CN108024060A - Face snap control method, electronic equipment and storage medium - Google Patents
Face snap control method, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN108024060A CN108024060A CN201711287136.5A CN201711287136A CN108024060A CN 108024060 A CN108024060 A CN 108024060A CN 201711287136 A CN201711287136 A CN 201711287136A CN 108024060 A CN108024060 A CN 108024060A
- Authority
- CN
- China
- Prior art keywords
- face
- submodule
- control
- tracking
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/60—Control of cameras or camera modules
- H04N23/61—Control of cameras or camera modules based on recognised objects
- H04N23/611—Control of cameras or camera modules based on recognised objects where the recognised objects include parts of the human body
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/60—Control of cameras or camera modules
- H04N23/617—Upgrading or updating of programs or applications for camera control
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/60—Control of cameras or camera modules
- H04N23/62—Control of parameters via user interfaces
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Human Computer Interaction (AREA)
- Software Systems (AREA)
- Studio Devices (AREA)
- Collating Specific Patterns (AREA)
Abstract
The present invention provides a kind of face snap control method, including:Obtain the selection instruction that scene is captured based on current face;According to the selection instruction, determine to capture the control flow of scene matching with the current face, the definite control flow includes at least one face control submodule and submodule order;According to the submodule sequentially, at least one face control submodule is integrated into the control programmed instruction of current face's candid photograph scene.The present invention also provides a kind of electronic equipment and storage medium.The present invention can be applicable in diversified face snap application scenarios, also be adapted to multiple hardwares device.
Description
Technical field
The present invention relates to field of artificial intelligence, and in particular to a kind of face snap control method, electronic equipment and deposits
Storage media.
Background technology
In computer vision field, face snap application scenarios are extensive, such as intelligent security guard, testimony of a witness verification, face gate inhibition, intelligence
It can take pictures.The face snap flow of different application scene is different, the hsrdware requirements difference of different application scene is also bigger.It is existing
Somebody's face method for snap control is all specifically designed just for concrete application scene.When have switched application scenarios, it is necessary to right
The face snap control program of electronic equipment is redesigned, then is imported in the electronic device.Therefore, existing face snap
Control method can not be applicable in diversified application scenarios, can not also be adapted to multiple hardwares device.
The content of the invention
In view of the foregoing, it is necessary to a kind of face snap control method, electronic equipment and storage medium are provided, can be applicable in
Diversified face snap application scenarios, are also adapted to multiple hardwares device.
A kind of face snap control method, the described method includes:
Obtain the selection instruction that scene is captured based on current face;
According to the selection instruction, determine to capture the control flow of scene matching with the current face, it is described definite
Control flow includes at least one face control submodule and submodule order;
According to submodule order, at least one face control submodule is integrated into the current face and is captured
The control programmed instruction of scene.
In alternative embodiment of the present invention, the method further includes:
Multiple face snap scenes are classified, determine multiple classifications;
Configure the control flow of each classification in the multiple classification;
The control flow of each classification and each classification is shown on a user interface.
In alternative embodiment of the present invention, described obtain captures the selection instruction of scene including with next based on current face
Kind is a variety of:
Obtain the selection for the classification for capturing scene to current face on a user interface;Or
Obtain the selection for the control flow for capturing scene to current face on a user interface.
In alternative embodiment of the present invention, when the control stream for capturing scene to current face on a user interface by obtaining
When the selection of journey captures the selection instruction of scene to obtain based on current face, the method further includes:
Face control submodule necessary to configuration face snap scene;
When in the definite control flow without the required face control submodule is included, user is prompted again
Select control flow.
In alternative embodiment of the present invention, when at least one face control submodule includes Face datection submodule
When, the method further includes:
The setting for obtaining the detection range to the Face datection submodule on a user interface instructs.
In alternative embodiment of the present invention, when at least one face control submodule include Face datection submodule and
During face tracking submodule, the method further includes:
Obtain the Face datection list determined by the face control submodule;
Obtain the face tracking list determined by face tracking submodule;
The Face datection list and the face tracking list are contrasted, determined in the face tracking list not
With the target of tracking;
The target for not having to tracking is deleted from face tracking list.
It is described to carry out the Face datection list and the face tracking list pair in alternative embodiment of the present invention
Than the target for determining not having to tracking in the face tracking list includes:
The Face datection list and the face tracking list are contrasted, determine to be present in the face tracking row
In table and the target that is not present in the Face datection list;
In each detection cycle of the Face datection submodule, the counting to definite target adds one;
From the definite target, screening counts when reaching the target of threshold value and being used as, and deletes the mesh for not having to track
Mark.
In alternative embodiment of the present invention, when at least one face control submodule include Face datection submodule and
During face tracking submodule, the method further includes:
When the destination number for determining the face tracking submodule tracking reaches default quantity, increase the Face datection
The detection cycle of submodule;
When starting to reduce after the destination number for determining the face tracking submodule tracking reaches peak value, reduce the people
The detection cycle of face detection sub-module.
A kind of electronic equipment, the electronic equipment include processor, and the processor is used to perform what is stored in memory
Face snap control method described in any embodiment is realized during computer program.
A kind of computer-readable recording medium, is stored thereon with computer instruction, and the computer instruction is held by processor
Face snap control method described in any embodiment is realized during row.
As can be seen from the above technical solutions, the present invention obtains the selection instruction that scene is captured based on current face;According to
The selection instruction, determines to capture the control flow of scene matching with the current face, the definite control flow includes
At least one face control submodule and submodule order;According to submodule order, at least one face is controlled
Submodule is integrated into the control programmed instruction that the current face captures scene.The present invention also provides a kind of electronic equipment and storage
Medium.The present invention can be applicable in diversified face snap application scenarios, also be adapted to multiple hardwares device.
