CN110035236A - Image processing method, device and electronic equipment - Google Patents
Image processing method, device and electronic equipment Download PDFInfo
- Publication number
- CN110035236A CN110035236A CN201910230223.XA CN201910230223A CN110035236A CN 110035236 A CN110035236 A CN 110035236A CN 201910230223 A CN201910230223 A CN 201910230223A CN 110035236 A CN110035236 A CN 110035236A
- Authority
- CN
- China
- Prior art keywords
- point
- image
- track
- target object
- image processing
- 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
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N5/00—Details of television systems
- H04N5/222—Studio circuitry; Studio devices; Studio equipment
- H04N5/262—Studio circuits, e.g. for mixing, switching-over, change of character of image, other special effects ; Cameras specially adapted for the electronic generation of special effects
- H04N5/2621—Cameras specially adapted for the electronic generation of special effects during image pickup, e.g. digital cameras, camcorders, video cameras having integrated special effects capability
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20112—Image segmentation details
- G06T2207/20164—Salient point detection; Corner detection
Abstract
The disclosure discloses a kind of image processing method, device and electronic equipment.Wherein, which includes: to obtain video image from image source, wherein including at least one target object in the video image;The target object is partitioned into from the video image;Obtain at least one first point on the target object;Same first point of connection in multiframe adjacent image frame is calculated into first point of the track;It obtains Image Processing parameter and is handled to obtain treated track to first point of the track.The image processing method of the embodiment of the present disclosure handles the special-effect that the track generates track using preset image procossing mode, improves the efficiency and flexibility for generating special efficacy by calculating the motion profile of the point on target object.
Description
Technical field
This disclosure relates to field of image processing, more particularly to a kind of image processing method, device and electronic equipment.
Background technique
With the development of computer technology, the application range of intelligent terminal has obtained extensive raising, such as can pass through
Intelligent terminal listens to music, plays game, chats on line and take pictures.For the shooting technology of intelligent terminal, pixel of taking pictures
Have reached ten million pixel or more, the effect of taking pictures of clarity with higher and the mm professional camera special that matches in excellence or beauty.
At present when being taken pictures using intelligent terminal, built-in software realization tradition of taking pictures when factory not only can be used
The effect of taking pictures of function can also realize tool by downloading application program (Application, referred to as are as follows: APP) from network-side
There is the effect of taking pictures of additional function, such as the APP of half-light detection, the U.S. functions such as face camera and super pixel may be implemented.Intelligence
The U.S. face function of terminal generally includes the U.S. face treatment effects such as colour of skin adjustment, mill skin, big eye and thin face, can be to having identified in image
All faces out carry out the U.S. face processing of same degree.Also there is APP that simple special efficacy may be implemented at present.
However current special effective function, the effect of special efficacy can only be pre-set, and be synthesized in video or image, such as
Fruit needs to modify special efficacy, then is synthesized in video or image again after needing to remake special efficacy, so that the generation of special efficacy is very not
Flexibly.
Summary of the invention
According to one aspect of the disclosure, the following technical schemes are provided:
A kind of image processing method, comprising:
Video image is obtained from image source, wherein including at least one target object in the video image;
The target object is partitioned into from the video image;
Obtain at least one first point on the target object;
Same first point of connection in multiframe adjacent image frame is calculated into first point of the track;
It obtains Image Processing parameter and is handled to obtain treated track to first point of the track.
Further, described to obtain video image from image source, wherein including at least one target in the video image
Object, comprising:
Video image is obtained from video acquisition device, includes multiple image frame, described image frame in the video image
In include at least one target object.
It is further, described that the target object is partitioned into from the video image, comprising:
Identify the target object in the video image;
It is partitioned into the profile of the target object;
Image in the profile and profile of the target object is extracted from the video image.
Further, at least one first point obtained on the target object, comprising:
At least one angle point on target object is obtained, the angle point is the friendship on two sides on the profile of target object
Point.
Further, at least one first point obtained on the target object, comprising:
Randomly select at least one random point on target object.
Further, same first point of connection by multiframe adjacent image frame calculates at described first point
Track, comprising:
Described first point is sorted according to first point of number;
First point that same number is identified in multiple image;
Is connected first point of track for generating the number at first point of the same number.
Further, the acquisition Image Processing parameter and handled to obtain that treated to first point of the track
Track, comprising:
Image processing mode and image processing resource are obtained from image procossing configuration file;
First point of the track is carried out handling everywhere according to described image tupe and image processing resource
Track after reason.
Further, in the acquisition Image Processing parameter and after being handled to obtain processing to first point of the track
Track after, further includes:
After the picture frame by predetermined quantity, at least one second point on the target object is obtained;
The same second point connection in multiframe adjacent image frame is calculated to the track of the second point;
It obtains Image Processing parameter and is handled to obtain treated track to the track of the second point.
Further, the acquisition Image Processing parameter and handled to obtain that treated to first point of the track
Track, comprising:
The image processing mode and image processing resource of different numbers are obtained from image procossing configuration file;
According to first point of the number for generating the track, the corresponding image processing mode of the number and figure are used
As first point of track of the process resource to the number is handled to obtain treated track.
According to another aspect of the disclosure, also the following technical schemes are provided:
A kind of image processing apparatus, comprising:
Image collection module, for obtaining video image from image source, wherein including at least one in the video image
Target object;
Divide module, for being partitioned into the target object from the video image;
Target object point obtains module, for obtaining at least one first point on the target object;
Trajectory computation module, for same first point of connection in multiframe adjacent image frame to be calculated described first
The track of point;
Trajectory processing module, for obtaining Image Processing parameter and being handled first point of the track
Track afterwards.
Further, described image obtains module, is also used to:
Video image is obtained from video acquisition device, includes multiple image frame, described image frame in the video image
In include at least one target object.
