CN110347877A - A kind of method for processing video frequency, device, electronic equipment and storage medium - Google Patents
A kind of method for processing video frequency, device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN110347877A CN110347877A CN201910569106.6A CN201910569106A CN110347877A CN 110347877 A CN110347877 A CN 110347877A CN 201910569106 A CN201910569106 A CN 201910569106A CN 110347877 A CN110347877 A CN 110347877A
- Authority
- CN
- China
- Prior art keywords
- frame
- processed
- video
- region
- human
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 50
- 238000012545 processing Methods 0.000 title claims abstract description 26
- 238000012216 screening Methods 0.000 claims abstract description 17
- 230000009467 reduction Effects 0.000 claims description 25
- 238000004891 communication Methods 0.000 claims description 19
- 230000001815 facial effect Effects 0.000 claims description 12
- 230000008569 process Effects 0.000 claims description 11
- 238000004590 computer program Methods 0.000 claims description 8
- 230000015572 biosynthetic process Effects 0.000 abstract description 4
- 210000000746 body region Anatomy 0.000 abstract description 4
- 238000005516 engineering process Methods 0.000 abstract description 4
- 238000003786 synthesis reaction Methods 0.000 abstract description 4
- 238000010586 diagram Methods 0.000 description 20
- 238000004422 calculation algorithm Methods 0.000 description 3
- 210000003423 ankle Anatomy 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 210000001981 hip bone Anatomy 0.000 description 2
- 210000003127 knee Anatomy 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 238000000802 evaporation-induced self-assembly Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 210000002414 leg Anatomy 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000002194 synthesizing effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
- G06F16/78—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/783—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
- G06F16/7837—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content using objects detected or recognised in the video content
- G06F16/784—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content using objects detected or recognised in the video content the detected or recognised objects being people
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
- H04N21/44—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream or rendering scenes according to encoded video stream scene graphs
- H04N21/44008—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream or rendering scenes according to encoded video stream scene graphs involving operations for analysing video streams, e.g. detecting features or characteristics in the video stream
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20112—Image segmentation details
- G06T2207/20132—Image cropping
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Library & Information Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Signal Processing (AREA)
- Image Processing (AREA)
Abstract
This application involves a kind of method for processing video frequency, device, electronic equipment and storage mediums, this method comprises: screening includes the frame to be processed of target person from video to be processed；The human region of the target person is identified from the frame to be processed；From the frame to be processed cut obtain include the human region clipping region image；It is generated according to the clipping region image and cuts video.The technical solution comes out each frame image zooming-out that video includes target person, identifies the human region in each frame image, and carry out into cutting based on the people's body region, the image synthesis after cutting is cut video.In this way, due to cut be based on human region, compared with the existing technology for, cut the human body image in video than more complete, also, human body image is in intermediate position in cutting out video, display is obvious.In addition, the content being not concerned with due to having eliminated other users, so that cutting out the content of the target person in video only including user's concern.
Description
Technical field
This application involves data processing fields more particularly to a kind of method for processing video frequency, device, electronic equipment and storage to be situated between
Matter.
Background technique
With the development of internet, more and more users watch video content in each network video platform.
Currently, existing network video platform have " only see that TA sees function, can be the segment in video about designated person
It picks out.The function is to play the time slice containing designated person, is to carry out editing to video on a timeline.
Although the prior art can come out the time slice editing comprising designated person according to user's needs, depending on
The position of the designated person may be in Video Edge position in frequency content.
Summary of the invention
In order to solve the above-mentioned technical problem or it at least is partially solved above-mentioned technical problem, this application provides a kind of views
Frequency processing method, device, electronic equipment and storage medium.
In a first aspect, this application provides a kind of method for processing video frequency, comprising:
Screening includes the frame to be processed of target person from video to be processed；
The human region of the target person is identified from the frame to be processed；
From the frame to be processed cut obtain include the human region clipping region image；
It is generated according to the clipping region image and cuts video.
Optionally, the screening from video to be processed includes the frame to be processed of target person, comprising:
The video to be processed is split as video frame；
When in the video frame including the facial image of the target person, determine that the video frame is described to be processed
Frame.
Optionally, the screening from video to be processed includes the frame to be processed of target person, further includes:
When not including the facial image in the video frame, the people in the preset time period of the video frame front and back is counted
The frequency of occurrence of face image；
When the frequency of occurrence is more than preset times, determine that the video frame is the frame to be processed.
Optionally, the human region that the target person is identified from the frame to be processed, comprising:
The human body key point of the target person is extracted from the frame to be processed；
The human region of the target person is calculated according to the human body key point.
Optionally, the human region that the target person is identified from the frame to be processed, further includes:
Judge whether the human body key point meets preset condition；
When the human body key point meets preset condition, the operation for calculating the human region is executed；The human body closes
Key point meets preset condition, comprising:
The human body key point includes designated key point；
And/or
The number of the human body key point is greater than or equal to predetermined number.
Optionally, from the frame to be processed cut obtain include the human region clipping region image, comprising:
Human body center point coordinate is calculated according to the human body key point coordinate；
It is calculated according to the human body center point coordinate, the resolution ratio of video to be processed and default resolution ratio to described default point
The reduction ratio of resolution；
The first candidate Crop Area is calculated according to the human body center point coordinate, the default resolution ratio and the reduction ratio
Domain；
Judge whether the human region exceeds the range of the described first candidate clipping region；
When range of the human region without departing from the described first candidate clipping region, according to the described first candidate cutting
Region cuts the frame to be processed, obtains the clipping region image.
Optionally, from the frame to be processed cut obtain include the human region clipping region image, further includes:
When range of the human region beyond the described first candidate clipping region, according to the seat of the human region
Mark, the reduction ratio and the default resolution ratio determine the second candidate clipping region；
The frame to be processed is cut according to the described second candidate clipping region, obtains the clipping region image.
Optionally, described generated according to the clipping region image cuts video, comprising:
When the true resolution of the cut out areas image is less than default resolution ratio, the cut out areas image is carried out
Super-resolution processing obtains the target image for meeting the default resolution ratio；
The target image is synthesized, obtains described cutting out video.