Brief description of the drawings
In order to illustrate more clearly about the embodiment of the present invention or technical scheme of the prior art, below will be to embodiment or existing
There is attached drawing needed in technology description to be briefly described, it should be apparent that, drawings in the following description are only this
The embodiment of invention, for those of ordinary skill in the art, without creative efforts, can also basis
The attached drawing of offer obtains other attached drawings.
Fig. 1 is the flow chart of the preferred embodiment of face method for snap control of the present invention.
Fig. 2 is the functional block diagram of the preferred embodiment of face snapping control device of the present invention.
Fig. 3 is the structure diagram of the preferred embodiment of electronic equipment at least one example of the present invention.
Embodiment
Below in conjunction with the attached drawing in the embodiment of the present invention, the technical solution in the embodiment of the present invention is carried out clear, complete
Site preparation describes, it is clear that described embodiment is only part of the embodiment of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, those of ordinary skill in the art are obtained every other without making creative work
Embodiment, belongs to the scope of protection of the invention.
In order to make the foregoing objectives, features and advantages of the present invention clearer and more comprehensible, it is below in conjunction with the accompanying drawings and specific real
Applying mode, the present invention is described in further detail.
As shown in Figure 1, it is the flow chart of the preferred embodiment of face method for snap control of the present invention.According to different need
Ask, the order of step can change in the flow chart, and some steps can be omitted.
S10, electronic equipment obtain the selection instruction that scene is captured based on current face.
In the present invention, face snap scene is a variety of, such as face authentication, portrait are found a view, trajectory track, are deployed troops on garrison duty and deployed to ensure effective monitoring and control of illegal activities
Deng application, the face snap scene is not limited to the citing of the present invention.Difference may be corresponding with different face snap scenes
Control flow.Each control flow includes at least one face control submodule and submodule order.At least one people
Face control submodule includes, but are not limited to:Face datection submodule, face tracking submodule, face screening submodule.
For example, the control flow of face authentication classification can include Face datection submodule, face screening submodule.It is described
Face authentication classification submodule order be:Face datection submodule is first carried out, then performs face screening submodule.Namely
Say, Face datection makees picture by Face datection submodule, then the face picture again the output of Face datection submodule is made
The input of submodule is screened for the face.
In the alternative embodiment of the present invention, scene and hsrdware requirements, choosing are captured according to current face in order to facilitate user
The control flow needed for face snap is selected, realizes the control flow of personalized customization face snap.The present invention provides user interface,
Offer and the relevant option of face snap scene on a user interface, for the choosing of user configuration and current face's candid photograph scene
.Therefore the electronic equipment, which obtains the selection instruction based on current face's candid photograph scene, includes following one or more:
(1) selection for the classification for capturing scene to current face on a user interface is obtained.
Further, the electronic equipment classifies multiple face snap scenes, determines multiple classifications;Described in configuration
The control flow of each classification in multiple classifications.Control flow in each classification is identical.Each classification can be in user
A corresponding category control on interface, when user captures scene according to the current face, chooses the category control (such as double
Hit or click the category control) when, the corresponding class of category control chosen described in the electronic equipment acquisition will be triggered
Not, the corresponding classification of the category control chosen is determined as to the classification of current face's candid photograph scene.
Further, the application scenarios that each classification is related to are shown on a user interface, for user's more intuitively basis
Current face captures scene configuration control flow.
(2) selection for the control flow for capturing scene to current face on a user interface is obtained.
Further, multiple face control submodules are shown on a user interface, and field is captured according to current face by user
The control flow that scape selection needs.Each face control submodule corresponds to a module control (e.g., icon) on a user interface,
User captures the needs of scene according to current face, successively the icon of face control submodule needed for choosing.The figure that will be chosen
Mark corresponding face control submodule and the face control submodule of scene is captured as the current face, and icon will be chosen
Order captures the submodule order of scene as the current face.
In the alternative embodiment of the present invention, the user interface of above-mentioned offer and the relevant option of face snap scene can be with
It is shown in the display of the electronic equipment, for example, the electronic equipment is camera, the user interface is shown in camera
On display.The user interface can also be shown on the display of the terminal device to communicate with the electronic equipment, for example,
The electronic equipment is camera device, and the terminal device is the mobile phone communicated with the camera device, by user circle
Face is shown on the display screen of the mobile phone of user.So user can pass through the control journey of camera device described in terminal equipment configuration
Sequence, while even if the configuration personnel of control program can also realize remote control not at the scene of camera device.
Alternatively, obtained when by obtaining the selection for the control flow for capturing scene to current face on a user interface
When capturing the selection instruction of scene based on current face, face control necessary to the electronic equipment face snap scene
Module;When in the definite control flow without the required face control submodule is included, user is prompted to select again
Select control flow.Wrong control flow can be so selected to avoid user.
S11, the electronic equipment determine to capture the control of scene matching with the current face according to the selection instruction
Flow, the definite control flow include at least one face control submodule and submodule order.
It is described according to the selection instruction in optional embodiment of the present invention, determine to capture field with the current face
The matched control flow of scape includes:
The classification that the current face captures scene is obtained from the selection instruction, determines to capture with the current face
The control flow of the categorical match of scene;Or
The control flow that the current face captures scene is directly acquired from the selection instruction.
In a preferred embodiment of the invention, multiple face control submodules are shown on a user interface, by user according to
Current face captures the control flow that scene selection needs, then the selection instruction includes, but are not limited to:At least one face control
System module and submodule order.For example, user have chosen Face datection submodule, face screening submodule successively.The son
Sequence of modules is:Face datection submodule is first carried out, then performs face screening submodule.That is, pass through Face datection
Module makees picture Face datection, and the face picture of Face datection submodule output is then screened submodule as the face again
The input of block.
Further, at least one face control submodule includes, but are not limited to following one or more kinds of group
Close:Face datection submodule, face tracking submodule, face screening submodule.
Alternatively, before Face datection submodule, collection submodule can also be included, for controlling camera device to obtain
Two field picture, and two field picture is exported into the inlet flow to the Face datection submodule as the Face datection submodule.According to
The difference of application scenarios, can also include other submodules in control flow, such as submodule be applied, for example, described apply submodule
Input picture is identified etc. in block.
In the present invention, the Face datection submodule is used to carry out the picture of input Face datection, the face with
Track submodule is used to the face detected is used to filter out optimal picture, exported into line trace, the face screening submodule
To using submodule, the application submodule handles the optimal picture, for example, carrying out face knowledge based on optimal picture
Not etc..The Face datection submodule, face tracking submodule, the implementation method of face screening submodule have many kinds, this
Any restrictions are not done in invention.
Further, when the definite flow is the first control flow, at least one face control submodule
Include, but are not limited to:Face datection submodule.First control flow can be used in the application of output face picture, example
Such as, in the face authentication application scenarios for attendance, camera device need to only be detected relatively small by Face datection submodule
In the range of face, then carry out feature extraction, compared with the database of storage, confirm the identity of face.Face authentication application
Scene is all relatively fewer to detection range and detection face number demand, low to hardware configuration demand, therefore can not have to selection
Face tracking module, face screening submodule.
When the definite flow is the second control flow, at least one face control submodule includes, but not
It is limited to:Face datection submodule, face tracking submodule.Second control flow can be used for needing the track progress to people
Tracking.For example, in hand-held intelligent camera apparatus, during shooting portrait is found a view, collection submodule collection video image, face
Face location information in detection sub-module detection image, and framed face including being aided in camera screen with rectangular frame
Find a view, in order to frame the movement of real-time display face, face tracking submodule is needed under the application scenarios.Due to being that auxiliary takes
Scape, is not required to face screening submodule.
When the definite flow is three control flow, at least one face control submodule includes, but not
It is limited to:Face datection submodule, face screening submodule.When the requirement to picture quality is higher, face sieve can be added
Submodule is selected, if for example, the 3rd control flow can be used, i.e., in people in face authentication application scenarios to requirement of real-time height
After face detection sub-module detects face picture, the high picture of face screening submodule screening mass is recycled, so as to improve
Certification speed.
When the definite flow is four control flow, at least one face control submodule includes, but not
It is limited to:Face datection submodule, face tracking submodule, face screening submodule.For example, the 4th control flow can be used
In with the relevant application of dynamic human face.Due to in the relevant application of dynamic human face, people is voluntomotory, it is therefore desirable to people
Face tracks submodule, simultaneously because, it is necessary to improve candid photograph rate under this application scenarios, it is necessary to provide real-time, it is possible to
Add face screening submodule.
Alternatively, to detection range and detection all relatively small number of application scenarios of face number demand under, in user
The option of the detection range for the picture for setting camera device to obtain is provided on interface, the electronic equipment obtains on a user interface
Setting to the detection range of the Face datection submodule instructs.After so setting detection range in advance, without at whole
It is detected in picture, improves detection speed.
Alternatively, when at least one face control submodule includes Face datection submodule and face tracking submodule
When, the method further includes:Obtain the Face datection list determined by the face control submodule;Obtain by face with
The face tracking list that track submodule determines;The Face datection list and the face tracking list are contrasted, determined
The target of tracking, i.e., the target finally to disappear are not had in the face tracking list;By the target for not having to tracking from face
Deleted in tracking list.
Further, it is described to be contrasted the Face datection list and the face tracking list, determine the people
Not having to the target of tracking in face tracking list includes:The Face datection list and the face tracking list are contrasted,
Determine to be present in the face tracking list and be not present in the target in the Face datection list;In the Face datection
In each detection cycle of submodule, the counting to definite target adds one;From the definite target, screening counting reaches
When the target of threshold value does not have to the target of tracking as described in, the target without tracking is deleted.Tracking can be so corrected in time
Target, reduces and captures redundancy, improves tracking accuracy.
Further, the Face datection list and the face tracking list are contrasted, determine the face with
The target of of short duration disappearance includes in track list:The Face datection list and the face tracking list are contrasted, determined
The target for being not present in the face tracking list and being present in the Face datection list;In the Face datection submodule
In each detection cycle of block, the counting to definite target adds one;From the definite target, screening counting is not reaching to
During target of the target of threshold value as the of short duration disappearance, the mesh of the of short duration disappearance is retained in the face tracking list
Mark.Of short duration occlusion issue can be so solved, avoids target from being considered fresh target when reappearing, the candid photograph for reducing same target is superfluous
It is remaining.
In an alternative embodiment, when at least one face control submodule include Face datection submodule and face with
During track submodule, the method further includes:When the destination number for determining the face tracking submodule tracking reaches default quantity
When, increase the detection cycle of the Face datection submodule;When the destination number for determining the face tracking submodule tracking reaches
When starting to reduce after to peak value, reduce the detection cycle of the Face datection submodule.For example, in intelligent security guard application scenarios
The face picture of different people in crawl video images as more as possible is needed, is stored in database, for trajectory track, cloth of deploying troops on garrison duty
The application such as control, pursues extremely low leakage candid photograph rate, but hardware unit has performance boundary, and actual scene is had beyond design
The situation of energy.Therefore, when happen suddenly super large flow of the people scene when, when the face tracking submodule tracking destination number reach pre-
If during quantity, if continuing the detection cycle according to normal flow of the people, capturing system stability cannot be guaranteed, at this time using stepping side
Formula increases detection cycle, progressively alleviates tracking bottleneck.When the destination number of face tracking submodule tracking reaches peak value again
After starting reduction, step-by-step movement reduces detection cycle, recovers normal and captures state.It can so reduce and Lou capture.
At least one face control submodule is integrated into by S12, the electronic equipment according to submodule order
The current face captures at least a portion control programmed instruction of scene.
In the alternative embodiment of the present invention, each face control submodule at least one face control submodule
A corresponding program block.It is described that at least one face control submodule is integrated into current face's candid photograph scene extremely
Few part control programmed instruction includes:According to submodule order, the output data of the first face control submodule is made
For the input data of the second face control submodule, the output data of the second face control submodule is as third party's face control
The input data of system module, and so on, until last face control submodule, obtains the current face and captures field
At least a portion control programmed instruction of scape.
The present invention obtains the selection instruction that scene is captured based on current face;According to the selection instruction, determine with it is described
Current face capture scene matching control flow, the definite control flow include at least one face control submodule and
Submodule order;According to submodule order, at least one face control submodule is integrated into the current face
Capture the control programmed instruction of scene.The face snap control of the present invention can be applicable in diversified face snap application scenarios,
It is adapted to multiple hardwares device.
As shown in Fig. 2, the functional block diagram of the preferred embodiment of face snapping control device of the present invention.The face snap
Control device 11 includes acquisition module 100, configuration module 101, display module 102, determining module 103, reminding module 104, tune
Mould preparation block 105 and integration module 106.Unit alleged by the present invention refer to it is a kind of can be by the processing of face snap control device 11
Device is performed and can complete the series of computation machine program segment of fixed function, it is stored in memory.In the present embodiment
In, the function on each unit will be described in detail in follow-up embodiment.
The acquisition module 100 obtains the selection instruction that scene is captured based on current face.
In the present invention, face snap scene is a variety of, such as face authentication, portrait are found a view, trajectory track, are deployed troops on garrison duty and deployed to ensure effective monitoring and control of illegal activities
Deng application, the face snap scene is not limited to the citing of the present invention.Difference may be corresponding with different face snap scenes
Control flow.Each control flow includes at least one face control submodule and submodule order.At least one people
Face control submodule includes, but are not limited to:Face datection submodule, face tracking submodule, face screening submodule.
For example, the control flow of face authentication classification can include Face datection submodule, face screening submodule.It is described
Face authentication classification submodule order be:Face datection submodule is first carried out, then performs face screening submodule.Namely
Say, Face datection makees picture by Face datection submodule, then the face picture again the output of Face datection submodule is made
The input of submodule is screened for the face.
In the alternative embodiment of the present invention, scene and hsrdware requirements, choosing are captured according to current face in order to facilitate user
The control flow needed for face snap is selected, realizes the control flow of personalized customization face snap.The present invention provides user interface,
Offer and the relevant option of face snap scene on a user interface, for the choosing of user configuration and current face's candid photograph scene
.Therefore the acquisition module 100, which obtains the selection instruction based on current face's candid photograph scene, includes following one or more:
(1) selection for the classification for capturing scene to current face on a user interface is obtained.
Further, the configuration module 101 is used for:Multiple face snap scenes are classified, determine multiple classifications;
Configure the control flow of each classification in the multiple classification.Control flow in each classification is identical.Each classification can
With on a user interface correspond to a category control, when user according to the current face capture scene, choose the classification control
During part (such as double-clicking or click the category control), the category control chosen described in the electronic equipment acquisition will be triggered
The corresponding classification of the category control chosen, is determined as the classification of current face's candid photograph scene by corresponding classification.
Further, the application scenarios that each classification is related to are shown on a user interface, for user's more intuitively basis
Current face captures scene configuration control flow.
(2) selection for the control flow for capturing scene to current face on a user interface is obtained.
Further, the display module 102 shows multiple face control submodules on a user interface, by user according to
Current face captures the control flow that scene selection needs.Each face control submodule corresponds to a module on a user interface
Control (e.g., icon), user capture the needs of scene according to current face, successively the figure of face control submodule needed for choosing
Mark.The face control submodule of scene is captured using the corresponding face control submodule of the icon chosen as the current face,
And the submodule order of scene is captured using the order for choosing icon as the current face.
In the alternative embodiment of the present invention, the user interface of above-mentioned offer and the relevant option of face snap scene can be with
It is shown in the display of the electronic equipment, for example, the electronic equipment is camera, the user interface is shown in camera
On display.The user interface can also be shown on the display of the terminal device to communicate with the electronic equipment, for example,
The electronic equipment is camera device, and the terminal device is the mobile phone communicated with the camera device, by user circle
Face is shown on the display screen of the mobile phone of user.So user can pass through the control journey of camera device described in terminal equipment configuration
Sequence, while even if the configuration personnel of control program can also realize remote control not at the scene of camera device.
Alternatively, obtained when by obtaining the selection for the control flow for capturing scene to current face on a user interface
When capturing the selection instruction of scene based on current face, the configuration module 101 configures face control necessary to face snap scene
System module;When in the definite control flow without the required face control submodule is included, the prompting mould
Block 104 prompts user to reselect control flow.Wrong control flow can be so selected to avoid user.
The determining module 103 determines to capture the control of scene matching with the current face according to the selection instruction
Flow, the definite control flow include at least one face control submodule and submodule order.
In optional embodiment of the present invention, the determining module 103 determines and described current according to the selection instruction
The control flow of face snap scene matching includes:
The classification that the current face captures scene is obtained from the selection instruction, determines to capture with the current face
The control flow of the categorical match of scene;Or
The control flow that the current face captures scene is directly acquired from the selection instruction.
In a preferred embodiment of the invention, multiple face control submodules are shown on a user interface, by user according to
Current face captures the control flow that scene selection needs, then the selection instruction includes, but are not limited to:At least one face control
System module and submodule order.For example, user have chosen Face datection submodule, face screening submodule successively.The son
Sequence of modules is:Face datection submodule is first carried out, then performs face screening submodule.That is, pass through Face datection
Module makees picture Face datection, and the face picture of Face datection submodule output is then screened submodule as the face again
The input of block.
Further, at least one face control submodule includes, but are not limited to following one or more kinds of group
Close:Face datection submodule, face tracking submodule, face screening submodule.
Alternatively, before Face datection submodule, collection submodule can also be included, for controlling camera device to obtain
Two field picture, and two field picture is exported into the inlet flow to the Face datection submodule as the Face datection submodule.According to
The difference of application scenarios, can also include other submodules in control flow, such as submodule be applied, for example, described apply submodule
Input picture is identified etc. in block.
In the present invention, the Face datection submodule is used to carry out the picture of input Face datection, the face with
Track submodule is used to the face detected is used to filter out optimal picture, exported into line trace, the face screening submodule
To using submodule, the application submodule handles the optimal picture, for example, carrying out face knowledge based on optimal picture
Not etc..The Face datection submodule, face tracking submodule, the implementation method of face screening submodule have many kinds, this
Any restrictions are not done in invention.
Further, when the definite flow is the first control flow, at least one face control submodule
Include, but are not limited to:Face datection submodule.First control flow can be used in the application of output face picture, example
Such as, in the face authentication application scenarios for attendance, camera device need to only be detected relatively small by Face datection submodule
In the range of face, then carry out feature extraction, compared with the database of storage, confirm the identity of face.Face authentication application
Scene is all relatively fewer to detection range and detection face number demand, low to hardware configuration demand, therefore can not have to selection
Face tracking module, face screening submodule.
When the definite flow is the second control flow, at least one face control submodule includes, but not
It is limited to:Face datection submodule, face tracking submodule.Second control flow can be used for needing the track progress to people
Tracking.For example, in hand-held intelligent camera apparatus, during shooting portrait is found a view, collection submodule collection video image, face
Face location information in detection sub-module detection image, and framed face including being aided in camera screen with rectangular frame
Find a view, in order to frame the movement of real-time display face, face tracking submodule is needed under the application scenarios.Due to being that auxiliary takes
Scape, is not required to face screening submodule.
When the definite flow is three control flow, at least one face control submodule includes, but not
It is limited to:Face datection submodule, face screening submodule.When the requirement to picture quality is higher, face sieve can be added
Submodule is selected, if for example, the 3rd control flow can be used, i.e., in people in face authentication application scenarios to requirement of real-time height
After face detection sub-module detects face picture, the high picture of face screening submodule screening mass is recycled, so as to improve
Certification speed.
When the definite flow is four control flow, at least one face control submodule includes, but not
It is limited to:Face datection submodule, face tracking submodule, face screening submodule.For example, the 4th control flow can be used
In with the relevant application of dynamic human face.Due to in the relevant application of dynamic human face, people is voluntomotory, it is therefore desirable to people
Face tracks submodule, simultaneously because, it is necessary to improve candid photograph rate under this application scenarios, it is necessary to provide real-time, it is possible to
Add face screening submodule.
Alternatively, to detection range and detection all relatively small number of application scenarios of face number demand under, in user
The option of the detection range for the picture for setting camera device to obtain is provided on interface, the acquisition module 100 is obtained in user circle
Setting on face to the detection range of the Face datection submodule instructs.After so setting detection range in advance, without
It is detected in whole pictures, improves detection speed.
Alternatively, when at least one face control submodule includes Face datection submodule and face tracking submodule
When, the determining module 103 is additionally operable to:Obtain the Face datection list determined by the face control submodule;Obtain logical
Cross the face tracking list that face tracking submodule determines;The Face datection list and the face tracking list are carried out pair
Than determining the target for not having to tracking in the face tracking list, i.e., the target finally to disappear;By the target for not having to tracking
Deleted from face tracking list.
Further, it is described to be contrasted the Face datection list and the face tracking list, the definite mould
The target that block 103 determines not having to tracking in the face tracking list includes:By the Face datection list and the face with
Track list is contrasted, and determines to be present in the face tracking list and be not present in the mesh in the Face datection list
Mark;In each detection cycle of the Face datection submodule, the counting to definite target adds one;From the definite mesh
In mark, when screening counts the target for reaching the target of threshold value as described and not having to tracking, the target for not having to track is deleted.This
Sample can correct tracking target in time, reduce and capture redundancy, improve tracking accuracy.
Further, the determining module 103 is contrasted the Face datection list and the face tracking list,
Determining the target of of short duration disappearance in the face tracking list includes:By the Face datection list and the face tracking list
Contrasted, determine to be not present in the face tracking list and be present in the target in the Face datection list;Institute
In each detection cycle for stating Face datection submodule, the counting to definite target adds one;From the definite target, sieve
When choosing counts target of the target for being not reaching to threshold value as the of short duration disappearance, in the face tracking list described in reservation
The target of of short duration disappearance.Of short duration occlusion issue can be so solved, avoids target from being considered fresh target when reappearing, is reduced same
The candid photograph redundancy of target.
In an alternative embodiment, when at least one face control submodule include Face datection submodule and face with
During track submodule, the adjustment module 105 further includes:When the destination number for determining the face tracking submodule tracking reaches pre-
If during quantity, increase the detection cycle of the Face datection submodule;When the target for determining the face tracking submodule tracking
Quantity reaches when starting after peak value to reduce, and reduces the detection cycle of the Face datection submodule.For example, in intelligent security guard application
The face pictures of different people in crawl video images much more as far as possible are needed in scene, are stored in database, for trajectory track,
Deploy troops on garrison duty the application such as deploy to ensure effective monitoring and control of illegal activities, pursue extremely low leakage candid photograph rate, but hardware unit has performance boundary, and also actual scene has and exceeds
The situation of design performance.Therefore, when happen suddenly super large flow of the people scene when, when the face tracking submodule tracking destination number
When reaching default quantity, if continuing the detection cycle according to normal flow of the people, capturing system stability cannot be guaranteed, use at this time
Step-by-step system increases detection cycle, progressively alleviates tracking bottleneck.When the destination number of face tracking submodule tracking reaches
After peak value starts reduction again, step-by-step movement reduces detection cycle, recovers normal and captures state.It can so reduce and Lou capture.
At least one face control submodule is integrated into by the integration module 106 according to submodule order
The current face captures at least a portion control programmed instruction of scene.
In the alternative embodiment of the present invention, each face control submodule at least one face control submodule
A corresponding program block.At least one face control submodule is integrated into the current face by the integration module 106
Capturing at least a portion control programmed instruction of scene includes:According to submodule order, by the first face control submodule
Output data, as the input data of the second face control submodule, the output data of the second face control submodule
As the input data of third party's face control submodule, and so on, until last face control submodule, obtains described
Current face captures at least a portion control programmed instruction of scene.
The present invention obtains the selection instruction that scene is captured based on current face;According to the selection instruction, determine with it is described
Current face capture scene matching control flow, the definite control flow include at least one face control submodule and
Submodule order;According to submodule order, at least one face control submodule is integrated into the current face
Capture the control programmed instruction of scene.The face snap control of the present invention can be applicable in diversified face snap application scenarios,
It is adapted to multiple hardwares device.
The above-mentioned integrated unit realized in the form of software function module, can be stored in one and computer-readable deposit
In storage media.Above-mentioned software function module is stored in a storage medium, including some instructions are used so that a computer
It is each that equipment (can be personal computer, server, or network equipment etc.) or processor (processor) perform the present invention
The part steps of embodiment the method.
As shown in figure 3, the electronic equipment 3 includes at least one dispensing device 31, at least one processor 32, at least one
A processor 33, at least one reception device 34 and at least one communication bus.Wherein, the communication bus is used for realization this
Connection communication between a little components.
The electronic equipment 3 be it is a kind of can according to the instruction for being previously set or storing, it is automatic carry out numerical computations and/or
The equipment of information processing, its hardware include but not limited to microprocessor, application-specific integrated circuit (Application Specific
Integrated Circuit, ASIC), programmable gate array (Field-Programmable Gate Array, FPGA), number
Word processing device (Digital Signal Processor, DSP), embedded device etc..The electronic equipment 3 may also include network
Equipment and/or user equipment.Wherein, the network equipment includes but not limited to single network server, multiple webservers
The server group of composition or the cloud being made of a large amount of hosts or the webserver based on cloud computing (Cloud Computing),
Wherein, cloud computing is one kind of Distributed Calculation, a super virtual computing being made of the computer collection of a group loose couplings
Machine.
The electronic equipment 3, which may be, but not limited to, any type, to pass through keyboard, touch pad or voice-operated device with user
Etc. the electronic product that mode carries out human-computer interaction, for example, tablet computer, smart mobile phone, personal digital assistant (Personal
Digital Assistant, PDA), intellectual Wearable, picture pick-up device, the terminal such as monitoring device.
Network residing for the electronic equipment 3 includes, but are not limited to internet, wide area network, Metropolitan Area Network (MAN), LAN, virtual
Dedicated network (Virtual Private Network, VPN) etc..
Wherein, the reception device 34 and the dispensing device 31 can be wired sending ports, or wirelessly set
It is standby, such as including antenna assembly, for other equipment into row data communication.
The memory 32 is used for store program codes.The memory 32 can not have physical form in integrated circuit
The circuit with store function, such as RAM (Random-Access Memory, random access memory), FIFO (First In
First Out) etc..Alternatively, the memory 32 can also be the memory for having physical form, such as memory bar, TF card
(Trans-flash Card), smart media card (smart media card), safe digital card (secure digital
Card), storage facilities such as flash memory cards (flash card) etc..
The processor 33 can include one or more microprocessor, digital processing unit.The processor 33 is adjustable
With the program code stored in memory 32 to perform relevant function.For example, the unit described in Fig. 2 is stored in institute
The program code in memory 32 is stated, and as performed by the processor 33, to realize a kind of face snap control method.It is described
Processor 33 is also known as central processing unit (CPU, Central Processing Unit), is one piece of ultra-large integrated circuit,
It is arithmetic core (Core) and control core (Control Unit).
The embodiment of the present invention also provides a kind of computer-readable recording medium, is stored thereon with computer instruction, the finger
Make when being performed by the electronic equipment including one or more processors, electronic equipment is performed as described in embodiment of the method above
Face snap control method.
In several embodiments provided by the present invention, it should be understood that disclosed system, apparatus and method can be with
Realize by another way.For example, device embodiment described above is only schematical, for example, the module
Division, is only a kind of division of logic function, can there is other dividing mode when actually realizing.
The module illustrated as separating component may or may not be physically separate, be shown as module
The component shown may or may not be physical location, you can with positioned at a place, or can also be distributed to multiple
In network unit.Some or all of module therein can be selected to realize the mesh of this embodiment scheme according to the actual needs
's.
In addition, each function module in each embodiment of the invention can be integrated in a processing unit, can also
That each unit is individually physically present, can also two or more units integrate in a unit.Above-mentioned integrated list
Member can both be realized in the form of hardware, can also be realized in the form of hardware adds software function module.
It is obvious to a person skilled in the art that the invention is not restricted to the details of above-mentioned one exemplary embodiment, Er Qie
In the case of without departing substantially from spirit or essential attributes of the invention, the present invention can be realized in other specific forms.Therefore, no matter
From the point of view of which point, the present embodiments are to be considered as illustrative and not restrictive, and the scope of the present invention is by appended power
Profit requires rather than described above limits, it is intended that all in the implication and scope of the equivalency of claim by falling
Change is included in the present invention.Any attached associated diagram mark in claim should not be considered as the involved right of limitation will
Ask.Furthermore, it is to be understood that one word of " comprising " is not excluded for other units or step, odd number is not excluded for plural number.Stated in system claims
Multiple units or device can also be realized by a unit or device by software or hardware.Second grade word is used for table
Show title, and be not offered as any specific order.
Finally it should be noted that the above embodiments are merely illustrative of the technical solutions of the present invention and it is unrestricted, although reference
The present invention is described in detail in preferred embodiment, it will be understood by those of ordinary skill in the art that, can be to the present invention's
Technical solution is modified or equivalent substitution, without departing from the spirit and scope of technical solution of the present invention.
Claims (10)
- A kind of 1. face snap control method, it is characterised in that the described method includes:Obtain the selection instruction that scene is captured based on current face;According to the selection instruction, determine to capture the control flow of scene matching, the definite control with the current face Flow includes at least one face control submodule and submodule order;According to submodule order, at least one face control submodule is integrated into the current face and captures scene Control programmed instruction.
- 2. face snap control method as claimed in claim 1, it is characterised in that the method further includes:Multiple face snap scenes are classified, determine multiple classifications;Configure the control flow of each classification in the multiple classification;The control flow of each classification and each classification is shown on a user interface.
- 3. face snap control method as claimed in claim 1, it is characterised in that described obtain captures field based on current face The selection instruction of scape includes following one or more:Obtain the selection for the classification for capturing scene to current face on a user interface;Obtain the selection for the control flow for capturing scene to current face on a user interface.
- 4. face snap control method as claimed in claim 3, it is characterised in that when by obtaining on a user interface to working as When the selection of the control flow of preceding face snap scene captures the selection instruction of scene to obtain based on current face, the method Further include:Face control submodule necessary to configuration face snap scene;When in the definite control flow without the required face control submodule is included, user is prompted to reselect Control flow.
- 5. face snap control method according to any one of claims 1 to 4, it is characterised in that when described at least one When face control submodule includes Face datection submodule, the method further includes:The setting for obtaining the detection range to the Face datection submodule on a user interface instructs.
- 6. face snap control method according to any one of claims 1 to 4, it is characterised in that when described at least one When face control submodule includes Face datection submodule and face tracking submodule, the method further includes:Obtain the Face datection list determined by the face control submodule;Obtain the face tracking list determined by face tracking submodule;The Face datection list and the face tracking list are contrasted, determine in the face tracking list do not have to The target of track;The target for not having to tracking is deleted from face tracking list.
- 7. face snap control method as claimed in claim 6, it is characterised in that described by the Face datection list and institute State face tracking list to be contrasted, the target for determining not having to tracking in the face tracking list includes:The Face datection list and the face tracking list are contrasted, determine to be present in the face tracking list And it is not present in the target in the Face datection list;In each detection cycle of the Face datection submodule, the counting to definite target adds one;From the definite target, screening counts when reaching the target of threshold value and being used as, and deletes the target for not having to track.
- 8. face snap control method according to any one of claims 1 to 4, it is characterised in that when described at least one When face control submodule includes Face datection submodule and face tracking submodule, the method further includes:When the destination number for determining the face tracking submodule tracking reaches default quantity, increase the Face datection submodule The detection cycle of block;When starting to reduce after the destination number for determining the face tracking submodule tracking reaches peak value, reduce the face inspection Survey the detection cycle of submodule.
- 9. a kind of electronic equipment, it is characterised in that the electronic equipment includes processor, and the processor is used to perform memory The face snap control method as described in any one in claim 1 to 8 is realized during the computer program of middle storage.
- 10. a kind of computer-readable recording medium, is stored thereon with computer instruction, it is characterised in that:The computer instruction The face snap control method as described in any one in claim 1 to 8 is realized when being executed by processor.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711287136.5A CN108024060B (en) | 2017-12-07 | 2017-12-07 | Face snapshot control method, electronic device and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711287136.5A CN108024060B (en) | 2017-12-07 | 2017-12-07 | Face snapshot control method, electronic device and storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN108024060A true CN108024060A (en) | 2018-05-11 |
CN108024060B CN108024060B (en) | 2020-07-21 |
Family
ID=62078947
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711287136.5A Active CN108024060B (en) | 2017-12-07 | 2017-12-07 | Face snapshot control method, electronic device and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108024060B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110348348A (en) * | 2019-06-30 | 2019-10-18 | 华中科技大学 | One kind personnel of taking part in building march into the arena identity method for quickly identifying and early warning system |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102214103A (en) * | 2011-07-08 | 2011-10-12 | 珠海脉络软件有限公司 | Method and system for establishing and performing task program based on functional unit |
CN102520968A (en) * | 2011-12-28 | 2012-06-27 | 用友软件股份有限公司 | Design and demonstration device for process capable of being customized and method |
CN102750527A (en) * | 2012-06-26 | 2012-10-24 | 浙江捷尚视觉科技有限公司 | Long-time stable human face detection and tracking method in bank scene and long-time stable human face detection and tracking device in bank scene |
CN102752519A (en) * | 2011-05-17 | 2012-10-24 | 新奥特(北京)视频技术有限公司 | Graph picture mixed processing method in two-dimensional and three-dimensional environments |
CN102930261A (en) * | 2012-12-05 | 2013-02-13 | 上海市电力公司 | Face snapshot recognition method |
CN104123061A (en) * | 2013-04-29 | 2014-10-29 | 鸿富锦精密工业(深圳)有限公司 | Process icon combination control system and electronic device |
CN104135645A (en) * | 2014-07-31 | 2014-11-05 | 天津市亚安科技股份有限公司 | Video surveillance system and method for face tracking and capturing |
CN104657817A (en) * | 2015-01-28 | 2015-05-27 | 四川君逸易视科技有限公司 | Face snapshotting, comparing, identifying, retrieving, and inquiring method for bank counter |
US20160048896A1 (en) * | 2014-08-15 | 2016-02-18 | Howard Lind | Custom flat cable configurator |
CN105355201A (en) * | 2015-11-27 | 2016-02-24 | 百度在线网络技术(北京)有限公司 | Scene-based voice service processing method and device and terminal device |
-
2017
- 2017-12-07 CN CN201711287136.5A patent/CN108024060B/en active Active
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102752519A (en) * | 2011-05-17 | 2012-10-24 | 新奥特(北京)视频技术有限公司 | Graph picture mixed processing method in two-dimensional and three-dimensional environments |
CN102214103A (en) * | 2011-07-08 | 2011-10-12 | 珠海脉络软件有限公司 | Method and system for establishing and performing task program based on functional unit |
CN102520968A (en) * | 2011-12-28 | 2012-06-27 | 用友软件股份有限公司 | Design and demonstration device for process capable of being customized and method |
CN102750527A (en) * | 2012-06-26 | 2012-10-24 | 浙江捷尚视觉科技有限公司 | Long-time stable human face detection and tracking method in bank scene and long-time stable human face detection and tracking device in bank scene |
CN102930261A (en) * | 2012-12-05 | 2013-02-13 | 上海市电力公司 | Face snapshot recognition method |
CN104123061A (en) * | 2013-04-29 | 2014-10-29 | 鸿富锦精密工业(深圳)有限公司 | Process icon combination control system and electronic device |
CN104135645A (en) * | 2014-07-31 | 2014-11-05 | 天津市亚安科技股份有限公司 | Video surveillance system and method for face tracking and capturing |
US20160048896A1 (en) * | 2014-08-15 | 2016-02-18 | Howard Lind | Custom flat cable configurator |
CN104657817A (en) * | 2015-01-28 | 2015-05-27 | 四川君逸易视科技有限公司 | Face snapshotting, comparing, identifying, retrieving, and inquiring method for bank counter |
CN105355201A (en) * | 2015-11-27 | 2016-02-24 | 百度在线网络技术(北京)有限公司 | Scene-based voice service processing method and device and terminal device |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110348348A (en) * | 2019-06-30 | 2019-10-18 | 华中科技大学 | One kind personnel of taking part in building march into the arena identity method for quickly identifying and early warning system |
Also Published As
Publication number | Publication date |
---|---|
CN108024060B (en) | 2020-07-21 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
KR101759453B1 (en) | Automated image cropping and sharing | |
CN104967803B (en) | A kind of video recording method and device | |
CN106603928B (en) | A kind of image pickup method and mobile terminal | |
US10360481B2 (en) | Unconstrained event monitoring via a network of drones | |
CN110012209A (en) | Panorama image generation method, device, storage medium and electronic equipment | |
CN102460433A (en) | Method and apparatus for selecting representative image | |
CN110012210A (en) | Photographic method, device, storage medium and electronic equipment | |
WO2021000830A1 (en) | Face recognition method, apparatus, computer device, and storage medium | |
CN111209331A (en) | Target object retrieval method and device and electronic equipment | |
CN105791674B (en) | Electronic equipment and focusing method | |
CN113794834B (en) | Image processing method and device and electronic equipment | |
JP2022019753A (en) | Analyzer, analysis method, and program | |
CN112532885B (en) | Anti-shake method and device and electronic equipment | |
CN108702463A (en) | A kind of image processing method, device and terminal | |
CN105868590A (en) | Method and device for processing handwriting data | |
CN111598176B (en) | Image matching processing method and device | |
CN110225243A (en) | Folding screen based shooting control method and device, storage medium and mobile terminal | |
CN110929063A (en) | Album generating method, terminal device and computer readable storage medium | |
CN108024060A (en) | Face snap control method, electronic equipment and storage medium | |
CN106357978A (en) | Image outputting method and device as well as terminal | |
CN110245696A (en) | Illegal incidents monitoring method, equipment and readable storage medium storing program for executing based on video | |
CN112511743B (en) | Video shooting method and device | |
CN113194256A (en) | Shooting method, shooting device, electronic equipment and storage medium | |
CN113010738A (en) | Video processing method and device, electronic equipment and readable storage medium | |
CN108263074A (en) | Localization method, device, terminal device and the readable storage medium storing program for executing of silk-screen halftone |
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 |