Further, the segmentation module, further includes:
Target object identification module, for identification target object in the video image;
Contours segmentation module, for being partitioned into the profile of the target object;
Target object extraction module, for the image in the profile and profile by the target object from the video figure
It is extracted as in.
Further, the target object point obtains module, further includes:
Angle point obtains module, and for obtaining at least one angle point on target object, the angle point is the wheel of target object
The intersection point on two sides on exterior feature.
Further, the target object point obtains module, further includes:
Random point obtains module, for randomly selecting at least one random point on target object.
Further, the trajectory computation module, further includes:
Sorting module sorts at described first point for the number according to first point;
First identification module, for identifying in multiple image at first point of same number;
Link block, for connecting at first point of the same number first point of track for generating the number.
Further, the trajectory processing module, further includes:
Processing parameter obtains module, for obtaining image processing mode and image procossing from image procossing configuration file
Resource;
First locus of points processing module is used for according to described image tupe and image processing resource to described first
The track of point is handled to obtain treated track.
Further, described device further include:
Second target object point obtains module, for obtaining the object after the picture frame by predetermined quantity
At least one second point on body;
Second link block, for the same second point connection in multiframe adjacent image frame to be calculated described second
The track of point;
Second point trajectory processing module, for obtaining Image Processing parameter and handle to the track of the second point
To treated track.
Further, the trajectory processing module, further includes:
Second processing parameter acquisition module, for obtaining the image procossing mould of different numbers from image procossing configuration file
Formula and image processing resource;
Multi-trace processing module, for being corresponded to using the number according to first point of the number for generating the track
Image processing mode and image processing resource handled to obtain treated rail to first point of track of the number
Mark.
According to the another aspect of the disclosure, and also the following technical schemes are provided:
A kind of electronic equipment, comprising: memory, for storing non-transitory computer-readable instruction;And processor, it uses
In running the computer-readable instruction, so that the processor realizes step described in any of the above-described image processing method when executing
Suddenly.
According to the another aspect of the disclosure, and also the following technical schemes are provided:
A kind of computer readable storage medium, for storing non-transitory computer-readable instruction, when the non-transitory
When computer-readable instruction is executed by computer, so that the step of computer executes described in any of the above-described method.
The disclosure discloses a kind of image processing method, device and electronic equipment.Wherein, the image processing method include: from
Image source obtains video image, wherein including at least one target object in the video image;Divide from the video image
Cut out the target object;Obtain at least one first point on the target object;It will be same in multiframe adjacent image frame
A first point of connection calculates first point of the track;It obtains Image Processing parameter and first point of the track is carried out
Processing obtains that treated track.The image processing method of the embodiment of the present disclosure, by the movement for calculating the point on target object
Track handles the special-effect that the track generates track using preset image procossing mode, improves generation special efficacy
Efficiency and flexibility.
Above description is only the general introduction of disclosed technique scheme, in order to better understand the technological means of the disclosure, and
It can be implemented in accordance with the contents of the specification, and to allow the above and other objects, features and advantages of the disclosure can be brighter
Show understandable, it is special below to lift preferred embodiment, and cooperate attached drawing, detailed description are as follows.
Detailed description of the invention
Fig. 1 is the flow diagram according to the image processing method of an embodiment of the present disclosure;
Fig. 2 is the target object Corner Detection schematic diagram according to an embodiment of the present disclosure;
Fig. 3 is the flow diagram according to the image processing method of the disclosure another embodiment;
Fig. 4 is the structural schematic diagram according to the image processing apparatus of an embodiment of the present disclosure;
Fig. 5 is the structural schematic diagram of the electronic equipment provided according to the embodiment of the present disclosure.
Specific embodiment
Illustrate embodiment of the present disclosure below by way of specific specific example, those skilled in the art can be by this specification
Disclosed content understands other advantages and effect of the disclosure easily.Obviously, described embodiment is only the disclosure
A part of the embodiment, instead of all the embodiments.The disclosure can also be subject to reality by way of a different and different embodiment
It applies or applies, the various details in this specification can also be based on different viewpoints and application, in the spirit without departing from the disclosure
Lower carry out various modifications or alterations.It should be noted that in the absence of conflict, the feature in following embodiment and embodiment can
To be combined with each other.Based on the embodiment in the disclosure, those of ordinary skill in the art are without creative efforts
Every other embodiment obtained belongs to the range of disclosure protection.
It should be noted that the various aspects of embodiment within the scope of the appended claims are described below.Ying Xian
And be clear to, aspect described herein can be embodied in extensive diversified forms, and any specific structure described herein
And/or function is only illustrative.Based on the disclosure, it will be understood by one of ordinary skill in the art that one described herein
Aspect can be independently implemented with any other aspect, and can combine the two or both in these aspects or more in various ways.
For example, carry out facilities and equipments in terms of any number set forth herein can be used and/or practice method.In addition, can make
With other than one or more of aspect set forth herein other structures and/or it is functional implement this equipment and/or
Practice the method.
It should also be noted that, diagram provided in following embodiment only illustrates the basic structure of the disclosure in a schematic way
Think, component count, shape and the size when only display is with component related in the disclosure rather than according to actual implementation in schema are drawn
System, when actual implementation kenel, quantity and the ratio of each component can arbitrarily change for one kind, and its assembly layout kenel can also
It can be increasingly complex.
In addition, in the following description, specific details are provided for a thorough understanding of the examples.However, fields
The skilled person will understand that the aspect can be practiced without these specific details.
