# US 12,001,479 B2 · Video processing method, video searching method, terminal device, and computer-readable storage medium

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

- Number: US 12,001,479 B2
- Document ID: US12001479B2
- Status: Granted
- Kind: B2
- Application number: 17/758,179
- Filed: 2020-08-25
- Published: 2023-02-09
- Granted: 2024-06-04
- Earliest claimed: 2019-12-30
- Assignees: Shenzhen Tcl New Technology Co., Ltd.
- Applicants: Shenzhen Tcl New Technology Co., Ltd.
- Inventors: Kaiwen Xue; Cheungming Lai; Yongze Xu
- Web page: https://patentgrep.com/patent/US12001479B2

## CPC

- G06F 16/7867: {using information manually generated, e.g. tags, keywords, comments, title and artist information, manually generated time, location and usage information, user ratings}
- G06F 16/784: {the detected or recognised objects being people}
- G06V 10/507: {Summing image-intensity values; Histogram projection analysis}
- G06V 10/761: {Proximity, similarity or dissimilarity measures}
- G06V 20/41: {Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items (segmenting video sequences G06V20/49)}
- G06V 20/46: {Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames}
- G06V 40/10: Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V 40/20: Movements or behaviour, e.g. gesture recognition (recognition of facial expressions G06V40/16)
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

A video processing method, including: according to scenes, editing a video to be edited, and obtaining a target video; acquiring feature parameters of the target video; generating, according to the feature parameters, keywords of the target video; and storing the keywords and the target video associatively.

## Claims

### Claim 1

A video processing method, wherein the video processing method comprises following steps:
editing a video to be edited, according to scenes in the video to be edited, into a plurality of segments as a plurality of target videos respectively corresponding to the plurality of scenes, wherein each of the target videos is a video where a corresponding one of the plurality of scenes is located;
acquiring feature parameters of each of the target videos;
generating keywords of each of the target videos according to the feature parameters of the target video; and
storing each of the target videos and the keywords of the target video associatively,
wherein the step of editing the video to be edited, according to the scenes in the video to be edited, into a plurality of segments as a plurality of target videos respectively corresponding to the plurality of scenes comprises:
extracting a plurality of image frames of the video to be edited in sequence at a preset frame rate;
converting the image frames into corresponding grayscale images;
determining whether there is a scene change in adjacent ones of the image frames according to the grayscale images of the adjacent ones of the image frames;
taking the adjacent ones of the image frames with the scene change as division frames when there is the scene change in the adjacent ones of the image frames; and
editing the video to be edited according to the division frames to acquire the target video, and
wherein the step of determining whether there is the scene change in the adjacent ones of the image frames according to the grayscale images of the adjacent ones of the image frames comprises:
extracting image blocks from the grayscale images corresponding to the adjacent ones of the image frames, respectively;
acquiring a number of pixels in each image block within each of preset grayscale ranges, to obtain numbers of pixels respectively in the adjacent ones of the image frames within each of the preset grayscale ranges;
acquiring an absolute value of a difference between the numbers of the pixels in the adjacent ones of the image frames within each of the preset grayscale ranges, to obtain absolute values of differences respectively within respective ones of the preset grayscale ranges;
summing the absolute values of the differences to acquire a sum; and
determining whether the sum is greater than a preset threshold, wherein it is determined that there is the scene change in the adjacent ones of the image frames when the sum is greater than the preset threshold.

### Claim 2 (depends on 1)

The video processing method as claimed in claim 1, wherein the step of acquiring the feature parameters of each of the target videos comprises:
extracting a plurality of image frames of the target video;
acquiring sub-feature parameters of the plurality of image frames of the target video; and
acquiring the feature parameters of the target video according to the sub-feature parameters.

### Claim 3 (depends on 2)

The video processing method as claimed in claim 2, wherein the step of acquiring the sub-feature parameters of the plurality of image frames of the target video comprises:
acquiring information on characters in the plurality of image frames of the target video; and
acquiring the sub-feature parameters according to behavior features of the characters corresponding to the information on the characters and human features of the characters corresponding to the information on the characters.

