CN108845742A - The acquisition methods and device and computer readable storage medium of a kind of image frame - Google Patents

The acquisition methods and device and computer readable storage medium of a kind of image frame Download PDF

Info

Publication number
CN108845742A
CN108845742A CN201810654362.0A CN201810654362A CN108845742A CN 108845742 A CN108845742 A CN 108845742A CN 201810654362 A CN201810654362 A CN 201810654362A CN 108845742 A CN108845742 A CN 108845742A
Authority
CN
China
Prior art keywords
image
picture
image frame
region
feature
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN201810654362.0A
Other languages
Chinese (zh)
Other versions
CN108845742B (en
Inventor
张云
周俊清
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Tencent Technology Shenzhen Co Ltd
Original Assignee
Tencent Technology Shenzhen Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Tencent Technology Shenzhen Co Ltd filed Critical Tencent Technology Shenzhen Co Ltd
Priority to CN201810654362.0A priority Critical patent/CN108845742B/en
Publication of CN108845742A publication Critical patent/CN108845742A/en
Application granted granted Critical
Publication of CN108845742B publication Critical patent/CN108845742B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
    • G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
    • G06F3/048—Interaction techniques based on graphical user interfaces [GUI]
    • G06F3/0484—Interaction techniques based on graphical user interfaces [GUI] for the control of specific functions or operations, e.g. selecting or manipulating an object, an image or a displayed text element, setting a parameter value or selecting a range

Abstract

The embodiment of the invention discloses a kind of acquisition methods of image frame and device and computer readable storage medium to promote effective information included by cover content for promoting the screenshot effect and screenshot quality of image frame.The acquisition methods of one of image frame, including：Image data stream is obtained, includes the image frame of multiframe in described image data flow；The first image frame is intercepted out from described image data flow, the first image picture belongs to the image frame of the multiframe；Identify the first user interface UI element from the first image picture, the first UI element is to be located at interface edge in the first image picture and UI element that element position remains unchanged within a preset period of time；Interface edge region where the first UI element is cut out from the first image picture, obtains the second image frame, second image frame is to cut out remaining image-region behind the interface edge region in the first image picture.

Description

The acquisition methods and device and computer readable storage medium of a kind of image frame
Technical field
The present invention relates to the acquisition methods and device of field of computer technology more particularly to a kind of image frame and calculating Machine readable storage medium storing program for executing.
Background technique
In game video field, it is often necessary to surface plot of the interception image as the game video from game video Picture.
The prior art provides the interception scheme of following video cover：Game video and live streaming interface are carried out taking frame at random After intercept whole image, then scaled down whole image again, using whole image after diminution as video or live streaming Cover image.
The above-mentioned prior art at least has the disadvantage that：When by whole screenshot of interception as cover, whole screenshot There is no the effective contents for helping user to identify video and live streaming, or even entire cover image can be made to become more mixed and disorderly, Have the defects that the cover image of high quality can not be obtained.
Summary of the invention
The embodiment of the invention provides a kind of acquisition methods of image frame and device and computer readable storage medium, For promoting the screenshot effect and screenshot quality of image frame, effective information included by cover content is promoted.
The embodiment of the present invention provides following technical scheme：
On the one hand, the embodiment of the present invention provides a kind of acquisition methods of image frame, including：
Image data stream is obtained, includes the image frame of multiframe in described image data flow；
The first image frame is intercepted out from described image data flow, the first image picture belongs to the figure of the multiframe As picture；
Identify that the first user interface UI element, the first UI element are described first from the first image picture It is located at the UI element that interface edge and element position remain unchanged within a preset period of time in image frame；
Interface edge region where the first UI element is cut out from the first image picture, obtains the second figure As picture, second image frame is to cut out remaining image district behind the interface edge region in the first image picture Domain.
On the other hand, the embodiment of the present invention also provides a kind of acquisition device of image frame, including：
Data flow obtains module, includes the image frame of multiframe for obtaining image data stream, in described image data flow；
Picture capturing module, for intercepting out the first image frame from described image data flow, the first image is drawn Face belongs to the image frame of the multiframe；
Picture recognition module, for identifying the first user interface UI element from the first image picture, described One UI element is the UI for being located at interface edge and element position in the first image picture and remaining unchanged within a preset period of time Element；
Region screen capture module, for by the interface edge region where the first UI element from the first image picture In cut out, obtain the second image frame, second image frame is to cut out the interface edge in the first image picture Remaining image-region behind region.
In aforementioned aspects, aforementioned one side face and various is can also be performed in the comprising modules of the acquisition device of image frame The step of described in possible implementation, is detailed in aforementioned to saying in aforementioned one side face and various possible implementations It is bright.
On the other hand, the embodiment of the present invention provides a kind of acquisition device of image frame, the acquisition device of the image frame Including：Processor, memory；Memory is for storing instruction；Processor is used to execute the instruction in memory, so that image is drawn The acquisition device in face executes the method such as any one of aforementioned one side face.
On the other hand, the embodiment of the invention provides a kind of computer readable storage medium, the computer-readable storages Instruction is stored in medium, when run on a computer, so that computer executes method described in above-mentioned various aspects.
In embodiments of the present invention, the image data stream including multiple image picture is got first, then from picture number According to the first image frame is intercepted out in stream, the first user interface UI element is next identified from the first image frame, this One UI element is the UI element for being located at interface edge and element position in the first image frame and remaining unchanged within a preset period of time, The interface edge region where the first UI element is cut out from the first image frame finally, obtains the second image frame, second Image frame is to cut out remaining image-region behind interface edge region in the first image frame.Due to can in the embodiment of the present invention To identify the first UI that positioned at interface edge and element position remains unchanged within a preset period of time from the first image frame Element, and the interface edge region where the first UI element is cut out from the first image frame, therefore is obtaining the second figure As be in picture do not include the first UI where interface edge region, therefore in the second image frame retain drop-down be interface The image of non-edge can intuitively be shown and the closer relevant screenshot of image data stream by the second image frame Content promotes the screenshot effect and screenshot quality of image frame, promotes effective information included by cover content.
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 skilled in the art, it is also possible to obtain other drawings based on these drawings.
Fig. 1 is system architecture schematic diagram applied by the acquisition methods of image frame provided in an embodiment of the present invention；
Fig. 2 is a kind of process blocks schematic diagram of the acquisition methods of image frame provided in an embodiment of the present invention；
Fig. 3 is the process blocks schematic diagram of the acquisition methods of another image frame provided in an embodiment of the present invention；
Fig. 4 takes frame screenshot effect at random for what the prior art provided, with the effect after region screenshot in the embodiment of the present invention Contrast schematic diagram；
Fig. 5 is the system architecture schematic diagram of live streaming surface plot interception provided in an embodiment of the present invention；
Fig. 6 is the matching flow diagram of image frame provided in an embodiment of the present invention and feature image；
Fig. 7-a is the schematic diagram of one of property data base provided in an embodiment of the present invention feature image；
Fig. 7-b is the schematic diagram of another feature image in property data base provided in an embodiment of the present invention；
Fig. 8-a is the schematic diagram provided in an embodiment of the present invention that non-core element is marked out from a kind of image frame；
Fig. 8-b is the schematic diagram provided in an embodiment of the present invention that non-core element is marked out from another image frame；
Fig. 8-c is the schematic diagram provided in an embodiment of the present invention that non-core element is marked out from another image frame；
Fig. 9-a is a kind of composed structure schematic diagram of the acquisition device of image frame provided in an embodiment of the present invention；
Fig. 9-b is a kind of composed structure schematic diagram of picture recognition module provided in an embodiment of the present invention；
Fig. 9-c is a kind of composed structure schematic diagram of image matching unit provided in an embodiment of the present invention；
Fig. 9-d is a kind of composed structure schematic diagram of Region Matching unit provided in an embodiment of the present invention；
Fig. 9-e is the composed structure schematic diagram of the acquisition device of another image frame provided in an embodiment of the present invention；
Figure 10 is that the composed structure that a kind of acquisition methods of image frame provided in an embodiment of the present invention are applied to terminal is shown It is intended to；
Figure 11 is the composed structure that a kind of acquisition methods of image frame provided in an embodiment of the present invention are applied to server Schematic diagram.
Specific embodiment
The embodiment of the invention provides a kind of acquisition methods of image frame and device and computer readable storage medium, For promoting the screenshot effect and screenshot quality of image frame, effective information included by cover content is promoted.
In order to make the invention's purpose, features and advantages of the invention more obvious and easy to understand, below in conjunction with the present invention Attached drawing in embodiment, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that disclosed below Embodiment be only a part of the embodiment of the present invention, and not all embodiments.Based on the embodiments of the present invention, this field Technical staff's every other embodiment obtained, shall fall within the protection scope of the present invention.
Term " includes " in description and claims of this specification and above-mentioned attached drawing and " having " and they Any deformation, it is intended that covering non-exclusive includes so as to a series of process, method comprising units, system, product or to set It is standby to be not necessarily limited to those units, but be not clearly listed or these process, methods, product or equipment are consolidated The other units having.
Referring to FIG. 1, it illustrates system trays applied by the acquisition methods of image frame provided by the embodiments of the present application Structure schematic diagram.The system may include：The acquisition device 120 of data stream server 110 and image frame, wherein data flow clothes Business device can provide image data stream to the acquisition device 120 of image frame, include the image picture of multiframe in the image data stream Face.Carried out data transmission between the acquisition device 120 and data stream server 110 of image frame by communication network.The image The acquisition device 120 of picture specifically can be terminal 120 as shown in Figure 1, and for another example the acquisition device 120 of the image frame can also To be the acquisition server of image frame.Terminal can be mobile phone, tablet computer, E-book reader, MP3 player (Moving Picture Experts Group Audio Layer III, dynamic image expert's compression standard audio level 3), MP4 (Moving Picture Experts Group Audio Layer IV, dynamic image expert's compression standard audio level 4) player, pocket computer on knee and desktop computer etc..
In embodiments of the present invention, terminal 120 can get picture number from data stream server 110 by communication network According to stream, terminal 120 carries out screenshot to the image data stream, obtains the first image frame.Then terminal 120 can be from first figure As the first user interface (User identified in picture positioned at interface edge and element position remains unchanged within a preset period of time Interface, UI) element, and the interface edge region where the first UI element is cut out from the first image frame, therefore In obtaining the second image frame being does not include interface edge region where the first UI, therefore is retained in the second image frame What is pulled down is the image of interface non-edge, can intuitively be shown by the second image frame tighter with image data stream Close relevant screenshot content promotes the screenshot effect and screenshot quality of image frame, promotes effective letter included by cover content Breath amount.
For example, image data stream specifically can be video data stream or live data streams, whole in the prior art The interception of image will appear a large amount of interface element and main broadcaster's coherent element, and (such as main broadcaster's head portrait, is opened main broadcaster's fan group information Broadcast information etc.), and these elements are smaller for identification live streaming and the content role of game video, but can make entire Cover screenshot becomes more mixed and disorderly.Picture recognition and interface non-edge screenshot in through the embodiment of the present invention, by video It does not change in live streaming interface, and removes in the first UI element of interface edge within a certain period of time, intercept out more core And interface clearly the second image frame, allow user intuitively to can see live streaming and the relevant game of video content, role, mould The relatively sharp information such as formula, stage property.
It is described in detail below from the angle of the acquisition device of image frame.The acquisition methods of image frame of the present invention One embodiment specifically can be applied to obtain in scene the cover image of image data stream, please refer to shown in Fig. 2, this hair The acquisition methods for the image frame that bright one embodiment provides, may include steps of：
201, image data stream is obtained, includes the image frame of multiframe in image data stream.
In embodiments of the present invention, data stream server provides image data stream, which can be video counts It is continuous by multiframe including the image frame of multiframe, such as image data stream in image data stream according to stream or live data streams Image frame constitute.The image frame can be the image in application program, such as can be game application generation Image.
The acquisition device of image frame can get image data stream from data stream server, and then triggering executes step 202。
202, the first image frame is intercepted out from image data stream, the first image frame belongs to the image frame of multiframe.
In embodiments of the present invention, the acquisition device of image frame can carry out screenshot to the image data stream, obtain the One image frame.In getting image data stream, whole image frame can be intercepted out from the image data stream, be area The image frame intercepted out from image data stream is known as the first figure by the image frame not intercepted in subsequent embodiment As picture, then first image frame may belong to a certain frame image frame in image data stream in the image frame of multiframe.
In some embodiments of the invention, step 202 intercepts out the first image frame from image data stream, including such as Lower step：
The first image frame is intercepted out in slave image data stream according to preset interception period timing.
Wherein, from image data stream when interception image picture, it can be timed interception according to the preset interception period, Such as the interception period can be for Application Type belonging to image data stream and be arranged, such as application program can be The interception period can be set for different game applications in game application.After setting intercepts the period, being based on should The time requirement in interception period can be intercepted periodically, then can intercept out multiple first images automatically from image data stream and draw Face.The subsequent step in the embodiment of the present invention can be executed, for each image frame to realize the boundary to each image frame The removal of face fringe region is detailed in the explanation of subsequent embodiment.
203, identify that the first UI element, the first UI element are to be located at boundary in the first image frame from the first image frame The UI element that face edge and element position remain unchanged within a preset period of time.
In embodiments of the present invention, the acquisition device of image frame intercepts after obtaining the first image frame, to this first Image frame carries out picture recognition, to identify the first UI element for including in the first image frame, wherein the first UI element Refer to the UI element for being located at interface edge in the first image frame and element position remains unchanged within a preset period of time.Citing Illustrate, the first UI element in the embodiment of the present invention refers to the picture element shown on UI.Under different application scenarios, First UI element can indicate specific picture element.It is illustrated below, by taking scene of game as an example, the first UI element can refer to Be non-core element in game image picture, such as operation button, game data, main broadcaster's head portrait in game image picture Deng almost motionless UI element in live streaming/video data stream.On the contrary, the core element in game image picture can To refer to the UI elements such as game role, stage property, skin in game image picture.
In embodiments of the present invention, picture recognition is carried out to the UI element in first image frame, to determine the Which UI element is the first UI element for meeting above-mentioned requirements in one image frame.Wherein, interface is located in the first image frame The UI element that edge and element position remain unchanged within a preset period of time is properly termed as the first UI element, and the first image is drawn herein It is located at interface edge in face and also refers at least one edge for being in interface in the first image frame, such as the Interfacial Edge Edge also refers at least one of interface top edge, interface lower edge, interface left edge or interface right hand edge edge.Example The surrounding that interface is in the first image frame is also referred to as being located at interface edge in the first image frame, i.e., around the There can be the first UI element on the peripheral region of core element in one image frame.
204, the interface edge region where the first UI element is cut out from the first image frame, obtains the second image picture Face, the second image frame are to cut out remaining image-region behind interface edge region in the first image frame.
In embodiments of the present invention, the first UI element is identified from the first image frame and then determine this first Image-region where first UI element is known as interface edge region, next to this by the image-region where UI element First image frame carries out region screenshot, that is, needs to cut in the interface edge region where element non-core in the first image frame Fall, remaining image-region is known as the second image frame after interface edge region being cut out in the first image frame, second figure As picture can be the image-region including core element, the union in second image frame and interface edge region is constituted First image frame.
It is illustrated below, it can be according to the interface edge region where the first UI element to first in the embodiment of the present invention Image frame carries out region screenshot, and region screenshot refers to that screenshot is done in some part to the entire picture of game, and removal video is straight Broadcast non-core element in random cover.By picture recognition and region screenshot, by what is do not changed in video and live streaming interface, and The game UI element of interface surrounding removes.Interception more core and interface clearly cover.Wherein, video can be user can The content watched repeatedly, live streaming timeliness is higher, and user can only watch in specific time.By to first in the embodiment of the present invention The rejecting of the first UI element in image frame, allow user intuitively can see live streaming and the relevant game of video content, role, The relatively sharp information such as mode, stage property.
In embodiments of the present invention, the image data stream including multiple image picture is got first, then from picture number According to the first image frame is intercepted out in stream, the first user interface UI element is next identified from the first image frame, this One UI element is the UI element for being located at interface edge and element position in the first image frame and remaining unchanged within a preset period of time, The interface edge region where the first UI element is cut out from the first image frame finally, obtains the second image frame, second Image frame is to cut out remaining image-region behind interface edge region in the first image frame.Due to can in the embodiment of the present invention To identify the first UI that positioned at interface edge and element position remains unchanged within a preset period of time from the first image frame Element, and the interface edge region where the first UI element is cut out from the first image frame, therefore is obtaining the second figure As be in picture do not include the first UI where interface edge region, therefore in the second image frame retain drop-down be interface The image of non-edge can intuitively be shown and the closer relevant screenshot of image data stream by the second image frame Content promotes the screenshot effect and screenshot quality of image frame, promotes effective information included by cover content.
It please refers to shown in Fig. 3, for the process blocks of the acquisition methods of another image frame provided in an embodiment of the present invention Schematic diagram.It mainly include following process：
301, image data stream is obtained, includes the image frame of multiframe in image data stream.
302, the first image frame is intercepted out from image data stream, the first image frame belongs to the image frame of multiframe.
Wherein, step 301 is similar to step 202 with the step 201 in previous embodiment to step 302, this time no longer It repeats.
After being truncated to the first image frame, the embodiment of the present invention can be with as follows 303 to step 306 side Formula identifies the first UI element from the first image frame.
303, property data base is obtained, includes the feature image of multiple in property data base.
The acquisition device of image frame can be pre-configured with property data base in embodiments of the present invention, in this feature data The feature image of multiple is stored in library, wherein feature image refer to include the core element of image frame image-region. For example, the core element in game image picture also refers to game role, stage property, skin in game image picture Equal UI element.
In some embodiments of the invention, the feature image in property data base including multiple is corresponded respectively to using journey Screenshot picture of the sequence in different application scenarios.
Wherein, for the different scenes of application program, different feature images can be respectively configured, such as can will apply Screenshot picture of the program in different application scenarios is stored in advance as feature image, the feature image extracted in advance In do not include non-core element.For example, property data base specifically can be game characteristic database, in game characteristic data It may include the screenshot for having clear part in game picture in library, the same game application can have multiple screenshots as trip Play feature image.
304, the feature image of multiple in the first image frame and property data base is matched respectively.
In embodiments of the present invention, from the first image frame intercepted out in image data stream can in property data base All feature images matched respectively, which kind of feature image phase in first image frame and property data base determined Matching.If in property data base there is no with the matched feature image of the first image frame or matching degree it is very low, return It fails to match, can re-execute the steps 302 at this time, reacquires the first image frame for arriving next frame, then again and feature Database is matched.
In embodiments of the present invention, the first image frame and the matching way of feature image can there are many, such as pass through figure Determine whether the first image frame and feature image match as similarity detection algorithm, illustration can use histogram into Row similarity detection, such as calculating histogram can there are two types of：Statistic histogram and accumulation histogram are based on histogram results Determine whether the first image frame and feature image match.For another example, the embodiment of the present invention can be according to Scale invariant features transform (Scale-Invariant Feature Transform, SIFT) algorithm determine the first image frame and feature image whether Match, can determine which kind of image similarity detection algorithm selected in conjunction with scene in practical applications.
In some embodiments of the invention, step 304 is by the spy of multiple in the first image frame and property data base Sign picture is matched respectively, including：
Fisrt feature point is extracted from the first image frame, and is mentioned from every in property data base feature image Take out second feature point；
Similitude matching is carried out to fisrt feature point and second feature point, obtains similitude matching result；
Determine whether the first image frame and feature image match according to similitude matching result.
Wherein it is possible to extract characteristic point respectively to all feature images in the first image frame and property data base.It should Characteristic point is referred to as key point, such as extracts the key point in image respectively according to SIFT algorithm.For ease of description, by The characteristic point extracted in one image frame is known as fisrt feature point, and the characteristic point extracted in feature image is known as the second spy Sign point.
In calculating separately after fisrt feature point and second feature point, fisrt feature point and second feature can be clicked through The matching of row similitude, obtains similitude matching result, determines the first image frame and characteristic pattern by the similitude matching result Whether piece matches, if picture is similar to execute step 305 again.It is illustrated below, using SIFI algorithm from the first image frame On extract the first SIFI feature, then carried out with the SIFI feature of the feature image in the SIFI feature and game characteristic database Matching.
305, when the fisrt feature picture in property data base is matched with the first image frame, from the first image frame Determine the characteristic matching region with fisrt feature picture match, fisrt feature picture belongs to the feature image of multiple.
In embodiments of the present invention, the first image frame is matched with all feature images in property data base respectively Later, however, it is determined that fisrt feature picture is matched with first image frame, then can determine feature from the first image frame Matching area, this feature matching area are the image-regions that can be matched with fisrt feature picture in the first image frame.Example The characteristic matching region with fisrt feature picture match is such as irised out in the first image frame.
In some embodiments of the invention, step 305 is determined and fisrt feature picture from the first image frame The characteristic matching region matched, including：
It is determined from multiple fisrt feature points of the first image frame with second feature point matched two to angular coordinate；
The length and width in characteristic matching region is obtained to the pixel value difference between angular coordinate according to two；
According to two length and width, the length and widths of fisrt feature picture to angular coordinate, characteristic matching region, from Screenshot coordinate is obtained in first image frame；
Characteristic matching region is determined according to the length and width of screenshot coordinate, characteristic matching region.
Wherein, when determining that fisrt feature picture is matched with the first image frame by similarity mode algorithm, according to first Second feature o'clock in feature image is determined to match with second feature point from multiple fisrt feature points of the first image frame Two to angular coordinate.Two refer to two fisrt feature that diagonal relationships are constituted in the first image frame to angular coordinate Point.Determine two to angular coordinate after, can according to two between angular coordinate pixel value difference obtain characteristic matching area The length and width in domain, such as another pixel value to angular coordinate is subtracted to the pixel value of angular coordinate with one, according to two The difference of pixel value calculates the length and width in characteristic matching region, which can be indicated by pixel.
When finding fisrt feature picture from property data base, available length and height to the fisrt feature picture Degree, then two length and widths to angular coordinate, characteristic matching region have been obtained known to aforementioned calculating, further according to feature Relationship between the length and width of matching area, the length and width of fisrt feature picture, using two to angular coordinate as ginseng Examination point, to determine which pixel can be used as screenshot coordinate in the first image frame, wherein screenshot coordinate is referred to One image frame carries out starting point coordinate when screenshot.It is illustrated below, according to two to angular coordinate, characteristic matching region The length and width of length and width, fisrt feature picture obtains screenshot coordinate, such as characteristic matching from the first image frame The length in region and the length of fisrt feature picture are subtracted each other, the width in characteristic matching region and the width of fisrt feature picture Subtracted each other, the difference in available length-width direction further according to the difference result in length-width direction from two as a result, diagonally sit Mark starts to deviate, and may thereby determine that out the screenshot coordinate in the first image frame.Finally according to screenshot coordinate, characteristic matching area The length and width in domain determines characteristic matching region, i.e., using screenshot coordinate as starting point, intercepts from fisrt feature image The image-region of the length scale in characteristic matching region and width size out.
For example, the first image frame is compared with the game characteristic picture in game characteristic database, if Picture is similar, so that it may the characteristic matching region with the game characteristic picture similar portion is intercepted out in the first image frame. Characteristic matching region can be according to two rectangular areas determined to angular coordinate in the first image frame.Determine the square Behind shape region, so that it may the picture in the rectangular area be intercepted out, as the second image obtained in subsequent embodiment is drawn Face, second image frame can be used as the current live cover of live data streams.
306, the first UI element is identified from the image-region for being not belonging to characteristic matching region in the first image frame.
In embodiments of the present invention, through the above way after detecting characteristic matching region in the first image frame, The image-region that characteristic matching region is then not belonging in first image frame carries out the identification of UI element, is not belonging to spy at this Levying the UI element identified in the image-region of matching area is exactly the first UI element described in previous embodiment.
307, the interface edge region where the first UI element is cut out from the first image frame, obtains the second image picture Face, the second image frame are to cut out remaining image-region behind interface edge region in the first image frame.
In embodiments of the present invention, the first UI element is identified from the first image frame and then determine this first Image-region where first UI element is known as interface edge region, next to this by the image-region where UI element First image frame carries out region screenshot, that is, needs to cut in the interface edge region where element non-core in the first image frame Fall, remaining image-region is known as the second image frame after interface edge region being cut out in the first image frame, second figure As picture can be the image-region including core element, the union in second image frame and interface edge region is constituted First image frame.
It is illustrated below, as shown in figure 4, taking frame screenshot effect at random for what the prior art provided, implements with the present invention The contrast schematic diagram of effect in example after the screenshot of region.It can be according to the Interfacial Edge where the first UI element in the embodiment of the present invention Edge region carries out region screenshot to the first image frame, and region screenshot refers to that some part to the entire picture of game is cut Figure removes non-core element in the random cover of net cast.It, will be in video and live streaming interface by picture recognition and region screenshot It does not change, and removes in the game UI element of interface surrounding.Interception more core and interface clearly cover.Wherein, video It can be the content that user can watch repeatedly, live streaming timeliness is higher, and user can only watch in specific time.The present invention is implemented By the rejecting to the first UI element in the first image frame in example, user is allowed intuitively to can see live streaming and video content phase The relatively sharp information such as game, role, mode, the stage property of pass.
In some embodiments of the invention, step 307 is by the interface edge region where the first UI element from the first figure As cutting out in picture, after obtaining the second image frame, method provided in an embodiment of the present invention further includes following steps：
Second image frame is sent to information server, the second image frame is updated to picture number by information server According to the cover image of stream.
Wherein, the acquisition device of image frame can be established with information server communication connection, which can To be video information server or live information server, image list is stored in information server, image frame obtains It takes device after determining the second image frame, is sent to information server, information server can obtaining from image frame Device is taken to get the second image frame, information server updates second image frame as image data in image list The cover image of stream, to realize the real-time acquisition to the cover image of image data stream.
This feature is passed through it is found that be pre-configured with property data base to the description of the embodiment of the present invention by above embodiments Multiple feature images matching with the first image frame respectively in database, is determined and the first image frame matched first Feature image determines the characteristic matching region with fisrt feature picture match from the first image frame, therefore in the first figure As being not belonging in picture in the image-region in characteristic matching region, so that it may detect positioned at interface edge and element position is pre- If the first UI element remained unchanged in the period, and the interface edge region where the first UI element is drawn from the first image It is cut out in face, therefore in obtaining the second image frame being does not include interface edge region where the first UI, therefore second In image frame retain drop-down be interface non-edge image, by the second image frame can intuitively show with The closer relevant screenshot content of image data stream promotes the screenshot effect and screenshot quality of image frame, promotes cover content Included effective information.
In order to facilitate a better understanding and implementation of the above scheme of the embodiment of the present invention, corresponding application scenarios of illustrating below come It is specifically described.
The present embodiment provides by picture recognition, automated regional screenshot removes non-core member in the random cover of net cast The cover interception of element, so as to intercept more core and interface clearly cover.Remove the game UI member of interface surrounding Element and text information reduce cover and feel in a jumble, the information transmitting of amplification game content itself.Here interface, which clearly refers to, to be passed through Preset model interface goes to match, and the interface being matched to is exactly clearly image section.
Fig. 5 is the system architecture schematic diagram of live streaming surface plot interception provided in an embodiment of the present invention.In the system architecture May include：Live stream or video stream server, game characteristic database, are broadcast live cover database, are more cover capture server A live information server, N number of user (respectively user 1, user 2 ..., user N-1, user N).Main includes following interaction Process：
Step 1, cover capture server get image data stream from live stream or video stream server, such as obtain To live data streams or video data stream.
Step 2, cover capture server intercept out image frame from image data stream, then with game characteristic database In game characteristic picture matched, non-core element is identified from the image frame, then by non-core in image frame Interface edge region removal where heart element, to obtain the image cover of image data stream, which is arrived It is broadcast live in cover database.
List can be broadcast live from live information server pull in step 3, user, be broadcast live in list comprising live streaming surface plot.
Wherein, the cover data for cover database being broadcast live are that cover capture server is periodically intercepted from live streaming/video flowing , it is the scene of game of preset in advance about game characteristic database that game characteristic database is pre-configured with when being product operation The feature database of image, game characteristic database are constructed by several game pictures.
Next the application scenarios of the embodiment of the present invention are illustrated：Cover interception scene backstage, include Live source and video library.The scene that cover is presented shows the Product Interface of live streaming and video content in PC and mobile terminal etc. In.Wherein, it needs to need if the screenshot from video pictures using view using live source if screenshot if from live streaming interface Frequency library.
The functional characteristic of the embodiment of the present invention is, identifies game UI element and the main broadcaster's relevant information etc. in image frame Constant non-core element is removed by automatic screenshot, retains core game interface as live streaming and view by constant UI element The cover of frequency content.
Fig. 6 is the matching flow diagram of image frame provided in an embodiment of the present invention and feature image, and main includes such as Lower step：
S01, live data streams or video data stream are read.
Wherein it is possible to read the image frame of the multiframe in live data streams or video data stream.