The embodiment of the present disclosure provides a kind of image processing method.The image processing method provided in this embodiment can be by one
Computing device executes, which can be implemented as software, or be embodied as the combination of software and hardware, the computing device
It can integrate and be arranged in server, terminal device etc..As shown in Figure 1, the image processing method mainly includes the following steps
S101 to step S105.Wherein:
Step S101: obtaining video image from image source, wherein including at least one target object in the video image;
In the disclosure, described image source be local storage space or network storage space, it is described from image source obtain
Video image, including video image, nothing are obtained from acquisition video image in local storage space or from network storage space
By video image is wherefrom obtained, first choice needs to obtain the storage address of video image, obtains video from the storage address later
Image, the video image include multiple images frame, and the video image can be video and be also possible to dynamic effect
Picture, as long as the image with multiframe may each be the video image in the disclosure.
In the disclosure, the video source can be video acquisition device, such as imaging sensor, described to obtain from image source
Video image, including video image is obtained from video acquisition device.Described image sensor, which refers to, can acquire the various of image
Equipment, typical imaging sensor are video camera, camera, camera etc..In this embodiment, described image sensor can be
The video image of camera on mobile terminal, such as the preposition or rear camera on smart phone, camera acquisition can
To directly display on a display of the handset, in this step, video captured by imaging sensor is obtained, as to be processed
Image.
It include at least one in the video image since the technical solution of the disclosure needs to identify target object
Target object.It wherein include at least one target object in the multiple image frame of the video image, it is possible to understand that, it is described
It also may include multiple target objects in video image, details are not described herein.
Step S101: the target object is partitioned into from the video image;
In the disclosure, described that the target object is partitioned into from the video image, comprising: to identify the video figure
Target object as in;It is partitioned into the profile of the target object;By the image in the profile and profile of the target object
It is extracted from the video image.
In this step, the video image is the picture frame in the video image, and described image frame is with target
The picture of object, the target object can be any object, and the target object is human body in this embodiment.
Image segmentation is generally divided into interactive image segmentation and self-action image segmentation, and image procossing traditionally generally makes
With interactive image segmentation, need artificially to participate in the segmentation of image.Self-action image segmentation is used in the disclosure, below with human body
For image segmentation, self-action image segmentation is illustrated.
In general, self-action human body image dividing method can be divided into following several: (1) based on the human body image of model
Dividing method detects face according to the priori knowledge of face first for this method, finds people using human trunk model later
The following trunk of face, then estimates the position of the lower part of the body according to the trunk divided, finally using estimating to obtain trunk and leg
Upper half limb region provides seed point for image segmentation to complete the segmentation of human body image;(2) human body image based on hierarchical tree point
Segmentation method models this method to neighbouring body part first, models later to entire human posture,
The different gestures of human body are modeled as to the adduction of node on the different paths in level detection tree, level detects layer different in tree
The model of corresponding different neighbouring human body parts corresponds to different human postures along the different paths on level detection tree,
It is detected downwards when detection along the root node of tree, the different gestures of human body is partitioned into along different paths;(3) it is based on reference signal
Independent component analysis human body image dividing method face is detected according to the priori knowledge of face first for this method,
The following trunk of face is found using human trunk model later, reference signal is obtained from the trunk detected later, then utilizes
Trunk is completed the segmentation of trunk by the Independent Component Analysis of reference signal from image convexity explict occurrence, other body parts
Divide similar, is finally completed the segmentation of entire human body image;(4) the human body image dividing method based on expectation-maximization algorithm,
For this method, the human posture in image is estimated using patterning model first, obtains the general of human posture
Rate figure reuses image partition method on the basis of probability graph later and obtains human body segmentation's image to the end.Above-mentioned segmentation side
In method, no matter which kind of method, which is typically necessary, is first identified that a part of human body perhaps human body is estimated or determined later
Image zooming-out in outer profile is finally come out and obtains the segmented image of human body by the outer profile of human body.
It should be understood that other human body image dividing methods can also be used, repeat no more in the disclosure, Ren Hetu
As dividing method can be introduced into the disclosure, to be partitioned into target object from video image.
Step S103: at least one first point on the target object is obtained;
In the disclosure, at least one first point obtained on the target object, comprising: obtain on target object
At least one angle point, the angle point be target object profile on two sides intersection point.Optionally, the target object is
Human body, the angle point are the angle point of human body jacket clothes, referring to fig. 2 shown in, wherein 201 for clothes at shoulder on human body angle
Point, 202 be the angle point of clothes at human body elbow, and 203 be the angle point of human body knee clothes.Obtain the angle on target object
Point, first choice need to carry out Corner Detection, and in the disclosure, any angular-point detection method can be used in Corner Detection, typically such as
Harris Corner Detection Algorithm, Moravec Corner Detection Algorithm, FAST Corner Detection Algorithm etc., it is in the disclosure and unlimited
Surely which kind of Corner Detection Algorithm it can be applied to the skill of the disclosure as long as the algorithm of angle point can be quickly detected using
In art scheme.In general, the angle point that detected is the intersection point on two sides on the profile of target object, in Fig. 2
Angle point 203 is the point of the point of intersection of human thigh and shank profile.The angle point that detected can be a point or more
It is a, when obtaining the angle point, one or more can be selected from the angle point that detected, when selecting the angle point,
Can be according to n angle point before the sequential selection for detecting the angle point, wherein n >=1;It can also be according to certain standard, such as
The color of angle point, the angle point that acquisition is determined with luminance differences etc. of other points of periphery, details are not described herein.
In the disclosure, at least one first point obtained on the target object, comprising: randomly select object
At least one random point on body.Optionally, the target object is human body, in this embodiment, at random in the profile of human body
At least one point is selected in upper or profile.At least one point of the selection can be used to be spread a little at random in the profile of human body
Mode is realized.Optionally, random function one random point of generation can be used should if the point is located in human body contour outline
Point abandons the point if the point is located at outside human body contour outline as a random point;It optionally, can be by the profile of human body
Interior image is cut into several triangles, and the range of triangle it was determined that spread a little at random in the range of triangle;It is optional
, quaternary tree can be used by the image in human body contour outline and be cut into multiple equal-sized squares, later by square
Center is as random point.The disclosure is not intended to limit the generating mode of random point, can be in human body contour outline with any method
The one or more random points of interior generation are chosen in the random point one or more as first point later.Selection it is described with
, can be according to n random point before the sequential selection for generating the random point when machine point, wherein n >=1;It can also be according to certain
Standard, such as the random point of position within a predetermined range, details are not described herein.
It should be understood that first point of the acquisition does not limit above two mode, as long as on objects' contour
Or the point in profile can be used as at first point, first in the disclosure point can be used various methods and obtain, herein no longer
It repeats.
Step S104: same first point of connection in multiframe adjacent image frame is calculated into first point of the rail
Mark;
In the disclosure, same first point of connection by multiframe adjacent image frame calculates at described first point
Track, comprising: according to first point of number by described first point sort;The first of same number is identified in multiple image
Point;Is connected first point of track for generating the number at first point of the same number.In this embodiment, described
A little with number, the number can be the number numbered in advance, and such as when detecting angle point, the 3 of detection fixation can be set
A angle point, as shown in Fig. 2, the number that this 3 angle point settings is fixed, if the number of angle point 201 is set as 001, angle point 202
Number is set as 002, and the number of angle point 203 is set as 003;In multiple image, identifies the angle point of same number, herein may be used
Position of the angle point occurred in first frame picture frame to use streamer method to calculate in subsequent picture frame, typical streamer meter
Calculation method be L-K algorithm, dense optical flow method, pyramid optical flow method etc., using optical flow method can be convenient in multiple image frame
The middle same point of tracking, the point can be characteristic point such as angle point, be also possible to random point or other any customized points.?
After the point for identifying the same number in multiple image frame, the point of same number is connected, generates the of the number
The track of a bit.When image frame sampling is more intensive, which can show the smoother fortune of the target object
Dynamic rail mark.
It should be understood that in this step, the method that the same point is tracked in multiple image frame is not limited to above-mentioned side
Method, it is any to track the method that the same point forms motion profile in multiple image frame and can be applied in the disclosure,
Details are not described herein.
Step S105: obtaining Image Processing parameter and is handled to obtain treated rail to first point of the track
Mark.
In the disclosure, the acquisition Image Processing parameter and first point of the track is handled after obtaining processing
Track, comprising: image processing mode and image processing resource are obtained from image procossing configuration file;According to described image
Tupe and image processing resource are handled to obtain treated track to first point of the track.Wherein, described
Image procossing configuration file is used to save the processing type of described image processing, such as textures, deformation, filter and described
The address of resource required for image procossing, in the position of textures required in stick picture disposing and textures, deformation process
Deformation Types and deformation parameter, the colour atla in filter processing and filter process range etc.;Later according to acquired
Tupe and image processing resource handle first point of the track to obtain the track with certain effect.It is optional
, for first point on the track is added textures, the textures include multiple textures frames, each textures for described image processing
The brightness of frame circulation change from small to large gets patch required for stick picture disposing from described image processing configuration file at this time
The address of figure, and corresponding textures frame is got, first point of the position in picture frame is got later, by the textures frame
It is rendered at described first point on the position of each textures frame, is flashed with achieving the effect that at first point in multiple image.It is optional
, described image processing is the textures that rainbow effect is added on the track, then handles configuration file from described image at this time
In get the addresses of textures required for stick picture disposing, textures herein are the rectangle rainbow figure of fixed size, by the square
The center line of shape rainbow figure fits on the track, and what is recycled later successively sticks entire track for the rainbow figure, to reach
To the effect of rainbow track.It should be understood that image procossing herein can be any processing, as long as can be to described first
The image procossing that is handled of point on the track or track of point can be applied in the disclosure, it is specific handle type and
The corresponding parameter of processing type can be preset with image procossing configuration file, and passing through modification configuration file in this way can be real
Now to the rendering of motion profile, achieve the effect that different, and the effect is on real-time rendering to motion profile, without record in advance
Video processed adds the effect by post-production, more convenient compared to conventional method.
In the disclosure, the acquisition Image Processing parameter and first point of the track is handled after obtaining processing
Track, can also include: the image processing mode and image procossing that different numbers are obtained from image procossing configuration file
Resource;According to first point of the number for generating the track, the corresponding image processing mode of the number and image are used
Process resource is handled to obtain treated track to first point of track of the number.Wherein, described image processing is matched
It sets including a variety of tupes and the corresponding resource of tupe in file, it will be described a variety of in image procossing configuration file
Tupe is mapped with first point of number, in this way can be with not for first point of track generated of different numbers
With image processing mode handle, the track that the angle point for being such as 001 to number generates to number is using stick picture disposing is flashed
The track that 002 angle point generates uses rainbow stick picture disposing, and different modes can be used to different tracks in this way and go to handle.
In addition, the case where for identifying multiple target objects in video image, can also be pre-configured with, with reality in configuration file
Existing multiple target object multi-trace is handled differently, and concrete configuration mode is similar with top, it is thus only necessary to distinguish target object and
The different tracks of target object, details are not described herein.
As shown in figure 3, being the flow diagram of another embodiment of the present disclosure.In this embodiment, video image is done
Segment processing, that is to say, that video image is divided into several stages, different processing is done to each stage.Specifically, described
After step S105, further includes:
Step S301: by predetermined quantity picture frame after, obtain on the target object at least one second
Point;
Step S302: the same second point connection in multiframe adjacent image frame is calculated to the rail of the second point
Mark;
Step S303: obtaining Image Processing parameter and is handled to obtain treated rail to the track of the second point
Mark.
In this embodiment it is possible to preset the picture frame of predetermined quantity as processing frame number, it is processing frame that M frame, which is such as arranged,
Number, that is to say, that each image procossing is using M frame as boundary, the targeted track of hand-off process and/or processing after more than M frame
Mode.Optionally, the second point can be identical as first point, can be used at this time and obtains first point of identical mode, after
Continuous to obtain second point, then second point is identical as first point, at this time only hand-off process mode, uses the place different from preceding M frame
Reason mode handles the track that the same point generates, and shows a kind of path effect of segmentation at this time.Optionally, the second point can
With different from first point, at this time after more than M frame, second point reacquired, new track is formed, difference can be formed at this time
The effect of track same treatment or different tracks different disposal.Specific processing configuration and processing mode may refer to step
Description in S105, configuration mode herein is same, repeats no more.
The disclosure discloses a kind of image processing method, device and electronic equipment.Wherein, the image processing method include: from
Image source obtains video image, wherein including at least one target object in the video image;Divide from the video image
Cut out the target object;Obtain at least one first point on the target object;It will be same in multiframe adjacent image frame
A first point of connection calculates first point of the track;It obtains Image Processing parameter and first point of the track is carried out
Processing obtains that treated track.The image processing method of the embodiment of the present disclosure, by the movement for calculating the point on target object
Track handles the special-effect that the track generates track using preset image procossing mode, improves generation special efficacy
Efficiency and flexibility.
Hereinbefore, although describing each step in above method embodiment, this field skill according to above-mentioned sequence
Art personnel it should be clear that the step in the embodiment of the present disclosure not necessarily executes in the order described above, can also with inverted order, it is parallel,
Other sequences such as intersection execute, moreover, those skilled in the art can also add other steps on the basis of above-mentioned steps
Suddenly, the mode of these obvious variants or equivalent replacement should also be included within the protection scope of the disclosure, and details are not described herein.
It is below embodiment of the present disclosure, embodiment of the present disclosure can be used for executing embodiments of the present disclosure realization
The step of, for ease of description, part relevant to the embodiment of the present disclosure is illustrated only, it is disclosed by specific technical details, it asks
Referring to embodiments of the present disclosure.
The embodiment of the present disclosure provides a kind of image processing apparatus.The device can execute above-mentioned image processing method embodiment
Described in the step of.As shown in figure 4, the device 400 specifically includes that image collection module 401, segmentation module 402, target object
Point obtains module 403, trajectory computation module 404 and trajectory processing module 405.Wherein,
Image collection module 401, for obtaining video image from image source, wherein including at least one in the video image
A target object;
Divide module 402, for being partitioned into the target object from the video image;
Target object point obtains module 403, for obtaining at least one first point on the target object;
Trajectory computation module 404, described in calculating same first point of connection in multiframe adjacent image frame
First point of track;
Trajectory processing module 405, for obtaining Image Processing parameter and being handled to obtain to first point of the track
Treated track.
Further, described image obtains module 401, is also used to:
Video image is obtained from video acquisition device, includes multiple image frame, described image frame in the video image
In include at least one target object.
Further, the segmentation module 402, further includes:
Target object identification module, for identification target object in the video image;
Contours segmentation module, for being partitioned into the profile of the target object;
Target object extraction module, for the image in the profile and profile by the target object from the video figure
It is extracted as in.
Further, the target object point obtains module 403, further includes:
Angle point obtains module, and for obtaining at least one angle point on target object, the angle point is the wheel of target object
The intersection point on two sides on exterior feature.
Further, the target object point obtains module 403, further includes:
Random point obtains module, for randomly selecting at least one random point on target object.
Further, the trajectory computation module 404, further includes:
Sorting module sorts at described first point for the number according to first point;
First identification module, for identifying in multiple image at first point of same number;
Link block, for connecting at first point of the same number first point of track for generating the number.
Further, the trajectory processing module 405, further includes:
Processing parameter obtains module, for obtaining image processing mode and image procossing from image procossing configuration file
Resource;
First locus of points processing module is used for according to described image tupe and image processing resource to described first
The track of point is handled to obtain treated track.
Further, described device 400 further include:
Second target object point obtains module, for obtaining the object after the picture frame by predetermined quantity
At least one second point on body;
Second link block, for the same second point connection in multiframe adjacent image frame to be calculated described second
The track of point;
Second point trajectory processing module, for obtaining Image Processing parameter and handle to the track of the second point
To treated track.
Further, the trajectory processing module 405, further includes:
Second processing parameter acquisition module, for obtaining the image procossing mould of different numbers from image procossing configuration file
Formula and image processing resource;
Multi-trace processing module, for being corresponded to using the number according to first point of the number for generating the track
Image processing mode and image processing resource handled to obtain treated rail to first point of track of the number
Mark.
The method that Fig. 4 shown device can execute Fig. 1 and embodiment illustrated in fig. 3, the part that the present embodiment is not described in detail,
It can refer to the related description to Fig. 1 and embodiment illustrated in fig. 3.The implementation procedure and technical effect of the technical solution referring to Fig. 1 and
Description in embodiment illustrated in fig. 3, details are not described herein.
Below with reference to Fig. 5, it illustrates the structural representations for the electronic equipment 500 for being suitable for being used to realize the embodiment of the present disclosure
Figure.Electronic equipment in the embodiment of the present disclosure can include but is not limited to such as mobile phone, laptop, digital broadcasting and connect
Receive device, PDA (personal digital assistant), PAD (tablet computer), PMP (portable media player), car-mounted terminal (such as vehicle
Carry navigation terminal) etc. mobile terminal and such as number TV, desktop computer etc. fixed terminal.Electricity shown in Fig. 5
Sub- equipment is only an example, should not function to the embodiment of the present disclosure and use scope bring any restrictions.