Second aspect, this application provides a kind of video process apparatus, comprising:
Screening module, for be processed frame of the screening including target person from video to be processed；
Identification module, for identifying the human region of the target person from the frame to be processed；
Cut module, for from the frame to be processed cut obtain include the human region clipping region image；
Generation module cuts video for generating according to the clipping region image.
The third aspect, this application provides a kind of electronic equipment, comprising: processor, communication interface, memory and communication are total
Line, wherein processor, communication interface, memory complete mutual communication by communication bus；
The memory, for storing computer program；
The processor when for executing the program stored on memory, realizes above method step.
Fourth aspect, this application provides a kind of computer readable storage mediums, are stored thereon with computer program, the meter
Above method step is realized when calculation machine program is executed by processor.
Above-mentioned technical proposal provided by the embodiments of the present application has the advantages that by video include mesh compared with prior art
Each frame image zooming-out of mark personage comes out, and identifies the human region in each frame image, and based on the people's body region carry out into
It cuts, the image synthesis after cutting is cut into video.In this way, being based on human region, compared with the existing technology due to cutting
For, the human body image in video is cut than more complete, also, human body image is in intermediate position in cutting out video,
Display is obvious.In addition, the content being not concerned with due to having eliminated other users, so that cutting out only includes user's concern in video
The content of target person.
Detailed description of the invention
The drawings herein are incorporated into the specification and forms part of this specification, and shows and meets implementation of the invention
Example, and be used to explain the principle of the present invention together with specification.
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, for those of ordinary skill in the art
Speech, without any creative labor, is also possible to obtain other drawings based on these drawings.
Fig. 1 is a kind of flow chart of method for processing video frequency provided by the embodiments of the present application；
Fig. 2 is a kind of flow chart for method for processing video frequency that another embodiment of the application provides；
Fig. 3 is a kind of flow chart for method for processing video frequency that another embodiment of the application provides；
Fig. 4 is a kind of flow chart for method for processing video frequency that another embodiment of the application provides；
Fig. 5 is the schematic diagram of human body key point provided by the embodiments of the present application；
Fig. 6 is the schematic diagram of human region provided by the embodiments of the present application；
Fig. 7 is a kind of flow chart of method for processing video frequency provided by the embodiments of the present application；
Fig. 8 is the schematic diagram of human region provided by the embodiments of the present application and clipping region；
Fig. 9 is the schematic diagram of human region and clipping region that another embodiment of the application provides；
Figure 10 is a kind of block diagram of video process apparatus provided by the embodiments of the present application；
Figure 11 is the block diagram of screening module 91 provided by the embodiments of the present application；
Figure 12 is the block diagram of identification module 92 provided by the embodiments of the present application；
Figure 13 is the block diagram for the identification module 92 that another embodiment of the application provides；
Figure 14 is the block diagram provided by the embodiments of the present application for cutting module 93；
Figure 15 is the block diagram of generation module 94 provided by the embodiments of the present application；
Figure 16 is the structural schematic diagram of a kind of electronic equipment provided by the embodiments of the present application.
Specific embodiment
To keep the purposes, technical schemes and advantages of the embodiment of the present application clearer, below in conjunction with the embodiment of the present application
In attached drawing, the technical scheme in the embodiment of the application is clearly and completely described, it is clear that described embodiment is
A part of the embodiment of the application, instead of all the embodiments.Based on the embodiment in the application, ordinary skill people
Member's every other embodiment obtained without making creative work, shall fall in the protection scope of this application.
A kind of method for processing video frequency is provided for the embodiments of the invention first below to be introduced.
Method provided by the embodiment of the present invention can be applied to any electronic equipment for needing video to handle, for example, can
Think the electronic equipments such as server, terminal, is not specifically limited herein, for convenience of description, subsequent referred to as electronic equipment.
Fig. 1 is a kind of flow chart of method for processing video frequency provided by the embodiments of the present application.As shown in Figure 1, this method includes
Following steps:
Step S11, screening includes the frame to be processed of target person from video to be processed.
Step S12 identifies the human region of target person from frame to be processed.
Wherein, human region refers to region completely including target person human body image.
Step S13, from frame to be processed cut obtain include human region clipping region image.
Step S14 is generated according to clipping region image and is cut video.
Each frame image zooming-out that video includes target person is come out, is identified in each frame image by the embodiment of the present application
Human region, and carried out based on the people's body region into cutting, the image synthesis after cutting cut into video.In this way, due to cutting out
Cut be based on human region, compared with the existing technology for, cut the human body image in video than more complete, also, human body
Image is in intermediate position in cutting out video, and display is obvious.In addition, due to having eliminated in other users are not concerned with
Hold, so that cutting out the content of the target person in video only including user's concern.
Fig. 2 is a kind of flow chart for method for processing video frequency that another embodiment of the application provides.As shown in Fig. 2, in step
In S11, comprising:
Video to be processed is split as video frame by step S21.
Step S22 determines that video frame is frame to be processed when in video frame including the facial image of target person.
Further, when not including facial image in video frame, interior face of preset time period before and after the video frame is counted
The frequency of occurrence of image；When frequency of occurrence is more than preset times, determine that video frame is frame to be processed.
The process of the frame to be processed with a specific example to screening including target person is illustrated below.
Fig. 3 is a kind of flow chart for method for processing video frequency that another embodiment of the application provides.As shown in figure 3, step S11
Can with specifically includes the following steps:
Video to be processed is split as video frame by step S31, which is 50 frames/second.
Step S32, in video frame whether include target person A facial image, if it is executing step S34, if not,
Execute step S33.
There is the number of facial image whether more than 200 times, if it is execution in 2.5 seconds in step S33, video frame front and back
Step S34, if not, executing step S35.
Step S34, the video frame include target person A, are video frame to be processed.
Step S35, the video frame do not include target person A, are not video frames to be processed.
In the present embodiment, 2.5 are shared and is applied in example in 2.5 seconds before and after the video frame, the video frame previous frame, if there is 200
Frame all recognizes the facial image, i.e., 80% frame all has the target person, it is contemplated that the continuity of video content can then recognize
It also include the target person for the video frame.