S02, timing interception image picture.
Such as the interception image picture according to preset interception period timing.
S03, game characteristic database is obtained.
Wherein, the game characteristic picture in game characteristic database is loaded, game characteristic database refers in game picture The screenshot of clear part, the same game have multiple screenshots.Such as Fig. 7-a is in property data base provided in an embodiment of the present invention A kind of feature image schematic diagram, Fig. 7-b be property data base provided in an embodiment of the present invention in another feature image Schematic diagram.Pass through Fig. 7-a and Fig. 7-b's for example, having had been removed non-core element, i.e. characteristic pattern in feature image Interface edge region in piece where non-core element has been removed.
S04, characteristic matching are completed？
Feature image in the image frame intercepted out and game characteristic database is matched, it is determined whether and game All feature images in property data base all match completion, if matching is completed, execute step S05 if not completing and execute step Rapid S06.
S05, it fails to match for return.
S06, a feature image is taken.
S07, the image frame being truncated to is matched with feature image.
For example, the game characteristic picture of truncated picture picture and game characteristic database is carried out according to SIFT algorithm Compare, if picture is similar, the SIFI feature extracted from the picture of interception using SIFI algorithm, then with the SIFI feature and Game characteristic database is matched.The region of similar portion can be intercepted in screenshot.Two are taken in characteristic matching region To angular coordinate, so that it may determine rectangular area.After determining rectangular area, so that it may the picture of rectangular area be intercepted out, made For the current live streaming cover of the live streaming.
It should be noted that any one feature image in truncated picture picture and game characteristic library data requires Matching, matching process here are circulations, until the feature image of the game has all matched.
SIFT algorithm searches key point (characteristic point) on two pictures, and calculates the direction of key point, according to matching Crucial points, determine whether screenshot matches with feature image.Such as one points threshold value of setting, if crucial points are greater than threshold Value, exactly matches, and otherwise just mismatches.
S08, whether match？
S09, matched characteristic matching region is returned to.
If it does, finding matched coordinate (x1, y1), (x2, y2), the two are a to angular coordinate.Calculate Matching band The length in domain：Length=x2-x1, wide width=y2-y1. assume that the length and width of feature image are L and W, then screenshot coordinate is just Should be：X=x1- (L-length)/2, Y=y2+ (W-width)/2.
Screenshot coordinate (X, Y) is had found, in addition its length (L) and wide (W) are assured that out characteristic matching region.If Matched feature image is not present in game characteristic database or matching degree is very low, then it fails to match for return.
In embodiments of the present invention, game characteristic database is preconfigured database, and this programme needs to prepare in advance The feature database of one scene of game image, as shown in Fig. 7-a and Fig. 7-b, game characteristic database is by several game pictures Construction.The characteristics of feature image is：1, the scene of game picture of standard, and eliminate static UI element；2, a game can To have multiple feature images to cover different scene of game.
If Fig. 8-a is the schematic diagram provided in an embodiment of the present invention for marking out non-core element from a kind of image frame, Fig. 8-b is the schematic diagram provided in an embodiment of the present invention that non-core element is marked out from another image frame, and Fig. 8-c is this The schematic diagram that non-core element is marked out from another image frame that inventive embodiments provide.In through the embodiment of the present invention The matching of image frame and feature image can identify non-core element from image frame, and determine non-core element institute Interface edge region, after interface edge region is got rid of, available interface non-edge.Fig. 8-a into Fig. 8-c for Different game image pictures carries out the interface edge region removal where non-core element.
It should be noted that can also be cut in the embodiment of the present invention in such a way that role follows interception come complete region It takes, such as includes role's picture in property data base, when the role in screenshot is similar with feature image, extract the role Picture.In addition, region screenshot can also be completed by the way that fixed area is equal between two parties than interception, i.e., for each screenshot, only protect That the screenshot part for staying picture area placed in the middle.
The embodiment of the present invention is matched using game characteristic data and the true picture of live streaming, such as according to SIFT algorithm Picture similarity mode is carried out, core element and scene in game process are automatically extracted, are preferably User shows the picture key element of live streaming main broadcaster, attracts user's viewing.The embodiment of the present invention can promote game live streaming and view The quality of frequency cover, validity, the aesthetic measure of cover etc. including pictorial information transmitting.Human-edited is not needed, game is special Levy picture, automatic screenshot.After cover effect is secure, whole live streaming and list of videos interface could more concise beauties It sees.
It should be noted that for the various method embodiments described above, for simple description, therefore, it is stated as a series of Combination of actions, but those skilled in the art should understand that, the present invention is not limited by the sequence of acts described because According to the present invention, some steps may be performed in other sequences or simultaneously.Secondly, those skilled in the art should also know It knows, the embodiments described in the specification are all preferred embodiments, and related actions and modules is not necessarily of the invention It is necessary.
For the above scheme convenient for the better implementation embodiment of the present invention, phase for implementing the above scheme is also provided below Close device.
It please refers to shown in Fig. 9-a, a kind of acquisition device 900 of image frame provided in an embodiment of the present invention may include： Data flow obtains module 901, picture capturing module 902, picture recognition module 903, region screen capture module 904, wherein
Data flow obtains module 901, includes the image picture of multiframe for obtaining image data stream, in described image data flow Face；
Picture capturing module 902, for intercepting out the first image frame, the first image from described image data flow Picture belongs to the image frame of the multiframe；
Picture recognition module 903, it is described for identifying the first user interface UI element from the first image picture First UI element is to be located at what interface edge and element position remained unchanged within a preset period of time in the first image picture UI element；
Region screen capture module 904, for by the interface edge region where the first UI element from the first image It is cut out in picture, obtains the second image frame, second image frame is to cut out the interface in the first image picture Remaining image-region after fringe region.
In some embodiments of the invention, it please refers to shown in Fig. 9-b, the picture recognition module 903, including：
Feature image loading unit 9031 includes the spy of multiple for obtaining property data base, in the property data base Levy picture；
Image matching unit 9032, for by the feature of multiple in the first image picture and the property data base Picture is matched respectively；
Region Matching unit 9033, for when the fisrt feature picture and the first image picture in the property data base When face matches, the characteristic matching region with the fisrt feature picture match is determined from the first image picture, it is described Fisrt feature picture belongs to multiple the feature image；
Elemental recognition unit 9034, for being not belonging to the image in the characteristic matching region from the first image picture The first UI element is identified in region.
In some embodiments of the invention, it please refers to shown in Fig. 9-c, described image matching unit 9032, including：
Feature extraction subelement 90321, for extracting fisrt feature point from the first image picture, and from institute It states and extracts second feature point in property data base in every feature image；
Similar computation subunit 90322, for carrying out similitude to the fisrt feature point and second feature point Match, obtains similitude matching result；
Subelement 90323 is determined, for determining the first image picture and the feature according to similitude matching result Whether picture matches.
In some embodiments of the invention, it please refers to shown in Fig. 9-d, the Region Matching unit 9033, including：
Subelement 90331 is determined to angular coordinate, for determining from multiple fisrt feature points of the first image picture Out with the second feature point matched two to angular coordinate；
Length and width computation subunit 90332, for obtaining the spy according to the pixel value difference between described two pairs of angular coordinates Levy the length and width of matching area；
Screenshot coordinate obtains subelement 90333, for the length according to described two pairs of angular coordinates, the characteristic matching region The length and width of degree and width, the fisrt feature picture obtains screenshot coordinate from the first image picture；
Matching area determines subelement 90334, for according to the length of the screenshot coordinate, the characteristic matching region and Width determines the characteristic matching region.
In some embodiments of the invention, the feature image in the property data base including multiple corresponds respectively to answer With screenshot picture of the program in different application scenarios.
In some embodiments of the invention, the picture capturing module 902 was specifically used for according to the preset interception period The first image frame is intercepted out in the slave described image data flow of timing.
In some embodiments of the invention, it please refers to shown in Fig. 9-e, relative to shown in Fig. 9-a, described image picture Acquisition device 900 further includes：
Sending module 905, for the region screen capture module by the interface edge region where the first UI element from It is cut out in the first image picture, after obtaining the second image frame, second image frame is sent to information service Second image frame is updated to the cover image of described image data flow by the information server by device.
By above to the description of the embodiment of the present invention it is found that getting the image data including multiple image picture first Stream, the first image frame is then intercepted out from image data stream, the first user is next identified from the first image frame Interface UI element, the first UI element are to be located at interface edge and element position in the first image frame to protect within a preset period of time Constant UI element is held, finally cuts out in the interface edge region where the first UI element from the first image frame, obtains Two image frames, the second image frame are to cut out remaining image-region behind interface edge region in the first image frame.Due to Can be identified from the first image frame in the embodiment of the present invention positioned at interface edge and element position within a preset period of time The first UI element remained unchanged, and the interface edge region where the first UI element is cut out from the first image frame, Therefore in obtaining the second image frame being does not include interface edge region where the first UI, therefore in the second image frame Retain drop-down is the image of interface non-edge, can intuitively be shown by the second image frame and image data stream Closer relevant screenshot content promotes the screenshot effect and screenshot quality of image frame, and being promoted has included by cover content Imitate information content.
The embodiment of the invention also provides another terminals, as shown in Figure 10, for ease of description, illustrate only and this hair The relevant part of bright embodiment, it is disclosed by specific technical details, please refer to present invention method part.The terminal can be with Being includes mobile phone, tablet computer, PDA (Personal Digital Assistant, personal digital assistant), POS (Point of Sales, point-of-sale terminal), any terminal device such as vehicle-mounted computer, taking the terminal as an example：