As shown in figure 5, electronic equipment 500 may include processing unit (such as central processing unit, graphics processor etc.)
501, random access can be loaded into according to the program being stored in read-only memory (ROM) 502 or from storage device 508
Program in memory (RAM) 503 and execute various movements appropriate and processing.In RAM 503, it is also stored with electronic equipment
Various programs and data needed for 500 operations.Processing unit 501, ROM 502 and RAM 503 pass through the phase each other of bus 504
Even.Input/output (I/O) interface 505 is also connected to bus 504.
In general, following device can connect to I/O interface 505: including such as touch screen, touch tablet, keyboard, mouse, figure
As the input unit 506 of sensor, microphone, accelerometer, gyroscope etc.;Including such as liquid crystal display (LCD), loudspeaking
The output device 507 of device, vibrator etc.;Storage device 508 including such as tape, hard disk etc.;And communication device 509.It is logical
T unit 509 can permit electronic equipment 500 and wirelessly or non-wirelessly be communicated with other equipment to exchange data.Although Fig. 4 shows
The electronic equipment 500 with various devices is gone out, it should be understood that being not required for implementing or having all dresses shown
It sets.It can alternatively implement or have more or fewer devices.
Particularly, in accordance with an embodiment of the present disclosure, it may be implemented as computer above with reference to the process of flow chart description
Software program.For example, embodiment of the disclosure includes a kind of computer program product comprising be carried on computer-readable medium
On computer program, which includes the program code for method shown in execution flow chart.In such reality
It applies in example, which can be downloaded and installed from network by communication device 509, or from storage device 508
It is mounted, or is mounted from ROM502.When the computer program is executed by processing unit 501, the embodiment of the present disclosure is executed
Method in the above-mentioned function that limits.
It should be noted that the above-mentioned computer-readable medium of the disclosure can be computer-readable signal media or meter
Calculation machine readable storage medium storing program for executing either the two any combination.Computer readable storage medium for example can be --- but not
Be limited to --- electricity, magnetic, optical, electromagnetic, infrared ray or semiconductor system, device or device, or any above combination.Meter
The more specific example of calculation machine readable storage medium storing program for executing can include but is not limited to: have the electrical connection, just of one or more conducting wires
Taking formula computer disk, hard disk, random access storage device (RAM), read-only memory (ROM), erasable type may be programmed read-only storage
Device (EPROM or flash memory), optical fiber, portable compact disc read-only memory (CD-ROM), light storage device, magnetic memory device,
Or above-mentioned any appropriate combination.In the disclosure, computer readable storage medium can be it is any include or storage journey
The tangible medium of sequence, the program can be commanded execution system, device or device use or in connection.And at this
In open, computer-readable signal media may include in a base band or as the data-signal that carrier wave a part is propagated,
In carry computer-readable program code.The data-signal of this propagation can take various forms, including but not limited to
Electromagnetic signal, optical signal or above-mentioned any appropriate combination.Computer-readable signal media can also be computer-readable and deposit
Any computer-readable medium other than storage media, the computer-readable signal media can send, propagate or transmit and be used for
By the use of instruction execution system, device or device or program in connection.Include on computer-readable medium
Program code can transmit with any suitable medium, including but not limited to: electric wire, optical cable, RF (radio frequency) etc. are above-mentioned
Any appropriate combination.
Above-mentioned computer-readable medium can be included in above-mentioned electronic equipment;It is also possible to individualism, and not
It is fitted into the electronic equipment.
Above-mentioned computer-readable medium carries one or more program, when said one or multiple programs are by the electricity
When sub- equipment executes, so that the electronic equipment: video image is obtained from image source, wherein including at least one in the video image
A target object;The target object is partitioned into from the video image;Obtain on the target object at least one
A bit;Same first point of connection in multiframe adjacent image frame is calculated into first point of the track;It obtains at image
Reason parameter is simultaneously handled to obtain treated track to first point of the track.
The calculating of the operation for executing the disclosure can be write with one or more programming languages or combinations thereof
Machine program code, above procedure design language include object oriented program language-such as Java, Smalltalk, C+
+, it further include conventional procedural programming language-such as " C " language or similar programming language.Program code can
Fully to execute, partly execute on the user computer on the user computer, be executed as an independent software package,
Part executes on the remote computer or executes on a remote computer or server completely on the user computer for part.
In situations involving remote computers, remote computer can pass through the network of any kind --- including local area network (LAN)
Or wide area network (WAN)-is connected to subscriber computer, or, it may be connected to outer computer (such as utilize Internet service
Provider is connected by internet).
Flow chart and block diagram in attached drawing are illustrated according to the system of the various embodiments of the disclosure, method and computer journey
The architecture, function and operation in the cards of sequence product.In this regard, each box in flowchart or block diagram can generation
A part of one module, program segment or code of table, a part of the module, program segment or code include one or more use
The executable instruction of the logic function as defined in realizing.It should also be noted that in some implementations as replacements, being marked in box
The function of note can also occur in a different order than that indicated in the drawings.For example, two boxes succeedingly indicated are actually
It can be basically executed in parallel, they can also be executed in the opposite order sometimes, and this depends on the function involved.Also it to infuse
Meaning, the combination of each box in block diagram and or flow chart and the box in block diagram and or flow chart can be with holding
The dedicated hardware based system of functions or operations as defined in row is realized, or can use specialized hardware and computer instruction
Combination realize.
Being described in unit involved in the embodiment of the present disclosure can be realized by way of software, can also be by hard
The mode of part is realized.Wherein, the title of unit does not constitute the restriction to the unit itself under certain conditions.
Above description is only the preferred embodiment of the disclosure and the explanation to institute's application technology principle.Those skilled in the art
Member is it should be appreciated that the open scope involved in the disclosure, however it is not limited to technology made of the specific combination of above-mentioned technical characteristic
Scheme, while should also cover in the case where not departing from design disclosed above, it is carried out by above-mentioned technical characteristic or its equivalent feature
Any combination and the other technical solutions formed.Such as features described above has similar function with (but being not limited to) disclosed in the disclosure
Can technical characteristic replaced mutually and the technical solution that is formed.
Claims (12)
1. a kind of image processing method, comprising:
Video image is obtained from image source, wherein including at least one target object in the video image;
The target object is partitioned into from the video image;
Obtain at least one first point on the target object;
Same first point of connection in multiframe adjacent image frame is calculated into first point of the track;
It obtains Image Processing parameter and is handled to obtain treated track to first point of the track.
2. image processing method as described in claim 1, wherein described obtain video image from image source, wherein the video
It include at least one target object in image, comprising:
Video image is obtained from video acquisition device, is included multiple image frame in the video image, is wrapped in described image frame
Include at least one target object.
3. image processing method as described in claim 1, wherein described be partitioned into the object from the video image
Body, comprising:
Identify the target object in the video image;
It is partitioned into the profile of the target object;
Image in the profile and profile of the target object is extracted from the video image.
4. image processing method as described in claim 1, wherein it is described obtain on the target object at least one first
Point, comprising:
At least one angle point on target object is obtained, the angle point is the intersection point on two sides on the profile of target object.
5. image processing method as described in claim 1, wherein it is described obtain on the target object at least one first
Point, comprising:
Randomly select at least one random point on target object.
6. image processing method as described in claim 1, wherein same described by multiframe adjacent image frame
Some connection calculates first point of the track, comprising:
Described first point is sorted according to first point of number;
First point that same number is identified in multiple image;
Is connected first point of track for generating the number at first point of the same number.
7. image processing method as described in claim 1, wherein the acquisition Image Processing parameter and to described first point
Track is handled to obtain treated track, comprising:
Image processing mode and image processing resource are obtained from image procossing configuration file;
First point of the track is handled after obtaining processing according to described image tupe and image processing resource
Track.
8. image processing method as described in claim 1, in the acquisition Image Processing parameter and to first point of the rail
Mark is handled to obtain after treated track, further includes:
After the picture frame by predetermined quantity, at least one second point on the target object is obtained;
The same second point connection in multiframe adjacent image frame is calculated to the track of the second point;
It obtains Image Processing parameter and is handled to obtain treated track to the track of the second point.
9. image processing method as claimed in claim 6, wherein the acquisition Image Processing parameter and to described first point
Track is handled to obtain treated track, comprising:
The image processing mode and image processing resource of different numbers are obtained from image procossing configuration file;
According to first point of the number for generating the track, at the corresponding image processing mode of the number and image
Reason resource is handled to obtain treated track to first point of track of the number.
10. a kind of image processing apparatus, comprising:
Image collection module, for obtaining video image from image source, wherein including at least one target in the video image
Object;
Divide module, for being partitioned into the target object from the video image;
Target object point obtains module, for obtaining at least one first point on the target object;
Trajectory computation module, for same first point of connection in multiframe adjacent image frame to be calculated at described first point
Track;
Trajectory processing module, for obtaining Image Processing parameter and being handled to obtain that treated to first point of the track
Track.
11. a kind of electronic equipment, comprising:
Memory, for storing computer-readable instruction;And
Processor, for running the computer-readable instruction, so that realizing according to claim 1-9 when the processor is run
Any one of described in image processing method.
12. a kind of non-transient computer readable storage medium, for storing computer-readable instruction, when the computer-readable finger
When order is executed by computer, so that the computer perform claim requires image processing method described in any one of 1-9.
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910230223.XA CN110035236A (en) | 2019-03-26 | 2019-03-26 | Image processing method, device and electronic equipment |
PCT/CN2019/126755 WO2020192195A1 (en) | 2019-03-26 | 2019-12-19 | Image processing method and apparatus, and electronic device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910230223.XA CN110035236A (en) | 2019-03-26 | 2019-03-26 | Image processing method, device and electronic equipment |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110035236A true CN110035236A (en) | 2019-07-19 |
Family
ID=67236606
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910230223.XA Pending CN110035236A (en) | 2019-03-26 | 2019-03-26 | Image processing method, device and electronic equipment |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN110035236A (en) |
WO (1) | WO2020192195A1 (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110781796A (en) * | 2019-10-22 | 2020-02-11 | 杭州宇泛智能科技有限公司 | Labeling method and device and electronic equipment |
WO2020192195A1 (en) * | 2019-03-26 | 2020-10-01 | 北京字节跳动网络技术有限公司 | Image processing method and apparatus, and electronic device |
WO2021068729A1 (en) * | 2019-10-10 | 2021-04-15 | 北京字节跳动网络技术有限公司 | Image synthesis method and apparatus, electronic device, and computer readable storage medium |
CN113709389A (en) * | 2020-05-21 | 2021-11-26 | 北京达佳互联信息技术有限公司 | Video rendering method and device, electronic equipment and storage medium |
WO2022002082A1 (en) * | 2020-07-01 | 2022-01-06 | 北京达佳互联信息技术有限公司 | Method and apparatus for displaying video special effect, and electronic device and storage medium |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112492196B (en) * | 2020-10-29 | 2022-01-07 | 贝壳技术有限公司 | Live broadcast in-process anchor tracking method, device and system |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20030063670A1 (en) * | 2001-09-28 | 2003-04-03 | Koichi Masukura | Image data processing method and article of manufacture |
CN106251387A (en) * | 2016-07-29 | 2016-12-21 | 武汉光之谷文化科技股份有限公司 | A kind of imaging system based on motion capture |
CN108537867A (en) * | 2018-04-12 | 2018-09-14 | 北京微播视界科技有限公司 | According to the Video Rendering method and apparatus of user's limb motion |
CN108712661A (en) * | 2018-05-28 | 2018-10-26 | 广州虎牙信息科技有限公司 | A kind of live video processing method, device, equipment and storage medium |
CN109191398A (en) * | 2018-08-29 | 2019-01-11 | Oppo广东移动通信有限公司 | Image processing method, device, computer readable storage medium and electronic equipment |
CN109242793A (en) * | 2018-08-29 | 2019-01-18 | Oppo广东移动通信有限公司 | Image processing method, device, computer readable storage medium and electronic equipment |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108090916B (en) * | 2017-12-21 | 2019-05-07 | 百度在线网络技术(北京)有限公司 | Method and apparatus for tracking the targeted graphical in video |
CN109068053B (en) * | 2018-07-27 | 2020-12-04 | 香港乐蜜有限公司 | Image special effect display method and device and electronic equipment |
CN110035236A (en) * | 2019-03-26 | 2019-07-19 | 北京字节跳动网络技术有限公司 | Image processing method, device and electronic equipment |
-
2019
- 2019-03-26 CN CN201910230223.XA patent/CN110035236A/en active Pending
- 2019-12-19 WO PCT/CN2019/126755 patent/WO2020192195A1/en active Application Filing
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20030063670A1 (en) * | 2001-09-28 | 2003-04-03 | Koichi Masukura | Image data processing method and article of manufacture |
CN106251387A (en) * | 2016-07-29 | 2016-12-21 | 武汉光之谷文化科技股份有限公司 | A kind of imaging system based on motion capture |
CN108537867A (en) * | 2018-04-12 | 2018-09-14 | 北京微播视界科技有限公司 | According to the Video Rendering method and apparatus of user's limb motion |
CN108712661A (en) * | 2018-05-28 | 2018-10-26 | 广州虎牙信息科技有限公司 | A kind of live video processing method, device, equipment and storage medium |
CN109191398A (en) * | 2018-08-29 | 2019-01-11 | Oppo广东移动通信有限公司 | Image processing method, device, computer readable storage medium and electronic equipment |
CN109242793A (en) * | 2018-08-29 | 2019-01-18 | Oppo广东移动通信有限公司 | Image processing method, device, computer readable storage medium and electronic equipment |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2020192195A1 (en) * | 2019-03-26 | 2020-10-01 | 北京字节跳动网络技术有限公司 | Image processing method and apparatus, and electronic device |
WO2021068729A1 (en) * | 2019-10-10 | 2021-04-15 | 北京字节跳动网络技术有限公司 | Image synthesis method and apparatus, electronic device, and computer readable storage medium |
CN110781796A (en) * | 2019-10-22 | 2020-02-11 | 杭州宇泛智能科技有限公司 | Labeling method and device and electronic equipment |
CN110781796B (en) * | 2019-10-22 | 2022-03-25 | 杭州宇泛智能科技有限公司 | Labeling method and device and electronic equipment |
CN113709389A (en) * | 2020-05-21 | 2021-11-26 | 北京达佳互联信息技术有限公司 | Video rendering method and device, electronic equipment and storage medium |
WO2022002082A1 (en) * | 2020-07-01 | 2022-01-06 | 北京达佳互联信息技术有限公司 | Method and apparatus for displaying video special effect, and electronic device and storage medium |
Also Published As
Publication number | Publication date |
---|---|
WO2020192195A1 (en) | 2020-10-01 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110035236A (en) | Image processing method, device and electronic equipment | |
CN108960090A (en) | Method of video image processing and device, computer-readable medium and electronic equipment | |
CN110047124A (en) | Method, apparatus, electronic equipment and the computer readable storage medium of render video | |
CN110062176A (en) | Generate method, apparatus, electronic equipment and the computer readable storage medium of video | |
CN110070063A (en) | Action identification method, device and the electronic equipment of target object | |
CN110070551A (en) | Rendering method, device and the electronic equipment of video image | |
CN108416744A (en) | Image processing method, device, equipment and computer readable storage medium | |
CN110210501B (en) | Virtual object generation method, electronic device and computer-readable storage medium | |
CN110047122A (en) | Render method, apparatus, electronic equipment and the computer readable storage medium of image | |
CN111210485B (en) | Image processing method and device, readable medium and electronic equipment | |
CN110070496A (en) | Generation method, device and the hardware device of image special effect | |
CN108491823A (en) | Method and apparatus for generating eye recognition model | |
CN110062157A (en) | Render method, apparatus, electronic equipment and the computer readable storage medium of image | |
CN110072047A (en) | Control method, device and the hardware device of image deformation | |
CN110378250A (en) | Training method, device and the terminal device of neural network for scene cognition | |
CN110288519A (en) | Image beautification method, device and electronic equipment | |
CN110084204A (en) | Image processing method, device and electronic equipment based on target object posture | |
CN109657185A (en) | Virtual scene sharing method and system in a kind of reality scene | |
CN110069125B (en) | Virtual object control method and device | |
CN112528811A (en) | Behavior recognition method and device | |
CN110070555A (en) | Image processing method, device, hardware device | |
CN108171167A (en) | For exporting the method and apparatus of image | |
CN110070554A (en) | Image processing method, device, hardware device | |
CN109510943A (en) | Method and apparatus for shooting image | |
CN111368668B (en) | Three-dimensional hand recognition method and device, electronic equipment 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 |
Application publication date: 20190719 |
|
RJ01 | Rejection of invention patent application after publication |