In the present embodiment, identification includes the video frame of target person in several ways, so that the identification to target person
More accurate reduction is omitted comprehensively, is as much as possible all screened all video frames including target person, is improved subsequent sanction
Cut the smoothness of rear video.
Fig. 4 is a kind of flow chart for method for processing video frequency that another embodiment of the application provides.As shown in figure 4, step S12
Include:
Step S41 extracts the human body key point of target person from frame to be processed；
Step S42 calculates the human region of target person according to human body key point.
The quantity of human body key point can be chosen according to actual needs, can choose 14,17 etc..
Fig. 5 is the schematic diagram of human body key point provided by the embodiments of the present application.As shown in figure 5,14 key points of human body and
Its coordinate is as follows:
Header key point p0=(x0, y0)
Neck key point p1=(x1, y1)
Right shoulder key point p2=(x2, y2)
Left shoulder key point p3=(x3, y3)
Right hand elbow key point p4=(x4, y4)
Left hand elbow key point p5=(x5, y5)
Right finesse key point p6=(x6, y6)
Left finesse key point p7=(x7, y7)
Right hipbone key point p8=(x8, y8)
Left hipbone key point p9=(x9, y9)
Right knee key point p10=(x10, y10)
Left knee key point p11=(x11, y11)
Right ankle key point p12=(x12, y12)
Left ankle key point p13=(x13, y13)
Wherein it is possible to the frame lower left corner to be processed is set as coordinate origin O, from coordinate origin O along frame left margin to be processed to
It is upper positive for y-axis, be to upper right from coordinate origin O along frame lower boundary to be processedxAxis is positive.
Further, step S12 further include: when calculating human region, need whether to meet human body key point default
Condition is judged, when human body key point meets preset condition, executes the operation of above-mentioned steps S42.Human body key point meets
Preset condition comprises at least one of the following situation:
(1) human body key point includes designated key point.
Detect that human body key point must include header key point, neck key point and left and right shoulder for example, can set
Portion's key point.
(2) number of human body key point is greater than or equal to predetermined number.
For example, can set need to detect at least 11 key points, it is just eligible.
In another example above two situation can be combined, and must detect header key point, neck key point and
Left and right shoulder key point, and the key point detected at least 11, just determine that human body key point meets preset condition.
If not extracting qualified human body key point, subsequent processing is not carried out to the frame to be processed, can abandoned
The frame.
Human region can be calculated according to the resolution ratio of human body key point coordinate, default flare factor and video to be processed
It obtains.
Fig. 6 is the schematic diagram of human region provided by the embodiments of the present application.As shown in fig. 6, for example, set human region as
Rectangular area 61, then can determine human region by calculating top left co-ordinate and the bottom right angular coordinate of the rectangular area
Position and size.Wherein, the resolution ratio of frame to be processed is w × h, and w, h are the width and height of frame to be processed, the default expansion system of x, y-axis
Number is respectively α, β.
Firstly, determine that the maximum value of all human body key point x coordinates is,
The minimum value of all human body key point x coordinates is,All human bodies are crucial
Point y-coordinate maximum value be,The minimum value of all human body key point y-coordinates is,
Calculate the width and height of human region:
Top left co-ordinateWith bottom right angular coordinateIn,Point
Not are as follows:
Due to general using selected frame in the prior art, frame selects the part of required cutting in image, then is cut, can
The situation that human region cannot completely be cut out can occur.And in the present embodiment, by according to human body key point to target person
Entire body position is estimated, the relatively complete human region of target person is obtained, so that after the subsequent cutting based on human region
In each frame video, for target person image than more complete and be in intermediate position, display is obvious.
Fig. 7 is a kind of flow chart of method for processing video frequency provided by the embodiments of the present application.As shown in fig. 7, step S13 is cut out
The process of frame to be processed is as follows:
Step S71 calculates human body center point coordinate according to human body key point coordinate.
Step S72 is calculated according to human body center point coordinate, the resolution ratio of video to be processed and default resolution ratio to default point
The reduction ratio of resolution.
Step S73 calculates the first candidate clipping region according to human body center point coordinate, default resolution ratio and reduction ratio.
Step S74, judges whether human region exceeds the range of the first candidate clipping region, if so, executing step
S76, if not, executing step S75.
Step S75, when range of the human region without departing from the first candidate clipping region, according to the first candidate clipping region
Frame to be processed is cut, clipping region image is obtained.
Step S76, when range of the human region beyond the first candidate clipping region, according to the coordinate of human region, contracting
Subtract ratio and default resolution ratio determines the second candidate clipping region.
Step S77 cuts frame to be processed according to the second candidate clipping region, obtains clipping region image.
The process of above-mentioned cutting frame to be processed is described in detail below.
The first step, if being extracted n human body key point, human body center point coordinate are as follows:
Second step, according to pc, video to be processed resolution ratio w wait for place and default resolution ratio w ' × h ' calculating to default resolution
The reduction ratio of rate.
Clipping region is set as rectangular area, then can sit and lower right corner seat by calculating the upper left corner of the rectangular area
Mark position and the size to determine clipping region.Wherein, w ', h ' are respectively the width and height of clipping region.
Fig. 8 and Fig. 9 is respectively the schematic diagram of human region provided by the embodiments of the present application and clipping region.
According to position of the human region 61 in frame to be processed, if the clipping region upper left corner being calculated and the lower right corner
Coordinate is in the frame regional scope to be processed, as shown in figure 8, that can be cut according to default resolution ratio.It is also possible to
The case where appearance can not be cut according to default resolution ratio, is cut as shown in figure 9, needing to reduce resolution ratio at this time.
Firstly, determining that coordinate range of the clipping region in x-axis is as follows based on human body center point coordinate:
The coordinate reduction ratio calculated according to the clipping region left border are as follows:
Value range be (0,0.5].
The coordinate reduction ratio calculated according to the clipping region right side boundary are as follows:
Value range be (0,0.5].
The clipping region actual coordinate reduction ratio can select the minimum value of above-mentioned two coordinate reduction ratio:
Value range be (0,0.5].
2 times of the clipping region actual coordinate reduction ratio, i.e.,For the reduction ratio for presetting resolution ratio.
