frame by using the coordinate transformation relation, to obtain affine-transformed first video frame; and
taking the affine-transformed first video frame as the aligned first video frame, and taking the luminance-aligned second video frame as the aligned second video frame.

### Claim 13 (depends on 12)

The video noise detection method according to claim 12, wherein the performing a phase alignment operation on the luminance-aligned first video frame and second video frame, to obtain a coordinate transformation relation between the first video frame and the second video frame, comprises:
performing down-sampling of a preset multiple on the luminance-aligned first video frame and second video frame, to obtain down-sampled first video frame and down-sampled second video frame;
performing a phase alignment operation on the down-sampled first video frame and the down-sampled second video frame, to obtain a rotation matrix and a down-sampling translation vector;
multiplying the down-sampling translation vector by the preset multiple, to obtain an original offset; and
determining the coordinate transformation relation according to the rotation matrix and the original offset.

### Claim 14 (depends on 1)

The video noise detection method according to claim 1, further comprising:
after the calculating a time-domain noise value corresponding to the first video frame, determining whether to perform noise reduction processing on the first video frame according to the time-domain noise value.

### Claim 15 (depends on 1)

The video noise detection method according to claim 1, wherein the performing differential processing on the first video frame and the second video frame, to obtain an inter-frame differential image between the first video frame and the second video frame, comprises:
subtracting gray values of pixels in the first video frame from gray values of pixels in the second video frame at corresponding positions of the first video frame, respectively, to obtain pixel gray differences; and
taking an image formed by the pixel gray differences in a ranking order of corresponding pixels in the first video frame and the second video frame, as the inter-frame differential image between the first video frame and the second video frame.

### Claim 16

(canceled)

### Claim 17

A computing device, comprising:
a processor; and
a memory configured to store executable instructions,
wherein the processor is configured to read the executable instructions from the memory and execute the executable instructions to implement a video noise detection method comprising:
extracting a first video frame and a second video frame from a target video, wherein the first video frame and the second video frame are adjacent video frames;
performing differential processing on the first video frame and the second video frame, to obtain an inter-frame differential image between the first video frame and the second video frame;
performing flat area detection on the first video frame and the second video frame, to obtain an intersection of flat areas in the first video frame and the second video frame; and
calculating a time-domain noise value corresponding to the first video frame by using pixel information of the intersection of the flat areas in the inter-frame differential image.

### Claim 18

A non-transitory computer-readable storage medium having thereon stored a computer program which, when executed by a processor, causes the processor to perform a video noise detection method comprising:
extracting a first video frame and a second video frame from a target video, wherein the first video frame and the second video frame are adjacent video frames;
performing differential processing on the first video frame and the second video frame, to obtain an inter-frame differential image between the first video frame and the second video frame;
performing flat area detection on the first video frame and the second video frame, to obtain an intersection of flat areas in the first video frame and the second video frame; and
calculating a time-domain noise value corresponding to the first video frame by using pixel information of the intersection of the flat areas in the inter-frame differential image.

### Claim 19

(canceled)

### Claim 20 (depends on 17)

The computing device according to claim 17, wherein the pixel information comprises pixel values of pixels of the intersection of the flat areas in the inter-frame differential image, and the calculating a time-domain noise value corresponding to the first video frame by using pixel information of the intersection of the flat areas in the inter-frame differential image comprises:
calculating a weighted average of the pixel values of the pixels; and
taking the weighted average as the time-domain noise value corresponding to the first video frame.

### Claim 21 (depends on 18)

The non-transitory computer-readable storage medium according to claim 18, wherein the pixel information comprises pixel values of pixels of the intersection of the flat areas in the inter-frame differential image, and the calculating a time-domain noise value corresponding to the first video frame by using pixel information of the intersection of the flat areas in the inter-frame differential image comprises:
calculating a weighted average of the pixel values of the pixels; and
taking the weighted average as the time-domain noise value corresponding to the first video frame.
