CN110334653A - Image processing method, device and equipment in video communication - Google Patents
Image processing method, device and equipment in video communication Download PDFInfo
- Publication number
- CN110334653A CN110334653A CN201910609634.XA CN201910609634A CN110334653A CN 110334653 A CN110334653 A CN 110334653A CN 201910609634 A CN201910609634 A CN 201910609634A CN 110334653 A CN110334653 A CN 110334653A
- Authority
- CN
- China
- Prior art keywords
- image
- target
- cropped area
- target image
- human body
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
Abstract
This application discloses image processing method, device and the equipment in a kind of video communication, belong to network technique field.This method comprises: obtaining the target image comprising human body subgraph；According to position of the target point in human body subgraph in image coordinate system, determine that cropped area, cropped area include human body subgraph region in image coordinate system；Target image is cut according to cropped area；Target image after cutting is sent to receiving end.Since the application can determine cropped area according to the target point of human body subgraph, and target image is cut based on the cropped area, so that receiving end shows the target image after cutting, improves the flexibility that receiving end shows image.
Description
Technical field
The present invention relates to network technique field, in particular to image processing method, device in a kind of video communication and set
It is standby.
Background technique
With the development of science and technology, television set also has the function of video calling at present.
In the related technology, the edge of the shell of television set is further typically provided with camera, in video call process, electricity
Can be by the camera collection image depending on machine, and acquired image can be sent to opposite end, so that opposite end shows the figure
Picture.Wherein, which can be mobile phone or television set.
But since camera is generally arranged at the fixed position of television set, acquisition range is relatively fixed.Therefore right
End display image be it is fixed, opposite end show image flexibility it is lower.
Summary of the invention
The embodiment of the invention provides image processing method, device and the equipment in a kind of video communication, can solve phase
Opposite end shows the lower problem of the flexibility of image in the technology of pass.The technical solution is as follows:
On the one hand, the image processing method in a kind of video communication is provided, which comprises
Obtain the target image comprising human body subgraph；
According to position of the target point in the human body subgraph in image coordinate system, in described image coordinate system really
Determine cropped area, the cropped area includes human body subgraph region；
The target image is cut according to the cropped area；
Target image after cutting is sent to receiving end.
On the other hand, the image processing apparatus in a kind of video communication is provided, described device includes:
Module is obtained, for obtaining the target image comprising human body subgraph；
Determining module, for the position according to the target point in the human body subgraph in image coordinate system, described
Determine that cropped area, the cropped area include human body subgraph region in image coordinate system；
Module is cut, for cutting the target image according to the cropped area；
Sending module, for the target image after cutting to be sent to receiving end.
Another aspect provides a kind of image processing equipment, comprising: memory and is stored in the memory at processor
On computer program, realized when the processor executes the computer program in the video communication as described in terms of above-mentioned
Image processing method.
Another aspect provides a kind of computer readable storage medium, is stored in the computer readable storage medium
Instruction, when the computer readable storage medium is run on computers, so that computer is executed as described in terms of above-mentioned
Image processing method in video communication.
Technical solution bring beneficial effect provided in an embodiment of the present invention includes at least:
The embodiment of the invention provides image processing method, device and the equipment in a kind of video communication, the image procossings
Method can determine cropped area according to position of the target point in human body subgraph in image coordinate system, and according to cutting
Region cuts target image, so that receiving end shows the target image after cutting, directly will compared to television set in the related technology
The image of camera acquisition is sent to receiving end and shows, improves the flexibility that receiving end shows image.
Detailed description of the invention
To describe the technical solutions in the embodiments of the present invention more clearly, make required in being described below to embodiment
Attached drawing is briefly described, it should be apparent that, drawings in the following description are only some embodiments of the invention, for
For those of ordinary skill in the art, without creative efforts, it can also be obtained according to these attached drawings other
Attached drawing.
Fig. 1 is implementation environment involved in image processing method in a kind of video communication provided in an embodiment of the present invention
Schematic diagram；
Fig. 2 is the flow chart of the image processing method in a kind of video communication provided in an embodiment of the present invention；
Fig. 3 is the flow chart of the image processing method in another video communication provided in an embodiment of the present invention；
Fig. 4 is a kind of schematic diagram of target point in human body subgraph provided in an embodiment of the present invention；
Fig. 5 is a kind of schematic diagram of cropped area provided in an embodiment of the present invention；
Fig. 6 is the schematic diagram of another cropped area provided in an embodiment of the present invention；
Fig. 7 is the schematic diagram of another cropped area provided in an embodiment of the present invention；
Fig. 8 is the schematic diagram of another cropped area provided in an embodiment of the present invention；
Fig. 9 is the schematic diagram of another cropped area provided in an embodiment of the present invention；
Figure 10 is the schematic diagram of another cropped area provided in an embodiment of the present invention；
Figure 11 is the schematic diagram of another cropped area provided in an embodiment of the present invention；
Figure 12 is the schematic diagram of another cropped area provided in an embodiment of the present invention；
Figure 13 is the schematic diagram of another cropped area provided in an embodiment of the present invention；
Figure 14 is the schematic diagram of another cropped area provided in an embodiment of the present invention；
Figure 15 is the schematic diagram of another cropped area provided in an embodiment of the present invention；
Figure 16 is the schematic diagram of another cropped area provided in an embodiment of the present invention；
Figure 17 is the schematic diagram of another cropped area provided in an embodiment of the present invention；
Figure 18 is the schematic diagram of another cropped area provided in an embodiment of the present invention；
Figure 19 is the schematic diagram of another cropped area provided in an embodiment of the present invention；
Figure 20 is the schematic diagram of another cropped area provided in an embodiment of the present invention；
Figure 21 is the schematic diagram of another cropped area provided in an embodiment of the present invention；
Figure 22 is the block diagram of the image processing apparatus in a kind of video communication provided in an embodiment of the present invention；
Figure 23 is a kind of block diagram for cutting module provided in an embodiment of the present invention；
Figure 24 is the block diagram of the image processing apparatus in another video communication provided in an embodiment of the present invention.
Specific embodiment
To make the object, technical solutions and advantages of the present invention clearer, below in conjunction with attached drawing to embodiment party of the present invention
Formula is described in further detail.
Fig. 1 is implementation environment involved in image processing method in a kind of video communication provided in an embodiment of the present invention
Schematic diagram.As shown in Figure 1, the implementation environment may include: image processing equipment 110 and at least one receiving end 120.Such as scheme
Two receiving ends 120 are shown in 1.The edge of 110 shell of image processing equipment is provided with camera and (does not show in Fig. 1
Out).The receiving end 120 can be provided with camera for television set, PC, laptop, tablet computer or mobile phone etc.
Equipment.It can be established and be connected by cable network or wireless network between the image processing equipment 110 and each receiving end 120
It connects.
It can be mounted on video communication client in image processing equipment 110 and receiving end 120, then image processing equipment
110 and receiving end 120 can based on the video communication client carry out video calling, during video calling, at image
Reason equipment 110 can determine cropped area according to position of the target point in human body subgraph in image coordinate system, and by base
It is sent to receiving end in the target image that the cropped area is cut, so that receiving end is shown, compared to the relevant technologies, is improved
Receiving end shows the flexibility of image.
In embodiments of the present invention, which can be television set, PC, laptop, put down
The equipment that plate computer or mobile phone etc. are provided with camera.
Fig. 2 is the flow chart of the image processing method in a kind of video communication provided in an embodiment of the present invention, at the image
Reason method can be applied in image processing equipment 110 shown in FIG. 1.As shown in Fig. 2, this method may include:
Step 201 obtains the target image comprising human body subgraph.
During carrying out video calling with receiving end, its available camera of image processing equipment acquires each
Frame image, and each frame image is identified using pre-stored human testing algorithm, and then obtains comprising human body
The target image of image.Wherein, it may include a human body subgraph in the target image, also may include multiple human body subgraphs
Picture.The ratio of the target image can be 16:9.
Step 202, the position according to the target point in human body subgraph in image coordinate system, in image coordinate system really
Determine cropped area.
Wherein, which can be the geometric center point of human body subgraph.Alternatively, target point may be the human body
Default characteristic point in subgraph.The default characteristic point can in human body subgraph head feature point and foot's characteristic point it
Between line midpoint, or can be the characteristic point of the nose in human body subgraph.
The cropped area may include human body subgraph region.
Optionally, the size of cropped area can be previously stored in image processing equipment, for example, the length of the cropped area
The length and width of wide ratio or cropped area.Image processing equipment, can after obtaining the target image comprising human body subgraph
First to determine position of the target point in image coordinate system in human body subgraph, for example, the target point is in image coordinate system
Coordinate.Image processing equipment can be based on the ruler of position and cropped area of the target point in image coordinate system later
It is very little, determine position of the cropped area in image coordinate system.
In embodiments of the present invention, since the acquisition range of camera is fixed, each frame figure of video camera acquisition
The size of picture is all the same, then image processing equipment can establish image coordinate system according to the first frame target image of acquisition, for
Each frame image, the image coordinate system that image processing equipment can be established based on the first frame target image determine each frame
The target point of target image.Alternatively, image coordinate system can also be previously stored in image processing equipment, and deposited in advance based on this
The image coordinate system of storage determines the target point of each frame target image.
Step 203 cuts target image according to cropped area.
Image processing equipment can cut target image as boundary line using the boundary of cropped area, the target figure after cutting
As the position in image coordinate system is overlapped with position of the cropped area in image coordinate system.
Target image after cutting is sent to receiving end by step 204.
Image processing equipment can also directly display the sanction while target image after cutting is sent to receiving end
Target image after cutting.Wherein, which can be television set, PC or mobile phone etc..
In conclusion the embodiment of the invention provides the image processing method in a kind of video communication, the image processing method
Method can determine cropped area according to position of the target point in human body subgraph in image coordinate system, and according to cutting area
Domain cuts target image, so that receiving end shows the target image after cutting, it is straight compared to image processing equipment in the related technology
It connects and the image of camera acquisition is sent to receiving end and show, improve the flexibility of receiving end display image.
Fig. 3 is the flow chart of the image processing method in another video communication provided in an embodiment of the present invention, the image
Processing method can be applied in image processing equipment 110 shown in FIG. 1.As shown in figure 3, this method may include:
Step 301 obtains the target image comprising human body subgraph.
In video call process, each frame image of the available camera acquisition of image processing equipment, and use people
Physical examination method of determining and calculating identifies each frame image, and then the image comprising human body subgraph is determined as target image.It can
Choosing, wherein may include a human body subgraph in the target image, also may include multiple human body subgraphs.The target
The ratio of image can be 16:9.
In embodiments of the present invention, image processing equipment can be according to for the face subgraph for including in target image
Number, to determine the number for the human body subgraph for including in the target image.
Multiple key points in step 302, identification human body subgraph.
Wherein, multiple key point may include main human body feature point in human body subgraph, such as may include nose
Characteristic point, the characteristic point of neck and the characteristic point at four limbs major joint position etc. of son.
In embodiments of the present invention, image processing equipment can identify multiple key point using human testing algorithm.
It is exemplary, it is assumed that as shown in figure 4, the target image that image processing equipment is got is 00, in the target image 00
Comprising a human body subgraph 01, image processing equipment can identify 10 key points 02 from human body subgraph 01.
Step 303 determines human geometry's figure based on multiple key points.
In embodiments of the present invention, the area that image processing equipment can surround multiple key point is maximum
Figure is determined as human geometry's figure.Alternatively, image processing equipment can determine that the area that multiple key points can surround is maximum
Figure, and the minimum circumscribed rectangle of the maximum figure of the area is determined as human geometry's figure, or can also be by the face
The minimum circumscribed circle of the maximum figure of product is determined as human geometry's figure.
If including a human body subgraph in target image, image processing equipment can be based on a human body subgraph
In multiple key points determine a human body geometric figure.
If including multiple human body subgraphs in target image, image processing equipment can be based on multiple human body subgraph
In multiple key points determine a human body geometric figure.Alternatively, image processing equipment can also be based on each human body subgraph
Key point as in determines a human body geometric figure, to obtain multiple human geometry's figures.
Exemplary, with reference to Fig. 4, image processing equipment is based in a human body subgraph 01 for including in target image 00
Multiple key points 01, determine the maximum figure of area that multiple key point 01 can surround, and by the maximum figure of the area
The minimum circumscribed rectangle 03 of shape is determined as human geometry's figure.
The central point of human geometry's figure is determined as target point by step 304.
Optionally, the central point of human body geometric figure can be the center of circle of the minimum circumscribed circle of human body geometric figure.
In embodiments of the present invention, image processing equipment can be after multiple key points in identification human body subgraph, mark
Remember position of multiple key point in image coordinate system, and the position based on multiple key point in image coordinate system,
Human geometry's figure is determined in image coordinate system.It later, can be by the central point of human body geometric figure in image coordinate system
Position is determined as position of the target point in image coordinate system.The central point of human body geometric figure is in image coordinate system
Position can refer to: coordinate of the central point of human body geometric figure in image coordinate system.The origin o of the image coordinate system can
Think that the pixel in the target image lower left corner or the pixel in the upper left corner, the horizontal axis x of the image coordinate system can be parallel to mesh
The pixel row direction of logo image, the longitudinal axis y of the image coordinate system can be parallel to the pixel column direction of target image.
Exemplary, with reference to Fig. 4, image processing equipment can be true by the center of circle 04 of the minimum circumscribed circle of human body geometric figure
It is set to target point, and position (x1, y1) of the target point 04 in image coordinate system is determined as the target point 04 and is sat in image
Position in mark system.
It should be noted that if image processing equipment determines multiple human geometry's figures in above-mentioned steps 303, then exist
In step 304, image processing equipment can determine the central point of each human body geometric figure respectively, later can be by multiple human bodies
The mean value of position of the central point of geometric figure in image coordinate system is determined as position of the target point in image coordinate system.
It should also be noted that, since the acquisition range of camera is fixed, each frame image of video camera acquisition
Size it is all the same, then image processing equipment can establish image coordinate system according to the first frame target image of acquisition, for every
One frame image, the image coordinate system that image processing equipment can be established based on the first frame target image determine each frame mesh
The target point of logo image.Alternatively, image coordinate system can also be previously stored in image processing equipment, and it is stored in advance based on this
Image coordinate system determine the target point of each frame target image.
Step 305, the position according to the target point in human body subgraph in image coordinate system, in image coordinate system really
Determine cropped area.
The cropped area includes human body subgraph region.Also, the cropped area can be rectangle.Of the invention real
It applies in example, when image processing equipment determines the cropped area of rectangle in image coordinate system, can determine each of cropped area
Position (such as the coordinate on each vertex) of a vertex in image coordinate system, so that the cropped area of the rectangle is flat there are two
The midpoint on capable side is conllinear with the target point.For example, the midpoint of two long sides of the cropped area of the rectangle can be made and be somebody's turn to do
Target point is conllinear, alternatively, the midpoint of two short sides of the cropped area of the rectangle can be made conllinear with the target point.
Optionally, in embodiments of the present invention, image processing equipment can centered on the target point point, in image coordinate
The cropped area of rectangle is determined in system.It that is to say, the midpoint on every two parallel sides in the cropped area of the rectangle can be made
It is conllinear with the target point.
As a kind of optional implementation, image processing equipment can centered on target point point, in image coordinate system
Middle determining length-width ratio is the cropped area of the rectangle of target proportion.The target proportion can be to be stored in advance in image processing equipment
's.Exemplary, which can be 16:9, or may be 1:1.
In embodiments of the present invention, which can be equal to the length-width ratio of target image.Also, image processing equipment
The ratio of length of the length and target image for the cropped area determined and the width of the width of cropped area and target image
The ratio of degree can be default ratio.The default ratio can be to be pre-stored in image processing equipment, for example, this is default
Ratio can be 0.1.
Fig. 5 is the schematic diagram that one kind provided in an embodiment of the present invention determines cropped area in the target image.Such as Fig. 5 institute
Show, include a human body subgraph in the target image 00, image processing equipment can be with human body that target image 00 includes
Point centered on target point 04 in image determines that length-width ratio is the cropped area 05 of target proportion 16:9.With reference to Fig. 6, image
Processing equipment can centered on the target point 04 in the human body subgraph for including in target image 00 point, determine that length-width ratio is
The cropped area 05 of target proportion 1:1.
It include two human body subgraphs in the target image 00, image processing equipment can be with the target image with reference to Fig. 7
Point centered on target point 04 in the 00 human body subgraph for including determines that length-width ratio is the cropped area of target proportion 16:9
05.With reference to Fig. 8, image processing equipment can be centered on the target point 04 in the human body subgraph for including in target image 00
Point determines that length-width ratio is the cropped area 05 of target proportion 1:1.Wherein, which is respectively positioned on cropped area
In 05.
As another optional implementation, image processing equipment can centered on target point point, in image coordinate
Determine that length is target length in system, width is the cropped area of the rectangle of target width.Wherein, the target length and target are wide
Degree can be pre-stored in image processing equipment.For example, the target length and the ratio of target width can be 16:9, or
Person may be 1:1.
Whether step 306, detection cropped area are located in target image region.
In embodiments of the present invention, whether image processing equipment can detecte the cropped area after determining cropped area
In target image region, if cropped area is located in target image region, step 307 can be executed.If
Cropped area partly overlaps with target image region, then can execute step 308.
Exemplary, with reference to Fig. 5, Fig. 6, Fig. 7 and Fig. 8, which is located in 00 region of target image, therefore
Image processing equipment can execute step 307.With reference to Fig. 9 and Figure 11, the cropped area 05 and 00 region of target image are only
It partly overlaps, i.e., the cropped area 05 is not fully located in target image region, then image processing equipment can execute step
Rapid 308.
Step 307 cuts part Chong Die with cropped area in target image.
After determining that cropped area is located in target image region, image processing equipment can be with the side of cropped area
Boundary is boundary line, cuts part Chong Die with cropped area in target image, and the target image after cutting is in image coordinate system
In position it is identical as position of the cropped area in image coordinate system.
Exemplary, with reference to Fig. 5, Fig. 6, Fig. 7 and Fig. 8, image processing equipment can be using the boundary of cropped area 05 as boundary
Line cuts part identical with the cropped area 05 in target image 00.
Step 308, position of the adjustment cropped area in image coordinate system, and cut in target image with sanction adjusted
Cut the part of region overlapping.
After determining that cropped area and target image region only partly overlap, image processing equipment is adjustable to be cut
Position of the region in image coordinate system, so that the cropped area is located in target image region, and then can be based on tune
Cropped area after whole cuts target image.
Optionally, image processing equipment can will in cropped area be located at target image region outside, and not with target
The boundary line of image intersection, the object boundary line overlap with target image are located at cropped area in target image region,
Part Chong Die with cropped area adjusted in target image is cut later.Wherein, which can be target figure
The boundary line intersected as in cropped area.The cropped area adjusted is located in target image region, and after adjustment
Cropped area at least one boundary line and target image boundary line overlap.
In embodiments of the present invention, in the cropped area be located at target image region outside, and not with target image phase
The boundary line of friendship may include at least one boundary line.If at least one boundary line includes a line boundary line, image procossing
Equipment can be Chong Die with a target boundary line of target image by a line boundary line, so that cropped area is located at target image
In region.One target boundary line can be boundary parallel with a line boundary line of cropped area in target image
Line.
If at least one boundary line includes first borderline and second borderline, image processing equipment can be with the first side
Boundary line and first object boundary line overlap, by second borderline and the second object boundary line overlap.Wherein, the first object boundary
Line is the boundary line parallel with the first borderline of cropped area in target image, the second object boundary line be in target image with
The parallel boundary line of the second borderline of cropped area.
Exemplary, with reference to Fig. 9, target image 00 includes a human body subgraph, and the length-width ratio of cropped area 05 is 16:
9, it is located at outside 00 region of target image in the cropped area 05, and the boundary line that intersect with the target image 00 is boundary
Line a.With reference to Figure 10, image processing equipment can be Chong Die with the object boundary line A of target image 00 by boundary line a, so as to cut out
It cuts region 05 to be located in 00 region of target image, which is in target image 00 and in cropped area 05
The parallel boundary line boundary line a.
Exemplary, with reference to Figure 11, target image 00 includes a human body subgraph, and the length-width ratio of cropped area 05 is
16:9 is located at outside 00 region of target image in the cropped area 05, and the boundary line intersected with the target image 00 includes
First borderline a and second borderline b.With reference to Figure 12, image processing equipment can be by first borderline a and target image 00
First object boundary line A overlapping, and it is second borderline b is Chong Die with the second object boundary line B of target image so that the sanction
Region 05 is cut to be located in 00 region of target image.The first object boundary line A be target image 00 in cropped area 05
The parallel boundary line first borderline a, which is the second side in target image 00 with cropped area 05
Boundary line b parallel boundary line.
It is exemplary, if being located at outside target image region in cropped area, and the boundary line that do not intersect with target image
It may include two boundary lines, with reference to Figure 13, target image 00 includes a human body subgraph, and the length-width ratio of cropped area is
1:1, image processing equipment adjusts the position of the cropped area 05 in image coordinate system, so that the cropped area 05 is located at target
In 00 region of image.With reference to Figure 14, target image 00 includes multiple human body subgraphs, and the length-width ratio of cropped area 05 is
16:9, image processing equipment adjusts the position of the cropped area 05 in image coordinate system, so that the cropped area 05 is located at mesh
In 00 region of logo image.With reference to Figure 15, target image 00 includes multiple human body subgraphs, and the length-width ratio of cropped area 05
For 1:1, image processing equipment adjusts the position of the cropped area 05 in image coordinate system, so that the cropped area 05 is located at mesh
In 00 region of logo image.
Target image after cutting is sent to receiving end by step 309.
Target image after cutting can be sent to reception after cutting to target image by image processing equipment
End, so that receiving end is shown.The receiving end can be television set, PC or mobile phone etc..
In embodiments of the present invention, when the position of target point 04 as shown in Figure 5 in human body subgraph is moved to Figure 16 institute
When at the position shown, image processing equipment can determine that user is in moving condition, then can be based on target point shown in Figure 16
04 position in image coordinate system, determines cropped area 05 as shown in figure 16, the central point of the cropped area 05 with should
The center that target point overlapping, i.e. human body subgraph are located at cropped area.
Since image processing equipment can adjust the position of cropped area in the picture according to the target point of human body subgraph,
So even being that user is in moving condition, human body subgraph can also remain at the center of the target image after cutting, connect
The human body subgraph that receiving end is shown can also remain at the center of the screen of receiving end, be ensured by the image processing method
The stability for the image that image processing equipment is transmitted to receiving end improves the display effect and spirit of the image that receiving end is shown
Activity.
With reference to Fig. 7 and Fig. 8, if including multiple human body subgraphs in target image, image processing equipment can be according to multiple
The target point that human body subgraph is determined determines cropped area, so that the central point of cropped area is Chong Die with the target point,
Thus while ensuring in target image that multiple human body subgraphs are respectively positioned on after cutting, multiple human body subgraph can position
The center of target image after cutting ensures that multiple human body subgraphs are respectively positioned on the center of receiving end screen, improves
The display effect for the image that receiving end is shown.
It include a human body subgraph, a people in Figure 17 in target image shown in fig. 5 with reference to Fig. 5, Figure 17 and Figure 18
Body subgraph is located in target image region, and a human body subgraph is located at outside target image region, shown in Figure 18
Target image in include two human body subgraphs.Can be seen that in conjunction with Fig. 5, Figure 17 and Figure 18, which ought have new user to enter, takes the photograph
As head acquisition range in when, the position for the target point in human body subgraph that image processing equipment is determined will become
Change, and then the position of cropped area 05 can be adjusted based on the target point after variation.It is hereby ensured that human body subgraphs to be located at
The center of target image after cutting.
It include two human body subgraphs in target image shown in Figure 19, compared to Figure 19 with reference to Figure 19, Figure 20 and Figure 21
Shown in the distance between two human body subgraphs, the distance between two human body subgraphs shown in Figure 20 increase.In Figure 21
Target image include a human body subgraph.Can be seen that work as in conjunction with Figure 19, Figure 20 and Figure 21 has user to leave camera
When acquisition range, the position of the target point for the human body subgraph that image processing equipment is determined can change, and then can be with base
The position of target point adjustment cropped area 05 after variation.It is hereby ensured that human body subgraphs to be located at the target figure after cutting
The center of picture.
Step 310 shows the target image after cutting.
In embodiments of the present invention, image processing equipment is while being sent to receiving end for the target image after cutting,
The target image after this cuts can also be shown, so that image processing equipment and the receiving end simultaneous display target image.
It should be noted that image processing equipment is determining the target point in human body subgraph in image coordinate system
After position, it can also first detect whether the target point is overlapped with the central point of target image, if the target point and target image
Central point be overlapped, then target image directly can be sent to receiving end by image processing equipment, and show the target image, and
Without executing above-mentioned steps 305 to image processing method shown in step 310.If the central point of the target point and target image is not
It is overlapped, then image processing equipment can execute above-mentioned steps 305 to image processing method shown in step 310.
It should also be noted that, image processing equipment after determining cropped area, can also show the side of the cropped area
Frame, so that user knows position of the cropped area on image processing equipment screen.
It should be noted the successive suitable of the image processing method step in video communication provided in an embodiment of the present invention
Sequence can carry out appropriate adjustment, and step can also be deleted according to circumstances.For example, step 302 to step 304 can be according to feelings
Condition is deleted, and step 306 to step 308 can also be deleted according to circumstances, and step 310 is also possible to according to circumstances carry out
It deletes.Anyone skilled in the art can readily occur in the side of variation in the technical scope that the disclosure discloses
Method should all cover within the protection scope of the disclosure, therefore repeat no more.
In conclusion the embodiment of the invention provides the image processing method in a kind of video communication, the image processing method
Method can determine cropped area according to position of the target point in human body subgraph in image coordinate system, and according to cutting area
Domain cuts target image, so that receiving end shows the target image after cutting, it is straight compared to image processing equipment in the related technology
It connects and the image of camera acquisition is sent to receiving end and show, improve the flexibility of receiving end display image.
Figure 22 is the block diagram of the image processing apparatus 220 in a kind of video communication provided in an embodiment of the present invention, the device
It include: to obtain module 2200, determining module 2201, cut module 2202 and sending module 2203.
Module 2200 is obtained, for obtaining the target image comprising human body subgraph；
Determining module 2201, for the position according to the target point in human body subgraph in image coordinate system, in image
Determine that cropped area, cropped area include human body subgraph region in coordinate system；
Module 2202 is cut, for cutting target image according to cropped area；
Sending module 2203, for the target image after cutting to be sent to receiving end.
Optionally, with reference to Figure 23, module 2202 is cut, comprising:
First cuts submodule 22021, if being located in target image region for cropped area, cuts target figure
The part Chong Die with cropped area as in；
Second cuts submodule 22022, if partly overlapping for cropped area and target image region, adjusts sanction
Position of the region in image coordinate system is cut, and cuts part Chong Die with cropped area adjusted in target image, wherein
Cropped area adjusted is located in target image region, and at least one boundary line of cropped area adjusted and mesh
The boundary line overlap of logo image.
Optionally, second submodule 22022 is cut, is used for:
It will be located at outside target image region in cropped area, and the boundary line that do not intersect with target image, with target
The object boundary line overlap of image is located at cropped area in target image region；
Wherein, object boundary line is the boundary line intersected in target image with cropped area.
Optionally, with reference to Figure 24, device further include:
Identification module 2204, for identification multiple key points in human body subgraph；
Determining module 2201 is also used to determine human geometry's figure based on multiple key points；It will be in human geometry's figure
Heart point is determined as target point.
Optionally, determining module 2201 are used for:
The point centered on target point determines that length-width ratio is the cropped area of the rectangle of target proportion in image coordinate system.
Optionally, determining module 2201 are used for:
The point centered on target point determines that length is target length in image coordinate system, and width is the square of target width
The cropped area of shape.
Optionally, with reference to Figure 24, device further include:
Display module 2205, for showing the target image after cutting after cutting target image according to cropped area.
In conclusion the embodiment of the invention provides the image processing apparatus in a kind of video communication, image procossing dress
Cropped area can be determined according to position of the target point in human body subgraph in image coordinate system by setting, and according to cutting area
Domain cuts target image, so that receiving end shows the target image after cutting, it is straight compared to image processing equipment in the related technology
It connects and the image of camera acquisition is sent to receiving end and show, improve the flexibility of receiving end display image.
The embodiment of the present invention provides a kind of image processing equipment, comprising: memory and is stored in storage at processor
Computer program on device, processor are realized when executing computer program at the image in video communication as shown in Figure 2 or Figure 3
Reason method.
The embodiment of the present invention provides a kind of computer readable storage medium, stores in computer readable storage medium
There is instruction, when computer readable storage medium is run on computers, so that computer executes view as shown in Figure 2 or Figure 3
Image processing method in frequency communication.
The foregoing is merely alternative embodiments of the invention, are not intended to limit the invention, it is all in spirit of the invention and
Within principle, any modification, equivalent replacement, improvement and so on be should all be included in the protection scope of the present invention.
Claims (10)
1. the image processing method in a kind of video communication, which is characterized in that the described method includes:
Obtain the target image comprising human body subgraph；
According to position of the target point in the human body subgraph in image coordinate system, determines and cut out in described image coordinate system
Region is cut, the cropped area includes human body subgraph region；
The target image is cut according to the cropped area；
Target image after cutting is sent to receiving end.
2. the method according to claim 1, wherein described cut the target figure according to the cropped area
Picture, comprising:
If the cropped area is located in the target image region, cuts in the target image and cut area with described
The part of domain overlapping；
If the cropped area partly overlaps with the target image region, the cropped area is adjusted in described image
Position in coordinate system, and cut part Chong Die with the cropped area adjusted in the target image, wherein adjustment
The cropped area afterwards is located in the target image region, and at least one side of the cropped area adjusted
The boundary line overlap in boundary line and the target image.
3. according to the method described in claim 2, it is characterized in that, the adjustment cropped area is in described image coordinate system
In position, comprising:
It will be located at outside the target image region in the cropped area, and the boundary that do not intersect with the target image
Line, the object boundary line overlap with the target image are located at the cropped area in the target image region；
Wherein, the object boundary line is the boundary line intersected in the target image with the cropped area.
4. method according to any one of claims 1 to 3, which is characterized in that the method also includes:
Identify multiple key points in the human body subgraph；
Human geometry's figure is determined based on the multiple key point；
The central point of human geometry's figure is determined as target point.
5. method according to any one of claims 1 to 3, which is characterized in that the mesh according in the human body subgraph
Position of the punctuate in image coordinate system determines cropped area in described image coordinate system, comprising:
Centered on target point point determines that length-width ratio is that the rectangle of target proportion cuts area in described image coordinate system
Domain.
6. method according to any one of claims 1 to 3, which is characterized in that the mesh according in the human body subgraph
Position of the punctuate in image coordinate system determines cropped area in described image coordinate system, comprising:
The point centered on the target point determines that length is target length in described image coordinate system, and width is target width
Rectangle cropped area.
7. method according to any one of claims 1 to 3, which is characterized in that cutting the mesh according to the cropped area
After logo image, the method also includes:
Target image after being cut described in display.
8. the image processing apparatus in a kind of video communication, which is characterized in that described device includes:
Module is obtained, for obtaining the target image comprising human body subgraph；
Determining module, for the position according to the target point in the human body subgraph in image coordinate system, in described image
Determine that cropped area, the cropped area include human body subgraph region in coordinate system；
Module is cut, for cutting the target image according to the cropped area；
Sending module, for the target image after cutting to be sent to receiving end.
9. a kind of image processing equipment characterized by comprising memory, processor and the meter being stored on the memory
Calculation machine program, the processor are realized when executing the computer program in the video communication as described in claim 1 to 7 is any
Image processing method.
10. a kind of computer readable storage medium, which is characterized in that instruction is stored in the computer readable storage medium,
When the computer readable storage medium is run on computers, so that computer is executed as described in claim 1 to 7 is any
Video communication in image processing method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910609634.XA CN110334653A (en) | 2019-07-08 | 2019-07-08 | Image processing method, device and equipment in video communication |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910609634.XA CN110334653A (en) | 2019-07-08 | 2019-07-08 | Image processing method, device and equipment in video communication |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110334653A true CN110334653A (en) | 2019-10-15 |
Family
ID=68143261
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910609634.XA Pending CN110334653A (en) | 2019-07-08 | 2019-07-08 | Image processing method, device and equipment in video communication |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110334653A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2023029547A1 (en) * | 2021-08-31 | 2023-03-09 | 荣耀终端有限公司 | Video processing method, and electronic device |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101557453A (en) * | 2008-04-09 | 2009-10-14 | 鸿富锦精密工业（深圳）有限公司 | Image acquisition device and picture arrangement method thereof |
| CN103914689A (en) * | 2014-04-09 | 2014-07-09 | 百度在线网络技术（北京）有限公司 | Picture cropping method and device based on face recognition |
| CN104881888A (en) * | 2015-06-17 | 2015-09-02 | 北京金山安全软件有限公司 | Picture clipping method and device |
| US9443306B2 (en) * | 2009-04-15 | 2016-09-13 | Microsoft Technology Licensing, Llc | Automated image cropping to include particular subjects |
| CN107872639A (en) * | 2017-11-14 | 2018-04-03 | 维沃移动通信有限公司 | Transmission method, device and the mobile terminal of communication video |
| CN108307036A (en) * | 2017-12-11 | 2018-07-20 | 维沃移动通信有限公司 | A kind of screenshotss method and terminal device |
| CN108364254A (en) * | 2018-03-20 | 2018-08-03 | 北京奇虎科技有限公司 | Image processing method, device and electronic equipment |
| CN109325450A (en) * | 2018-09-25 | 2019-02-12 | Oppo广东移动通信有限公司 | Image processing method, device, storage medium and electronic equipment |
| CN109359618A (en) * | 2018-10-30 | 2019-02-19 | 北京市商汤科技开发有限公司 | A kind of image processing method and its device, equipment and storage medium |
-
2019
- 2019-07-08 CN CN201910609634.XA patent/CN110334653A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101557453A (en) * | 2008-04-09 | 2009-10-14 | 鸿富锦精密工业（深圳）有限公司 | Image acquisition device and picture arrangement method thereof |
| US9443306B2 (en) * | 2009-04-15 | 2016-09-13 | Microsoft Technology Licensing, Llc | Automated image cropping to include particular subjects |
| CN103914689A (en) * | 2014-04-09 | 2014-07-09 | 百度在线网络技术（北京）有限公司 | Picture cropping method and device based on face recognition |
| CN104881888A (en) * | 2015-06-17 | 2015-09-02 | 北京金山安全软件有限公司 | Picture clipping method and device |
| CN107872639A (en) * | 2017-11-14 | 2018-04-03 | 维沃移动通信有限公司 | Transmission method, device and the mobile terminal of communication video |
| CN108307036A (en) * | 2017-12-11 | 2018-07-20 | 维沃移动通信有限公司 | A kind of screenshotss method and terminal device |
| CN108364254A (en) * | 2018-03-20 | 2018-08-03 | 北京奇虎科技有限公司 | Image processing method, device and electronic equipment |
| CN109325450A (en) * | 2018-09-25 | 2019-02-12 | Oppo广东移动通信有限公司 | Image processing method, device, storage medium and electronic equipment |
| CN109359618A (en) * | 2018-10-30 | 2019-02-19 | 北京市商汤科技开发有限公司 | A kind of image processing method and its device, equipment and storage medium |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2023029547A1 (en) * | 2021-08-31 | 2023-03-09 | 荣耀终端有限公司 | Video processing method, and electronic device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20200401790A1 (en) | Face image processing method and device, and storage medium | |
| US20200126295A1 (en) | Method and/or system for reconstructing from images a personalized 3d human body model and thereof | |
| CN109948590A (en) | Pose problem detection method and device | |
| CN112017222B (en) | Video panorama stitching and three-dimensional fusion method and device | |
| CN110009561A (en) | A kind of monitor video target is mapped to the method and system of three-dimensional geographical model of place | |
| CN106055446B (en) | A kind of test method and device of mobile terminal | |
| CN105147311B (en) | For the visualization device sub-scanning localization method and system in CT system | |
| US11194536B2 (en) | Image processing method and apparatus for displaying an image between two display screens | |
| CN106650682A (en) | Method and device for face tracking | |
| WO2021169668A1 (en) | Image processing method and related device | |
| CN106934777A (en) | Scan image acquisition methods and device | |
| KR102331651B1 (en) | Method and apparatus for recognizing descriptive properties of apparent features | |
| WO2020220832A1 (en) | Method and apparatus for achieving projection picture splicing, and projection system | |
| US8705145B2 (en) | Systems and methods for resuming capture of a base image of an object by a mobile scanner | |
| CN114640833A (en) | Projection picture adjusting method and device, electronic equipment and storage medium | |
| CN110191369A (en) | Image interception method, apparatus, equipment and storage medium | |
| CN105654531B (en) | Method and device for drawing image contour | |
| CN110827301A (en) | Method and apparatus for processing image | |
| CN110334653A (en) | Image processing method, device and equipment in video communication | |
| CN111462098A (en) | Method, device, equipment and medium for detecting overlapping of shadow areas of object to be detected | |
| CN108111747A (en) | A kind of image processing method, terminal device and computer-readable medium | |
| EP3359024A1 (en) | Method and system for capturing an image for wound assessment | |
| CN110852934A (en) | Image processing method and apparatus, image device, and storage medium | |
| CN113485660A (en) | Folding screen picture display method and device | |
| CN114187349B (en) | Product processing method and device, terminal device and storage medium |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20191015 |