### Claim 4 (depends on 3)

The video processing method as claimed in claim 3, wherein the step of generating the keywords of the target video according to the feature parameters of the target video comprises:
acquiring a behavior feature category corresponding to the behavior features;
acquiring identity information corresponding to the human features; and
setting the behavior feature category and the identity information as the keywords of the target video.

### Claim 5 (depends on 4)

The video processing method as claimed in claim 4, further comprising:
adding behavior start time of a target character and behavior end time of the target character to the keywords of the target video.

### Claim 6 (depends on 4)

The video processing method as claimed in claim 4, wherein the step of acquiring the identity information corresponding to the human features further comprises:
comparing the human features and preset human features to acquire a comparison result;
acquiring the preset human features corresponding to the human features according to the comparison result; and
acquiring the identity information according to the preset human features corresponding to the human features.

### Claim 7 (depends on 6)

The video processing method as claimed in claim 6, wherein the human features comprise one or more of facial features, iris features, and body features, and the preset human features are corresponding to the human features.

### Claim 8 (depends on 6)

The video processing method as claimed in claim 6, further comprising:
determining that the comparison result is matched successfully and taking the identity information of the preset human features corresponding to the human features as identity information of the characters with the human features.

### Claim 9 (depends on 1)

The video processing method as claimed in claim 1, wherein the step of determining whether there is the scene change in the adjacent ones of the image frames according to the grayscale images of the adjacent ones of the image frames comprises:
extracting image blocks from the grayscale images corresponding to the adjacent ones of the image frames, respectively; and positions and sizes of the image blocks extracted in the adjacent ones of the image frames are same;
acquiring a number of pixels in each image block within each of preset grayscale ranges, to obtain numbers of pixels respectively in the adjacent ones of the image frames within each of the preset grayscale ranges;
acquiring an absolute value of a difference between the numbers of the pixels in the adjacent ones of the image frames within each of the preset grayscale ranges, to obtain absolute values of differences respectively within respective ones of the preset grayscale ranges;
summing the absolute values of the differences to acquire a sum; and
determining whether the sum is greater than a preset threshold, wherein determining that there is the scene change in the adjacent ones of the image frames when the sum is greater than the preset threshold.

### Claim 10 (depends on 1)

The video processing method as claimed in claim 1, wherein the feature parameters comprise one or more of scene parameters, information on characters, or sound parameters.

### Claim 11

A video searching method, wherein the video searching method comprises following steps:
acquiring target keywords entered in a search interface; and
searching a target video in a preset database according to the target keywords and displaying the target video associated with the target keywords; wherein the target video is acquired according to a video processing method,
wherein the video processing method comprises:
editing a video to be edited, according to scenes in the video to be edited, into a plurality of segments as a plurality of target videos respectively corresponding to the plurality of scenes, wherein each of the target video is a video where a corresponding one of the plurality of scenes is located;
acquiring feature parameters of each of the target videos;
generating keywords of each of the target videos according to the feature parameters of the target video; and
storing each of the target videos and the keywords of the target video associatively,
wherein the step of editing the video to be edited, according to the scenes in the video to be edited, into a plurality of segments as a plurality of target videos respectively corresponding to the plurality of scenes comprises:
extracting a plurality of image frames of the video to be edited in sequence at a preset frame rate;
converting the image frames into corresponding grayscale images;
determining whether there is a scene change in adjacent ones of the image frames according to the grayscale images of the adjacent ones of the image frames;
taking the adjacent ones of the image frames with the scene change as division frames when there is the scene change in the adjacent ones of the image frames; and
editing the video to be edited according to the division frames to acquire the target video, and
wherein the step of determining whether there is the scene change in the adjacent ones of the image frames according to the grayscale images of the adjacent ones of the image frames comprises:
extracting image blocks from the grayscale images corresponding to the adjacent ones of the image frames, respectively;
acquiring a number of pixels in each image block within each of preset grayscale ranges, to obtain numbers of pixels respectively in the adjacent ones of the image frames within each of the preset grayscale ranges;
acquiring an absolute value of a difference between the numbers of the pixels in the adjacent ones of the image frames within each of the preset grayscale ranges, to obtain absolute values of differences respectively within respective ones of the preset grayscale ranges;
summing the absolute values of the differences to acquire a sum; and
determining whether the sum is greater than a preset threshold, wherein determining that there is the scene change in the adjacent ones of the image frames when the sum is greater than the preset threshold.

### Claim 12

A terminal device, wherein the terminal device comprises a processor, a memory, and a video processing program or a video searching program stored in the memory and executable on the processor; the video processing program is executed by the processor to implement operations of a video processing method,
wherein the video processing method comprises:
editing a video to be edited, according to scenes in the video to be edited, into a plurality of segments as a plurality of target videos respectively corresponding to the plurality of scenes, wherein each of the target video is a video where a corresponding one of the plurality of scenes is located;
acquiring feature parameters of each of the target videos;
generating keywords of each of the target videos according to the feature parameters of the target video; and
storing each of the target videos and the keywords of the target video associatively,
wherein the step of editing the video to be edited, according to the scenes in the video to be edited, into a plurality of segments as a plurality of target videos respectively corresponding to the plurality of scenes comprises:
extracting a plurality of image frames of the video to be edited in sequence at a preset frame rate;
converting the image frames into corresponding grayscale images;
determining whether there is a scene change in adjacent ones of the image frames according to the grayscale images of the adjacent ones of the image frames;
taking the adjacent ones of the image frames with the scene change as division frames when there is the scene change in the adjacent ones of the image frames; and
editing the video to be edited according to the division frames to acquire the target video, and
wherein the step of determining whether there is the scene change in the adjacent ones of the image frames according to the grayscale images of the adjacent ones of the image frames comprises:
extracting image blocks from the grayscale images corresponding to the adjacent ones of the image frames, respectively;
acquiring a number of pixels in each image block within each of preset grayscale ranges, to obtain numbers of pixels respectively in the adjacent ones of the image frames within each of the preset grayscale ranges;
acquiring an absolute value of a difference between the numbers of the pixels in the adjacent ones of the image frames within each of the preset grayscale ranges, to obtain absolute values of differences respectively within respective ones of the preset grayscale ranges;
summing the absolute values of the differences to acquire a sum; and
determining whether the sum is greater than a preset threshold, wherein determining that there is the scene change in the adjacent ones of the image frames when the sum is greater than the preset threshold.

### Claim 13

A computer-readable storage medium, wherein the computer-readable storage medium stores a video processing program or a video searching program; the video processing program is executed by a processor to implement operations of a video processing method,
wherein the video processing method comprises:
editing a video to be edited, according to scenes in the video to be edited, into a plurality of segments as a plurality of target videos respectively corresponding to the plurality of scenes, wherein each of the target video is a video where a corresponding one of the plurality of scenes is located;
acquiring feature parameters of each of the target videos;
generating keywords of each of the target videos according to the feature parameters of the target video; and
storing each of the target videos and the keywords of the target video associatively,
wherein the step of editing the video to be edited, according to the scenes in the video to be edited, into a plurality of segments as a plurality of target videos respectively corresponding to the plurality of scenes comprises:
extracting a plurality of image frames of the video to be edited in sequence at a preset frame rate;
converting the image frames into corresponding grayscale images;
determining whether there is a scene change in adjacent ones of the image frames according to the grayscale images of the adjacent ones of the image frames;
taking the adjacent ones of the image frames with the scene change as division frames when there is the scene change in the adjacent ones of the image frames; and
editing the video to be edited according to the division frames to acquire the target video, and
wherein the step of determining whether there is the scene change in the adjacent ones of the image frames according to the grayscale images of the adjacent ones of the image frames comprises:
extracting image blocks from the grayscale images corresponding to the adjacent ones of the image frames, respectively;
acquiring a number of pixels in each image block within each of preset grayscale ranges, to obtain numbers of pixels respectively in the adjacent ones of the image frames within each of the preset grayscale ranges;
acquiring an absolute value of a difference between the numbers of the pixels in the adjacent ones of the image frames within each of the preset grayscale ranges, to obtain absolute values of differences respectively within respective ones of the preset grayscale ranges;
summing the absolute values of the differences to acquire a sum; and
determining whether the sum is greater than a preset threshold, wherein determining that there is the scene change in the adjacent ones of the image frames when the sum is greater than the preset threshold.