Third step, according to above-mentioned reduction ratio, can calculate the first candidate clipping region in x-axis the maximum value of coordinate and
Minimum value are as follows:
For example, situation as shown in Figure 8, w '=10, w=50, when human body center point coordinate is (18,7),Then It, can be according to as it can be seen that do not reduce to clipping region 81 actually
Default resolution ratio is cut.
In another example situation as shown in Figure 9, w '=10, w=50, when human body center point coordinate is (3,7), xc=3, ThenIn fact, It can be seen that actually
The width of clipping region 82 is 6, is actually 0.6 to the reduction ratio of default resolution ratio.
It can determine that the coordinate range of the first candidate clipping region on the y axis is as follows according to above-mentioned coordinate reduction ratio:
4th step, judges whether human region exceeds the range of the first candidate clipping region.
It can determine whether human region exceeds the first time by comparing the height of the first candidate clipping region and human region
Select the range of clipping region.
The height of first candidate clipping regionHuman region it is a height of
5th step, whenWhen, as shown in figure 8, range of the human region without departing from the first candidate clipping region, nothing
Human region need to be cut.
It calculates the first candidate clipping region y-coordinate maximum value and minimum value is respectively as follows:
For example, situation as shown in Figure 8, h '=6, when human body center point coordinate is (18,7), the y-axis of clipping region 81
Coordinate range are as follows:
The top left co-ordinate of first candidate clipping regionWith bottom right angular coordinateSuch as
Under:
According toWithCoordinate, frame to be processed is cut, clipping region image is obtained.
6th step, whenWhen, i.e. the human region range that has exceeded the first candidate clipping region is then needed to people
Body region is cut.As shown in figure 9, clipping region 82 cannot include completely human region, need human region dismissing one
Part, can be according to human region top left co-ordinateIt is real to calculate the range of the second candidate clipping region on the y axis
Border are as follows:
The top left co-ordinate bottom right angular coordinate of second candidate clipping region is as follows:
For example, situation as shown in Figure 9, h '=6, human body center point coordinate are (3,7), human region upper left corner y-axis is sat
MarkHuman region lower right corner y-axis coordinatePass through the above-mentioned reduction ratio being calculatedThen
A height of the 3.6 of clipping region after reduction, and a height of the 6 of human region, it needs to cut human region.According toIt can determine
The y-axis coordinate range of second candidate clipping region 82 are as follows:
As it can be seen that should guarantee the top half of human region as far as possible when clipping region cannot include human region completely, that is, wrap
Being partially contained in clipping region for neck key point is included, the part of the leg of human region can be cut.
In the embodiment of the present application, the position of coordinate origin O may be set to be other positions, for example, frame to be processed is left
Upper angle is set as coordinate origin O, and above-mentioned 6th step calculates the second candidate clipping region y-axis coordinate range are as follows:
In the above-described embodiments, the human region in each frame is intercepted as much as possible completely and is come out, when due to human body area
Domain is in the marginal position in video, when so that can not normally intercept according to default resolution ratio, can be scaled down default point
Resolution is cut；When cannot human region be intercepted completely, then retain the key component of human region.In this way, not only improving
The accuracy of the cutting of target person human body image also improves the completeness and efficiency of human body image.In addition, by above-mentioned
The true resolution that embodiment can be seen that final clipping region image is likely less than default resolution ratio, at this time, it may be necessary to cutting
It cuts out area image and carries out super-resolution processing, the target image for meeting default resolution ratio is obtained, in this way, user can watch more
Add continuous clearly video.
Adoptable super-resolution algorithms include, such as super-resolution convolutional neural networks (Super-
ResolutionConvolutional Neural Network, SRCNN) algorithm, the enhancing depth for single image super-resolution
Rest network (Enhanced Deep Residual Networks for Single Image Super-Resolution,
EDSR the above-mentioned resolution processes by clipping region image can be achieved to default resolution ratio, herein not one by one in) algorithm, etc.
It enumerates.
Following is embodiment of the present disclosure, can be used for executing embodiments of the present disclosure.
Figure 10 is a kind of block diagram of video process apparatus provided by the embodiments of the present application, which can be by software, hard
Part or both is implemented in combination with as some or all of of electronic equipment.As shown in Figure 10, which includes:
Screening module 91, for be processed frame of the screening including target person from video to be processed；
Identification module 92, for identifying the human region of target person from frame to be processed；
Cut module 93, for from frame to be processed cut obtain include human region clipping region image；
Generation module 94 cuts video for generating according to clipping region image.
Figure 11 is the block diagram of screening module 91 provided by the embodiments of the present application, and as shown in figure 11, which includes:
Submodule 101 is split, for video to be processed to be split as video frame；
Frame determines submodule 102, for when in video frame include target person facial image when, determine video frame be to
Handle frame.
Further, frame determines submodule 102, and being also used to work as in video frame does not include facial image, before counting video frame
Afterwards in preset time period facial image frequency of occurrence；When frequency of occurrence is more than preset times, determine that video frame is to be processed
Frame.
Figure 12 is the block diagram of identification module 92 provided by the embodiments of the present application, and as shown in figure 12, which includes:
Key point extracting sub-module 111, for extracting the human body key point of target person from frame to be processed；
Human region computational submodule 112, for calculating the human region of target person according to human body key point.
Figure 13 is the block diagram of identification module 92 provided by the embodiments of the present application, as shown in figure 13, further, identification module
92 further include:
Judging submodule 113, for judging whether human body key point meets preset condition；
Human region computational submodule 112, for executing and calculating human region when human body key point meets preset condition
Operation.
Wherein, human body key point meets preset condition, comprising:
Human body key point includes designated key point；
And/or
The number of human body key point is greater than or equal to predetermined number.
Figure 14 is the block diagram provided by the embodiments of the present application for cutting module 93, and as shown in figure 14, which includes:
Central point computational submodule 121, for calculating human body center point coordinate according to human body key point coordinate；
Reduction ratio computational submodule 122, for according to the resolution ratio of human body center point coordinate, video to be processed and default
Resolution ratio calculates the reduction ratio to default resolution ratio；
Coordinate computational submodule 123, for calculating first according to human body center point coordinate, default resolution ratio and reduction ratio
Candidate clipping region；
Judging submodule 124, for judging whether human region exceeds the range of the first candidate clipping region:
Submodule 125 is cut, for being waited according to first when range of the human region without departing from the first candidate clipping region
It selects clipping region to cut frame to be processed, obtains clipping region image.
As shown in figure 14, the cutting module 93 further include:
Coordinate computational submodule 123, when for exceeding the range of the first candidate clipping region when human region, according to human body
Coordinate, reduction ratio and the default resolution ratio in region determine the second candidate clipping region；
Submodule 125 is cut, for cutting according to the second candidate clipping region to frame to be processed, obtains clipping region
Image.
Figure 15 is the block diagram of generation module 94 provided by the embodiments of the present application, and as shown in figure 15, which includes:
Super-resolution processing submodule 131, for when the true resolution of cut out areas image is less than default resolution ratio,
Super-resolution processing is carried out to cut out areas image, obtains the target image for meeting default resolution ratio；
Synthesis submodule 132 obtains cutting out video for synthesizing target image.
The embodiment of the present application also provides a kind of electronic equipment, and as shown in figure 16, electronic equipment may include: processor
1501, communication interface 1502, memory 1503 and communication bus 1504, wherein processor 1501, communication interface 1502, storage
Device 1503 completes mutual communication by communication bus 1504.
Memory 1503, for storing computer program；
Processor 1501 when for executing the program stored on memory 1503, realizes the step of above method embodiment
Suddenly.The communication bus that above-mentioned electronic equipment is mentioned can be Peripheral Component Interconnect standard (Peripheral
ComponentInterconnect, P C I) bus or expanding the industrial standard structure (Extended Industry
StandardArchitecture, EISA) bus etc..The communication bus can be divided into address bus, data/address bus, control bus
Deng.Only to be indicated with a thick line in figure, it is not intended that an only bus or a type of bus convenient for indicating.
Communication interface is for the communication between above-mentioned electronic equipment and other equipment.
Memory may include random access memory (Random Access Memory, RAM), also may include non-easy
The property lost memory (Non-Volatile Memory, NVM), for example, at least a magnetic disk storage.Optionally, memory may be used also
To be storage device that at least one is located remotely from aforementioned processor.
Above-mentioned processor can be general processor, including central processing unit (CentralProcessing Unit,
CPU), network processing unit (Network Processor, NP) etc.；It can also be digital signal processor (Digital
SignalProcessing, DSP), specific integrated circuit (Application Specific Integrated Circuit,
ASIC), field programmable gate array (Field-Programmable Gate Array, FPGA) or other programmable logic
Device, discrete gate or transistor logic, discrete hardware components.
The application also provides a kind of computer readable storage medium, is stored thereon with computer program, the computer program
The step of above method embodiment is realized when being executed by processor.
It should be noted that for above-mentioned apparatus, electronic equipment and computer readable storage medium embodiment, due to
It is substantially similar to embodiment of the method, so being described relatively simple, related place is referring to the part explanation of embodiment of the method
It can.
Explanation is needed further exist for, herein, the relational terms of such as " first " and " second " or the like are only used
Distinguish one entity or operation from another entity or operation, without necessarily requiring or implying these entities or
There are any actual relationship or orders between operation.Moreover, the terms "include", "comprise" or its any other change
Body is intended to non-exclusive inclusion, so that the process, method, article or equipment including a series of elements is not only wrapped
Those elements are included, but also including other elements that are not explicitly listed, or further includes for this process, method, article
Or the element that equipment is intrinsic.In the absence of more restrictions, the element limited by sentence " including one ... ",
Be not precluded include element process, method, article or equipment in there is also other identical elements.
The above is only a specific embodiment of the invention, make skilled artisans appreciate that or realizing of the invention.It is right
A variety of modifications of these embodiments will be apparent to one skilled in the art, general original as defined herein
Reason can be realized in other embodiments without departing from the spirit or scope of the present invention.Therefore, the present invention will not
It is intended to be limited to the embodiments shown herein, and is to fit to consistent most with applied principle and features of novelty herein
Wide range.
Claims (11)
1. a kind of method for processing video frequency characterized by comprising
Screening includes the frame to be processed of target person from video to be processed；
The human region of the target person is identified from the frame to be processed；
From the frame to be processed cut obtain include the human region clipping region image；
It is generated according to the clipping region image and cuts video.
2. the method according to claim 1, wherein the screening from video to be processed includes target person
Frame to be processed, comprising:
The video to be processed is split as video frame；
When in the video frame including the facial image of the target person, determine that the video frame is the frame to be processed.
3. according to the method described in claim 2, it is characterized in that, the screening from video to be processed includes target person
Frame to be processed, further includes:
When not including the facial image in the video frame, the face figure in the preset time period of the video frame front and back is counted
The frequency of occurrence of picture；
When the frequency of occurrence is more than preset times, determine that the video frame is the frame to be processed.
4. the method according to claim 1, wherein described identify the target person from the frame to be processed
Human region, comprising:
The human body key point of the target person is extracted from the frame to be processed；
The human region of the target person is calculated according to the human body key point.
5. according to the method described in claim 4, it is characterized in that, described identify the target person from the frame to be processed
Human region, further includes:
Judge whether the human body key point meets preset condition；
When the human body key point meets preset condition, the operation for calculating the human region is executed；
The human body key point meets preset condition, comprising:
The human body key point includes designated key point；
And/or
The number of the human body key point is greater than or equal to predetermined number.
6. according to the method described in claim 4, obtaining including the human body it is characterized in that, cutting from the frame to be processed
The clipping region image in region, comprising:
Human body center point coordinate is calculated according to the human body key point coordinate；
It is calculated according to the human body center point coordinate, the resolution ratio of video to be processed and default resolution ratio to the default resolution ratio
Reduction ratio；
The first candidate clipping region is calculated according to the human body center point coordinate, the default resolution ratio and the reduction ratio；
Judge whether the human region exceeds the range of the described first candidate clipping region；
When range of the human region without departing from the described first candidate clipping region, according to the described first candidate clipping region
The frame to be processed is cut, the clipping region image is obtained.
7. according to the method described in claim 6, obtaining including the human body it is characterized in that, cutting from the frame to be processed
The clipping region image in region, further includes:
When range of the human region beyond the described first candidate clipping region, according to the coordinate of the human region, institute
It states reduction ratio and the default resolution ratio determines the second candidate clipping region；
The frame to be processed is cut according to the described second candidate clipping region, obtains the clipping region image.
8. the method according to claim 1, wherein described generated according to the clipping region image cuts view
Frequently, comprising:
When the true resolution of the cut out areas image is less than default resolution ratio, oversubscription is carried out to the cut out areas image
Resolution processing, obtains the target image for meeting the default resolution ratio；
The target image is synthesized, obtains described cutting out video.
9. a kind of video process apparatus characterized by comprising
Screening module, for be processed frame of the screening including target person from video to be processed；
Identification module, for identifying the human region of the target person from the frame to be processed；
Cut module, for from the frame to be processed cut obtain include the human region clipping region image；
Generation module cuts video for generating according to the clipping region image.
10. a kind of electronic equipment characterized by comprising processor, communication interface, memory and communication bus, wherein place
Device, communication interface are managed, memory completes mutual communication by communication bus；
The memory, for storing computer program；
The processor when for executing the program stored on memory, realizes the described in any item methods of claim 1-8
Step.
11. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the computer program quilt
Claim 1-8 described in any item method and steps are realized when processor executes.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910569106.6A CN110347877B (en) | 2019-06-27 | 2019-06-27 | Video processing method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910569106.6A CN110347877B (en) | 2019-06-27 | 2019-06-27 | Video processing method and device, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110347877A true CN110347877A (en) | 2019-10-18 |
| CN110347877B CN110347877B (en) | 2022-02-11 |
Family
ID=68176788
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910569106.6A Active CN110347877B (en) | 2019-06-27 | 2019-06-27 | Video processing method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110347877B (en) |
Cited By (28)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110856014A (en) * | 2019-11-05 | 2020-02-28 | 北京奇艺世纪科技有限公司 | Moving image generation method, moving image generation device, electronic device, and storage medium |
| CN111145093A (en) * | 2019-12-20 | 2020-05-12 | 北京五八信息技术有限公司 | Image display method, image display device, electronic device, and storage medium |
| CN111179281A (en) * | 2019-12-24 | 2020-05-19 | 广东省智能制造研究所 | Human body image extraction method and human body action video extraction method |
| CN111222493A (en) * | 2020-01-20 | 2020-06-02 | 北京捷通华声科技股份有限公司 | Video processing method and device |
| CN111311617A (en) * | 2020-03-26 | 2020-06-19 | 北京奇艺世纪科技有限公司 | Method, device and equipment for cutting dynamic graph and storage medium |
| CN111356016A (en) * | 2020-03-11 | 2020-06-30 | 北京松果电子有限公司 | Video processing method, video processing apparatus, and storage medium |
| CN111460219A (en) * | 2020-04-01 | 2020-07-28 | 百度在线网络技术（北京）有限公司 | Video processing method and device and short video platform |
| CN111881755A (en) * | 2020-06-28 | 2020-11-03 | 腾讯科技（深圳）有限公司 | Method and device for cutting video frame sequence |
| CN112131984A (en) * | 2020-09-11 | 2020-12-25 | 咪咕文化科技有限公司 | Video clipping method, electronic device and computer-readable storage medium |
| CN112132836A (en) * | 2020-08-14 | 2020-12-25 | 咪咕文化科技有限公司 | Video image clipping method and device, electronic equipment and storage medium |
| CN112164108A (en) * | 2020-11-27 | 2021-01-01 | 大汉软件股份有限公司 | Method for ensuring correct display of position of character in thumbnail |
| CN112612434A (en) * | 2020-12-16 | 2021-04-06 | 杭州当虹科技股份有限公司 | Video vertical screen solution method based on AI technology |
| CN112765399A (en) * | 2020-12-25 | 2021-05-07 | 联想(北京)有限公司 | Video data processing method and electronic equipment |
| CN112800805A (en) * | 2019-10-28 | 2021-05-14 | 上海哔哩哔哩科技有限公司 | Video editing method, system, computer device and computer storage medium |
| CN112860633A (en) * | 2019-11-28 | 2021-05-28 | 上海宇季文化传播有限公司 | Animation file searching system for graphic features |
| CN112948627A (en) * | 2019-12-11 | 2021-06-11 | 杭州海康威视数字技术股份有限公司 | Alarm video generation method, display method and device |
| CN113014793A (en) * | 2019-12-19 | 2021-06-22 | 华为技术有限公司 | Video processing method and electronic equipment |
| CN113269790A (en) * | 2021-03-26 | 2021-08-17 | 北京达佳互联信息技术有限公司 | Video clipping method and device, electronic equipment, server and storage medium |
| CN113469113A (en) * | 2021-07-19 | 2021-10-01 | 浙江大华技术股份有限公司 | Action counting method and device, electronic equipment and storage medium |
| CN113591644A (en) * | 2021-07-21 | 2021-11-02 | 此刻启动(北京)智能科技有限公司 | Mirror-moving video processing method and system, storage medium and electronic equipment |
| WO2021217927A1 (en) * | 2020-04-29 | 2021-11-04 | 平安国际智慧城市科技股份有限公司 | Video-based exercise evaluation method and apparatus, and computer device and storage medium |
| CN113613059A (en) * | 2021-07-30 | 2021-11-05 | 杭州时趣信息技术有限公司 | Short-cast video processing method, device and equipment |
| CN114448952A (en) * | 2020-10-19 | 2022-05-06 | 腾讯科技（深圳）有限公司 | Streaming media data transmission method and device, storage medium and electronic equipment |
| WO2022100162A1 (en) * | 2020-11-13 | 2022-05-19 | 深圳市前海手绘科技文化有限公司 | Method and apparatus for producing dynamic shots in short video |
| CN114885210A (en) * | 2022-04-22 | 2022-08-09 | 海信集团控股股份有限公司 | Course video processing method, server and display equipment |
| CN116074582A (en) * | 2023-01-31 | 2023-05-05 | 北京奇艺世纪科技有限公司 | Implant position determining method and device, electronic equipment and storage medium |
| CN116074581A (en) * | 2023-01-31 | 2023-05-05 | 北京奇艺世纪科技有限公司 | Implant position determining method and device, electronic equipment and storage medium |
| CN117082207A (en) * | 2023-06-16 | 2023-11-17 | 广东视安通智慧显控股份有限公司 | Doorbell system based on image motion shearing |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070126884A1 (en) * | 2005-12-05 | 2007-06-07 | Samsung Electronics, Co., Ltd. | Personal settings, parental control, and energy saving control of television with digital video camera |
| CN103428537A (en) * | 2013-07-30 | 2013-12-04 | 北京小米科技有限责任公司 | Video processing method and video processing device |
| CN103442252A (en) * | 2013-08-21 | 2013-12-11 | 宇龙计算机通信科技(深圳)有限公司 | Method and device for processing video |
| CN106548148A (en) * | 2016-10-26 | 2017-03-29 | 北京意泰物联软件科技有限公司 | Method and system for identifying unknown face in video |
| CN107809670A (en) * | 2017-10-31 | 2018-03-16 | 长光卫星技术有限公司 | Suitable for the video clipping system and method for large area array meter level high-resolution satellite |
| CN108710829A (en) * | 2018-04-19 | 2018-10-26 | 北京红云智胜科技有限公司 | A method of the expression classification based on deep learning and the detection of micro- expression |
| CN109040780A (en) * | 2018-08-07 | 2018-12-18 | 北京优酷科技有限公司 | A kind of method for processing video frequency and server |
| CN109190454A (en) * | 2018-07-17 | 2019-01-11 | 北京新唐思创教育科技有限公司 | The method, apparatus, equipment and medium of target person in video for identification |
| CN109447072A (en) * | 2018-11-08 | 2019-03-08 | 北京金山安全软件有限公司 | Thumbnail clipping method and device, electronic equipment and readable storage medium |
| CN109670474A (en) * | 2018-12-28 | 2019-04-23 | 广东工业大学 | A kind of estimation method of human posture based on video, device and equipment |
| CN113423001A (en) * | 2021-06-16 | 2021-09-21 | 深圳市海雀科技有限公司 | Method, system and device for playing video |
-
2019
- 2019-06-27 CN CN201910569106.6A patent/CN110347877B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070126884A1 (en) * | 2005-12-05 | 2007-06-07 | Samsung Electronics, Co., Ltd. | Personal settings, parental control, and energy saving control of television with digital video camera |
| CN103428537A (en) * | 2013-07-30 | 2013-12-04 | 北京小米科技有限责任公司 | Video processing method and video processing device |
| CN103442252A (en) * | 2013-08-21 | 2013-12-11 | 宇龙计算机通信科技(深圳)有限公司 | Method and device for processing video |
| CN106548148A (en) * | 2016-10-26 | 2017-03-29 | 北京意泰物联软件科技有限公司 | Method and system for identifying unknown face in video |
| CN107809670A (en) * | 2017-10-31 | 2018-03-16 | 长光卫星技术有限公司 | Suitable for the video clipping system and method for large area array meter level high-resolution satellite |
| CN108710829A (en) * | 2018-04-19 | 2018-10-26 | 北京红云智胜科技有限公司 | A method of the expression classification based on deep learning and the detection of micro- expression |
| CN109190454A (en) * | 2018-07-17 | 2019-01-11 | 北京新唐思创教育科技有限公司 | The method, apparatus, equipment and medium of target person in video for identification |
| CN109040780A (en) * | 2018-08-07 | 2018-12-18 | 北京优酷科技有限公司 | A kind of method for processing video frequency and server |
| CN109447072A (en) * | 2018-11-08 | 2019-03-08 | 北京金山安全软件有限公司 | Thumbnail clipping method and device, electronic equipment and readable storage medium |
| CN109670474A (en) * | 2018-12-28 | 2019-04-23 | 广东工业大学 | A kind of estimation method of human posture based on video, device and equipment |
| CN113423001A (en) * | 2021-06-16 | 2021-09-21 | 深圳市海雀科技有限公司 | Method, system and device for playing video |
Cited By (36)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112800805A (en) * | 2019-10-28 | 2021-05-14 | 上海哔哩哔哩科技有限公司 | Video editing method, system, computer device and computer storage medium |
| CN110856014B (en) * | 2019-11-05 | 2023-03-07 | 北京奇艺世纪科技有限公司 | Moving image generation method, moving image generation device, electronic device, and storage medium |
| CN110856014A (en) * | 2019-11-05 | 2020-02-28 | 北京奇艺世纪科技有限公司 | Moving image generation method, moving image generation device, electronic device, and storage medium |
| CN112860633B (en) * | 2019-11-28 | 2022-11-29 | 上海宇季文化传播有限公司 | Animation file searching system for graphic features |
| CN112860633A (en) * | 2019-11-28 | 2021-05-28 | 上海宇季文化传播有限公司 | Animation file searching system for graphic features |
| CN112948627A (en) * | 2019-12-11 | 2021-06-11 | 杭州海康威视数字技术股份有限公司 | Alarm video generation method, display method and device |
| CN113014793A (en) * | 2019-12-19 | 2021-06-22 | 华为技术有限公司 | Video processing method and electronic equipment |
| WO2021121374A1 (en) * | 2019-12-19 | 2021-06-24 | 华为技术有限公司 | Video processing method and electronic device |
| CN111145093A (en) * | 2019-12-20 | 2020-05-12 | 北京五八信息技术有限公司 | Image display method, image display device, electronic device, and storage medium |
| CN111179281A (en) * | 2019-12-24 | 2020-05-19 | 广东省智能制造研究所 | Human body image extraction method and human body action video extraction method |
| CN111222493A (en) * | 2020-01-20 | 2020-06-02 | 北京捷通华声科技股份有限公司 | Video processing method and device |
| CN111356016A (en) * | 2020-03-11 | 2020-06-30 | 北京松果电子有限公司 | Video processing method, video processing apparatus, and storage medium |
| US11488383B2 (en) | 2020-03-11 | 2022-11-01 | Beijing Xiaomi Pinecone Electronics Co., Ltd. | Video processing method, video processing device, and storage medium |
| CN111311617A (en) * | 2020-03-26 | 2020-06-19 | 北京奇艺世纪科技有限公司 | Method, device and equipment for cutting dynamic graph and storage medium |
| CN111311617B (en) * | 2020-03-26 | 2024-07-19 | 北京奇艺世纪科技有限公司 | Method, device, equipment and storage medium for cutting out dynamic diagram |
| CN111460219A (en) * | 2020-04-01 | 2020-07-28 | 百度在线网络技术（北京）有限公司 | Video processing method and device and short video platform |
| WO2021217927A1 (en) * | 2020-04-29 | 2021-11-04 | 平安国际智慧城市科技股份有限公司 | Video-based exercise evaluation method and apparatus, and computer device and storage medium |
| CN111881755A (en) * | 2020-06-28 | 2020-11-03 | 腾讯科技（深圳）有限公司 | Method and device for cutting video frame sequence |
| CN111881755B (en) * | 2020-06-28 | 2022-08-23 | 腾讯科技（深圳）有限公司 | Method and device for cutting video frame sequence |
| CN112132836A (en) * | 2020-08-14 | 2020-12-25 | 咪咕文化科技有限公司 | Video image clipping method and device, electronic equipment and storage medium |
| CN112131984A (en) * | 2020-09-11 | 2020-12-25 | 咪咕文化科技有限公司 | Video clipping method, electronic device and computer-readable storage medium |
| CN114448952A (en) * | 2020-10-19 | 2022-05-06 | 腾讯科技（深圳）有限公司 | Streaming media data transmission method and device, storage medium and electronic equipment |
| WO2022100162A1 (en) * | 2020-11-13 | 2022-05-19 | 深圳市前海手绘科技文化有限公司 | Method and apparatus for producing dynamic shots in short video |
| CN112164108A (en) * | 2020-11-27 | 2021-01-01 | 大汉软件股份有限公司 | Method for ensuring correct display of position of character in thumbnail |
| CN112612434A (en) * | 2020-12-16 | 2021-04-06 | 杭州当虹科技股份有限公司 | Video vertical screen solution method based on AI technology |
| CN112765399A (en) * | 2020-12-25 | 2021-05-07 | 联想(北京)有限公司 | Video data processing method and electronic equipment |
| CN113269790A (en) * | 2021-03-26 | 2021-08-17 | 北京达佳互联信息技术有限公司 | Video clipping method and device, electronic equipment, server and storage medium |
| CN113469113A (en) * | 2021-07-19 | 2021-10-01 | 浙江大华技术股份有限公司 | Action counting method and device, electronic equipment and storage medium |
| CN113591644A (en) * | 2021-07-21 | 2021-11-02 | 此刻启动(北京)智能科技有限公司 | Mirror-moving video processing method and system, storage medium and electronic equipment |
| CN113613059A (en) * | 2021-07-30 | 2021-11-05 | 杭州时趣信息技术有限公司 | Short-cast video processing method, device and equipment |
| CN113613059B (en) * | 2021-07-30 | 2024-01-26 | 杭州时趣信息技术有限公司 | Short-cast video processing method, device and equipment |
| CN114885210A (en) * | 2022-04-22 | 2022-08-09 | 海信集团控股股份有限公司 | Course video processing method, server and display equipment |
| CN114885210B (en) * | 2022-04-22 | 2023-11-28 | 海信集团控股股份有限公司 | Tutorial video processing method, server and display device |
| CN116074582A (en) * | 2023-01-31 | 2023-05-05 | 北京奇艺世纪科技有限公司 | Implant position determining method and device, electronic equipment and storage medium |
| CN116074581A (en) * | 2023-01-31 | 2023-05-05 | 北京奇艺世纪科技有限公司 | Implant position determining method and device, electronic equipment and storage medium |
| CN117082207A (en) * | 2023-06-16 | 2023-11-17 | 广东视安通智慧显控股份有限公司 | Doorbell system based on image motion shearing |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110347877B (en) | 2022-02-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110347877A (en) | A kind of method for processing video frequency, device, electronic equipment and storage medium | |
| JP4824411B2 (en) | Face extraction device, semiconductor integrated circuit | |
| CN112288665B (en) | Image fusion method and device, storage medium and electronic equipment | |
| JP4473754B2 (en) | Virtual fitting device | |
| US8706663B2 (en) | Detection of people in real world videos and images | |
| CN104134435B (en) | Image processing equipment and image processing method | |
| CN108875533B (en) | Face recognition method, device, system and computer storage medium | |
| WO2019237745A1 (en) | Facial image processing method and apparatus, electronic device and computer readable storage medium | |
| CN104794462A (en) | Figure image processing method and device | |
| CN112102340B (en) | Image processing method, apparatus, electronic device, and computer-readable storage medium | |
| TWI525555B (en) | Image processing apparatus and processing method thereof | |
| KR101786754B1 (en) | Device and method for human age estimation | |
| US20190370537A1 (en) | Keypoint detection to highlight subjects of interest | |
| TW202044194A (en) | Image processing method, apparatus and computer storage medium | |
| CN111489290A (en) | Face image super-resolution reconstruction method and device and terminal equipment | |
| CN110458790A (en) | A kind of image detecting method, device and computer storage medium | |
| CN108765317A (en) | A kind of combined optimization method that space-time consistency is stablized with eigencenter EMD adaptive videos | |
| CN110505398B (en) | Image processing method and device, electronic equipment and storage medium | |
| CN107146197A (en) | A kind of reduced graph generating method and device | |
| JP2017045441A (en) | Image generation method and image generation system | |
| CN111008935A (en) | Face image enhancement method, device, system and storage medium | |
| CN106997580B (en) | Picture processing method and device | |
| CN113706373A (en) | Model reconstruction method and related device, electronic equipment and storage medium | |
| CN107529071A (en) | A kind of video data handling procedure and device | |
| JP6403207B2 (en) | Information terminal equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |