CN110047034A - Stingy figure under online education scene changes background method, client and system - Google Patents
Stingy figure under online education scene changes background method, client and system Download PDFInfo
- Publication number
- CN110047034A CN110047034A CN201910235728.5A CN201910235728A CN110047034A CN 110047034 A CN110047034 A CN 110047034A CN 201910235728 A CN201910235728 A CN 201910235728A CN 110047034 A CN110047034 A CN 110047034A
- Authority
- CN
- China
- Prior art keywords
- image
- background
- pixel
- stingy
- alpha
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 32
- 239000000463 material Substances 0.000 claims abstract description 59
- 238000001514 detection method Methods 0.000 claims abstract description 6
- 238000001914 filtration Methods 0.000 claims description 13
- 238000000605 extraction Methods 0.000 claims description 9
- 238000012545 processing Methods 0.000 claims description 8
- 230000005540 biological transmission Effects 0.000 claims description 5
- 239000000284 extract Substances 0.000 claims description 4
- 230000015572 biosynthetic process Effects 0.000 claims description 3
- 238000003786 synthesis reaction Methods 0.000 claims description 3
- 230000007704 transition Effects 0.000 claims description 3
- 230000008859 change Effects 0.000 abstract description 4
- 230000003068 static effect Effects 0.000 abstract description 4
- 230000006978 adaptation Effects 0.000 abstract description 2
- 230000036039 immunity Effects 0.000 abstract description 2
- 238000012163 sequencing technique Methods 0.000 abstract description 2
- 238000006748 scratching Methods 0.000 description 10
- 230000002393 scratching effect Effects 0.000 description 10
- 238000007654 immersion Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000009499 grossing Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000002146 bilateral effect Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 238000004891 communication Methods 0.000 description 1
- 238000005034 decoration Methods 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000012805 post-processing Methods 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 230000009885 systemic effect Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/04—Context-preserving transformations, e.g. by using an importance map
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/194—Segmentation; Edge detection involving foreground-background segmentation
-
- 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
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
-
- 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
- G06T2207/10—Image acquisition modality
- G06T2207/10024—Color image
-
- 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
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30196—Human being; Person
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Electrically Operated Instructional Devices (AREA)
Abstract
The present invention relates to the stingy figures under a kind of online education scene to change background method, includes the following steps: to obtain original image and background material image;Pass through the rough foreground pixel of Edge Gradient Feature;Updated accurate background pixel and accurate foreground pixel are obtained using hsv color space, the transparency that the channel Alpha of background pixel in original image is arranged is all-transparent;The color value of the color value of the original image and the background material image is overlapped according to the Alpha channel image of the background image, obtains superimposed image.Additionally provide corresponding client and system, for user teaching scene in dynamic configuration and teaching scene.Stingy drawing method, client and system in the embodiment of the present invention have used texture+color mode to carry out the detection of background pixel, have many advantages, such as strong interference immunity, wide adaptation range.Multiple dynamics or static scene material can be added, and carries out the display of material sequencing according to the level of material.
Description
Technical field
The present invention relates to field of image processing, in particular to the stingy figure under a kind of online education scene change background method,
Client and system.
Background technique
In online education teacher with student and student with the communication between student be all by real-time Online Video into
Row is linked up.Therefore the visual effect of video will have a direct impact on the Experience Degree of attending class of student and teacher, in order to promote experience of attending class
Degree, it may be considered that promote Experience Degree of attending class by the way of scratching figure.The way that current stingy figure generallys use is taken in film studio
It builds a background with green curtain perhaps blue screen making and then allows personage's recorded video in green curtain or blue curtain scene, in video
The background of green curtain or blue curtain is substituted for other scenes again in post-processing.However, above-mentioned prior art is still
It makes user not convenient enough and experiences imperfect place:
1, current stingy nomography, for the scene light of record screen and blue curtain, shade etc. has higher requirement.
2, offline to use the interactivity being unable to satisfy between school session user.
3, offline stingy figure is unable to satisfy the requirement of the course scene in classroom, and feeling of immersion is insufficient.
4, can not online real-time update, manage, be adapted to a variety of stingy figures dynamics and static background material.
Summary of the invention
The present invention is in order to solve existing above-mentioned technical problem, in a first aspect, scratching under providing a kind of online education scene
Figure changes background method, includes the following steps:
Client obtains original image from camera, obtains background material image from server;
Rough foreground pixel is carried out to original image by edge feature to extract, and includes in the foreground pixel of extraction
A small amount of background pixel;
The rough foreground pixel image that previous step obtains is converted into HSV image, basis is set in HSV space
Fixed color gamut further extracts the foreground pixel in rough foreground pixel, and the extraction of this step is accurate prospect
Pixel;All pixels in original image in addition to accurate foreground pixel are background pixel;
An Alpha transparent channel is created for original image, sets 0,0 for the Alpha channel value of accurate foreground pixel
Indicate opaque, setting 255,255 for the Alpha channel value of background pixel indicates transparent, then carries out to the channel Alpha high
This smothing filtering;
The superposition that original image and background image are carried out according to above-mentioned Alpha channel value, according to the channel Alpha transparency
Value original image is added to background picture.
Further, described that background pixel and foreground pixel in original image are extracted by edge feature and pixel color
Step includes:
The edge feature value for extracting original image obtains edge feature image;
The edge feature image is cut into strip image according to preset width;
According to the edge feature value of the strip image, scanning first is more than the marginal position point of threshold value T from top to bottom;
Pixel more than marginal position point position is divided into background pixel, remaining is foreground pixel.
Further, described the step of obtaining marginal position point according to the edge feature value of the strip image, includes:
Each strip image is scanned from the top down, and recording point of first marginal value greater than threshold value T in strip image is side
Edge location point;If the value at all edges is both less than threshold value T in strip image, the point for recording the strip image bottom end is edge
Location point.
Further, the rough foreground pixel obtained to previous step is transformed into hsv color space, according to
The pixel value in hsv color space, further to the detection of rough foreground pixel nearly the row background and prospect, including,
The pixel color of the rough foreground image is converted into hsv color value;
The pixel for traversing the rough foreground image judges hsv color of the hsv color value in the default background of pixel
When in range, the pixel in this rough foreground image is incorporated into the background pixel, it otherwise will be in this rough foreground image
Pixel incorporate into the foreground pixel.
It further, further include that background pixel and prospect picture are carried out to Alpha channel image using the mode of gaussian filtering
Element carries out smooth transition processing.
It further, further include that before extracting background image, the disposal of gentle filter is carried out to the original image.
Further, the Alpha channel image according to the background image by the color value of the original image and
The step of color value of the background material image is overlapped includes being overlapped according to the following formula,
R=Ro* (1-Alpha/255)+Rb*Alpha/255;
G=Go* (1-Alpha/255)+Gb*Alpha/255;
B=Bo* (1-Alpha/255)+Bb*Alpha/255;
R, G, B represent the color value of the superimposed pixel of background in above-mentioned formula, and Ro, Go, Bo indicate the face of original image
Color value, Rb, Gb, Bb represent the pixel color value of background material image, and Alpha indicates the transparency channel of original image.
Further, the original image is the user images that camera acquires in real time.
Second aspect, the embodiment of the present invention provide the stingy figure client under a kind of online education scene, including,
Input module obtains background material image from server for obtaining original image from camera;
Edge Gradient Feature module, for extracting rough foreground pixel from original image by edge feature;
The rough foreground image is transformed into hsv color space, according to default HSV background color model by HSV computing module
It encloses and further detects fine foreground pixel and fine background pixel to rough foreground pixel, be arranged in original image and finely carry on the back
The transparency in the channel Alpha of scene element is all-transparent;
Superimposed image synthesis module, for according to the Alpha channel image of the fine background image by the original graph
The color value of the color value of picture and the background material image is overlapped, and calculates superimposed image.
The third aspect, the embodiment provides the stingy drawing systems under a kind of online education scene, including above-mentioned
Figure client is scratched, further includes server, camera, the camera is used for for acquiring user images, the server in real time
Material image is stored, and different background pictures, the stingy figure client is arranged in the course types and teaching material attended class according to user
It is downloaded for obtaining the user images acquired in real time as the original image, and according to the setting of server end from server end
Corresponding background material generates superimposed image, specifically,
The academics and students after starting that attend class pass through client and use server described in account and password login;From server
Download the material of multiple this section courses in end;
The stingy figure control authority of all students in the same teaching material and classroom, the control is arranged in teacher in course
Permission includes: whether the student can replace for oneself using figure and background is scratched, and whether which can add stingy figure to others
It is replaced with background;
It is relevant by client to add course to oneself or to others by middle teacher or the student having permission at school
Scratch figure background;
Whether teacher controls owner using the replacement of figure background is scratched by client, replaces different stingy figure backgrounds, makes to replace
The background changed is in conjunction with the video scene of user;
Client carries out background replacement, processing to the video of the camera capture of user according to the stingy pixel material of each user
Video image later is by network transmission in client used in the teacher and other students in same hall class.
Stingy drawing method, stingy figure client and system in the present invention can be scratched except the subsequent background of personage in video, and
Dynamic is substituted for the relevant picture background of teaching material scene of attending class, the interest of raising online education course, feeling of immersion, and mutually
Dynamic property.Texture+color mode has been used to carry out the detection of background pixel, there is strong interference immunity, wide adaptation range etc. is excellent
Point.Multiple dynamics or static scene material can be added, and carries out the display of material sequencing according to the level of material.
The replacement of video matting background is introduced into online education classroom by the embodiment of the present invention, designs a set of online education
Real-time video matting background replacement system in scene: it can accomplish that video background matches with teaching scene, with specific class
Journey matches, and interacts matching with teacher student, can not only beautify video of attending class, while allowing classroom to have and preferably immersing
Sense and interactivity.Stingy figure operation is fast, does not do complicated matrix operation, only does simple linear operation, real-time is higher.
