CN110458052A - Recongnition of objects method, apparatus based on augmented reality, equipment, medium - Google Patents
Recongnition of objects method, apparatus based on augmented reality, equipment, medium Download PDFInfo
- Publication number
- CN110458052A CN110458052A CN201910678874.5A CN201910678874A CN110458052A CN 110458052 A CN110458052 A CN 110458052A CN 201910678874 A CN201910678874 A CN 201910678874A CN 110458052 A CN110458052 A CN 110458052A
- Authority
- CN
- China
- Prior art keywords
- augmented reality
- feature
- target object
- recongnition
- objects
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/46—Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]; Salient regional features
- G06V10/462—Salient features, e.g. scale invariant feature transforms [SIFT]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/20—Scenes; Scene-specific elements in augmented reality scenes
Abstract
The recongnition of objects method and device that the disclosure is directed to a kind of based on augmented reality, electronic equipment, storage medium, it is related to augmented reality field, this method comprises: obtaining the first kind feature of multiple objects within the vision by augmented reality equipment, and object to be selected is determined according to the first kind feature；The Second Type feature of Second Type feature and target object to the object to be selected is compared to obtain comparing result；If determining that the object to be selected is the target object according to the comparing result, the information of the target object is sent to terminal, and execute prompt operation.The disclosure can accurately identify target object, improve recognition efficiency and accuracy rate, increase operation convenience.
Description
Technical field
This disclosure relates to augmented reality field, in particular to a kind of recongnition of objects side of augmented reality
Recongnition of objects device, electronic equipment and the computer readable storage medium of method, augmented reality.
Background technique
The masses can assist the personage of police's searching specific type.In the related technology, the masses find special in the auxiliary police
When the personage of type, general photo and other identity informations by that will issue, that sees with itself is compared, thus really
Whether recognize is the personage for needing to find.In aforesaid way, since the personage that the masses remember inaccuracy either specific type passes through
Camouflage may cause the problem of leakage identification and identification inaccuracy, and lower by the efficiency that manual type is identified.Separately
Outside, if it find that the personage of specific type, alarm either notify household when, need to make a phone call manually, it is time-consuming
It is longer, inconvenient, and the safety of the masses can not be protected.
It should be noted that information is only used for reinforcing the reason to the background of the disclosure disclosed in above-mentioned background technology part
Solution, therefore may include the information not constituted to the prior art known to persons of ordinary skill in the art.
Summary of the invention
The disclosure be designed to provide a kind of recongnition of objects method and device based on augmented reality, electronics is set
Standby, storage medium, and then recognition result caused by the limitation and defect due to the relevant technologies is overcome at least to a certain extent
The problem of inaccuracy.
Other characteristics and advantages of the disclosure will be apparent from by the following detailed description, or partially by the disclosure
Practice and acquistion.
According to one aspect of the disclosure, a kind of recongnition of objects method based on augmented reality is provided, comprising: logical
The first kind feature that augmented reality equipment obtains multiple objects within the vision is crossed, and true according to the first kind feature
Fixed object to be selected；The Second Type feature of Second Type feature and target object to the object to be selected is compared to obtain
Comparing result；If determining that the object to be selected is the target object according to the comparing result, by the target object
Information is sent to terminal, and executes prompt operation.
In a kind of exemplary embodiment of the disclosure, obtained by augmented reality equipment within the vision multiple
The first kind feature of object, and determine that object to be selected includes: to set by the augmented reality according to the first kind feature
Camera in standby, the image of the within the vision the multiple object of the acquisition in the augmented reality equipment；From
The first kind feature is extracted in described image, the first kind feature includes facial characteristics；By the multiple object
The first kind feature is matched with the first kind feature of the target object, to determine matching result；By institute
Stating matching result is the corresponding object of the first kind feature of successful match as the object to be selected.
In a kind of exemplary embodiment of the disclosure, by the first kind feature of the multiple object and the mesh
The first kind feature of mark object is matched, to determine that matching result includes: calculate the multiple object described the
Similarity between one type feature and the first kind feature of the target object；If the similarity meets threshold value item
Part, it is determined that the matching result is successful match.
In a kind of exemplary embodiment of the disclosure, when determining the object to be selected, the method also includes: to institute
It states object to be selected to conduct the locking operations, and the prompt information for reminding object to be selected is provided.
In a kind of exemplary embodiment of the disclosure, determine that the object to be selected is the mesh according to the comparing result
If mark object includes: that the Second Type feature of the object to be selected is consistent with the Second Type feature of the target object, really
The fixed object to be selected is the target object；If the second of the Second Type feature of the object to be selected and the target object
Type feature is inconsistent, it is determined that the object to be selected is not belonging to the target object.
In a kind of exemplary embodiment of the disclosure, it includes: by institute that the information of the target object, which is sent to terminal,
The information for stating field range corresponding to the location information and the target object of target object is sent to the terminal.
In a kind of exemplary embodiment of the disclosure, executing prompt operation includes: in response to setting to the augmented reality
Standby trigger action, executes the prompt operation, and the prompt operation includes quick alarm operation and/or quick notice operation.
According to one aspect of the disclosure, a kind of recongnition of objects device based on augmented reality is provided, comprising: to be selected
Object determining module, for obtaining the first kind feature of multiple objects within the vision, and root by augmented reality equipment
Object to be selected is determined according to the first kind feature；Characteristic Contrast module, for the Second Type feature to the object to be selected
It compares with the Second Type feature of target object to obtain comparing result；Target determination module, if for according to described right
It determines that the object to be selected is the target object than result, then the information of the target object is sent to terminal, and execute
Prompt operation.
According to one aspect of the disclosure, a kind of electronic equipment is provided, comprising: processor；And memory, for storing
The executable instruction of the processor；Wherein, the processor is configured to above-mentioned to execute via the executable instruction is executed
Recongnition of objects method described in any one based on augmented reality.
According to one aspect of the disclosure, a kind of computer readable storage medium is provided, computer program is stored thereon with,
The computer program realizes the recongnition of objects described in above-mentioned any one based on augmented reality when being executed by processor
Method.
The recongnition of objects method based on augmented reality that is there is provided in disclosure exemplary embodiment, based on augmented reality
Recongnition of objects device, in electronic equipment and computer readable storage medium, acquired by augmented reality equipment
One type feature determines object to be selected, and determines target object according to Second Type feature in object to be selected.On the one hand, due to
Object to be selected can be determined according to the first kind feature of augmented reality equipment multiple objects within the vision, and according to second
Type feature determines target object from object to be selected, can pass through first kind feature and Second Type feature screen simultaneously from
And determine whether some object to be selected is target object, since first kind feature and Second Type feature can accurately comprehensively
Ground reflects the feature of object, and have passed through two layers of screening and judgement, therefore avoids and only manually known roughly according to photo
Other limitation improves the comprehensive and accuracy of identification.On the other hand, augmented reality equipment can be automatically according to the first kind
Type feature and Second Type feature judge whether it is target object, without manually performing any operation, improve identification
Efficiency.In another aspect, improving prompt operation due to that the information of target object can be sent to terminal to carry out prompt operation
Convenience, and can guarantee the safety of user.
It should be understood that above general description and following detailed description be only it is exemplary and explanatory, not
The disclosure can be limited.
Detailed description of the invention
The drawings herein are incorporated into the specification and forms part of this specification, and shows the implementation for meeting the disclosure
Example, and together with specification for explaining the principles of this disclosure.It should be evident that the accompanying drawings in the following description is only the disclosure
Some embodiments for those of ordinary skill in the art without creative efforts, can also basis
These attached drawings obtain other attached drawings.
Fig. 1 shows a kind of system of recongnition of objects method based on augmented reality using the present exemplary embodiment
Architecture diagram.
Fig. 2 schematically shows a kind of recongnition of objects method based on augmented reality in disclosure exemplary embodiment
Schematic diagram.
Fig. 3 schematically shows the schematic diagram that object to be selected is determined in disclosure exemplary embodiment.
Fig. 4 schematically shows the schematic diagram that matching result is determined in disclosure exemplary embodiment.
Fig. 5 schematically shows the frame of the recongnition of objects device in disclosure exemplary embodiment based on augmented reality
Figure.
Fig. 6 schematically shows the block diagram of a kind of electronic equipment in disclosure exemplary embodiment.
Specific embodiment
Example embodiment is described more fully with reference to the drawings.However, example embodiment can be with a variety of shapes
Formula is implemented, and is not understood as limited to example set forth herein；On the contrary, thesing embodiments are provided so that the disclosure will more
Fully and completely, and by the design of example embodiment comprehensively it is communicated to those skilled in the art.Described feature, knot
Structure or characteristic can be incorporated in any suitable manner in one or more embodiments.In the following description, it provides perhaps
More details fully understand embodiment of the present disclosure to provide.It will be appreciated, however, by one skilled in the art that can
It is omitted with technical solution of the disclosure one or more in the specific detail, or others side can be used
Method, constituent element, device, step etc..In other cases, be not shown in detail or describe known solution to avoid a presumptuous guest usurps the role of the host and
So that all aspects of this disclosure thicken.
In addition, attached drawing is only the schematic illustrations of the disclosure, it is not necessarily drawn to scale.Identical attached drawing mark in figure
Note indicates same or similar part, thus will omit repetition thereof.Some block diagrams shown in the drawings are function
Energy entity, not necessarily must be corresponding with physically or logically independent entity.These function can be realized using software form
Energy entity, or these functional entitys are realized in one or more hardware modules or integrated circuit, or at heterogeneous networks and/or place
These functional entitys are realized in reason device device and/or microcontroller device.
Fig. 1 show can using the present exemplary embodiment a kind of recongnition of objects method based on augmented reality and
The schematic diagram of the system architecture of the exemplary context of use of device.
As shown in Figure 1, system architecture 100 may include one or more of equipment 101,102,103,104 He of network
Server 105 and terminal 106.Network 104 is logical to provide between equipment 101,102,103 and server 105 and terminal 106
Believe the medium of link.Network 104 may include various connection types, such as wired, wireless communication link or fiber optic cables etc.
Deng.Equipment 101,102,103 can be various augmented reality equipment (such as augmented reality glasses and the augmented reality helmet etc.)
Can either acquire with the terminal device of contrast characteristic etc..It should be understood that the number of equipment, network and server in Fig. 1
Mesh is only schematical.According to needs are realized, any number of equipment, network and server can have.Such as server
105 can be the server cluster etc. of multiple server compositions.Terminal 106 can for receive information terminal, such as computer or
Person is mobile phone etc..