Figure 10 shows the block diagram of the part-structure of mobile phone relevant to terminal provided in an embodiment of the present invention.With reference to figure 10, mobile phone includes：Radio frequency (Radio Frequency, RF) circuit 1010, memory 1020, input unit 1030, display unit 1040, sensor 1050, voicefrequency circuit 1060, Wireless Fidelity (wireless fidelity, WiFi) module 1070, processor The components such as 1080 and power supply 1090.It will be understood by those skilled in the art that handset structure shown in Figure 10 is not constituted pair The restriction of mobile phone may include perhaps combining certain components or different component cloth than illustrating more or fewer components It sets.
It is specifically introduced below with reference to each component parts of the Figure 10 to mobile phone：
RF circuit 1010 can be used for receiving and sending messages or communication process in, signal sends and receivees, particularly, by base station After downlink information receives, handled to processor 1080；In addition, the data for designing uplink are sent to base station.In general, RF circuit 1010 include but is not limited to antenna, at least one amplifier, transceiver, coupler, low-noise amplifier (Low Noise Amplifier, LNA), duplexer etc..In addition, RF circuit 1010 can also be logical with network and other equipment by wireless communication Letter.Any communication standard or agreement, including but not limited to global system for mobile communications (Global can be used in above-mentioned wireless communication System of Mobile communication, GSM), general packet radio service (General Packet Radio Service, GPRS), CDMA (Code Division Multiple Access, CDMA), wideband code division multiple access (Wideband Code Division Multiple Access, WCDMA), long term evolution (Long Term Evolution, LTE), Email, short message service (Short Messaging Service, SMS) etc..
Memory 1020 can be used for storing software program and module, and processor 1080 is stored in memory by operation 1020 software program and module, thereby executing the various function application and data processing of mobile phone.Memory 1020 can be led It to include storing program area and storage data area, wherein storing program area can be needed for storage program area, at least one function Application program (such as sound-playing function, image player function etc.) etc.；Storage data area, which can be stored, uses institute according to mobile phone Data (such as audio data, phone directory etc.) of creation etc..In addition, memory 1020 may include high random access storage Device, can also include nonvolatile memory, and a for example, at least disk memory, flush memory device or other volatibility are solid State memory device.
Input unit 1030 can be used for receiving the number or character information of input, and generate with the user setting of mobile phone with And the related key signals input of function control.Specifically, input unit 1030 may include touch panel 1031 and other inputs Equipment 1032.Touch panel 1031, also referred to as touch screen collect touch operation (such as the user of user on it or nearby Use the behaviour of any suitable object or attachment such as finger, stylus on touch panel 1031 or near touch panel 1031 Make), and corresponding attachment device is driven according to preset formula.Optionally, touch panel 1031 may include touch detection Two parts of device and touch controller.Wherein, the touch orientation of touch detecting apparatus detection user, and detect touch operation band The signal come, transmits a signal to touch controller；Touch controller receives touch information from touch detecting apparatus, and by it It is converted into contact coordinate, then gives processor 1080, and order that processor 1080 is sent can be received and executed.In addition, Touch panel 1031 can be realized using multiple types such as resistance-type, condenser type, infrared ray and surface acoustic waves.In addition to touch surface Plate 1031, input unit 1030 can also include other input equipments 1032.Specifically, other input equipments 1032 may include But in being not limited to physical keyboard, function key (such as volume control button, switch key etc.), trace ball, mouse, operating stick etc. It is one or more.
Display unit 1040 can be used for showing information input by user or be supplied to user information and mobile phone it is each Kind menu.Display unit 1040 may include display panel 1041, optionally, can use liquid crystal display (Liquid Crystal Display, LCD), the forms such as Organic Light Emitting Diode (Organic Light-Emitting Diode, OLED) To configure display panel 1041.Further, touch panel 1031 can cover display panel 1041, when touch panel 1031 detects After arriving touch operation on it or nearby, processor 1080 is sent to determine the type of touch event, is followed by subsequent processing device 1080 provide corresponding visual output according to the type of touch event on display panel 1041.Although in Figure 10, touch surface Plate 1031 and display panel 1041 are the input and input function for realizing mobile phone as two independent components, but certain In embodiment, can be integrated by touch panel 1031 and display panel 1041 and that realizes mobile phone output and input function.
Mobile phone may also include at least one sensor 1050, such as optical sensor, motion sensor and other sensors. Specifically, optical sensor may include ambient light sensor and proximity sensor, wherein ambient light sensor can be according to ambient light Light and shade adjust the brightness of display panel 1041, proximity sensor can close display panel when mobile phone is moved in one's ear 1041 and/or backlight.As a kind of motion sensor, accelerometer sensor can detect in all directions (generally three axis) and add The size of speed can detect that size and the direction of gravity when static, can be used to identify application (such as the horizontal/vertical screen of mobile phone posture Switching, dependent game, magnetometer pose calibrating), Vibration identification correlation function (such as pedometer, tap) etc.；Also as mobile phone The other sensors such as configurable gyroscope, barometer, hygrometer, thermometer, infrared sensor, details are not described herein.
Voicefrequency circuit 1060, loudspeaker 1061, microphone 1062 can provide the audio interface between user and mobile phone.Audio Electric signal after the audio data received conversion can be transferred to loudspeaker 1061, be converted by loudspeaker 1061 by circuit 1060 For voice signal output；On the other hand, the voice signal of collection is converted to electric signal by microphone 1062, by voicefrequency circuit 1060 Audio data is converted to after reception, then by after the processing of audio data output processor 1080, through RF circuit 1010 to be sent to ratio Such as another mobile phone, or audio data is exported to memory 1020 to be further processed.
WiFi belongs to short range wireless transmission technology, and mobile phone can help user's transceiver electronics postal by WiFi module 1070 Part, browsing webpage and access streaming video etc., it provides wireless broadband internet access for user.Although Figure 10 is shown WiFi module 1070, but it is understood that, and it is not belonging to must be configured into for mobile phone, it can according to need do not changing completely Become in the range of the essence of invention and omits.
Processor 1080 is the control centre of mobile phone, using the various pieces of various interfaces and connection whole mobile phone, By running or execute the software program and/or module that are stored in memory 1020, and calls and be stored in memory 1020 Interior data execute the various functions and processing data of mobile phone, to carry out integral monitoring to mobile phone.Optionally, processor 1080 may include one or more processing units；Preferably, processor 1080 can integrate application processor and modulation /demodulation processing Device, wherein the main processing operation system of application processor, user interface and application program etc., modem processor is mainly located Reason wireless communication.It is understood that above-mentioned modem processor can not also be integrated into processor 1080.
Mobile phone further includes the power supply 1090 (such as battery) powered to all parts, it is preferred that power supply can pass through power supply Management system and processor 1080 are logically contiguous, to realize management charging, electric discharge and power consumption pipe by power-supply management system The functions such as reason.
Although being not shown, mobile phone can also include camera, bluetooth module etc., and details are not described herein.
In embodiments of the present invention, processor 1080 included by the terminal also has control execution is above to be executed by terminal Image frame acquisition methods process.
Figure 11 is a kind of server architecture schematic diagram provided in an embodiment of the present invention, which can be because of configuration or property Energy is different and generates bigger difference, may include one or more central processing units (central processing Units, CPU) 1122 (for example, one or more processors) and memory 1132, one or more storage applications The storage medium 1130 (such as one or more mass memory units) of program 1142 or data 1144.Wherein, memory 1132 and storage medium 1130 can be of short duration storage or persistent storage.The program for being stored in storage medium 1130 may include one A or more than one module (diagram does not mark), each module may include to the series of instructions operation in server.More into One step, central processing unit 1122 can be set to communicate with storage medium 1130, execute storage medium on server 1100 Series of instructions operation in 1130.
Server 1100 can also include one or more power supplys 1126, one or more wired or wireless nets Network interface 1150, one or more input/output interfaces 1158, and/or, one or more operating systems 1141, example Such as Windows ServerTM, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM etc..
The acquisition methods step of the image frame as performed by server can be based on shown in the Figure 11 in above-described embodiment Server architecture.
In addition it should be noted that, the apparatus embodiments described above are merely exemplary, wherein described as separation The unit of part description may or may not be physically separated, component shown as a unit can be or It can not be physical unit, it can it is in one place, or may be distributed over multiple network units.It can be according to reality Border needs to select some or all of the modules therein to achieve the purpose of the solution of this embodiment.In addition, provided by the invention In Installation practice attached drawing, the connection relationship between module indicates there is communication connection between them, specifically can be implemented as one Item or a plurality of communication bus or signal wire.Those of ordinary skill in the art are without creative efforts, it can It understands and implements.
Through the above description of the embodiments, it is apparent to those skilled in the art that the present invention can borrow Help software that the mode of required common hardware is added to realize, naturally it is also possible to by specialized hardware include specific integrated circuit, specially It is realized with CPU, private memory, special components and parts etc..Under normal circumstances, all functions of being completed by computer program are ok It is easily realized with corresponding hardware, moreover, being used to realize that the specific hardware structure of same function is also possible to a variety of more Sample, such as analog circuit, digital circuit or special circuit etc..But software program is real in situations more for the purpose of the present invention It is now more preferably embodiment.Based on this understanding, technical solution of the present invention substantially in other words makes the prior art The part of contribution can be embodied in the form of software products, which is stored in the storage medium that can be read In, such as the floppy disk of computer, USB flash disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory Device (RAM, Random Access Memory), magnetic or disk etc., including some instructions are with so that a computer is set Standby (can be personal computer, server or the network equipment etc.) executes method described in each embodiment of the present invention.
In conclusion the above embodiments are merely illustrative of the technical solutions of the present invention, rather than its limitations；Although referring to upper Stating embodiment, invention is explained in detail, those skilled in the art should understand that：It still can be to upper Technical solution documented by each embodiment is stated to modify or equivalent replacement of some of the technical features；And these It modifies or replaces, the spirit and scope for technical solution of various embodiments of the present invention that it does not separate the essence of the corresponding technical solution.

Claims (16)

1. a kind of acquisition methods of image frame, which is characterized in that including：
Image data stream is obtained, includes the image frame of multiframe in described image data flow；
The first image frame is intercepted out from described image data flow, the image that the first image picture belongs to the multiframe is drawn Face；
Identify that the first user interface UI element, the first UI element are the first image from the first image picture It is located at the UI element that interface edge and element position remain unchanged within a preset period of time in picture；
Interface edge region where the first UI element is cut out from the first image picture, obtains the second image picture Face, second image frame are to cut out remaining image-region behind the interface edge region in the first image picture.
2. the method according to claim 1, wherein described identify the first use from the first image picture Family interface UI element, including：
Property data base is obtained, includes the feature image of multiple in the property data base；
The feature image of multiple in the first image picture and the property data base is matched respectively；
When the fisrt feature picture in the property data base is matched with the first image picture, drawn from the first image Determine the characteristic matching region with the fisrt feature picture match in face, the fisrt feature picture belong to it is described multiple Feature image；
The first UI member is identified from the image-region for being not belonging to the characteristic matching region in the first image picture Element.
3. according to the method described in claim 2, it is characterized in that, described by the first image picture and the characteristic The feature image of multiple in library is matched respectively, including：
Fisrt feature point is extracted from the first image picture, and every feature image from the property data base In extract second feature point；
Similitude matching is carried out to the fisrt feature point and second feature point, obtains similitude matching result；
Determine whether the first image picture and the feature image match according to similitude matching result.
4. according to the method described in claim 2, it is characterized in that, it is described determined from the first image picture with it is described The characteristic matching region of fisrt feature picture match, including：
It is determined from multiple fisrt feature points of the first image picture diagonal with matched two of the second feature point Coordinate；
The length and width in the characteristic matching region is obtained according to the pixel value difference between described two pairs of angular coordinates；
According to described two pairs of angular coordinates, the length and width in the characteristic matching region, the length of the fisrt feature picture And width, screenshot coordinate is obtained from the first image picture；
The characteristic matching region is determined according to the length and width of the screenshot coordinate, the characteristic matching region.
5. according to the method described in claim 2, it is characterized in that, including the feature image point of multiple in the property data base It Dui Yingyu not screenshot picture of the application program in different application scenarios.
6. the method according to any one of claims 1 to 5, which is characterized in that described to be cut from described image data flow The first image frame is taken out, including：
The first image frame is intercepted out in slave described image data flow according to preset interception period timing.
7. the method according to any one of claims 1 to 5, which is characterized in that it is described will be where the first UI element Interface edge region cut out from the first image picture, after obtaining the second image frame, the method also includes：
Second image frame is sent to information server, is updated second image frame by the information server For the cover image of described image data flow.
8. a kind of acquisition device of image frame, which is characterized in that including：
Data flow obtains module, includes the image frame of multiframe for obtaining image data stream, in described image data flow；
Picture capturing module, for intercepting out the first image frame, the first image picture category from described image data flow In the image frame of the multiframe；
Picture recognition module, for identifying the first user interface UI element, the first UI from the first image picture Element is the UI element for being located at interface edge and element position in the first image picture and remaining unchanged within a preset period of time；
Region screen capture module, for cutting the interface edge region where the first UI element from the first image picture Fall, obtain the second image frame, second image frame is to cut out the interface edge region in the first image picture Remaining image-region afterwards.
9. device according to claim 8, which is characterized in that the picture recognition module, including：
Feature image loading unit includes the feature image of multiple for obtaining property data base, in the property data base；
Image matching unit, for distinguishing the feature image of multiple in the first image picture and the property data base It is matched；
Region Matching unit, for being matched when the fisrt feature picture in the property data base with the first image picture When, the characteristic matching region with the fisrt feature picture match is determined from the first image picture, described first is special Sign picture belongs to multiple the feature image；
Elemental recognition unit, for knowing from the image-region for being not belonging to the characteristic matching region in the first image picture It Chu not the first UI element.
10. device according to claim 9, which is characterized in that described image matching unit, including：
Feature extraction subelement, for extracting fisrt feature point from the first image picture, and from the characteristic According to extracting second feature point in every in library feature image；
Similar computation subunit obtains phase for carrying out similitude matching to the fisrt feature point and second feature point Like property matching result；
Determine subelement, for according to similitude matching result determine the first image picture and the feature image whether Match.
11. device according to claim 9, which is characterized in that the Region Matching unit, including：
Subelement is determined to angular coordinate, for determining from multiple fisrt feature points of the first image picture and described Two of two Feature Points Matchings are to angular coordinate；
Length and width computation subunit, for obtaining the characteristic matching region according to the pixel value difference between described two pairs of angular coordinates Length and width；
Screenshot coordinate obtains subelement, for according to the length and widths of described two pairs of angular coordinates, the characteristic matching region, The length and width of the fisrt feature picture obtains screenshot coordinate from the first image picture；
Matching area determines subelement, for being determined according to the length and width of the screenshot coordinate, the characteristic matching region The characteristic matching region out.
12. device according to claim 9, which is characterized in that include the feature image of multiple in the property data base Correspond respectively to screenshot picture of the application program in different application scenarios.
13. the device according to any one of claim 8 to 12, which is characterized in that the picture capturing module is specific to use The first image frame is intercepted out in the slave described image data flow according to preset interception period timing.
14. the device according to any one of claim 8 to 12, which is characterized in that the acquisition device of described image picture, Further include：
Sending module, for the region screen capture module by the interface edge region where the first UI element from described first It is cut out in image frame, after obtaining the second image frame, second image frame is sent to information server, by described Second image frame is updated to the cover image of described image data flow by information server.
15. a kind of computer readable storage medium, including instruction, when run on a computer, so that computer executes such as Method described in claim 1 to 7 any one.
16. a kind of acquisition device of image frame, which is characterized in that the acquisition device of described image picture includes：Processor and Memory；
The memory, for storing instruction；
The processor is executed as described in any one of claims 1 to 7 for executing the described instruction in the memory Method.
CN201810654362.0A 2018-06-22 2018-06-22 Image picture acquisition method and device and computer readable storage medium Active CN108845742B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201810654362.0A CN108845742B (en) 2018-06-22 2018-06-22 Image picture acquisition method and device and computer readable storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201810654362.0A CN108845742B (en) 2018-06-22 2018-06-22 Image picture acquisition method and device and computer readable storage medium

