CN108492352A - Implementation method, device, system, computer equipment and the storage medium of augmented reality - Google Patents
Implementation method, device, system, computer equipment and the storage medium of augmented reality Download PDFInfo
- Publication number
- CN108492352A CN108492352A CN201810242139.5A CN201810242139A CN108492352A CN 108492352 A CN108492352 A CN 108492352A CN 201810242139 A CN201810242139 A CN 201810242139A CN 108492352 A CN108492352 A CN 108492352A
- Authority
- CN
- China
- Prior art keywords
- target
- reality
- webpage
- augmented reality
- reality scene
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T15/00—3D [Three Dimensional] image rendering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T19/00—Manipulating 3D models or images for computer graphics
- G06T19/006—Mixed reality
Abstract
This application involves a kind of implementation method of augmented reality, this method includes：Terminal receives the reality scene acquisition request that webpage is initiated, request call photographic device, which is acquired, according to the reality scene acquires reality scene picture, the collected reality scene picture is subjected to real-time exhibition on webpage, and replicate the augmented reality identification module that the reality scene picture passes to terminal local, the augmented reality identification module carries out target identification to the reality scene picture, obtain recognition result, the recognition result is returned into webpage, so that webpage carries out augmented reality processing according to the recognition result to the reality scene picture shown on webpage.The implementation method of the augmented reality so that the page is provided with the AR recognition effects of Native (local), substantially increases the performance of the augmented reality under page scene.In addition, it is also proposed that a kind of realization device of augmented reality, computer equipment and storage medium.
Description
Technical field
This application involves computer processing technical fields, more particularly to a kind of implementation method of augmented reality, device, are
System, computer equipment and storage medium.
Background technology
There are many open platforms in the direction augmented reality (Augmented Reality, abbreviation AR) at present, but these are opened
Platform is both for Native (local) scene, and there are no good methods under web (webpage) scene.Traditional fields web
AR under scape is identification, the tracking by front end JS (JavaScript) to target object, along with the rendering of 3D animations comes in fact
Existing.But JavaScript is a kind of weak object script, the poor ability on image procossing is applied to, so traditional
The poor performance of augmented reality under web scenes.
Invention content
Based on this, it is necessary in view of the above-mentioned problems, propose a kind of implementation method for the augmented reality that performance is high, device,
System, computer equipment and storage medium.
A kind of implementation method of augmented reality, the method includes：
Terminal receives the reality scene acquisition request that webpage is initiated, and request call camera shooting dress is acquired according to the reality scene
Set acquisition reality scene picture；
The collected reality scene picture is subjected to real-time exhibition on webpage, and replicates the reality scene picture
The augmented reality identification module of terminal local is passed to, the augmented reality identification module carries out mesh to the reality scene picture
Mark is other, obtains recognition result；
The recognition result is returned into webpage, so that webpage is described existing to what is shown on webpage according to the recognition result
Real scenic picture carries out augmented reality processing.
A kind of realization device of augmented reality, described device include：
Acquisition module, the reality scene for receiving webpage initiation acquire request, are acquired and asked according to the reality scene
Photographic device is called to acquire reality scene picture；
Transfer module for the collected reality scene picture to be carried out real-time exhibition on webpage, and replicates institute
State the augmented reality identification module that reality scene picture passes to terminal local；
The augmented reality identification module is used to carry out target identification to the reality scene picture, obtains recognition result；
Return module, for the recognition result to be returned to webpage so that webpage according to the recognition result to webpage
The reality scene picture of upper displaying carries out augmented reality processing.
A kind of realization system of augmented reality, the system comprises：
Terminal, the reality scene for receiving webpage initiation acquire request, request call are acquired according to the reality scene
Photographic device acquires reality scene picture, the collected reality scene picture is carried out real-time exhibition on webpage, and multiple
The augmented reality identification module that the reality scene picture passes to terminal local is made, the augmented reality identification module is to real-time
The clarity of collected reality scene picture is identified, and filters out the first object video that clarity is more than predetermined threshold value
Frame, by the first object video frame transmission to server；
Server, the first object object in the first object video frame, returns and the first object for identification
The corresponding first object identification model of object；
The terminal is additionally operable to according to the first object identification model to the first object in the reality scene picture
Object is identified, and obtains recognition result, and the recognition result is returned to webpage, so that webpage is according to the recognition result pair
The reality scene picture shown on webpage carries out augmented reality processing.
A kind of computer equipment, including memory and processor, the memory are stored with computer program, the calculating
When machine program is executed by the processor so that the processor executes following steps：
The reality scene acquisition request that webpage is initiated is received, request call photographic device is acquired according to the reality scene and is adopted
Collect reality scene picture；
The collected reality scene picture is subjected to real-time exhibition on webpage, and replicates the reality scene picture
The augmented reality identification module of terminal local is passed to, the augmented reality identification module carries out mesh to the reality scene picture
Mark is other, obtains recognition result；
The recognition result is returned into webpage, so that webpage is described existing to what is shown on webpage according to the recognition result
Real scenic picture carries out augmented reality processing.
A kind of computer readable storage medium is stored with computer program, when the computer program is executed by processor,
So that the processor executes following steps：
The reality scene acquisition request that webpage is initiated is received, request call photographic device is acquired according to the reality scene and is adopted
Collect reality scene picture；
The collected reality scene picture is subjected to real-time exhibition on webpage, and replicates the reality scene picture
The augmented reality identification module of terminal local is passed to, the augmented reality identification module carries out mesh to the reality scene picture
Mark is other, obtains recognition result；
The recognition result is returned into webpage, so that webpage is described existing to what is shown on webpage according to the recognition result
Real scenic picture carries out augmented reality processing.
Implementation method, device, system, computer equipment and the storage medium of above-mentioned augmented reality are collecting real field
After scape picture, collected reality scene picture is on the one hand subjected to real-time exhibition on webpage, on the other hand showing duplication
The augmented reality identification module progress target identification that real scenic picture passes to terminal local obtains recognition result, and identification is tied
Fruit returns to webpage, and webpage carries out augmented reality processing according to recognition result to the reality scene picture shown on webpage.The increasing
The implementation method of strong reality carries out target knowledge by using the augmented reality identification module of terminal local to reality scene picture
Not so that the page is provided with the AR recognition effects of Native (local), substantially increases the property of the augmented reality under page scene
Energy.
Description of the drawings
Fig. 1 is the applied environment figure of the implementation method of augmented reality in one embodiment；
Fig. 2 is the flow chart of the implementation method of augmented reality in one embodiment；
Fig. 3 A are the interface schematic diagram for carrying out target identification in one embodiment to collected reality scene picture；
Fig. 3 B are the interface schematic diagram that augmented reality is shown in one embodiment；
Fig. 4 is that augmented reality identification module carries out target identification to the reality scene picture in one embodiment, is obtained
The method flow diagram of recognition result；
Fig. 5 is the implementation method flow chart of augmented reality in another embodiment；
Fig. 6 is the method flow diagram that reality scene picture is identified in browsing serves kernel module in one embodiment；
Fig. 7 is the Organization Chart of the implementation method of augmented reality in one embodiment；
Fig. 8 is the flow chart of the implementation method of augmented reality in another embodiment；
Fig. 9 is the structure diagram of the realization device of augmented reality in one embodiment；
Figure 10 is the structure diagram that serves kernel module is browsed in one embodiment；
Figure 11 is the block diagram of the realization system of augmented reality in one embodiment；
Figure 12 is the structure diagram of one embodiment Computer equipment.
Specific implementation mode
It is with reference to the accompanying drawings and embodiments, right in order to make the object, technical solution and advantage of the application be more clearly understood
The application is further elaborated.It should be appreciated that specific embodiment described herein is only used to explain the application, and
It is not used in restriction the application.
Fig. 1 is the applied environment figure of the implementation method of augmented reality in one embodiment.Referring to Fig.1, the augmented reality
Implementation method is applied to the realization system of augmented reality.The realization system of the augmented reality includes terminal 110 and server 120.
Terminal 110 and server 120 pass through network connection.Terminal 110 can be specifically terminal console or mobile terminal, mobile terminal tool
Body can be at least one of mobile phone, tablet computer, laptop etc..Server 120 can with independent server or
It is the server cluster of multiple servers composition to realize.Specifically, terminal 110 receives the reality scene acquisition that webpage is initiated and asks
It asks, acquiring request call photographic device according to the reality scene acquires reality scene picture, by the collected real field
Scape picture carries out real-time exhibition on webpage, and replicates the augmented reality identification that the reality scene picture passes to terminal local
Module, the augmented reality identification module by it is collected include that the video frame of reality scene picture is uploaded to server 120,
The target object in reality scene picture is identified in server 120, obtains recognition result, and recognition result is returned to institute
State augmented reality identification module.Recognition result is returned to webpage by augmented reality identification module again, so that webpage is tied according to identification
Fruit carries out augmented reality processing to the reality scene picture shown on webpage.
As shown in Fig. 2, in one embodiment, providing a kind of implementation method of augmented reality.The present embodiment mainly with
It is illustrated applied to terminal 110.The implementation method of the augmented reality specifically comprises the following steps：
Step S202, terminal receive the reality scene acquisition request that webpage is initiated, request call are acquired according to reality scene
Photographic device acquires reality scene picture.
Wherein, photographic device refers to the equipment for shooting video, for example, camera.In order under webpage (web) scene
Realize augmented reality, it is necessary first to the photographic device in terminal be called to be acquired reality scene picture.Specifically, terminal connects
The reality scene acquisition request that webpage is initiated is received, reality scene acquisition request call photographic device is then responding to and reality scene is drawn
Face is acquired.Reality scene picture refers to the picture with the real world captured by photographic device, what real world referred to
It is to be present in the objective world except human brain, is the appreciable world.
Collected reality scene picture is carried out real-time exhibition by step S204 on webpage, and replicates reality scene picture
Face passes to the augmented reality identification module of terminal local, and augmented reality identification module carries out target knowledge to reality scene picture
Not, recognition result is obtained.
Wherein, augmented reality identification module is used to that the target object in reality scene picture to be identified to obtain identification knot
Fruit.Recognition result includes the location information of target object and target object that identification obtains.Terminal local, that is, computer equipment
Itself, the content of terminal local refers to being stored in terminal inner, does not need the terminal content that network can be accessed directly, than
Such as, the content being stored in terminal disk.Terminal belongs to the content of page end by the content that network could access.Terminal obtains
To after by the collected reality scene picture of photographic device, on the one hand collected reality scene picture is carried out on webpage
On the other hand real-time exhibition replicates a reality scene picture and passes to the augmented reality identification module in terminal local,
In, reality scene picture refers to collected video frame, and video is made of the image of a frame frame, and each video frame corresponds to one
A reality scene picture.Target identification is carried out to reality scene picture by augmented reality identification module, obtains recognition result.Increase
Strong reality identification module is by AR-SDK (AR-Software Development kit, Software Development Kit) come what is realized.
Since augmented reality identification module is present in terminal local, so being provided with identification and the tracking target of Native (local)
The ability of object, recognition capability are improved significantly, to be conducive to improve the display effect of follow-up augmented reality.
In another embodiment, may include multiple target objects in the same reality scene picture, and it is different
Target object need different Model of Target Recognition to be identified, in order to improve identification target object speed, can be simultaneously
It replicates more parts of reality scene pictures and passes to multiple Model of Target Recognition in augmented reality identification module, in this way, multiple targets
Identification model can simultaneously be identified target object, improve the speed of identification.
In one embodiment, it is that will be collected by the webpage real-time communication module (WEBRTC modules) in terminal local
Include that the video flowing of reality scene picture copies as two parts, a copy of it, which is passed to webpage front-end, to be shown, will be another
Portion passes to augmented reality identification module and carries out target identification.Wherein, WEBRTC (Web Real-Time
Communication, webpage real-time Communication for Power) it is the technology that a supported web page browser carries out video conversation, it is mainly responsible for
The rendering of reality scene real-time pictures.
In another embodiment, the video flowing of duplication is passed to AR engine modules first to pre-process, is pre-processed
Including judging whether video frame is clear, the relatively high video frame etc. of clarity is filtered out, it then again will in advance by AR engine modules
Video frame after reason passes to enhancing identification module and carries out target identification, obtains recognition result.
Recognition result is returned to webpage by step S206 so that webpage according to recognition result to the reality that is shown on webpage
Scenic picture carries out augmented reality processing.
Wherein, augmented reality (Augmented Reality, abbreviation AR) is a kind of calculating camera image in real time
Position and angle and the technology for adding respective image, video, 3D models, the purpose of this technology is on the screen virtual world
It is sleeved on real world and carries out interaction.Augmented reality can exist the information seamless integration of the information of real world and virtual world
Together, by virtual Information application to real world, true environment and virtual object have been added to the same picture in real time
Face or space and exist simultaneously, two kinds of information are complementary to one another superposition.It include the position of the target object recognized in recognition result
Confidence ceases, and the display location of virtual objects is determined according to the location information of target object, then according to the displaying of virtual objects
Position carries out virtual objects with target object to merge displaying, to realize augmented reality under the scene of webpage.Such as Fig. 3 A and
Shown in 3B, to increase the interface schematic diagram of reality in one embodiment, wherein Fig. 3 A be to collected reality scene picture into
The interface schematic diagram of row target identification, Fig. 3 B are the interface schematic diagram that show of augmented reality, are reality scene and virtually right in figure
Picture shown in after being superimposed as (for example, virtual castle in figure).
The implementation method of above-mentioned augmented reality, after collecting reality scene picture, on the one hand by collected real field
Scape picture carries out real-time exhibition on webpage, and on the other hand enhancing that the reality scene picture of duplication is passed to terminal local shows
Real identification module carries out target identification and obtains recognition result, and recognition result is returned to webpage, and webpage is according to recognition result pair
The reality scene picture shown on webpage carries out augmented reality processing.The implementation method of the augmented reality, by using terminal sheet
The augmented reality identification module on ground carries out target identification to reality scene picture so that the page is provided with the AR of (local) Native
Recognition effect substantially increases the performance of the augmented reality under page scene.
In one embodiment, the augmented reality identification module carries out target identification to the reality scene picture, obtains
Include to the step of recognition result：The augmented reality identification module obtains Model of Target Recognition, using the target identification mould
The target object in the reality scene picture is identified in type, obtains recognition result.
Wherein, Model of Target Recognition is pre-established for the target object in reality scene picture to be identified
Model.Model of Target Recognition corresponding to different target objects is different.Before reality scene picture is identified, first
Then the determination target object to be identified obtains Model of Target Recognition corresponding with the target object, using the target identification mould
The target object in reality scene picture is identified in type, obtains recognition result.
In one embodiment, it is also wrapped before the step of augmented reality identification module obtains Model of Target Recognition
It includes：The augmented reality identification module reception includes the sample image of target object, to the target pair in the sample image
The feature of elephant extracts；The Model of Target Recognition is established according to the feature of extraction.
Wherein, augmented reality identification module is carrying out the target object in reality scene picture using Model of Target Recognition
Before identification, need to pre-establish Model of Target Recognition.Model of Target Recognition is by including to the one or more of registration
The sample image of target object carries out feature extraction, is then trained the target identification that study obtains according to the feature extracted
Model.For example, if it is desired to " hand " is identified, registration one first includes the picture of " hand ", by picture
The feature of " hand " is identified to obtain the Model of Target Recognition of " hand " for identification.
As shown in figure 4, in one embodiment, the augmented reality identification module carries out mesh to the reality scene picture
Mark is other, and the step of obtaining recognition result includes：
The clarity of real-time collected reality scene picture is identified in step S204A, augmented reality identification module,
Filter out the first object video frame that clarity is more than predetermined threshold value.
Wherein, clarity refers to the readability on each thin portion shadow line and its boundary on reality scene picture, for reflecting figure
The resolution ratio of video pictures may be used to measure in image quality amount, clarity.In order to get Model of Target Recognition from server end,
Need to select from the video flowing of reality scene picture clearly video frame upload onto the server, then by server to video frame
Including target object be identified, corresponding Model of Target Recognition is issued to terminal according to the obtained target object of identification.Tool
Body, the clarity of real-time collected reality scene picture is identified, clarity is then filtered out and is more than predetermined threshold value
First object video frame.Wherein, predetermined threshold value is to define setting, the frame of first object video frame in advance according to actual conditions
Number self-defined can also be arranged, for example, can be a frame, or multiframe.
Step S204B, by first object video frame transmission to server, so that in server identification first object video frame
First object object, return to corresponding with first object object first object identification model.
Wherein, the Model of Target Recognition corresponding to different target objects is different, and different mesh are stored with respectively in server
Mark the corresponding Model of Target Recognition of object.In order to neatly be selected according to the target object for including in reality scene picture
Then Model of Target Recognition, the first object video frame transmission by that will screen identify first object to server by server
First object identification model corresponding with the first object object is returned to augmented reality knowledge by the first object object of video frame
Other module, augmented reality identification module is according to the first object identification model received to the first object in reality scene picture
Object is identified.
Step S204C is identified the first object object in reality scene picture according to first object identification model,
Obtain recognition result.
Wherein, after the augmented reality identification module of terminal local receives the first object identification model that server returns,
The first object object in reality scene picture is identified using the first object identification model, identification obtains first object
Position where object, convenient for subsequently determining the display location of virtual objects according to the position where first object object, after
And the first object object in virtual objects and reality scene is combined displaying.
As shown in figure 5, in one embodiment, the implementation method of above-mentioned augmented reality further includes：
Step S208, detecting the scene corresponding to reality scene picture, whether occurrence scene switches, if so, entering step
S210, if it is not, then continuing to detect, until terminating.
Wherein, when the scene occurrence scene of reality scene picture switches, illustrate the target for including in reality scene picture
Object has been likely occurred change, for example, the target object in reality scene picture before changed for " face " after show
Target object in real scenic picture may be " hand ".So when detecting the scene occurrence scene corresponding to reality scene picture
When switching, need to redefine Model of Target Recognition corresponding with target object.Wherein, whether detection reality scene picture occurs
Scene switching, in case of variation, is said by comparing whether the picture in continuous several video frame is changed
Light field scape is changed, and is needed to obtain the video frame corresponding to the more new scene after switching, is then filtered out more new scene pair
The the second target video frame answered.
Step S210 obtains the video frame corresponding to the more new scene after scene switching, screening and the more new scene pair
The the second target video frame answered.
Wherein, after detecting that scene switches, the video frame corresponding to the more new scene after switching is obtained, according to clear
Degree filters out the second target video frame corresponding with more new scene.
The second target video frame is transmitted to server by step S212, so that server identification described second
The second target object in target video frame returns to the second Model of Target Recognition corresponding with second target object.
Wherein, the second target video frame filtered out is uploaded onto the server, in server pair the second target video frame
Second target object is identified, and the second Model of Target Recognition corresponding with the second target object is then obtained, by second mesh
Mark does not return to the augmented reality identification module of terminal local.
Step S214, according to second Model of Target Recognition to the second target object in the reality scene picture into
Row identification, obtains recognition result.
Wherein, the augmented reality identification module of terminal local uses the second Model of Target Recognition in reality scene picture
Second target object is identified, and then obtains the location information of the second target object.
In one embodiment, the augmented reality identification module carries out target identification to the reality scene picture, obtains
Include to the step of recognition result：The clarity of real-time collected reality scene picture is identified, clarity is filtered out
More than the target video frame of predetermined threshold value；The target video frame is transmitted to server, so that described in server identification
Target object in reality scene picture, obtains recognition result；Receive the recognition result that the server returns.
Wherein, in order to which from server acquisition recognition result, the clarity of collected reality scene picture is identified,
The target video frame that clarity is more than predetermined threshold value is filtered out, target video frame is then transmitted to server, server is to mesh
The target object for including in mark video frame is identified, and obtains recognition result, recognition result is then returned to terminal local
Augmented reality identification module.Specifically, the Model of Target Recognition that identification target object is contained in server, using target identification
The target object in target video frame is identified in model, obtains recognition result.
In one embodiment, the recognition result is the location information of target object；It is described to return the recognition result
Back to webpage, so that webpage carries out at augmented reality the reality scene picture shown on webpage according to the recognition result
The step of reason includes：The location information of the target object is returned into webpage, so that the webpage is according to the target object
Location information determine the corresponding display location of virtual objects, according to the display location by the virtual objects and the target
Object is combined displaying.
Wherein, recognition result is the location information of target object, and the location information for the target object that identification is obtained returns
To webpage, webpage determines the display location of virtual objects according to the location information of target object, will be virtual right according to display location
As being combined displaying with target object.In one embodiment, the processing of augmented reality is to use WebGL (Web
Graphics Library) for technology come what is realized, WebGL is the necessary technology of web front-end page rendering 3D animations.
As shown in fig. 6, in one embodiment, the terminal local includes browsing serves kernel module, the browsing clothes
Business kernel module includes webpage real-time communication module and augmented reality identification module；
It is described that the collected reality scene picture is subjected to real-time exhibition on webpage, and replicate the reality scene
Picture passes to the augmented reality identification module of terminal local, the augmented reality identification module to the reality scene picture into
Row target identification, the step S204 for obtaining recognition result include：
Step S204a browses serves kernel mould webpage real-time communication module in the block by collected reality scene picture
Real-time exhibition is carried out on webpage, and is replicated reality scene picture and passed to augmented reality identification module.
Wherein, browsing serves kernel module refers to being stored with the module of browsing serves kernel (for example, TBS kernels), wherein
TBS refers to Tencent's browsing service, relies on X5 kernels, X5 kernels are the browser rendering engines based on Chromium, wherein
Chromium is a kind of browser engine.Browsing serves kernel module includes webpage real-time communication module and augmented reality identification mould
Block.After webpage real-time communication module gets reality scene picture, two parts are copied as, by a copy of it reality scene picture in net
Real-time exhibition is carried out on page, another passes to augmented reality identification module.
Step S204b, augmented reality identification module carry out target identification to reality scene picture, obtain recognition result, will
Recognition result returns to webpage, so that webpage carries out augmented reality according to recognition result to the reality scene picture shown on webpage
Processing.
Wherein, augmented reality identification module is identified for the target object in reality scene picture to be identified
As a result, recognition result is then passed to front end webpage, webpage is according to recognition result to the reality scene picture that is shown on webpage
Carry out augmented reality processing.
Such as the Organization Chart that Fig. 7 is the implementation method of augmented reality in one embodiment.With reference to figure 7, inside in the terminal
Store browsing serves kernel (for example, TBS kernels) module, the browser server kernel module include AR-SDK modules (i.e.
Augmented reality identification module), AR engine modules, WEBRTC modules, WEBGL modules and JSAPI interfaces.Wherein, AR-SDK modules
In be integrated with AR software tool kits, it is (i.e. fixed for the target object in reality scene picture to be identified and tracked
Position).AR engine modules are responsible for the transmission of data, compatibility for being pre-processed to the reality scene picture received
Processing etc..WEBRTC is a kind of technical solution that H5 (HTML 5) page shows camera content of shooting.WEBRTC modules are used for
The video flowing of the reality scene picture of photographic device acquisition is obtained, and is responsible for video flowing copying as two parts, portion is in preceding end page
Face is shown, another passes to AR engine modules, and AR engine modules pre-process the video flowing received, then will
Pretreated video flowing passes to AR-SDK modules.WEBGL modules are used to carry out 3D animation renderings to front end page, to realize
Augmented reality processing to reality scene picture.JSAPI (JavaScript API) interface refers to providing output for front end page
API (Application Program Interface, application programming interfaces) interface, pass through the JSAPI forward end pages return
Recognition result.Specifically, the collected reality scene picture of photographic device is obtained by WEBRTC modules first, it on the one hand will be real
On the other hand scenic picture and to reality scene picture replicate passing to AR engine modules, AR in page end real-time display
Engine modules pre-process reality scene picture, and pretreated reality scene picture is passed to AR-SDK modules,
AR-SDK modules obtain recognition result, then by recognition result for the target object in reality scene picture to be identified
AR engine modules are passed to, then recognition result is returned to WEB application, WEB application root by AR engine modules by JSAPI interfaces
WEBGL modules are called to carry out the processing that 3D renders realization augmented reality according to recognition result.
In another embodiment, AR-SDK modules are additionally operable to be communicatively coupled with server, to pass video frame
It is defeated by server, then the target object in reality scene picture is identified by server, then returns to recognition result
Give AR-SDK modules.
As shown in Figure 8, it is proposed that a kind of implementation method of augmented reality, including webpage real-time communication module and augmented reality
Identification module specifically includes following steps：
Step S801, terminal receive the reality scene acquisition request that webpage is initiated, request call are acquired according to reality scene
Photographic device acquires reality scene picture.
Collected reality scene picture is carried out real-time exhibition by step S802, webpage real-time communication module on webpage,
And replicate the augmented reality identification module that reality scene picture passes to terminal local.
The clarity of real-time collected reality scene picture is identified in step S803, augmented reality identification module,
Filter out the first object video frame that clarity is more than predetermined threshold value.
Step S804, by first object video frame transmission to server, so that in server identification first object video frame
First object object, return to corresponding with first object object first object identification model.
Step S805 is identified the first object object in reality scene picture according to first object identification model,
Obtain the first recognition result.
First recognition result is returned to webpage by step S806 so that webpage according to the first recognition result to being opened up on webpage
The reality scene picture shown carries out augmented reality processing.
Step S807 judges whether occurrence scene switches the scene corresponding to reality scene picture, if so, entering step
S808, if it is not, then terminating.
Step S808, obtains the video frame corresponding to the more new scene after scene switching, and screening is corresponding with more new scene
Second target video frame.
Second target video frame is transmitted to server by step S809, so that server identifies in the second target video frame
The second target object, return to corresponding with the second target object the second Model of Target Recognition.
Step S810 is identified the second target object in reality scene picture according to the second Model of Target Recognition,
Obtain the second recognition result.
Second recognition result is returned to webpage by step S811 so that webpage according to the second recognition result to being opened up on webpage
The reality scene picture shown carries out augmented reality processing.
As shown in Figure 9, it is proposed that a kind of realization device of augmented reality, the device include：
Acquisition module 902, the reality scene for receiving webpage initiation acquire request, are asked according to reality scene acquisition
It asks and calls photographic device acquisition reality scene picture；
Transfer module 904 for the collected reality scene picture to be carried out real-time exhibition on webpage, and replicates
The reality scene picture passes to the augmented reality identification module 906 of terminal local；
The augmented reality identification module 906 is used to carry out target identification to the reality scene picture, obtains identification knot
Fruit；
Return module 908, for the recognition result to be returned to webpage so that webpage according to the recognition result to net
The reality scene picture shown on page carries out augmented reality processing.
In one embodiment, the augmented reality identification module 906 is additionally operable to obtain Model of Target Recognition, using described
The target object in the reality scene picture is identified in Model of Target Recognition, obtains recognition result.
In one embodiment, the augmented reality identification module 906 is additionally operable to the sample that reception includes target object
Image extracts the feature of the target object in the sample image, and the target is established according to the feature of extraction
Identification model.
In one embodiment, the augmented reality identification module 906 is additionally operable to draw collected reality scene in real time
The clarity in face is identified, and filters out the first object video frame that clarity is more than predetermined threshold value, the first object is regarded
Frequency frame is transmitted to server so that the server identifies the first object object in the first object video frame, return with
The corresponding first object identification model of the first object object, according to the first object identification model to the reality scene
First object object in picture is identified, and obtains recognition result.
In one embodiment, the augmented reality identification module 906, which is additionally operable to work as, recognizes the reality scene picture
When corresponding scene occurrence scene switches, then the video frame corresponding to the more new scene after scene switching, screening and institute are obtained
The corresponding second target video frame of more new scene is stated, the second target video frame is transmitted to server, so that the service
Device identifies the second target object in the second target video frame, returns to the second target corresponding with second target object
Identification model is identified the second target object in the reality scene picture according to second Model of Target Recognition,
Obtain recognition result.
In one embodiment, the augmented reality identification module 906 is additionally operable to draw collected reality scene in real time
The clarity in face is identified, and filters out the target video frame that clarity is more than predetermined threshold value, the target video frame is transmitted
To server, so that the server identifies the target object in the reality scene picture, recognition result is obtained, described in reception
The recognition result that server returns.
In one embodiment, the recognition result is the location information of target object；The return module 908 is additionally operable to
The location information of the target object is returned into webpage, so that the webpage is determined according to the location information of the target object
The virtual objects and the target object are combined exhibition by the corresponding display location of virtual objects according to the display location
Show.
As shown in Figure 10, in one embodiment, the terminal local includes browsing serves kernel module 100, described clear
Serves kernel module of looking at includes webpage real-time communication module 1002 and augmented reality identification module 1004；
The webpage real-time communication module 1002 is used to carry out the collected reality scene picture on webpage real
When show, and replicate the reality scene picture and pass to the augmented reality identification module；
The augmented reality identification module 1004 is used to carry out target identification to the reality scene picture, obtains identification knot
The recognition result is returned to webpage by fruit so that webpage according to the recognition result to the real field that is shown on webpage
Scape picture carries out augmented reality processing.
As shown in figure 11, it is proposed that a kind of realization system of augmented reality, the system comprises：
Terminal 1102, the reality scene for receiving webpage initiation acquire request, are acquired and asked according to the reality scene
It calls photographic device to acquire reality scene picture, the collected reality scene picture is subjected to real-time exhibition on webpage,
And the augmented reality identification module that the reality scene picture passes to terminal local is replicated, the augmented reality identification module pair
The clarity of real-time collected reality scene picture is identified, and the first object for filtering out clarity more than predetermined threshold value regards
Frequency frame, by the first object video frame transmission to server；
Server 1104, the first object object in the first object video frame, returns and described first for identification
The corresponding first object identification model of target object；
The terminal 1102 is additionally operable to according to the first object identification model to first in the reality scene picture
Target object is identified, and obtains recognition result, and the recognition result is returned to webpage, so that webpage is tied according to the identification
Fruit carries out augmented reality processing to the reality scene picture shown on webpage.
In one embodiment, terminal 1102 is additionally operable to work as the scene occurrence scene recognized corresponding to reality scene picture
When switching, then the video frame corresponding to the more new scene after scene switching is obtained, screens the second target corresponding with more new scene
Video frame；Second target video frame is transmitted to server；Server 1104 is additionally operable to the in the second target video frame of identification
Two target objects return to the second Model of Target Recognition corresponding with the second target object；Terminal 1102 is additionally operable to according to the second mesh
The second target object in reality scene picture is identified in mark identification model, obtains recognition result.
In one embodiment, terminal 1102 is additionally operable to know the clarity of real-time collected reality scene picture
Not, the target video frame that clarity is more than predetermined threshold value is filtered out；Target video frame is transmitted to server；Server 1104 is also
Target object in reality scene picture for identification, obtains recognition result；Terminal 1102 is additionally operable to receive what server returned
Recognition result.
Figure 12 shows the internal structure chart of one embodiment Computer equipment.The computer equipment can be specifically eventually
End.As shown in figure 12, which includes processor, memory, network interface, the input dress connected by system bus
It sets, photographic device and display screen.Wherein, memory includes non-volatile memory medium and built-in storage.The computer equipment
Non-volatile memory medium is stored with operating system, can also be stored with computer program, which is executed by processor
When, it may make processor to realize the implementation method of augmented reality.Also computer program can be stored in the built-in storage, the calculating
When machine program is executed by processor, processor may make to execute the implementation method of augmented reality.The photographic device of computer equipment
For camera, for acquiring image.The display screen of computer equipment can be liquid crystal display or electric ink display screen, meter
Calculate machine equipment input unit can be the touch layer covered on display screen, can also be arranged on computer equipment shell by
Key, trace ball or Trackpad can also be external keyboard, Trackpad or mouse etc..It will be understood by those skilled in the art that figure
Structure shown in 12 is not constituted only with the block diagram of the relevant part-structure of application scheme to application scheme institute
The restriction for the computer equipment being applied thereon, specific computer equipment may include than more or fewer portions as shown in the figure
Part either combines certain components or is arranged with different components.
In one embodiment, the implementation method of augmented reality provided by the present application can be implemented as a kind of computer program
Form, computer program can run on computer equipment as shown in figure 12.It can be stored in the memory of computer equipment
Each program module of the realization device of the augmented reality is formed, for example, the acquisition module 902 of Fig. 9, transfer module 904, enhancing
Real identification module 906 and return module 908.The computer program that each program module is constituted makes processor execute this explanation
Step in the realization device of the augmented reality of each embodiment of the application described in book.For example, computer shown in Figure 12
Equipment can receive the reality scene that webpage is initiated by the acquisition module 902 of the realization device of augmented reality as shown in Figure 9
Acquisition request acquires request call photographic device according to the reality scene and acquires reality scene picture, passes through transfer module 904
The collected reality scene picture is subjected to real-time exhibition on webpage, and replicates the reality scene picture and passes to end
Local augmented reality identification module is held, target knowledge is carried out to the reality scene picture by augmented reality identification module 906
, do not obtain recognition result, by return module 908 recognition result is returned into webpage so that webpage according to recognition result to net
The reality scene picture shown on page carries out augmented reality processing.
In one embodiment it is proposed that a kind of computer equipment, including memory and processor, the memory storage
There is computer program, when the computer program is executed by the processor so that the processor executes following steps：It receives
The reality scene acquisition request that webpage is initiated acquires request call photographic device acquisition reality scene according to the reality scene and draws
Face；The collected reality scene picture is subjected to real-time exhibition on webpage, and replicates the reality scene picture and transmits
To the augmented reality identification module of computer equipment local, the augmented reality identification module carries out the reality scene picture
Target identification obtains recognition result；The recognition result is returned into webpage so that webpage according to the recognition result to webpage
The reality scene picture of upper displaying carries out augmented reality processing.
In one embodiment, the augmented reality identification module carries out target identification to the reality scene picture, obtains
Include to the step of recognition result：The augmented reality identification module obtains Model of Target Recognition, using the target identification mould
The target object in the reality scene picture is identified in type, obtains recognition result.
In one embodiment, the processor is additionally operable to execute following steps：The augmented reality identification module receives
Include the sample image of target object, the feature of the target object in the sample image is extracted；According to extraction
The feature establishes the Model of Target Recognition.
In one embodiment, the augmented reality identification module carries out target identification to the reality scene picture, obtains
Include to the step of recognition result：The augmented reality identification module to the clarity of real-time collected reality scene picture into
Row identification filters out the first object video frame that clarity is more than predetermined threshold value；By the first object video frame transmission to clothes
Business device returns and the first object so that the server identifies the first object object in the first object video frame
The corresponding first object identification model of object；According to the first object identification model to first in the reality scene picture
Target object is identified, and obtains recognition result.
In one embodiment, the processor is additionally operable to execute following steps：When recognizing the reality scene picture
When corresponding scene occurrence scene switches, then the video frame corresponding to the more new scene after scene switching, screening and institute are obtained
State the corresponding second target video frame of more new scene；The second target video frame is transmitted to server, so that the service
Device identifies the second target object in the second target video frame, returns to the second target corresponding with second target object
Identification model；The second target object in the reality scene picture is identified according to second Model of Target Recognition,
Obtain recognition result.
In one embodiment, the augmented reality identification module carries out target identification to the reality scene picture, obtains
Include to the step of recognition result：The clarity of real-time collected reality scene picture is identified, clarity is filtered out
More than the target video frame of predetermined threshold value；The target video frame is transmitted to server, so that described in server identification
Target object in reality scene picture, obtains recognition result；Receive the recognition result that the server returns.
In one embodiment, the recognition result is the location information of target object；It is described to return the recognition result
Back to webpage, so that webpage carries out at augmented reality the reality scene picture shown on webpage according to the recognition result
The step of reason includes：The location information of the target object is returned into webpage, so that the webpage is according to the target object
Location information determine the corresponding display location of virtual objects, according to the display location by the virtual objects and the target
Object is combined displaying.
In one embodiment, the computer equipment includes locally browsing serves kernel module, in the browsing service
Core module includes webpage real-time communication module and augmented reality identification module；It is described by the collected reality scene picture
Real-time exhibition is carried out on webpage, and replicates the augmented reality identification module that the reality scene picture passes to terminal local,
The augmented reality identification module carries out target identification to the reality scene picture, and the step of obtaining recognition result includes：Institute
Browsing serves kernel mould webpage real-time communication module in the block is stated to carry out the collected reality scene picture on webpage
Real-time exhibition, and replicate the reality scene picture and pass to the augmented reality identification module, the augmented reality identifies mould
Block carries out target identification to the reality scene picture, obtains recognition result, the recognition result is returned to webpage, so that net
Page carries out augmented reality processing according to the recognition result to the reality scene picture shown on webpage.
In one embodiment it is proposed that a kind of computer readable storage medium, is stored with computer program, the calculating
When machine program is executed by processor so that the processor executes following steps：The reality scene acquisition that webpage is initiated is received to ask
It asks, acquiring request call photographic device according to the reality scene acquires reality scene picture；By the collected real field
Scape picture carries out real-time exhibition on webpage, and replicate the reality scene picture pass to computer equipment local enhancing it is existing
Real identification module, the augmented reality identification module carry out target identification to the reality scene picture, obtain recognition result；It will
The recognition result returns to webpage so that webpage according to the recognition result to the reality scene picture that is shown on webpage
Carry out augmented reality processing.
In one embodiment, the augmented reality identification module carries out target identification to the reality scene picture, obtains
Include to the step of recognition result：The augmented reality identification module obtains Model of Target Recognition, using the target identification mould
The target object in the reality scene picture is identified in type, obtains recognition result.
In one embodiment, the processor is additionally operable to execute following steps：The augmented reality identification module receives
Include the sample image of target object, the feature of the target object in the sample image is extracted；According to extraction
The feature establishes the Model of Target Recognition.
In one embodiment, the augmented reality identification module carries out target identification to the reality scene picture, obtains
Include to the step of recognition result：The augmented reality identification module to the clarity of real-time collected reality scene picture into
Row identification filters out the first object video frame that clarity is more than predetermined threshold value；By the first object video frame transmission to clothes
Business device returns and the first object so that the server identifies the first object object in the first object video frame
The corresponding first object identification model of object；According to the first object identification model to first in the reality scene picture
Target object is identified, and obtains recognition result.
In one embodiment, the processor is additionally operable to execute following steps：When recognizing the reality scene picture
When corresponding scene occurrence scene switches, then the video frame corresponding to the more new scene after scene switching, screening and institute are obtained
State the corresponding second target video frame of more new scene；The second target video frame is transmitted to server, so that the service
Device identifies the second target object in the second target video frame, returns to the second target corresponding with second target object
Identification model；The second target object in the reality scene picture is identified according to second Model of Target Recognition,
Obtain recognition result.
In one embodiment, the augmented reality identification module carries out target identification to the reality scene picture, obtains
Include to the step of recognition result：The clarity of real-time collected reality scene picture is identified, clarity is filtered out
More than the target video frame of predetermined threshold value；The target video frame is transmitted to server, so that described in server identification
Target object in reality scene picture, obtains recognition result；Receive the recognition result that the server returns.
In one embodiment, the recognition result is the location information of target object；It is described to return the recognition result
Back to webpage, so that webpage carries out at augmented reality the reality scene picture shown on webpage according to the recognition result
The step of reason includes：The location information of the target object is returned into webpage, so that the webpage is according to the target object
Location information determine the corresponding display location of virtual objects, according to the display location by the virtual objects and the target
Object is combined displaying.
In one embodiment, the processor is additionally operable to execute following steps：The browsing serves kernel mould is in the block
The collected reality scene picture is carried out real-time exhibition by webpage real-time communication module on webpage, and replicates the reality
Scenic picture passes to the augmented reality identification module, and the augmented reality identification module carries out the reality scene picture
Target identification obtains recognition result, and the recognition result is returned to webpage so that webpage according to the recognition result to webpage
The reality scene picture of upper displaying carries out augmented reality processing.
One of ordinary skill in the art will appreciate that realizing all or part of flow in above-described embodiment method, being can be with
Relevant hardware is instructed to complete by computer program, the program can be stored in a non-volatile computer and can be read
In storage medium, the program is when being executed, it may include such as the flow of the embodiment of above-mentioned each method.Wherein, provided herein
Each embodiment used in any reference to memory, storage, database or other media, may each comprise non-volatile
And/or volatile memory.Nonvolatile memory may include that read-only memory (ROM), programming ROM (PROM), electricity can be compiled
Journey ROM (EPROM), electrically erasable ROM (EEPROM) or flash memory.Volatile memory may include random access memory
(RAM) or external cache.By way of illustration and not limitation, RAM is available in many forms, such as static state RAM
(SRAM), dynamic ram (DRAM), synchronous dram (SDRAM), double data rate sdram (DDRSDRAM), enhanced SDRAM
(ESDRAM), synchronization link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) directly RAM (RDRAM), straight
Connect memory bus dynamic ram (DRDRAM) and memory bus dynamic ram (RDRAM) etc..
Each technical characteristic of above example can be combined arbitrarily, to keep description succinct, not to above-described embodiment
In each technical characteristic it is all possible combination be all described, as long as however, the combination of these technical characteristics be not present lance
Shield is all considered to be the range of this specification record.
The several embodiments of the application above described embodiment only expresses, the description thereof is more specific and detailed, but simultaneously
Cannot the limitation to the application the scope of the claims therefore be interpreted as.It should be pointed out that for those of ordinary skill in the art
For, under the premise of not departing from the application design, various modifications and improvements can be made, these belong to the guarantor of the application
Protect range.Therefore, the protection domain of the application patent should be determined by the appended claims.
Claims (15)
1. a kind of implementation method of augmented reality, the method includes：
Terminal receives the reality scene acquisition request that webpage is initiated, and acquires request call photographic device according to the reality scene and adopts
Collect reality scene picture；
The collected reality scene picture is subjected to real-time exhibition on webpage, and replicates the reality scene picture and transmits
To the augmented reality identification module of terminal local, the augmented reality identification module carries out target knowledge to the reality scene picture
Not, recognition result is obtained；
The recognition result is returned into webpage so that webpage according to the recognition result to the real field that is shown on webpage
Scape picture carries out augmented reality processing.
2. according to the method described in claim 1, it is characterized in that, the augmented reality identification module draws the reality scene
Face carries out target identification, and the step of obtaining recognition result includes：
The augmented reality identification module obtains Model of Target Recognition, is drawn to the reality scene using the Model of Target Recognition
Target object in face is identified, and obtains recognition result.
3. according to the method described in claim 2, it is characterized in that, obtaining target identification mould in the augmented reality identification module
Further include before the step of type：
The augmented reality identification module reception includes the sample image of target object, to the target pair in the sample image
The feature of elephant extracts；
The Model of Target Recognition is established according to the feature of extraction.
4. according to the method described in claim 1, it is characterized in that, the augmented reality identification module draws the reality scene
Face carries out target identification, and the step of obtaining recognition result includes：
The clarity of real-time collected reality scene picture is identified in the augmented reality identification module, and it is clear to filter out
First object video frame of the degree more than predetermined threshold value；
By the first object video frame transmission to server, so that the server identifies in the first object video frame
First object object returns to first object identification model corresponding with the first object object；
The first object object in the reality scene picture is identified according to the first object identification model, is known
Other result.
5. according to the method described in claim 4, it is characterized in that, the method further includes：
When recognizing the scene occurrence scene switching corresponding to the reality scene picture, then the update after scene switching is obtained
Video frame corresponding to scene screens the second target video frame corresponding with the more new scene；
The second target video frame is transmitted to server, so that the server identifies in the second target video frame
Second target object returns to the second Model of Target Recognition corresponding with second target object；
The second target object in the reality scene picture is identified according to second Model of Target Recognition, is known
Other result.
6. according to the method described in claim 1, it is characterized in that, the augmented reality identification module draws the reality scene
Face carries out target identification, and the step of obtaining recognition result includes：
The clarity of real-time collected reality scene picture is identified, the target that clarity is more than predetermined threshold value is filtered out
Video frame；
The target video frame is transmitted to server, so that the server identifies the target pair in the reality scene picture
As obtaining recognition result；
Receive the recognition result that the server returns.
7. according to the method described in claim 1, it is characterized in that, the recognition result is the location information of target object；
It is described that the recognition result is returned into webpage, so that webpage is described existing to what is shown on webpage according to the recognition result
Real scenic picture carries out the step of augmented reality processing and includes：
The location information of the target object is returned into webpage, so that location information of the webpage according to the target object
It determines the corresponding display location of virtual objects, is tied the virtual objects and the target object according to the display location
Close displaying.
8. according to the method described in claim 1, it is characterized in that, the terminal local includes browsing serves kernel module, institute
It includes webpage real-time communication module and augmented reality identification module to state browsing serves kernel module；
It is described that the collected reality scene picture is subjected to real-time exhibition on webpage, and replicate the reality scene picture
The augmented reality identification module of terminal local is passed to, the augmented reality identification module carries out mesh to the reality scene picture
Mark is other, and the step of obtaining recognition result includes：
The browsing serves kernel mould webpage real-time communication module in the block is by the collected reality scene picture in webpage
Upper carry out real-time exhibition, and replicate the reality scene picture and pass to the augmented reality identification module；
The augmented reality identification module carries out target identification to the reality scene picture, recognition result is obtained, by the knowledge
Other result returns to webpage, so that webpage increases the reality scene picture shown on webpage according to the recognition result
Strong reality processing.
9. a kind of realization device of augmented reality, described device include：
Acquisition module, the reality scene for receiving webpage initiation acquire request, request call are acquired according to the reality scene
Photographic device acquires reality scene picture；
Transfer module for the collected reality scene picture to be carried out real-time exhibition on webpage, and replicates described existing
Real scenic picture passes to the augmented reality identification module of terminal local；
The augmented reality identification module is used to carry out target identification to the reality scene picture, obtains recognition result；
Return module, for the recognition result to be returned to webpage so that webpage according to the recognition result to being opened up on webpage
The reality scene picture shown carries out augmented reality processing.
10. device according to claim 9, which is characterized in that the augmented reality identification module is additionally operable to obtain target
Identification model is identified the target object in the reality scene picture using the Model of Target Recognition, is identified
As a result.
11. device according to claim 10, which is characterized in that the augmented reality identification module, which is additionally operable to receive, includes
The sample image for having target object extracts the feature of the target object in the sample image, according to extraction
Feature establishes the Model of Target Recognition.
12. a kind of realization system of augmented reality, the system comprises：
Terminal, the reality scene for receiving webpage initiation acquire request, and request call camera shooting is acquired according to the reality scene
Device acquires reality scene picture, the collected reality scene picture is carried out real-time exhibition on webpage, and replicate institute
The augmented reality identification module that reality scene picture passes to terminal local is stated, the augmented reality identification module to acquiring in real time
To the clarity of reality scene picture be identified, filter out the first object video frame that clarity is more than predetermined threshold value, will
The first object video frame transmission is to server；
Server, the first object object in the first object video frame, returns and the first object object for identification
Corresponding first object identification model；
The terminal is additionally operable to according to the first object identification model to the first object object in the reality scene picture
Be identified, obtain recognition result, the recognition result is returned into webpage so that webpage according to the recognition result to webpage
The reality scene picture of upper displaying carries out augmented reality processing.
13. system according to claim 12, which is characterized in that the terminal, which is additionally operable to work as, recognizes the reality scene
When scene occurrence scene corresponding to picture switches, then the video frame corresponding to the more new scene after scene switching is obtained, screened
The second target video frame is transmitted to server by the second target video frame corresponding with the more new scene；
The server is additionally operable to identify the second target object in the second target video frame, returns and second target
Corresponding second Model of Target Recognition of object；
The terminal is additionally operable to according to second Model of Target Recognition to the second target object in the reality scene picture
It is identified, obtains recognition result.
14. a kind of computer readable storage medium is stored with computer program, when the computer program is executed by processor,
So that the processor is executed such as the step of any one of claim 1 to 8 the method.
15. a kind of computer equipment, including memory and processor, the memory is stored with computer program, the calculating
When machine program is executed by the processor so that the processor executes the step such as any one of claim 1 to 8 the method
Suddenly.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810242139.5A CN108492352B (en) | 2018-03-22 | 2018-03-22 | Augmented reality implementation method, device, system, computer equipment and storage medium |
| PCT/CN2019/077781 WO2019179331A1 (en) | 2018-03-22 | 2019-03-12 | Augmented reality implementation method, apparatus and system, and computer device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810242139.5A CN108492352B (en) | 2018-03-22 | 2018-03-22 | Augmented reality implementation method, device, system, computer equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108492352A true CN108492352A (en) | 2018-09-04 |
| CN108492352B CN108492352B (en) | 2021-10-22 |
Family
ID=63319449
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810242139.5A Active CN108492352B (en) | 2018-03-22 | 2018-03-22 | Augmented reality implementation method, device, system, computer equipment and storage medium |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN108492352B (en) |
| WO (1) | WO2019179331A1 (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109561278A (en) * | 2018-09-21 | 2019-04-02 | 中建科技有限公司深圳分公司 | A kind of display system and method for augmented reality |
| CN109889814A (en) * | 2019-03-18 | 2019-06-14 | 罗叶迪 | On-fixed panoramic video wears primary real-time video live broadcasting method to virtual reality |
| CN110134532A (en) * | 2019-05-13 | 2019-08-16 | 浙江商汤科技开发有限公司 | A kind of information interacting method and device, electronic equipment and storage medium |
| CN110147288A (en) * | 2019-05-13 | 2019-08-20 | 浙江商汤科技开发有限公司 | Information interacting method and device, electronic equipment and storage medium |
| WO2019179331A1 (en) * | 2018-03-22 | 2019-09-26 | 腾讯科技（深圳）有限公司 | Augmented reality implementation method, apparatus and system, and computer device and storage medium |
| CN110553714A (en) * | 2019-08-31 | 2019-12-10 | 深圳市广宁股份有限公司 | Intelligent vibration augmented reality testing method and related product |
| CN112330816A (en) * | 2020-10-19 | 2021-02-05 | 杭州易现先进科技有限公司 | AR identification processing method and device and electronic device |
| WO2022057566A1 (en) * | 2020-09-21 | 2022-03-24 | 奇噢创新有限公司 | Method and system for distributing augmented reality content, and computer-readable storage medium |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112712098A (en) * | 2019-10-25 | 2021-04-27 | 北京四维图新科技股份有限公司 | Image data processing method and device |
| CN111986333A (en) * | 2020-09-01 | 2020-11-24 | Oppo广东移动通信有限公司 | Image generation method and device based on augmented reality, terminal and storage medium |
| CN112577488B (en) * | 2020-11-24 | 2022-09-02 | 腾讯科技（深圳）有限公司 | Navigation route determining method, navigation route determining device, computer equipment and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106937531A (en) * | 2014-06-14 | 2017-07-07 | 奇跃公司 | Method and system for producing virtual and augmented reality |
| CN107222529A (en) * | 2017-05-22 | 2017-09-29 | 北京邮电大学 | Augmented reality processing method, WEB modules, terminal and cloud server |
| CN107316035A (en) * | 2017-08-07 | 2017-11-03 | 北京中星微电子有限公司 | Object identifying method and device based on deep learning neutral net |
| CN107480587A (en) * | 2017-07-06 | 2017-12-15 | 阿里巴巴集团控股有限公司 | A kind of method and device of model configuration and image recognition |
| CN107609051A (en) * | 2017-08-22 | 2018-01-19 | 阿里巴巴集团控股有限公司 | A kind of image rendering method, device and electronic equipment |
| US20180070019A1 (en) * | 2016-09-06 | 2018-03-08 | Thomson Licensing | Methods, devices and systems for automatic zoom when playing an augmented scene |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160180594A1 (en) * | 2014-12-22 | 2016-06-23 | Hand Held Products, Inc. | Augmented display and user input device |
| CN107085868A (en) * | 2017-04-27 | 2017-08-22 | 腾讯科技（深圳）有限公司 | image drawing method and device |
| CN107608649A (en) * | 2017-11-02 | 2018-01-19 | 泉州创景视迅数字科技有限公司 | A kind of AR augmented realities intelligent image identification displaying content system and application method |
| CN108492352B (en) * | 2018-03-22 | 2021-10-22 | 腾讯科技（深圳）有限公司 | Augmented reality implementation method, device, system, computer equipment and storage medium |
-
2018
- 2018-03-22 CN CN201810242139.5A patent/CN108492352B/en active Active
-
2019
- 2019-03-12 WO PCT/CN2019/077781 patent/WO2019179331A1/en active Application Filing
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106937531A (en) * | 2014-06-14 | 2017-07-07 | 奇跃公司 | Method and system for producing virtual and augmented reality |
| US20180070019A1 (en) * | 2016-09-06 | 2018-03-08 | Thomson Licensing | Methods, devices and systems for automatic zoom when playing an augmented scene |
| CN107222529A (en) * | 2017-05-22 | 2017-09-29 | 北京邮电大学 | Augmented reality processing method, WEB modules, terminal and cloud server |
| CN107480587A (en) * | 2017-07-06 | 2017-12-15 | 阿里巴巴集团控股有限公司 | A kind of method and device of model configuration and image recognition |
| CN107316035A (en) * | 2017-08-07 | 2017-11-03 | 北京中星微电子有限公司 | Object identifying method and device based on deep learning neutral net |
| CN107609051A (en) * | 2017-08-22 | 2018-01-19 | 阿里巴巴集团控股有限公司 | A kind of image rendering method, device and electronic equipment |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019179331A1 (en) * | 2018-03-22 | 2019-09-26 | 腾讯科技（深圳）有限公司 | Augmented reality implementation method, apparatus and system, and computer device and storage medium |
| CN109561278A (en) * | 2018-09-21 | 2019-04-02 | 中建科技有限公司深圳分公司 | A kind of display system and method for augmented reality |
| CN109561278B (en) * | 2018-09-21 | 2020-12-29 | 中建科技有限公司深圳分公司 | Augmented reality display system and method |
| CN109889814A (en) * | 2019-03-18 | 2019-06-14 | 罗叶迪 | On-fixed panoramic video wears primary real-time video live broadcasting method to virtual reality |
| CN110134532A (en) * | 2019-05-13 | 2019-08-16 | 浙江商汤科技开发有限公司 | A kind of information interacting method and device, electronic equipment and storage medium |
| CN110147288A (en) * | 2019-05-13 | 2019-08-20 | 浙江商汤科技开发有限公司 | Information interacting method and device, electronic equipment and storage medium |
| CN110553714A (en) * | 2019-08-31 | 2019-12-10 | 深圳市广宁股份有限公司 | Intelligent vibration augmented reality testing method and related product |
| WO2022057566A1 (en) * | 2020-09-21 | 2022-03-24 | 奇噢创新有限公司 | Method and system for distributing augmented reality content, and computer-readable storage medium |
| GB2612244A (en) * | 2020-09-21 | 2023-04-26 | Creote Studio Ltd | Method and system for distributing augmented reality content and computer- readable storage medium |
| CN112330816A (en) * | 2020-10-19 | 2021-02-05 | 杭州易现先进科技有限公司 | AR identification processing method and device and electronic device |
| CN112330816B (en) * | 2020-10-19 | 2024-03-26 | 杭州易现先进科技有限公司 | AR identification processing method and device and electronic device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108492352B (en) | 2021-10-22 |
| WO2019179331A1 (en) | 2019-09-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108492352A (en) | Implementation method, device, system, computer equipment and the storage medium of augmented reality | |
| US11079841B2 (en) | Enabling augmented reality using eye gaze tracking | |
| CN107204031B (en) | Information display method and device | |
| US10896518B2 (en) | Image processing method, image processing apparatus and computer readable storage medium | |
| Wang et al. | PISA: Pixelwise image saliency by aggregating complementary appearance contrast measures with edge-preserving coherence | |
| Chen et al. | A Siamese network based U-Net for change detection in high resolution remote sensing images | |
| Johnston et al. | A review of digital video tampering: From simple editing to full synthesis | |
| CN107222529A (en) | Augmented reality processing method, WEB modules, terminal and cloud server | |
| CN110309876A (en) | Object detection method, device, computer readable storage medium and computer equipment | |
| CN106384388B (en) | The real-time try-in method of internet glasses and system based on HTML5 and augmented reality | |
| CN113076685A (en) | Training method of image reconstruction model, image reconstruction method and device thereof | |
| AU2013273829A1 (en) | Time constrained augmented reality | |
| Hu et al. | Sherf: Generalizable human nerf from a single image | |
| CN105354231A (en) | Image selection method and apparatus, and image processing method and apparatus | |
| CN113269858A (en) | Virtual scene rendering method and device, computer equipment and storage medium | |
| CN107920202A (en) | Method for processing video frequency, device and electronic equipment based on augmented reality | |
| Fieraru et al. | REMIPS: Physically consistent 3D reconstruction of multiple interacting people under weak supervision | |
| CN109035287A (en) | Foreground image extraction method and device, moving vehicle recognition methods and device | |
| CN110517186A (en) | Eliminate method, apparatus, storage medium and the computer equipment of invoice seal | |
| Ji et al. | Geometry-aware single-image full-body human relighting | |
| Hu et al. | Texture-enhanced light field super-resolution with spatio-angular decomposition kernels | |
| CN106101578A (en) | Image combining method and equipment | |
| Wang et al. | Supervised video-to-video synthesis for single human pose transfer | |
| KR101910931B1 (en) | Method for providing 3d ar contents service on food using 64bit-identifier | |
| Huo et al. | Small object detection for birds with Swin transformer |
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 |