In the present exemplary embodiment, the feature of 101,102,103 pairs of multiple objects within the vision of equipment is extracted,
And compare the feature of target object present in database, obtain target object；Server 105 receive equipment 101,
102, after the information of 103 target objects sent, it can be forwarded to terminal 106, and can be according to the information of target object
Carry out the subsequent processings such as responding.Terminal 106 can receive the information of target object, and carry out subsequent processing.
Recongnition of objects method provided by the present exemplary embodiment is generally executed by equipment 101,102,103, but this
Field technical staff is it is easily understood that recongnition of objects method provided by the present exemplary embodiment can also be by server
It executes, does not do particular determination to this herein.
A kind of recongnition of objects method based on augmented reality is provided firstly in the present exemplary embodiment, can be applied
In the target scene that the special personnels such as suspicion personnel, missing crew are identified and found.With reference to shown in Fig. 2, the party
Method includes step S210, step S220 and step S230, in which:
In step S210, the first kind feature of multiple objects within the vision is obtained by augmented reality equipment,
And object to be selected is determined according to the first kind feature；
In step S220, the Second Type feature of Second Type feature and target object to the object to be selected is carried out
Comparison is to obtain comparing result；
In step S230, if determining that the object to be selected is the target object according to the comparing result, by institute
The information for stating target object is sent to terminal, and executes prompt operation.
In the recongnition of objects method based on augmented reality provided in disclosure exemplary embodiment, on the one hand, by
In can determine object to be selected according to the first kind feature of augmented reality equipment multiple objects within the vision, and according to
Two type features determine target object from object to be selected, can be screened simultaneously by first kind feature and Second Type feature
So that it is determined that whether some object to be selected is target object, since first kind feature and Second Type feature can be accurately complete
Reflect to face the feature of object, and have passed through two layers of screening and judgement, therefore avoids and only manually carried out according to photo roughly
The limitation of identification improves the comprehensive and accuracy of identification.On the other hand, augmented reality equipment can be automatically according to first
Type feature and Second Type feature judge whether it is target object, without manually performing any operation, improve identification
Efficiency.In another aspect, improving operation due to that the information of target object can be sent to terminal to carry out prompt operation
Convenience, and can guarantee the safety of user.
Next, the recongnition of objects method in the present exemplary embodiment is specifically described with reference to attached drawing.
In step S210, the first kind feature of multiple objects within the vision is obtained by augmented reality equipment,
And object to be selected is determined according to the first kind feature.
In the present exemplary embodiment, augmented reality equipment can be augmented reality glasses, the augmented reality helmet etc., can also
Think the terminal for being equipped with the application program of augmented reality class, is said by taking augmented reality glasses as an example in the present exemplary embodiment
It is bright.Augmented reality glasses can be monocular AR (Augmented Reality, augmented reality) intelligent glasses or binocular AR Brilliant Eyes
Mirror specifically may include but be not limited to head-mounted display, built-in camera, sensor, controller, touch sensor and key etc.
Deng.Augmented reality equipment is worn on eye locations by user, checks ambient enviroment by the augmented reality equipment.Augmented reality is set
Standby field range refers to the field range that eyes of user can be seen, and can be become according to the variation of the position of user
Change.The field range of augmented reality equipment can be the angular range of the equipment in the horizontal and vertical directions.Specifically,
Obtain azimuth and the pitch angle of the augmented reality equipment；According to the azimuth of the augmented reality equipment, the augmented reality is determined
Angular range in the horizontal direction of equipment；According to the pitch angle of the augmented reality equipment, the vertical of augmented reality equipment is determined
Angular range on direction；The angular range of horizontal direction and vertical direction is determined as to the visual field model of the augmented reality equipment
It encloses.
Multiple objects can be all objects within the vision of augmented reality equipment, such as can be all persons.
Multiple objects may be with the part personage of target object the same category (such as target object be children when, multiple objects can
Think children within the vision), to reduce calculation amount.First kind feature for example can for multiple objects facial characteristics or
Person is eye feature etc., this is illustrated for sentencing facial characteristics.Further, after obtaining first kind feature,
The first kind feature of multiple objects can be compared one by one with the target object in database, in order to accurately determine
Object to be selected.Wherein, object to be selected can be the either multiple and target object of one in multiple objects within the vision
Association either similar object.
It should be noted that the police can build the database entry of target object first or the glasses device side AR is built
The database entry of target object.Further, the police upload the characteristic of target object or family members upload target object
Characteristic, in order to which augmented reality equipment determines object to be selected.Characteristic herein includes but is not limited to the first kind
Feature and Second Type feature.
The flow chart for determining object to be selected is diagrammatically illustrated in Fig. 3, mainly includes step S310 with reference to shown in Fig. 3
To step S340, and step S310 is the specific implementation of step S210 to step S340, in which:
In step s310, by the camera in the augmented reality equipment, acquisition is in the augmented reality equipment
The multiple object within the vision image.
In the present exemplary embodiment, camera can be set in augmented reality equipment, set for acquiring in augmented reality
The image of standby multiple objects within the vision.Image herein can be single image, or video, as long as packet
Containing multiple objects.It should be noted that augmented reality equipment can be with the image of the multiple objects of automatic collection to improve in time
Property；It can also only acquire when receiving and taking pictures trigger action to reduce power consumption, be not particularly limited herein.Take pictures triggering behaviour
Making can be for for triggering sound taken pictures either gesture etc..
In step s 320, the first kind feature is extracted from described image, the first kind feature includes face
Portion's feature.
In the present exemplary embodiment, after collecting image, the feature of image can extract.Specifically, can be by appointing
Suitable machine learning model of anticipating either deep learning model carries out feature extraction to the image of multiple objects, each to obtain
The first kind feature of image.Wherein, machine learning model includes but is not limited to CNN convolutional neural networks, VGG neural network etc.
Deng.The feature of image can indicate with feature vector, therefore, the output result of machine learning model be image feature to
Amount.For example, trained machine learning model can be inputted the image 1 of object 1, with export the feature vector of the image 1 be to
Measure A.By machine learning model, more accurate feature vector can be obtained, to obtain more accurate recognition result.It needs to mend
Fill, can also extract the facial characteristics of target object in database, for example, target object 0 facial characteristics feature vector
It can be vector M, and the two can be extracted by identical algorithm or model, to guarantee accuracy.
In step S330, by the first kind feature of the multiple object and described the first of the target object
Type feature is matched, to determine matching result.
In the present exemplary embodiment, matching result may include successful match and it fails to match two kinds of situations.With reference in Fig. 4
Shown, the specific implementation of step S330 may include step S410 and step S420, in which:
In step S410, obtain the multiple object the first kind feature and the target object described the
Similarity between one type feature；
In the step s 420, if the similarity meets threshold condition, it is determined that the matching result is successful match.
In the present exemplary embodiment, mesh in the corresponding feature vector of each collected image and database can be calculated
Mark the similarity between the corresponding feature vector of object.It specifically, can be corresponding according to each image of distance calculation formula calculating
Characteristic distance between the feature vector of facial characteristics and the feature vector of the facial characteristics for indicating target object, Jin Ergen
The similarity between the facial characteristics of each image and the facial characteristics of target object is determined according to characteristic distance.Wherein, feature away from
From can include but is not limited to Euclidean distance, COS distance, mahalanobis distance etc., this is illustrated for sentencing Euclidean distance.
Specifically, similarity and Euclidean distance are negatively correlated, i.e., Euclidean distance is bigger, and similarity is smaller；Euclidean distance is smaller, and similarity is got over
Greatly.In order to realize the accurate screening to multiple objects, can be provided in advance one for indicate multiple objects and target object it
Between whether similar threshold condition, the threshold condition can for similarity be greater than or equal to similarity threshold set in advance.For
Raising accuracy, similarity threshold herein can be biggish numerical value, such as 0.8 or 0.9 etc..When multiple
Similarity between the feature vector of the image of one of object and the feature vector of target object, which is greater than, is either equal to 0.8
When, it is believed that the two successful match.When the similarity between the feature vector of image and the feature vector of target object is less than
When 0.8, it is believed that it fails to match for the two.For example, the spy of the facial characteristics of the feature vector A and target object 0 of object 1
Levying the similarity between vector M is 0.9, then it is assumed that object 1 is similar to target object 0.By this method, it can be determined that multiple
Whether object is similar to target object.If some object is similar to target object, matching result is successful match；If some is right
As dissimilar with target object, then matching result is that it fails to match.
In step S340, using the matching result be successful match the corresponding object of the first kind feature as
The object to be selected.
In the present exemplary embodiment, on the basis of step S330, it can filter out and the facial characteristics of target object
The similar feature vector of feature vector, and then corresponding image object corresponding with the image is obtained according to these feature vectors,
And using these objects as the object to be selected chosen roughly.For example, the feature vector of object 1 and target object 0
Feature vector is similar, then it is assumed that object 1 and 0 successful match of target object can regard object 1 as object to be selected at this time.
Technical solution in Fig. 3, can be according to comparison first kind feature to the within the vision of augmented reality equipment
Multiple objects are screened, and obtain object more similar with target object as object to be selected, in order to from object to be selected
Continue to select, improves the accuracy of Object identifying and screening.
It, can be in order to improve identification and find the focus of target object you need to add is that after determining object to be selected
It conducts the locking operations, and is provided for reminding the prompt information for getting object to be selected to obtained object to be selected.Lock operation
It can be marking operation, such as be marked by additional character etc..By lock operation, the model of subsequent search can be reduced
It encloses, reduces interference and calculation amount, increase convenience, and make result more acurrate.Prompt information can be for example written form
The information etc. of information either form of sound, the information of written form can be shown in locating for user by augmented reality equipment
Real scene in.
With continued reference to shown in Fig. 2, in step S220, Second Type feature and target object to the object to be selected
Second Type feature is compared to obtain comparing result.
In the present exemplary embodiment, Second Type is characterized in the other types information different from first kind feature, can be with
Photo, physical trait, historical archives, identity information, age of object and target object including but not limited to be selected etc. believe in detail
Breath.Target object includes but is not limited to either other personnel for needing to find of suspicion personnel, missing crew etc..
It specifically, can be using by the of the target object in the Second Type feature of each object to be selected and database
Two type features are compared one by one, to judge whether consistent.Wherein it is possible to judge two by the methods of machine learning model
Whether the photo of person is consistent with physical trait.At the same time, it can also be transferred by the passport NO. of object to be selected to believe in detail
Whether breath, the details to judge object to be selected are identical as the details of target object.
With continued reference to shown in Fig. 2, in step S230, if determining the object to be selected for institute according to the comparing result
Target object is stated, then the information of the target object is sent to terminal, and execute prompt operation.
In the present exemplary embodiment, on the basis of step S220, if all in the Second Type feature of object to be selected
Information is consistent with all information of Second Type feature of target object, it is determined that the object to be selected is target object.If to be selected
The information of the Second Type feature of at least one information and target object in the Second Type feature of object is inconsistent, it is determined that
Object to be selected is not target object.For example, object 1 is similar to the facial characteristics of target object 0, then can make object 1
For object to be selected；Object 1 is consistent with the Second Type feature of target object 0, then object 1 seeks to the target object 0 found.It is right
As 2 similar to the facial characteristics of target object 0, then object 2 can be regard as object to be selected；The second of object 2 and target object 0
Type feature is inconsistent, then object 2 is not meant to the target object 0 found.It should be noted that a target object finally matches
Determining object only one.Based on this, available accurate recognition result.
On this basis, according to first kind feature and Second Type feature from the within the vision of augmented reality equipment
After determining the target object to be found in multiple objects, the information of target object can be sent to terminal.End herein
End for example can be the terminal of the information of upload target object, such as police's terminal either family members' terminal.
Wherein, by the information of the target object be sent to terminal include: by the location information of the target object and
Field range corresponding to the target object is sent to the terminal.Specifically, after determining target object, augmented reality
Equipment can be by GPS (Global Positioning System, global positioning system) module for being arranged thereon to target object
It carries out positioning in real time and obtains its location information.It further, can will be where the location information and target object of target object
Information within the vision is sent to terminal.Information within the vision where target object can be for example ambient enviroment
Details.By the way that location information and information within the vision are sent to terminal, the police can be assisted to be handled.
Under the scene of the present exemplary embodiment, prompt operation can include but is not limited to quick alarm operation and/or fast
Victory notice operation.Wherein, quick alarm operation refers to key alarm operation, such as sends warning message to the police and either beat
Phone.Quick notice operation refers to sending notification information to family members' terminal of target object.It is suspicion personnel in target object
When, triggering quick alarm operation.When target object is missing crew, the operation of triggering quick alarm and/or quick notice operation.
Specifically, the prompt operation can be executed in response to the trigger action to augmented reality equipment.Trigger action can be for report
Alert key and the pressing operation for notifying key；Or different gesture operations, such as the gesture of triggering quick alarm operation
To shake the hand, triggering fast notifies the gesture of operation to clench fist etc., as long as being different gesture.Trigger action can also be
Other are suitably operated, and are not particularly limited herein.It is quick by being executed in response to trigger action after determining target object
The mode of operation, avoid user alarm either notify when, need to make a phone call either operating terminal manually
Problem reduces time-consuming, improves convenience.In addition, entirely to the recognition and verification process of target object and prompt operation process
It is very hidden rapid, user will not be exposed, so as to protect the safety of user.
In the present exemplary embodiment, a kind of recongnition of objects device based on augmented reality is additionally provided, with reference in Fig. 4
Shown, which mainly comprises the following modules:
Object determining module 401 to be selected, for obtaining the of multiple objects within the vision by augmented reality equipment
One type feature, and object to be selected is determined according to the first kind feature；
Characteristic Contrast module 402, the Second Type for Second Type feature and target object to the object to be selected
Feature is compared to obtain comparing result；
Target determination module 403, if for determining that the object to be selected is the target object according to the comparing result,
The information of the target object is then sent to terminal, and executes prompt operation.
In a kind of exemplary embodiment of the disclosure, object determining module to be selected includes: image capture module, for leading to
The camera in the augmented reality equipment is crossed, acquisition is described within the vision described more in the augmented reality equipment
The image of a object；Fisrt feature extraction module, for extracting the first kind feature, the first kind from described image
Type feature includes facial characteristics；Characteristic matching module, for by the first kind feature of the multiple object and the mesh
The first kind feature of mark object is matched, to determine matching result；Object determining module, for tying the matching
Fruit is the corresponding object of the first kind feature of successful match as the object to be selected.
In a kind of exemplary embodiment of the disclosure, characteristic matching module includes: that similarity obtains module, for obtaining
Similarity between the first kind feature of the multiple object and the first kind feature of the target object；
With control module, if meeting threshold condition for the similarity, it is determined that the matching result is successful match.
In a kind of exemplary embodiment of the disclosure, when determining the object to be selected, described device further include: prompt
Module for conducting the locking operations to the object to be selected, and provides the prompt information for reminding object to be selected.
In a kind of exemplary embodiment of the disclosure, target determination module includes: the first determining module, if for described
The Second Type feature of object to be selected and the Second Type feature of the target object are consistent, it is determined that the object to be selected is institute
State target object；Second determining module, if the Second Type feature and the second of the target object for the object to be selected
Type feature is inconsistent, it is determined that the object to be selected is not belonging to the target object.
In a kind of exemplary embodiment of the disclosure, target determination module includes: information sending module, and being used for will be described
The information of field range corresponding to the location information of target object and the target object is sent to the terminal.
In a kind of exemplary embodiment of the disclosure, target determination module includes: prompt operation control module, for ringing
Ying Yu executes the prompt operation to the trigger action of the augmented reality equipment, and the prompt operation includes quick alarm behaviour
Make and/or quick notice operates.
It should be noted that the detail of each module has been in the above-mentioned recongnition of objects device based on augmented reality
It is described in detail in the corresponding recongnition of objects method based on augmented reality, therefore details are not described herein again.
It should be noted that although being referred to several modules or list for acting the equipment executed in the above detailed description
Member, but this division is not enforceable.In fact, according to embodiment of the present disclosure, it is above-described two or more
Module or the feature and function of unit can embody in a module or unit.Conversely, an above-described mould
The feature and function of block or unit can be to be embodied by multiple modules or unit with further division.
In addition, although describing each step of method in the disclosure in the accompanying drawings with particular order, this does not really want
These steps must be executed in this particular order by asking or implying, or having to carry out step shown in whole could realize
Desired result.Additional or alternative, it is convenient to omit multiple steps are merged into a step and executed by certain steps, and/
Or a step is decomposed into execution of multiple steps etc..
In an exemplary embodiment of the disclosure, a kind of electronic equipment that can be realized the above method is additionally provided.
Person of ordinary skill in the field it is understood that various aspects of the invention can be implemented as system, method or
Program product.Therefore, various aspects of the invention can be embodied in the following forms, it may be assumed that complete hardware embodiment, complete
The embodiment combined in terms of full Software Implementation (including firmware, microcode etc.) or hardware and software, can unite here
Referred to as circuit, " module " or " system ".
The electronic equipment 600 of this embodiment according to the present invention is described referring to Fig. 6.The electronics that Fig. 6 is shown
Equipment 600 is only an example, should not function to the embodiment of the present invention and use scope bring any restrictions.
As shown in fig. 6, electronic equipment 600 is showed in the form of universal computing device.The component of electronic equipment 600 can wrap
It includes but is not limited to: at least one above-mentioned processing unit 610, at least one above-mentioned storage unit 620, the different system components of connection
The bus 650 of (including storage unit 620 and processing unit 610).
Wherein, the storage unit is stored with program code, and said program code can be held by the processing unit 610
Row, so that various according to the present invention described in the execution of the processing unit 610 above-mentioned " illustrative methods " part of this specification
The step of illustrative embodiments.For example, the processing unit 610 can execute step as shown in Figure 2.
Storage unit 620 may include the readable medium of volatile memory cell form, such as Random Access Storage Unit
(RAM) 6201 and/or cache memory unit 6202, it can further include read-only memory unit (ROM) 6203.
Storage unit 620 can also include program/utility with one group of (at least one) program module 6205
6204, such program module 6205 includes but is not limited to: operating system, one or more application program, other program moulds
It may include the realization of network environment in block and program data, each of these examples or certain combination.
Bus 630 can be to indicate one of a few class bus structures or a variety of, including storage unit bus or storage
Cell controller, peripheral bus, graphic accelerating interface, processing unit use any bus structures in a variety of bus structures
Local bus.
Electronic equipment 600 can also be with one or more external equipments 700 (such as keyboard, sensing equipment, bluetooth equipment
Deng) communication, can also be enabled a user to one or more equipment interact with the electronic equipment 600 communicate, and/or with make
Any equipment (such as the router, modulation /demodulation that the electronic equipment 600 can be communicated with one or more of the other calculating equipment
Device etc.) communication.This communication can be carried out by input/output (I/O) interface 650.Also, electronic equipment 600 can be with
By network adapter 660 and one or more network (such as local area network (LAN), wide area network (WAN) and/or public network,
Such as internet) communication.As shown, network adapter 660 is communicated by bus 630 with other modules of electronic equipment 600.
It should be understood that although not shown in the drawings, other hardware and/or software module can not used in conjunction with electronic equipment 600, including but not
Be limited to: microcode, device driver, redundant processing unit, external disk drive array, RAID system, tape drive and
Data backup storage system etc..
In an exemplary embodiment of the disclosure, a kind of computer readable storage medium is additionally provided, energy is stored thereon with
Enough realize the program product of this specification above method.In some possible embodiments, various aspects of the invention may be used also
In the form of being embodied as a kind of program product comprising program code, when described program product is run on the terminal device, institute
Program code is stated for executing the terminal device described in above-mentioned " illustrative methods " part of this specification according to this hair
The step of bright various illustrative embodiments.
The program product for realizing the above method of embodiment according to the present invention can use Portable, compact
Disk read-only memory (CD-ROM) and including program code, and can be run on terminal device, such as PC.However,
Program product of the invention is without being limited thereto, and in this document, readable storage medium storing program for executing, which can be, any includes or storage program has
Shape medium, the program can be commanded execution system, device or device use or in connection.
Described program product can be using any combination of one or more readable mediums.Readable medium can be readable letter
Number medium or readable storage medium storing program for executing.Readable storage medium storing program for executing for example can be but be not limited to electricity, magnetic, optical, electromagnetic, infrared ray or
System, device or the device of semiconductor, or any above combination.The more specific example of readable storage medium storing program for executing is (non exhaustive
List) include: electrical connection with one or more conducting wires, portable disc, hard disk, random access memory (RAM), read-only
Memory (ROM), erasable programmable read only memory (EPROM or flash memory), optical fiber, portable compact disc read only memory
(CD-ROM), light storage device, magnetic memory device or above-mentioned any appropriate combination.
Computer-readable signal media may include in a base band or as carrier wave a part propagate data-signal,
In carry readable program code.The data-signal of this propagation can take various forms, including but not limited to electromagnetic signal,
Optical signal or above-mentioned any appropriate combination.Readable signal medium can also be any readable Jie other than readable storage medium storing program for executing
Matter, the readable medium can send, propagate or transmit for by instruction execution system, device or device use or and its
The program of combined use.
The program code for including on readable medium can transmit with any suitable medium, including but not limited to wirelessly, have
Line, optical cable, RF etc. or above-mentioned any appropriate combination.
The program for executing operation of the present invention can be write with any combination of one or more programming languages
Code, described program design language include object oriented program language-Java, C++ etc., further include conventional
Procedural programming language-such as " C " language or similar programming language.Program code can be fully in user
It calculates and executes in equipment, partly executes on a user device, being executed as an independent software package, partially in user's calculating
Upper side point is executed on a remote computing or is executed in remote computing device or server completely.It is being related to far
Journey calculates in the situation of equipment, and remote computing device can pass through the network of any kind, including local area network (LAN) or wide area network
(WAN), it is connected to user calculating equipment, or, it may be connected to external computing device (such as utilize ISP
To be connected by internet).
In addition, above-mentioned attached drawing is only the schematic theory of processing included by method according to an exemplary embodiment of the present invention
It is bright, rather than limit purpose.It can be readily appreciated that the time that above-mentioned processing shown in the drawings did not indicated or limited these processing is suitable
Sequence.In addition, be also easy to understand, these processing, which can be, for example either synchronously or asynchronously to be executed in multiple modules.
Those skilled in the art after considering the specification and implementing the invention disclosed here, will readily occur to its of the disclosure
His embodiment.This application is intended to cover any variations, uses, or adaptations of the disclosure, these modifications, purposes or
Adaptive change follow the general principles of this disclosure and including the undocumented common knowledge in the art of the disclosure or
Conventional techniques.The description and examples are only to be considered as illustrative, and the true scope and spirit of the disclosure are by claim
It points out.
Claims (10)
1. a kind of recongnition of objects method based on augmented reality characterized by comprising
The first kind feature of multiple objects within the vision is obtained by augmented reality equipment, and according to the first kind
Feature determines object to be selected；
The Second Type feature of Second Type feature and target object to the object to be selected is compared to obtain comparison knot
Fruit；
If determining that the object to be selected is the target object according to the comparing result, the information of the target object is sent out
It send to terminal, and executes prompt operation.
2. the recongnition of objects method according to claim 1 based on augmented reality, which is characterized in that existing by enhancing
Real equipment obtains the first kind feature of multiple objects within the vision, and according to the first kind feature determine to
The object is selected to include:
By the camera in the augmented reality equipment, acquisition is described within the vision in the augmented reality equipment
The image of the multiple object；
The first kind feature is extracted from described image, the first kind feature includes facial characteristics；
The first kind feature of the multiple object is matched with the first kind feature of the target object,
To determine matching result；
Using the corresponding object of the first kind feature that the matching result is successful match as the object to be selected.
3. the recongnition of objects method according to claim 2 based on augmented reality, which is characterized in that will be the multiple
The first kind feature of object is matched with the first kind feature of the target object, to determine matching result
Include:
It obtains between the first kind feature of the multiple object and the first kind feature of the target object
Similarity；
If the similarity meets threshold condition, it is determined that the matching result is successful match.
4. the recongnition of objects method according to claim 1 based on augmented reality, which is characterized in that described in determination
When object to be selected, the method also includes:
It conducts the locking operations to the object to be selected, and the prompt information for reminding object to be selected is provided.
5. the recongnition of objects method according to claim 1 based on augmented reality, which is characterized in that according to described right
Determine that the object to be selected is that the target object includes: than result
If the Second Type feature of the object to be selected is consistent with the Second Type feature of the target object, it is determined that it is described to
Selecting object is the target object；
If the Second Type feature of the object to be selected and the Second Type feature of the target object are inconsistent, it is determined that described
Object to be selected is not belonging to the target object.
6. the recongnition of objects method according to claim 1 based on augmented reality, which is characterized in that by the target
The information of object is sent to terminal
The information of field range corresponding to the location information of the target object and the target object is sent to described
Terminal.
7. the recongnition of objects method according to claim 1 based on augmented reality, which is characterized in that execute quick behaviour
Work includes:
In response to the trigger action to the augmented reality equipment, the prompt operation is executed, the prompt operation includes quick
Alarm operation and/or quick notice operation.
8. a kind of recongnition of objects device based on augmented reality characterized by comprising
Object determining module to be selected, the first kind for obtaining multiple objects within the vision by augmented reality equipment are special
Sign, and object to be selected is determined according to the first kind feature；
Characteristic Contrast module, the Second Type feature for Second Type feature and target object to the object to be selected carry out
Comparison is to obtain comparing result；
Target determination module, if for determining that the object to be selected is the target object according to the comparing result, by institute
The information for stating target object is sent to terminal, and executes prompt operation.
9. a kind of electronic equipment characterized by comprising
Processor；And
Memory, for storing the executable instruction of the processor；
Wherein, the processor is configured to come described in perform claim requirement 1-7 any one via the execution executable instruction
The recongnition of objects method based on augmented reality.
10. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the computer program
The recongnition of objects method based on augmented reality described in claim 1-7 any one is realized when being executed by processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910678874.5A CN110458052B (en) | 2019-07-25 | 2019-07-25 | Target object identification method, device, equipment and medium based on augmented reality |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910678874.5A CN110458052B (en) | 2019-07-25 | 2019-07-25 | Target object identification method, device, equipment and medium based on augmented reality |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110458052A true CN110458052A (en) | 2019-11-15 |
| CN110458052B CN110458052B (en) | 2023-04-07 |
Family
ID=68483562
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910678874.5A Active CN110458052B (en) | 2019-07-25 | 2019-07-25 | Target object identification method, device, equipment and medium based on augmented reality |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110458052B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111104927A (en) * | 2019-12-31 | 2020-05-05 | 维沃移动通信有限公司 | Target person information acquisition method and electronic equipment |
| CN112949488A (en) * | 2021-03-01 | 2021-06-11 | 北京京东振世信息技术有限公司 | Picture information processing method and device, computer storage medium and electronic equipment |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018119599A1 (en) * | 2016-12-26 | 2018-07-05 | 深圳前海达闼云端智能科技有限公司 | Method and device for searching for person and communication system |
| CN108776787A (en) * | 2018-06-04 | 2018-11-09 | 北京京东金融科技控股有限公司 | Image processing method and device, electronic equipment, storage medium |
| CN109190601A (en) * | 2018-10-19 | 2019-01-11 | 银河水滴科技（北京）有限公司 | Recongnition of objects method and device under a kind of monitoring scene |
| CN109508524A (en) * | 2018-11-14 | 2019-03-22 | 李泠瑶 | Authentication method, system and storage medium |
| CN109800737A (en) * | 2019-02-02 | 2019-05-24 | 深圳市商汤科技有限公司 | Face recognition method and device, electronic equipment and storage medium |
| US20190163975A1 (en) * | 2017-11-30 | 2019-05-30 | Salesforce.Com, Inc. | System and method for retrieving and displaying supplemental information and pertinent data using augmented reality |
-
2019
- 2019-07-25 CN CN201910678874.5A patent/CN110458052B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018119599A1 (en) * | 2016-12-26 | 2018-07-05 | 深圳前海达闼云端智能科技有限公司 | Method and device for searching for person and communication system |
| US20190163975A1 (en) * | 2017-11-30 | 2019-05-30 | Salesforce.Com, Inc. | System and method for retrieving and displaying supplemental information and pertinent data using augmented reality |
| CN108776787A (en) * | 2018-06-04 | 2018-11-09 | 北京京东金融科技控股有限公司 | Image processing method and device, electronic equipment, storage medium |
| CN109190601A (en) * | 2018-10-19 | 2019-01-11 | 银河水滴科技（北京）有限公司 | Recongnition of objects method and device under a kind of monitoring scene |
| CN109508524A (en) * | 2018-11-14 | 2019-03-22 | 李泠瑶 | Authentication method, system and storage medium |
| CN109800737A (en) * | 2019-02-02 | 2019-05-24 | 深圳市商汤科技有限公司 | Face recognition method and device, electronic equipment and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 严雷等: "结合图像识别的移动增强现实系统设计与应用", 《中国图象图形学报》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111104927A (en) * | 2019-12-31 | 2020-05-05 | 维沃移动通信有限公司 | Target person information acquisition method and electronic equipment |
| CN111104927B (en) * | 2019-12-31 | 2024-03-22 | 维沃移动通信有限公司 | Information acquisition method of target person and electronic equipment |
| CN112949488A (en) * | 2021-03-01 | 2021-06-11 | 北京京东振世信息技术有限公司 | Picture information processing method and device, computer storage medium and electronic equipment |
| CN112949488B (en) * | 2021-03-01 | 2023-09-01 | 北京京东振世信息技术有限公司 | Picture information processing method and device, computer storage medium and electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110458052B (en) | 2023-04-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10930010B2 (en) | Method and apparatus for detecting living body, system, electronic device, and storage medium | |
| EP3584745A1 (en) | Live body detection method and apparatus, system, electronic device, and storage medium | |
| US20210224752A1 (en) | Work support system and work support method | |
| CN111259751A (en) | Video-based human behavior recognition method, device, equipment and storage medium | |
| CN106462242A (en) | User interface control using gaze tracking | |
| CN109766755B (en) | Face recognition method and related product | |
| CN108986245A (en) | Work attendance method and terminal based on recognition of face | |
| CN108805071A (en) | Identity verification method and device, electronic equipment, storage medium | |
| JPH11175246A (en) | Sight line detector and method therefor | |
| JP7106742B2 (en) | Face recognition method, device, electronic device and computer non-volatile readable storage medium | |
| CN108197318A (en) | Face identification method, device, robot and storage medium | |
| CN111914775B (en) | Living body detection method, living body detection device, electronic equipment and storage medium | |
| CN108596110A (en) | Image-recognizing method and device, electronic equipment, storage medium | |
| CN110458052A (en) | Recongnition of objects method, apparatus based on augmented reality, equipment, medium | |
| KR20190119212A (en) | System for performing virtual fitting using artificial neural network, method thereof and computer recordable medium storing program to perform the method | |
| CN111091044A (en) | Network appointment-oriented in-vehicle dangerous scene identification method | |
| CN111783674A (en) | Face recognition method and system based on AR glasses | |
| CN113409056B (en) | Payment method and device, local identification equipment, face payment system and equipment | |
| CN108197608A (en) | Face identification method, device, robot and storage medium | |
| CN107622246A (en) | Face identification method and Related product | |
| CN110059542A (en) | The method and relevant device of face In vivo detection based on improved Resnet | |
| CN110908718A (en) | Face recognition activated voice navigation method, system, storage medium and equipment | |
| CN114567535B (en) | Product interaction and fault diagnosis method based on augmented reality | |
| KR20150108575A (en) | Apparatus identifying the object based on observation scope and method therefor, computer readable medium having computer program recorded therefor | |
| KR102635351B1 (en) | Crime prevention system |
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 |