# US 11,114,130 B2 · Method and device for processing video

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

- Number: US 11,114,130 B2
- Document ID: US11114130B2
- Status: Granted
- Kind: B2
- Application number: 16/918,894
- Filed: 2020-07-01
- Published: 2020-10-22
- Granted: 2021-09-07
- Earliest claimed: 2019-07-02
- Assignees: Beijing Dajia Internet Information Technology Co., Ltd.
- Applicants: Beijing Dajia Internet Information Technology Co., Ltd.
- Inventors: Peihong Hou; Yibing Ma
- Web page: https://patentgrep.com/patent/US11114130B2

## CPC

- G06T 11/60: Creating or editing images; Combining images with text
- G06V 20/46: {Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames}
- G11B 27/036: Insert-editing
- Y02D 10/00: Energy efficient computing, e.g. low power processors, power management or thermal management
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- 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)
- Y02D: CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE

## Abstract

The present disclosure provides a method and device for processing a video. The method includes: determining a special effect video frame of a video, where a target feature area of the special effect video frame includes a preset special effect map; and modifying a display effect of the special effect map upon determining that a shielded area exists in the target feature area.

## Claims

### Claim 1

A device for processing a video, comprising a memory and at least one processor, wherein the at least one processor is configured to read and execute instructions stored in the memory to:
determine a special effect video frame of the video, wherein a target feature area of the special effect video frame comprises a preset special effect map;
extract a mask corresponding to the special effect video frame;
determine a weight value of the special effect video frame based on topological relation information corresponding to the special effect video frame, the mask and a preset legal key point upon determining that the shielded area exists in the target feature area of the mask;
generate a replacing video frame based on the special effect video frame and the weight value; and
replace the special effect video frame with the replacing video frame.

### Claim 2 (depends on 1)

The device according to claim 1, wherein the at least one processor is further configured to read and execute instructions stored in the memory to:
map the mask to an empty graph layer based on the topological relation information, the mask, and the preset legal key point, wherein the empty graph layer has a preset size; and
obtain the weight value based on channel information of the empty graph layer, after setting transparency of the empty graph layer to a preset degree.

### Claim 3 (depends on 2)

The device according to claim 2, wherein the at least one processor is further configured to read and execute instructions stored in the memory to:
obtain a legal image with the preset size, wherein the legal image comprises the target feature area; and
extract the preset legal key point from the target feature area.

### Claim 4 (depends on 2)

The device according to claim 2, wherein the at least one processor is further configured to read and execute instructions stored in the memory to:
extract a pixel value of each pixel in the empty graph layer;
determine a swipe area value according to the pixel value of each pixel; and
replace the special effect map with another special effect map in response to the swipe area value being greater than or equal to a first preset threshold value.

### Claim 5 (depends on 4)

The device according to claim 4, wherein the at least one processor is further configured to read and execute instructions stored in the memory to:
determine a plurality of target pixels whose pixel values are greater than or equal to a second preset threshold value from all the pixels of the empty graph layer; and
take a ratio of a sum of the pixel values of the target pixels to the number of the target pixels as the swipe area value.

### Claim 6 (depends on 4)

The device according to claim 4, wherein the at least one processor is further configured to read and execute instructions stored in the memory to:
send the empty graph layer to a central processing unit through a graphics processor; and
extract the pixel value of each pixel in the empty graph layer by the central processing unit.

### Claim 7 (depends on 1)

The device according to claim 1, wherein the at least one processor is further configured to read and execute instructions stored in the memory to:
determine the weight value of the special effect video frame based on the topological relation information, the mask and the preset legal key point upon determining that a non-mask area exists in the target feature area of the mask.

### Claim 8 (depends on 1)

The device according to claim 1, wherein the at least one processor is further configured to read and execute instructions stored in the memory to:
extract a plurality of video frames of the video based on a preset time period;
collect a plurality of target key points of target feature areas in the video frames; and
determine the topological relation information based on relative position vector information among the plurality of target key points.

### Claim 9 (depends on 1)

The device according to claim 1, wherein the at least one processor is further configured to read and execute instructions stored in the memory to:
increase a size of the mask based on a preset multiple; and
fuzz the mask.

### Claim 10

A non-transitory computer readable storage medium, wherein the computer readable storage medium is stored with instructions thereon, and the instructions are executed by a processor to:
determine a special effect video frame of the video, wherein a target feature area of the special effect video frame comprises a preset special effect map;
extract a mask corresponding to the special effect video frame;
determine a weight value of the special effect video frame based on topological relation information corresponding to the special effect video frame, the mask and a preset legal key point upon determining that the shielded area exists in the target feature area of the mask;
generate a replacing video frame based on the special effect video frame and the weight value; and
replace the special effect video frame with the replacing video frame.

### Claim 11 (depends on 10)

The non-transitory computer readable storage medium according to claim 10, wherein the instructions are executed by the processor to:
map the mask to an empty graph layer based on the topological relation information, the mask, and the preset legal key point, wherein the empty graph layer has a preset size; and
obtain the weight value based on channel information of the empty graph layer, after setting transparency of the empty graph layer to a preset degree.

### Claim 12 (depends on 11)

The non-transitory computer readable storage medium according to claim 11, wherein the instructions are executed by the processor to:
obtain a legal image with the preset size, wherein the legal image comprises the target feature area; and
extract the preset legal key point from the target feature area.

### Claim 13 (depends on 11)

The non-transitory computer readable storage medium according to claim 11, wherein the instructions are executed by the processor to:
extract a pixel value of each pixel in the empty graph layer;
determine a swipe area value according to the pixel value of each pixel; and
replace the special effect map with another special effect map in response to the swipe area value being greater than or equal to a first preset threshold value.

### Claim 14 (depends on 13)

The non-transitory computer readable storage medium according to claim 13, wherein the instructions are executed by the processor to:
determine a plurality of target pixels whose pixel values are greater than or equal to a second preset threshold value from all the pixels of the empty graph layer; and
take a ratio of a sum of the pixel values of the target pixels to the number of the target pixels as the swipe area value.

### Claim 15 (depends on 13)

The non-transitory computer readable storage medium according to claim 13, wherein the instructions are executed by the processor to:
send the empty graph layer to a central processing unit through a graphics processor; and
extract the pixel value of each pixel in the empty graph layer by the central processing unit.

### Claim 16 (depends on 10)

The non-transitory computer readable storage medium according to claim 10, wherein the instructions are executed by the processor to:
determine the weight value of the special effect video frame based on the topological relation information, the mask and the preset legal key point upon determining that a non-mask area exists in the target feature area of the mask.

### Claim 17 (depends on 10)

The non-transitory computer readable storage medium according to claim 10, wherein the instructions are executed by the processor to:
extract a plurality of video frames of the video based on a preset time period;
collect a plurality of target key points of target feature areas in the video frames; and
determine the topological relation information based on relative position vector information among the plurality of target key points.

### Claim 18 (depends on 10)

The non-transitory computer readable storage medium according to claim 10, wherein the instructions are executed by the processor to:
increase a size of the mask based on a preset multiple; and
fuzz the mask.