Detailed description of the invention
The features and advantages of the present invention will be more clearly understood by referring to the accompanying drawings, and attached drawing is schematically without that should manage
Solution is carries out any restrictions to the present invention, in the accompanying drawings:
Fig. 1 changes the method flow signal of background method for the stingy figure under the online education scene in some embodiments of the invention
Figure;
Fig. 2 is the client operation process having in the on-line education system for scratching figure function in some embodiments of the invention
Schematic diagram;
Fig. 3 is that the image procossing that the stingy figure under the online education scene in some embodiments of the invention changes in background method shows
It is intended to;
Fig. 4 is that the image procossing that the stingy figure under the online education scene in some embodiments of the invention changes in background method shows
It is intended to;
Fig. 5 is that the image procossing that the stingy figure under the online education scene in some embodiments of the invention changes in background method shows
It is intended to;
Fig. 6 is that the stingy figure under the online education scene in some embodiments of the invention changes the original in background method practice
Beginning image schematic diagram;
Fig. 7 is changed in background method practice for the stingy figure under the online education scene in some embodiments of the invention and is based on
Superimposed image schematic diagram after original image is overlapped in Fig. 6;
Fig. 8 is the system schematic of the stingy figure client under the online education scene in some embodiments of the invention;
Fig. 9 is the system schematic of the stingy drawing system under the online education scene in some embodiments of the invention.
Specific embodiment
To better understand the objects, features and advantages of the present invention, with reference to the accompanying drawing and specific real
Applying mode, the present invention is further described in detail.It should be noted that in the absence of conflict, the implementation of the application
Feature in example and embodiment can be combined with each other.
In the following description, numerous specific details are set forth in order to facilitate a full understanding of the present invention, still, the present invention may be used also
To be implemented using other than the one described here other modes, therefore, protection scope of the present invention is not by described below
Specific embodiment limitation.
Under online education scene, client and server, which are attached, realizes that voice, image, video material exchange, real
Existing online education usually shows the head portrait acquisition image of oneself or teacher, classmate to realize that user experience is true
In client.In order to adapt to different background materials, head portrait is dissolved into background material, the embodiment of the invention provides one kind
Nomography is scratched, the permission for scratching figure can be configured as needed, and background material, which highlights, to be selected or be uploaded as needed.
As shown in Figure 1, the embodiment of the invention provides the stingy figures under a kind of online education scene to change background method, including such as
Lower step:
S110, original image is obtained from camera, obtains background material image from server;
S120, rough foreground pixel extraction, the foreground pixel of extraction are carried out to original image by edge feature
In include a small amount of background pixel;
S130, the rough foreground pixel image that previous step obtains is converted into HSV image, in HSV space
Further the foreground pixel in rough foreground pixel is extracted according to the color gamut of setting, the extraction of this step is essence
True foreground pixel;All pixels in original image in addition to accurate foreground pixel are background pixel;
S140, an Alpha transparent channel is created for original image, the Alpha channel value of accurate foreground pixel is arranged
It is that 0,0 expression is opaque, setting 255,255 for the Alpha channel value of background pixel indicates transparent, then to the channel Alpha
Carry out Gaussian smoothing filter;
S150, the superposition that original image and background image are carried out according to above-mentioned Alpha channel value, according to the channel Alpha
Original image is added to background picture by the value of transparency.
The color of the default background is usually the color of green curtain or blue curtain, by the edge feature to original image into
Row extracts, and obtains corresponding Edge Feature Points, to obtain background image region, the corresponding Alpha of background image region is led to
Road image is set as all-transparent, then utilizes the transparence value (gray value) of Alpha channel image, by original image and background element
The color value of the pixel of material image, which is overlapped to calculate, obtains final stacking chart.So that image co-registration is rapidly completed, special energy
It enough applies in video fusion, in use, camera acquires user's realtime graphic, is then merged with background material, sufficiently
Consider timeliness.Method in the present invention first passes through the differentiation that edge unity and coherence in writing feature carries out foreground and background, then from extraction
Prospect in further judged using hsv color space, judged so as to avoid directlying adopt hsv color space
When, since bias light of taking pictures changes so that scratching the problem of figure error greatly.
Further, described that background pixel and foreground pixel in original image are extracted by edge feature and pixel color
Step includes:
The edge feature value for extracting original image obtains edge feature image;
The edge feature image is cut into strip image according to preset width;
According to the edge feature value of the strip image, scanning first is more than the marginal position point of threshold value T from top to bottom;
Pixel more than marginal position point position is divided into background pixel, remaining is foreground pixel.
It is divided into strip image, convenient for quickly calculating, reduces feature quantity.
Further, described the step of obtaining marginal position point according to the edge feature value of the strip image, includes:
Each strip image is scanned from the top down, and recording point of first marginal value greater than threshold value T in strip image is side
Edge location point;If the value at all edges is both less than threshold value T in strip image, the point for recording the strip image bottom end is edge
Location point.
In order to guarantee to remove the pixel containing default background image color in above-mentioned foreground image, realization is sufficiently superimposed,
The rough foreground pixel obtained to previous step is transformed into hsv color space, according to the pixel in hsv color space
Value, further to the detection of rough foreground pixel nearly the row background and prospect, including,
The pixel color of the rough foreground image is converted into hsv color value;
The pixel for traversing the rough foreground image judges hsv color of the hsv color value in the default background of pixel
When in range, the pixel in this rough foreground image is incorporated into the background pixel, it otherwise will be in this rough foreground image
Pixel incorporate into the foreground pixel.
It further include carrying out the picture of background image to Alpha channel image using the mode of gaussian filtering to reduce noise
The pixel of element and foreground image carries out smooth transition processing.
In order to guarantee that feature extraction result is preferable, before extracting background image, smothing filtering is carried out to the original image
Processing.
Further, the Alpha channel image according to the background image by the color value of the original image and
The step of color value of the background material image is overlapped includes being overlapped according to the following formula,
R=Ro* (1-Alpha/255)+Rb*Alpha/255;
G=Go* (1-Alpha/255)+Gb*Alpha/255
B=Bo* (1-Alpha/255)+Bb*Alpha/255
R, G, B represent the color value of the superimposed pixel of background in above-mentioned formula, and Ro, Go, Bo indicate the face of original image
Color value, Rb, Gb, Bb represent the pixel color value of background material image, and Alpha indicates the transparency channel of original image.
In order to adapt to online education scene, the original image is the user images that camera acquires in real time, is realized real-time
Scratch figure.
Stingy drawing method in the embodiment of the present invention can apply in online education scene.Specifically, as shown in Figure 2.
1, attend class beginning after academics and students' account and password login server.
2, the material of multiple this section courses is downloaded from server end.Course and religion of the server end according to academics and students
Material downloads corresponding multiple static and dynamic and scratches figure decoration background.
3, stingy figure control authority (such as of all students in the same teaching material and classroom is arranged in teacher in course
Whether raw can be oneself using figure and background replacement is scratched, and whether which can add to others is scratched figure and background replacement)
4, middle teacher or the student having permission can add the relevant stingy figure of course to oneself or to others at school
Background replacement, reaches beautification video, improves feeling of immersion, enhances the interaction between teacher student.
5, whether teacher possesses highest permission can control owner using the replacement of figure background is scratched, and can replace different scratch
Figure background makes the background of replacement and the video scene perfect combination of user.
6, it scratches nomography module and background is carried out to the video of the camera capture of user according to the stingy pixel material of each user
Replacement, the image after handling is by network transmission to the teacher and other students in same hall class.
Nomography module is scratched to be described below:
Algorithm needs the background detection of green curtain or blue curtain in the original image by input to come out in scratching module, to green
The pixel of curtain or blue curtain part adds the channel Alpha, then adds background to original image according to the color value in the channel Alpha
Image.Algorithm process process:
1. carrying out smothing filtering (Gaussian smoothing, bilateral filtering, median filtering etc. can be used) to original image, original graph is reduced
The noise of picture.
2. extracting the edge feature image (sobel operator can be used, the methods of canny is extracted) of input picture.
3. edge image is cut into strip image according to the width of 20 pixels, as shown in Figure 3.
4. because the human body generally position on the lower side in video in instructional video, detects above-mentioned each strip image
The larger edge of first appearance can determine the outline position of human body.Concrete operations: each bar graph is scanned from the top down
Picture records the point that first marginal value in strip image is greater than threshold value T, if the value at all edges is both less than T in strip image,
Then the point for recording the strip image is the bottom end of strip image.Strip picture point after having handled is as shown in Figure 4.
5. generating the identical Alpha channel image with original image size, more than the location point for marking each strip image
Alpha is all-transparent.As shown in figure 5, the Alpha of background pixel is all-transparent.
6. by step 5. in pixel color in addition to background pixel be converted into hsv color space.
7. then according to threshold range Hmin, Hmax of the color of green curtain (such as green curtain or blue curtain) setting HSV, Smin,
Smax, Vmin, Vmax (threshold range herein can be by systemic presupposition).
8. traversal step 6. in HSV pixel, if the pixel is corresponded to position in step threshold value 7. by some pixel
The transparency for the Alpha channel image set is set as all-transparent.
9. the mode using gaussian filtering carries out the smooth of background pixel and foreground pixel to the image in the channel Alpha.
10. the Alpha channel image that is 9. generated using step is overlapped original image and background material.Superposition meter
Calculate formula are as follows:
R=Ro* (1-Alpha/255)+Rb*Alpha/255;
G=Go* (1-Alpha/255)+Gb*Alpha/255
B=Bo* (1-Alpha/255)+Bb*Alpha/255
R, G, B represent the color value of the superimposed pixel of background in above-mentioned formula, and Ro, Go, Bo indicate original graph target face
Color value, Rb Gb Bb represent the pixel color value of background material.
(11) the final picture 10. generated by the Internet transmission step is shown to other users.
The technical solution bring of the embodiment of the present invention the utility model has the advantages that
The replacement of video matting background is introduced into online education classroom by the present invention, is designed real in a set of online education scene
When video matting background replacement system: can accomplish video background with teaching scene match, match with specific course,
Matching is interacted with teacher student, video of attending class can not only be beautified, while classroom being allowed to have better feeling of immersion and interaction
Property.Stingy figure operation is fast, does not do complicated matrix operation, only does simple linear operation, real-time is higher.
In practice, in the embodiment of the present invention there is the on-line education system for scratching figure function can be realized: stingy figure is replaced
The background material changed is related with online course, can provide multiple and different background materials according to different course styles, mention
The feeling of immersion in high classroom;The type and quantity of background material can be updated by the online flexible configuration of server with real-time perfoming;Scratch figure
Replacing background can mutually be decorated by mutual operation between user, improve the interactivity of classroom student;Original image is carried out flat
Sliding filtering (can use Gaussian smoothing, bilateral filtering, median filtering etc.), reduces influence of the noise pixel to stingy figure precision in picture;
Whether scratching figure replacement background, there is permission to control, can have permission to carry out scratching figure replacement to the video of oneself with facility some user and carry on the back
Scape, or others' video is carried out to scratch figure replacement background.
In actual use, original as shown in Fig. 6 (green curtain background), image is as shown in Figure 7 after superposition.
Based on above-mentioned stingy drawing method, as shown in figure 8, the embodiment of the invention also provides under a kind of online education scene
Figure client 100 is scratched, including,
Input module 110, for obtaining original image from camera and obtaining background material image from server;
Edge Gradient Feature module 120, for extracting rough foreground pixel from original image by edge feature;
The rough foreground image is transformed into hsv color space, according to default HSV background face by HSV computing module 130
Color range further detects fine foreground pixel and fine background pixel to rough foreground pixel, and essence in original image is arranged
The transparency in the channel Alpha of thin background pixel is all-transparent;
Superimposed image synthesis module 140, for will be described original according to the Alpha channel image of the fine background image
The color value of the color value of image and the background material image is overlapped, and calculates superimposed image.
The concrete configuration and function of above-mentioned module are described in detail in the functional module in corresponding method, herein not
It does and excessively repeats.
Based on above-mentioned stingy figure client 100, as shown in figure 9, the embodiment of the invention also provides a kind of online education fields
Stingy drawing system 200 under scape further includes server 210, camera 220, the camera shooting including above-mentioned stingy figure client 100
First 220 for acquiring user images in real time, and the server 210 stores material image, and the course types attended class according to user
Different background pictures is set with teaching material, the stingy figure client 100 is used to obtain described in the user images conduct acquired in real time
Original image, and corresponding background material is downloaded from server end according to the setting of server end, superimposed image is generated, specifically
Ground,
The academics and students after starting that attend class pass through client and use server described in account and password login;From server
Download the material of multiple this section courses in end;
The stingy figure control authority of all students in the same teaching material and classroom, the control is arranged in teacher in course
Permission includes: whether the student can replace for oneself using figure and background is scratched, and whether which can add stingy figure to others
It is replaced with background;
It is relevant by client to add course to oneself or to others by middle teacher or the student having permission at school
Scratch figure background;
Whether teacher controls owner using the replacement of figure background is scratched by client, replaces different stingy figure backgrounds, makes to replace
The background changed is in conjunction with the video scene of user;
Client carries out background replacement, processing to the video of the camera capture of user according to the stingy pixel material of each user
Image later is by network transmission in client used in the teacher and other students in same hall class.
Stingy drawing system 200 in the embodiment of the present invention belongs to the part system in on-line education system.By scratching diagram technology,
The user experience is improved.
In the present invention, term " first ", " second ", " third " are used for description purposes only, and should not be understood as instruction or
Imply relative importance.Term " multiple " refers to two or more, unless otherwise restricted clearly.
The foregoing is only a preferred embodiment of the present invention, is not intended to restrict the invention, for the skill of this field
For art personnel, the invention may be variously modified and varied.All within the spirits and principles of the present invention, made any to repair
Change, equivalent replacement, improvement etc., should all be included in the protection scope of the present invention.
Claims (10)
1. the stingy figure under a kind of online education scene changes background method, which comprises the steps of:
Client obtains original image from camera, obtains background material image from server;
It carries out rough foreground pixel to original image by edge feature to extract, comprising a small amount of in the foreground pixel of extraction
Background pixel;
The rough foreground pixel image that previous step obtains is converted into HSV image, according to setting in HSV space
Color gamut further extracts the foreground pixel in rough foreground pixel, and the extraction of this step is accurate prospect picture
Element;All pixels in original image in addition to accurate foreground pixel are background pixel;
An Alpha transparent channel is created for original image, sets 0,0 expression for the Alpha channel value of accurate foreground pixel
Opaque, setting 255,255 for the Alpha channel value of background pixel indicates transparent, and it is flat then to carry out Gauss to the channel Alpha
Sliding filtering;
The superposition that original image and background image are carried out according to above-mentioned Alpha channel value, according to the value of the channel Alpha transparency
Original image is added to background picture.
2. the stingy figure under online education scene according to claim 1 changes background method, which is characterized in that described to pass through side
Edge feature and pixel color extract the step of background pixel and foreground pixel in original image and include:
The edge feature value for extracting original image obtains edge feature image;
The edge feature image is cut into strip image according to preset width;
According to the edge feature value of the strip image, scanning first is more than the marginal position point of threshold value T from top to bottom;
Pixel more than marginal position point position is divided into background pixel, remaining is foreground pixel.
3. the stingy figure under online education scene according to claim 2 changes background method, which is characterized in that described according to institute
State strip image edge feature value obtain marginal position point the step of include:
Each strip image is scanned from the top down, and recording point of first marginal value greater than threshold value T in strip image is margin location
It sets a little;If the value at all edges is both less than threshold value T in strip image, the point for recording the strip image bottom end is marginal position
Point.
4. the stingy figure under online education scene according to claim 3 changes background method, which is characterized in that described pair upper one
The rough foreground pixel that step obtains is transformed into hsv color space, according to the pixel value in hsv color space, further
Detection to rough foreground pixel nearly the row background and prospect, including,
The pixel color of the rough foreground image is converted into hsv color value;
The pixel for traversing the rough foreground image judges hsv color range of the hsv color value in the default background of pixel
When interior, the pixel in this rough foreground image is incorporated into the background pixel, otherwise by the picture in this rough foreground image
Element incorporates into the foreground pixel.
5. the stingy figure under online education scene according to claim 4 changes background method, which is characterized in that further include making
Background pixel is carried out to Alpha channel image with the mode of gaussian filtering and foreground pixel carries out smooth transition processing.
6. the stingy figure under online education scene according to claim 1 changes background method, which is characterized in that further include mentioning
Before taking background image, the disposal of gentle filter is carried out to the original image.
7. the stingy figure under any online education scene changes background method according to claim 1~6, which is characterized in that institute
It states the face of the color value of the original image and the background material image according to the Alpha channel image of the background image
The step of color value is overlapped includes being overlapped according to the following formula,
R=Ro* (1-Alpha/255)+Rb*Alpha/255;
G=Go* (1-Alpha/255)+Gb*Alpha/255;
B=Bo* (1-Alpha/255)+Bb*Alpha/255;
R, G, B represent the color value of the superimposed pixel of background in above-mentioned formula, and Ro, Go, Bo indicate the color value of original image,
Rb, Gb, Bb represent the pixel color value of background material image, and Alpha indicates the transparency channel of original image.
8. the stingy figure under online education scene according to claim 1 changes background method, which is characterized in that the original graph
As the user images acquired in real time for camera.
9. the stingy figure client under a kind of online education scene, which is characterized in that including,
Input module obtains background material image from server for obtaining original image from camera;
Edge Gradient Feature module, for extracting rough foreground pixel from original image by edge feature;
The rough foreground image is transformed into hsv color space, according to default HSV background color range pair by HSV computing module
Rough foreground pixel further detects fine foreground pixel and fine background pixel, and fine background picture in original image is arranged
The transparency in the channel Alpha of element is all-transparent;
Superimposed image synthesis module, for according to the Alpha channel image of the fine background image by the original image
The color value of color value and the background material image is overlapped, and calculates superimposed image.
10. the stingy drawing system under a kind of online education scene, which is characterized in that including stingy figure client as claimed in claim 9,
It further include server, camera, the camera for acquiring user images in real time, and the server is for storing material figure
Picture, and different background pictures is arranged in the course types and teaching material attended class according to user, the stingy figure client is for obtaining reality
When the user images that acquire as the original image, and according to the setting of server end download corresponding background from server end
Material generates superimposed image, specifically,
The academics and students after starting that attend class pass through client and use server described in account and password login;Server according to
Course types that family is attended class and teaching material are arranged different background pictures, and client is according to the setting of server end from server end
The material of corresponding background material and this section course is downloaded,;
The stingy figure control authority of all students in the same teaching material and classroom, the control authority is arranged in teacher in course
Include: whether the student can replace for oneself using figure and background is scratched, whether which can add to others is scratched figure and back
Scape replacement;
Middle teacher or the student having permission add the relevant stingy figure of course to oneself or to others by client at school
Background;
Whether teacher controls owner using the replacement of figure background is scratched by client, replaces different stingy figure backgrounds, makes replacement
Background is in conjunction with the video scene of user;
Client carries out background replacement to the video of the camera capture of user according to the stingy pixel material of each user, after processing
Video image by network transmission in client used in the teacher and other students in same hall class.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910235728.5A CN110047034A (en) | 2019-03-27 | 2019-03-27 | Stingy figure under online education scene changes background method, client and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910235728.5A CN110047034A (en) | 2019-03-27 | 2019-03-27 | Stingy figure under online education scene changes background method, client and system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110047034A true CN110047034A (en) | 2019-07-23 |
Family
ID=67275175
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910235728.5A Pending CN110047034A (en) | 2019-03-27 | 2019-03-27 | Stingy figure under online education scene changes background method, client and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110047034A (en) |
Cited By (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110913267A (en) * | 2019-11-29 | 2020-03-24 | 上海赛连信息科技有限公司 | Image processing method, device, system, interface, medium and computing equipment |
CN110969595A (en) * | 2019-12-02 | 2020-04-07 | 成都索贝数码科技股份有限公司 | Pure-color background matting and synthesizing method based on real-time background color overflow inhibition |
CN111722902A (en) * | 2020-06-15 | 2020-09-29 | 朱利戈 | Method and system for realizing rich media interactive teaching based on window transparentization processing |
CN112351291A (en) * | 2020-09-30 | 2021-02-09 | 深圳点猫科技有限公司 | Teaching interaction method, device and equipment based on AI portrait segmentation |
CN112689196A (en) * | 2021-03-09 | 2021-04-20 | 北京世纪好未来教育科技有限公司 | Interactive video playing method, player, equipment and storage medium |
CN112804516A (en) * | 2021-04-08 | 2021-05-14 | 北京世纪好未来教育科技有限公司 | Video playing method and device, readable storage medium and electronic equipment |
CN113206971A (en) * | 2021-04-13 | 2021-08-03 | 聚好看科技股份有限公司 | Image processing method and display device |
CN113362220A (en) * | 2021-05-26 | 2021-09-07 | 稿定(厦门)科技有限公司 | Multi-equipment sectional drawing method |
CN113382276A (en) * | 2021-06-09 | 2021-09-10 | 湖南快乐阳光互动娱乐传媒有限公司 | Picture processing method and system |
CN113422914A (en) * | 2021-06-24 | 2021-09-21 | 脸萌有限公司 | Video generation method, device, equipment and medium |
CN113923431A (en) * | 2020-04-15 | 2022-01-11 | 深圳市瑞立视多媒体科技有限公司 | Real-time image matting method, device, equipment and storage medium based on high-definition video |
WO2022179487A1 (en) * | 2021-02-24 | 2022-09-01 | 影石创新科技股份有限公司 | Video processing method for making stealth special effect, filter, device, and medium |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101686338A (en) * | 2008-09-26 | 2010-03-31 | 索尼株式会社 | System and method for partitioning foreground and background in video |
US20120306904A1 (en) * | 2011-06-02 | 2012-12-06 | Yoostar Entertainment Group, Inc. | Image processing |
WO2013013484A1 (en) * | 2011-07-26 | 2013-01-31 | 深圳市万兴软件有限公司 | An image synthesis method and system using alpha channel |
CN103473780A (en) * | 2013-09-22 | 2013-12-25 | 广州市幸福网络技术有限公司 | Portrait background cutout method |
CN106952270A (en) * | 2017-03-01 | 2017-07-14 | 湖南大学 | A kind of quickly stingy drawing method of uniform background image |
CN107516319A (en) * | 2017-09-05 | 2017-12-26 | 中北大学 | A kind of high accuracy simple interactive stingy drawing method, storage device and terminal |
-
2019
- 2019-03-27 CN CN201910235728.5A patent/CN110047034A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101686338A (en) * | 2008-09-26 | 2010-03-31 | 索尼株式会社 | System and method for partitioning foreground and background in video |
US20120306904A1 (en) * | 2011-06-02 | 2012-12-06 | Yoostar Entertainment Group, Inc. | Image processing |
WO2013013484A1 (en) * | 2011-07-26 | 2013-01-31 | 深圳市万兴软件有限公司 | An image synthesis method and system using alpha channel |
CN103473780A (en) * | 2013-09-22 | 2013-12-25 | 广州市幸福网络技术有限公司 | Portrait background cutout method |
CN106952270A (en) * | 2017-03-01 | 2017-07-14 | 湖南大学 | A kind of quickly stingy drawing method of uniform background image |
CN107516319A (en) * | 2017-09-05 | 2017-12-26 | 中北大学 | A kind of high accuracy simple interactive stingy drawing method, storage device and terminal |
Non-Patent Citations (3)
Title |
---|
兰红等: "一种基于HSV空间的自然图像抠图算法", 《计算机应用与软件》 * |
吴玉娥等: "一种基于简单笔画交互的迭代图像抠图方法", 《中国图象图形学报》 * |
郭康等: "基于HSV空间的彩色监控视频前景提取方法", 《电子质量》 * |
Cited By (20)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110913267B (en) * | 2019-11-29 | 2020-11-06 | 上海赛连信息科技有限公司 | Image processing method, device, system, interface, medium and computing equipment |
CN110913267A (en) * | 2019-11-29 | 2020-03-24 | 上海赛连信息科技有限公司 | Image processing method, device, system, interface, medium and computing equipment |
CN110969595A (en) * | 2019-12-02 | 2020-04-07 | 成都索贝数码科技股份有限公司 | Pure-color background matting and synthesizing method based on real-time background color overflow inhibition |
CN110969595B (en) * | 2019-12-02 | 2023-08-01 | 成都索贝数码科技股份有限公司 | Pure-color background matting synthesis method based on real-time background color overflow inhibition |
CN113923431A (en) * | 2020-04-15 | 2022-01-11 | 深圳市瑞立视多媒体科技有限公司 | Real-time image matting method, device, equipment and storage medium based on high-definition video |
CN113923430A (en) * | 2020-04-15 | 2022-01-11 | 深圳市瑞立视多媒体科技有限公司 | Real-time image matting method, device, equipment and storage medium based on high-definition video |
CN111722902A (en) * | 2020-06-15 | 2020-09-29 | 朱利戈 | Method and system for realizing rich media interactive teaching based on window transparentization processing |
CN112351291A (en) * | 2020-09-30 | 2021-02-09 | 深圳点猫科技有限公司 | Teaching interaction method, device and equipment based on AI portrait segmentation |
WO2022179487A1 (en) * | 2021-02-24 | 2022-09-01 | 影石创新科技股份有限公司 | Video processing method for making stealth special effect, filter, device, and medium |
CN112689196A (en) * | 2021-03-09 | 2021-04-20 | 北京世纪好未来教育科技有限公司 | Interactive video playing method, player, equipment and storage medium |
CN112689196B (en) * | 2021-03-09 | 2021-06-11 | 北京世纪好未来教育科技有限公司 | Interactive video playing method, player, equipment and storage medium |
CN112804516B (en) * | 2021-04-08 | 2021-07-06 | 北京世纪好未来教育科技有限公司 | Video playing method and device, readable storage medium and electronic equipment |
CN112804516A (en) * | 2021-04-08 | 2021-05-14 | 北京世纪好未来教育科技有限公司 | Video playing method and device, readable storage medium and electronic equipment |
CN113206971A (en) * | 2021-04-13 | 2021-08-03 | 聚好看科技股份有限公司 | Image processing method and display device |
CN113206971B (en) * | 2021-04-13 | 2023-10-24 | 聚好看科技股份有限公司 | Image processing method and display device |
CN113362220A (en) * | 2021-05-26 | 2021-09-07 | 稿定(厦门)科技有限公司 | Multi-equipment sectional drawing method |
CN113362220B (en) * | 2021-05-26 | 2023-08-18 | 稿定(厦门)科技有限公司 | Multi-equipment matting drawing method |
CN113382276A (en) * | 2021-06-09 | 2021-09-10 | 湖南快乐阳光互动娱乐传媒有限公司 | Picture processing method and system |
CN113422914A (en) * | 2021-06-24 | 2021-09-21 | 脸萌有限公司 | Video generation method, device, equipment and medium |
CN113422914B (en) * | 2021-06-24 | 2023-11-21 | 脸萌有限公司 | Video generation method, device, equipment and medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110047034A (en) | Stingy figure under online education scene changes background method, client and system | |
CN105654471B (en) | Augmented reality AR system and method applied to internet video live streaming | |
CN104867123B (en) | Enhanced using the infrared resolution and contrast of fusion | |
Brinkmann | The art and science of digital compositing: Techniques for visual effects, animation and motion graphics | |
JP6905602B2 (en) | Image lighting methods, devices, electronics and storage media | |
WO2021169307A1 (en) | Makeup try-on processing method and apparatus for face image, computer device, and storage medium | |
CN101213576B (en) | Album creating apparatus, album creating method | |
Kimmel et al. | Space-dependent color gamut mapping: A variational approach | |
US20080043041A2 (en) | Image Blending System, Method and Video Generation System | |
CN107993216A (en) | A kind of image interfusion method and its equipment, storage medium, terminal | |
Lachambre et al. | Photogrammetry workflow | |
CN103745430A (en) | Rapid beautifying method of digital image | |
CN105827975B (en) | A kind of color on-line correction method for panoramic video splicing | |
Zhang et al. | Atmospheric perspective effect enhancement of landscape photographs through depth-aware contrast manipulation | |
CN113724175A (en) | Image processing method and device based on artificial intelligence and electronic equipment | |
CN105812668A (en) | Image processing method, processing device and photographing apparatus | |
CN109189246B (en) | Method, device and system for processing scribbled content on handwriting board | |
Seo et al. | Interactive painterly rendering with artistic error correction | |
CN103971365B (en) | A kind of image saliency map extracting method | |
Gao et al. | PencilArt: a chromatic penciling style generation framework | |
Garstki | Virtual authority and the expanding role of 3D digital artefacts | |
CN106954060B (en) | A kind of three-dimensional video-frequency generation method and auxiliary filming apparatus towards smart phone | |
US11778306B2 (en) | Method for editing an image | |
CN113935894B (en) | Ink and wash style scene rendering method and equipment and storage medium | |
Pauls et al. | The Depth Estimation of 2D Content: A New Life for Paintings |
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 | ||
TA01 | Transfer of patent application right |
Effective date of registration: 20220627 Address after: 100085 third floor, No. 9, Shangdi East Road, Haidian District, Beijing Applicant after: Beijing havo Online Technology Co.,Ltd. Address before: 100085 No.1, South District, 6th floor, No.9 Shangdi East Road, Haidian District, Beijing Applicant before: BEIJING DASHENG ONLINE TECHNOLOGY Co.,Ltd. |
|
TA01 | Transfer of patent application right | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20190723 |
|
WD01 | Invention patent application deemed withdrawn after publication |