Publications (2)

Publication Number Publication Date
CN108845742A true CN108845742A (en) 2018-11-20
CN108845742B CN108845742B (en) 2020-05-05

Family

ID=64203514

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201810654362.0A Active CN108845742B (en) 2018-06-22 2018-06-22 Image picture acquisition method and device and computer readable storage medium

Country Status (1)

Country Link
CN (1) CN108845742B (en)

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109522085A (en) * 2018-11-28 2019-03-26 珠海金山网络游戏科技有限公司 Data processing method, calculates equipment and storage medium at device
CN110677734A (en) * 2019-09-30 2020-01-10 北京达佳互联信息技术有限公司 Video synthesis method and device, electronic equipment and storage medium
CN110782459A (en) * 2019-01-08 2020-02-11 北京嘀嘀无限科技发展有限公司 Image processing method and device
CN111163138A (en) * 2019-12-18 2020-05-15 北京智明星通科技股份有限公司 Method, device and server for reducing network load during game
CN111491209A (en) * 2020-04-08 2020-08-04 咪咕文化科技有限公司 Video cover determining method and device, electronic equipment and storage medium

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107657583A (en) * 2017-08-29 2018-02-02 努比亚技术有限公司 A kind of screenshot method, terminal and computer-readable recording medium
CN107967339A (en) * 2017-12-06 2018-04-27 广东欧珀移动通信有限公司 Image processing method, device, computer-readable recording medium and computer equipment

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107657583A (en) * 2017-08-29 2018-02-02 努比亚技术有限公司 A kind of screenshot method, terminal and computer-readable recording medium
CN107967339A (en) * 2017-12-06 2018-04-27 广东欧珀移动通信有限公司 Image processing method, device, computer-readable recording medium and computer equipment

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109522085A (en) * 2018-11-28 2019-03-26 珠海金山网络游戏科技有限公司 Data processing method, calculates equipment and storage medium at device
CN109522085B (en) * 2018-11-28 2022-02-01 珠海金山网络游戏科技有限公司 Data processing method and device, computing equipment and storage medium
CN110782459A (en) * 2019-01-08 2020-02-11 北京嘀嘀无限科技发展有限公司 Image processing method and device
CN110677734A (en) * 2019-09-30 2020-01-10 北京达佳互联信息技术有限公司 Video synthesis method and device, electronic equipment and storage medium
CN111163138A (en) * 2019-12-18 2020-05-15 北京智明星通科技股份有限公司 Method, device and server for reducing network load during game
CN111163138B (en) * 2019-12-18 2022-04-12 北京智明星通科技股份有限公司 Method, device and server for reducing network load during game
CN111491209A (en) * 2020-04-08 2020-08-04 咪咕文化科技有限公司 Video cover determining method and device, electronic equipment and storage medium

Also Published As

Publication number Publication date
CN108845742B (en) 2020-05-05

Similar Documents

Publication Publication Date Title
CN108845742A (en) The acquisition methods and device and computer readable storage medium of a kind of image frame
CN109819179B (en) Video editing method and device
CN106131627B (en) A kind of method for processing video frequency, apparatus and system
CN104135609B (en) Auxiliary photo-taking method, apparatus and terminal
CN106296617B (en) The processing method and processing device of facial image
US20170032219A1 (en) Methods and devices for picture processing
CN110140106A (en) According to the method and device of background image Dynamically Announce icon
CN108875451A (en) A kind of method, apparatus, storage medium and program product positioning image
CN108900778A (en) A kind of image pickup method, mobile terminal and computer readable storage medium
CN106789565A (en) Social content sharing method and device
CN109145809A (en) A kind of note spectrum processing method and device and computer readable storage medium
CN107959795A (en) A kind of information collecting method, equipment and computer-readable recording medium
CN108234879A (en) It is a kind of to obtain the method and apparatus for sliding zoom video
CN110209245A (en) Face identification method and Related product
CN110070034A (en) Model training method, section recognition methods, device, equipment and medium
CN108460817A (en) A kind of pattern splicing method and mobile terminal
CN110059753A (en) Model training method, interlayer are every recognition methods, device, equipment and medium
CN110162653A (en) A kind of picture and text sort recommendations method and terminal device
CN110198421B (en) Video processing method and related product
CN110363702B (en) Image processing method and related product
CN108460769A (en) Image processing method and terminal device
CN108121583B (en) Screen capturing method and related product
KR20220043004A (en) Method and apparatus for detecting occluded image and medium
CN108287873A (en) Data processing method and related product
CN106095558B (en) A kind of method and terminal of audio effect processing

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant