CN110462693A - Door lock and recognition methods - Google Patents
Door lock and recognition methods Download PDFInfo
- Publication number
- CN110462693A CN110462693A CN201980001121.9A CN201980001121A CN110462693A CN 110462693 A CN110462693 A CN 110462693A CN 201980001121 A CN201980001121 A CN 201980001121A CN 110462693 A CN110462693 A CN 110462693A
- Authority
- CN
- China
- Prior art keywords
- face
- angle
- door lock
- field
- image
- 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
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
- G06V40/166—Detection; Localisation; Normalisation using acquisition arrangements
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C9/00—Individual registration on entry or exit
- G07C9/00174—Electronically operated locks; Circuits therefor; Nonmechanical keys therefor, e.g. passive or active electrical keys or other data carriers without mechanical keys
- G07C9/00563—Electronically operated locks; Circuits therefor; Nonmechanical keys therefor, e.g. passive or active electrical keys or other data carriers without mechanical keys using personal physical data of the operator, e.g. finger prints, retinal images, voicepatterns
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Lock And Its Accessories (AREA)
Abstract
The application provides a kind of door lock and method, and door lock includes: three-dimensional identification structure, for shooting the first image of face；Processor, for generating driving signal when the first image does not meet default identification condition；Driving structure, for driving the three-dimensional identification structure motion under driving signal driving, to change the angle of the three-dimensional identification structure, so that the first image meets default identification condition.The present embodiment provides in door lock, processor judges whether the first image of three-dimensional identification structure shooting meets default identification condition, when the first image is unsatisfactory for default identification condition, then change the angle of three-dimensional identification structure, so that the first image meets default identification condition.Compared to existing door lock, door lock provided in this embodiment can adjust the angle of three-dimensional identification structure, and three-dimensional identification structure is enabled to shoot the picture for meeting default identification condition.
Description
Technical field
The present invention relates to technical field of face recognition more particularly to a kind of door lock and recognition methods.
Background technique
With the rise of 3D face recognition scheme, more and more products start to increase 2D or 3D face identification functions, such as
Intelligent door lock.
Fig. 1 is the application scenario diagram of existing door lock, and Fig. 2 is the visual field figure of existing door lock.As depicted in figs. 1 and 2, door
The mounting height of lock is relatively with about 1.2 meters of ground, and for the height of 9 years old child generally in 1.2m or so, the height of adult is most
Number is between 1.4 meters to 2 meters.The opposite range that 0.3 meter to 1 meter is likely distributed in the standing distance of door.The length one of face
As within 0.2 meter.So, it is desirable to all above crowds can normal use door lock, then the visual field of structure optical module at least needs
It will be at 100 °.And the visual field of existing door lock is usually no more than 90 °.In addition, it is generally the case that 300 are at least needed on face
Speckle could effectively rebuild 3D face.The size of face is generally at 0.025~0.04 square metre.So when at 1 meter of position, people
Face only accounts for 0.4% or so of whole market area.So at least needing 55000 speckles that could effectively rebuild at 1 meter of position
3D face.
However, the visual field of existing door lock is unable to reach 100 °, clapped when the user to all ages and classes layer identifies
The picture taken the photograph be not able to satisfy identification require, in addition, when user distance farther out when, existing structure optical module can not be in face upslide
55000 speckles are penetrated, and then causes captured picture not to be able to satisfy identification and requires.
Summary of the invention
The application provides a kind of door lock and recognition methods, it is intended to solve existing door lock and carry out in the user to all ages and classes layer
Captured picture is not able to satisfy the technical issues of identification requires when identification, and when user distance farther out when, existing structure
Optical module can not project 55000 speckles on face, and then cause captured picture not to be able to satisfy the technology that identification requires and ask
Topic.
In a first aspect, the present invention provides a kind of door lock, comprising:
Three-dimensional identification structure, for shooting the first image of face；
Processor, for generating driving signal when the first image does not meet default identification condition；
Driving structure, for driving three-dimensional identification structure motion under driving signal driving, to change three-dimensional identification structure
Field of view angle so that the first image meets default identification condition.
Optionally, the first image of face does not meet default identification condition and specifically includes:
The relationship of the visual field of face and three-dimensional identification structure progress identifying processing is that face is in three-dimensional identification structure progress
Except the visual field of identifying processing.
Optionally, the face is in except the visual field and specifically includes:
The ratio of face part and the face in the visual field is less than default value；And/or
The key component of the face is in the visual field.
Optionally, the first image of face does not meet default identification condition and specifically includes:
Total speckle count on face is less than preset quantity.
Optionally, the speckle count in multiple first images on face is counted, to obtain total speckle count.
Optionally, door lock further include: the first shell；Three-dimensional identification structure and the first housing hinge.
Optionally, driving structure includes: driver and electromagnet；Three-dimensional identification structure is equipped with Attraction block；
Driver makes electromagnet be powered, so as to electromagnetic force be generated between electromagnet and Attraction block, to drive three-dimensional identification knot
Structure movement.
Optionally, electromagnet includes: upper electromagnet and lower electromagnet；
Attraction block is between upper electromagnet and lower electromagnet.
Optionally, driving structure includes gear set and motor；Three-dimensional identification structure passes through articulated shaft and the first housing hinge；
Gear in gear set in end is installed on articulated shaft, motor-driven gear group movement, so that gear set band
Dynamic three-dimensional identification structure motion.
Second aspect, the present invention provide a kind of recognition methods, are applied to door lock, and door lock includes: three-dimensional identification structure and drive
Dynamic structure；Method includes:
Obtain the first image of the face of three-dimensional identification structure shooting；
Judge whether the first image meets default identification condition；
If judging result be it is no, move driving structure, to drive three-dimensional identification structure so that the first image meet it is default
Identification condition；
Identifying processing is carried out using the first image.
Optionally, judge whether the first image meets default identification condition, specifically include:
Whether the relationship for judging that face and three-dimensional identification structure carry out the visual field of identifying processing is that face is in three-dimensional identification
Structure carries out within the visual field of identifying processing.
Optionally, the face is in except the visual field and specifically includes:
The ratio of face part and the face in the visual field is less than default value；And/or
The key component of the face is in the visual field.
Optionally, driving structure is moved, to drive three-dimensional identification structure, specifically included:
The current angular of three-dimensional identification structure is obtained according to the first image；
Extract the positional relationship of face and the first image in the first image；
The target angle of three-dimensional identification structure is determined according to current angular and positional relationship；
Make three-dimensional identification structure motion, so that three-dimensional identification structure moves to target angle by current angular.
Optionally, current angular is first angle or second angle；Target angle is first angle or second angle；
And target angle and current angular be not identical.
Optionally, the first field of view angle of three-dimensional identification structure and the sum of the second field of view angle of three-dimensional identification structure are greater than
100°；
Wherein, the first field of view angle is field of view angle when three-dimensional identification structure is located at first angle, the second field of view angle
It is located at field of view angle when second angle for three-dimensional identification structure.
The application provides a kind of door lock and recognition methods, which includes three-dimensional identification structure, driving structure and processing
Device.Processor judges whether the first image of three-dimensional identification structure shooting meets default identification condition, when the first image is unsatisfactory for
When default identification condition, then change the angle of three-dimensional identification structure, so that the first image meets default identification condition.Compared to existing
Some door locks, door lock provided in this embodiment can adjust the angle of three-dimensional identification structure, and three-dimensional identification structure is clapped
Take out the picture for meeting default identification condition.
Detailed description of the invention
In order to illustrate the technical solutions in the embodiments of the present application or in the prior art more clearly, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is this Shen
Some embodiments please for those of ordinary skill in the art without any creative labor, can be with
It obtains other drawings based on these drawings.
Fig. 1 is the application scenario diagram of existing door lock；
Fig. 2 is the visual field figure of existing door lock；
Fig. 3 is the structural schematic diagram of present invention door lock shown according to an exemplary embodiment；
Fig. 4 is the visual field schematic diagram based on the door lock shown in embodiment illustrated in fig. 3；
Fig. 5 is another visual field schematic diagram based on the door lock shown in embodiment illustrated in fig. 3；
Fig. 6 is the structural schematic diagram for the door lock that the present invention is shown according to another exemplary embodiment；
Fig. 7 is the working principle diagram based on the door lock shown in embodiment illustrated in fig. 6；
Fig. 8 is the structural schematic diagram for the door lock that the present invention is shown according to a further exemplary embodiment；
Fig. 9 is structural schematic diagram of the present invention according to the door lock shown in another exemplary embodiment；
Figure 10 is the working principle diagram based on the door lock shown in embodiment illustrated in fig. 9；
Figure 11 is structural schematic diagram of the present invention according to the door lock shown in another exemplary embodiment again；
Figure 12 is the working principle diagram based on the door lock shown in embodiment illustrated in fig. 11；
Figure 13 is the schematic diagram of present invention recognition methods shown according to an exemplary embodiment；
Figure 14 is the schematic diagram for the recognition methods that the present invention is shown according to another exemplary embodiment.
Specific embodiment
To keep the purposes, technical schemes and advantages of the embodiment of the present application clearer, below in conjunction with the embodiment of the present application
In attached drawing, the technical scheme in the embodiment of the application is clearly and completely described, it is clear that described embodiment is
Some embodiments of the present application, instead of all the embodiments.Based on the embodiment in the application, those of ordinary skill in the art
Every other embodiment obtained without creative efforts, shall fall in the protection scope of this application.
The description and claims of this application and term " first ", " second ", " third ", " in above-mentioned attached drawing
The (if present)s such as four " are to be used to distinguish similar objects, without being used to describe a particular order or precedence order.It should manage
The data that solution uses in this way are interchangeable under appropriate circumstances, so as to embodiments herein described herein, such as can be with
Sequence other than those of illustrating or describing herein is implemented.In addition, term " includes " and " having " and their times
What is deformed, it is intended that cover it is non-exclusive include, for example, contain the process, method of a series of steps or units, system,
Product or equipment those of are not necessarily limited to be clearly listed step or unit, but may include be not clearly listed or for
The intrinsic other step or units of these process, methods, product or equipment.
The application provides a kind of door lock and recognition methods, it is intended to solve existing door lock and carry out in the user to all ages and classes layer
Captured picture is not able to satisfy the technical issues of identification requires when identification, and when user distance farther out when, existing structure
Optical module can not project 55000 speckles on face, and then cause captured picture not to be able to satisfy the technology that identification requires and ask
Topic.
Fig. 3 is the structural schematic diagram of present invention door lock shown according to an exemplary embodiment.As shown in figure 3, this implementation
The door lock 100 that example provides, comprising: three-dimensional identification structure 101, driving structure 102 and processor 103.
Above-mentioned three-dimensional identification structure 101 is used to shoot the first image of face.Processor 103 is for judging that the first image is
It is no to meet default identification condition and generate driving signal if the first image does not meet default identification condition.Driving structure is being driven
Dynamic signal driving is lower to drive three-dimensional identification structure motion, to change the field of view angle of three-dimensional identification structure, so that the first image accords with
Close default identification condition.
The present embodiment provides in door lock, it is default that processor judges whether the first image of three-dimensional identification structure shooting meets
Identification condition then changes the field of view angle of three-dimensional identification structure, so that first when the first image is unsatisfactory for default identification condition
Image meets default identification condition.Compared to existing door lock, door lock provided in this embodiment can adjust three-dimensional identification structure
Field of view angle, enable three-dimensional identification structure to shoot the picture for meeting default identification condition.
Door lock shown in another exemplary embodiment of the present invention includes: three-dimensional identification structure, driving structure and processor.
Above-mentioned door lock is installed on a door, and face is stood in front of the door, and three-dimensional identification structure passes through the first image of shooting face,
Processor carries out the visual field relationship of identifying processing according to the first image zooming-out face and three-dimensional identification structure.If face is known in three-dimensional
Other structure carries out not generating driving signal within the visual field of identifying processing.If face carries out identifying processing in three-dimensional identification structure
Visual field except, then generate driving signal.Driving structure drives three-dimensional identification structure motion under the driving of driving signal, to change
Become the field of view angle of three-dimensional identification structure, so that face is in three-dimensional identification structure and carries out in the visual field of identifying processing.
The working principle of door lock provided by the invention is described in detail below:
Fig. 4 is the visual field schematic diagram based on the door lock shown in embodiment illustrated in fig. 3.As shown in figure 4, three-dimensional identification structure
Angle with horizontal plane is α1, the field of view angle of three-dimensional identification structure is θ, and the mounting height of door lock is 1.2, the height of face by
It is fluctuated between 1m to 2m, face standing place is fluctuated between 0.3m to 1m with a distance from door lock.
Three-dimensional identification structure and the angle of horizontal plane are α1When, it is assumed that the length of face is 0.2m, and three-dimensional identification structure is only
Energy height is more than that the face of 1.4m is identified, when face standing place only has 0.3m from door lock, possibly can not be to height
The face of 1.4m is identified.When three-dimensional identification structure detection identifies structure to when can not identify to face, adjustment is three-dimensional
Field of view angle.
Fig. 5 is another visual field schematic diagram based on the door lock shown in embodiment illustrated in fig. 3.As shown in figure 5, when being in angle
α1Three-dimensional identification structure detection arrive when can not be identified to face, driving structure driving is three-dimensional in door lock identifies structure, makes
Three-dimensional identification structure and the angle of horizontal plane are α2.The field of view angle of three-dimensional identification structure is still θ, but since three-dimensional identifies structure
With the angle change of horizontal plane, three-dimensional identification structure, which can be realized, identifies the face of height 1m, expands the view of door lock
Rink corner degree.
Door lock provided in this embodiment, three-dimensional identification structure are used to carry out identifying processing to face, when face is in three-dimensional
When identifying except the visual field of structure, driving structure drives three-dimensional identification structure motion, to change the field angle of three-dimensional identification structure
Degree so that face is in three-dimensional identification structure and carries out in the visual field of identifying processing, and then expands the field range of door lock, Jin Erke
To carry out identifying processing to the face in all ages and classes layer.
The knot of door lock in the structure and embodiment illustrated in fig. 3 of door lock shown in another exemplary embodiment provided by the invention
Structure is identical.Difference is only that: three-dimensional identification structure shoots the first image of first face, and processor extracts above-mentioned first image
Speckle count on middle face.If speckle count is more than or equal to preset quantity, driving signal is not generated.If speckle count is less than pre-
If quantity, driving signal is generated.Driving structure drives three-dimensional identification structure motion under the driving of driving signal, to change three-dimensional
Identify the field of view angle of structure, three-dimensional identification structure shoots the first image again under new field of view angle, and processor extracts the
Speckle count in one image on face, and the speckle count in multiple first images on face is counted, it is total on face to obtain
Speckle count does not generate driving signal when total speckle count is more than or equal to preset quantity.If total speckle count is less than present count
Amount generates driving signal.Driving structure drives three-dimensional identification structure motion under the driving of driving signal, to change three-dimensional identification
The field of view angle of structure, until total speckle count is more than or equal to preset quantity.
In door lock provided in this embodiment, changes the field of view angle of three-dimensional identification structure by driving structure, shoot more
The first picture is opened, then counts the speckle count of face in multiple first pictures, the speckle count for passing through multiple the first pictures is superimposed
Mode finally carries out recognition of face using multiple first pictures so that speckle count meets default identification condition on face.
Fig. 6 is the structural schematic diagram for the door lock that the present invention is shown according to another exemplary embodiment.As shown in fig. 6, this reality
The door lock 200 for applying example offer includes: three-dimensional identification structure 201, driving structure 202, processor 203, memory 204 and first
Shell.Wherein, driving structure 202 includes driver 205 and executing agency 206.Three-dimensional identification structure 201 include second housing,
Infrared sensor, RGB sensor, structured light projector and light compensating lamp.
In above-mentioned door lock, processor 203 connects with three-dimensional identification structure 201, driver 205 and memory 204 respectively
It connects, driver 205 is connect with executing agency 206, and executing agency 206 connect with three-dimensional identification structure 201.Three-dimensional identification structure
201 and first housing hinge.Infrared sensor, RGB sensor, structured light projector and light compensating lamp are respectively positioned in second housing
Portion.
In above-mentioned door lock, presetting identification condition is that face is within the visual field of three-dimensional identification structure.Three-dimensional identification knot
First image of infrared sensor or RGB sensor shooting face in structure 201, and the first image is sent to processor 203,
Processor 203 extracts the positional relationship of face and the first image in the first image after receiving the first image.Wherein, position
Relationship can be with are as follows: face is in the middle position of the first image, and face is in the marginal position of the first image.According to positional relationship
Determine that face and three-dimensional identification structure carry out the relationship of identifying processing visual field.Wherein, face is identified with three-dimensional identification structure
The relationship of processing visual field can be divided into: face is in except the visual field of three-dimensional identification structure or face is in three-dimensional identification structure
In visual field.
Judging whether face is within the visual field of three-dimensional identification structure can be with are as follows: judges human face region in the first image
Size, perhaps judges whether face key component has the size and key for judging human face region in the first image or simultaneously
Whether part is in the first image.
Such as: the first judgment mode are as follows: there are 2/3 or more human face regions in the first image, then can be directly sharp
Face identification is carried out with first image.Second of judgment mode are as follows: these faces of eyebrow, eyes, nose and mouth
Feature then directly can carry out face identification using second image in the second image.The third judgment mode are as follows: In
There are 2/3 or more human face region in second image, and eyebrow, eyes, nose and mouth these face characteristics are in the second figure
As in, then face identification directly can be carried out using second image.
When face is in the marginal position of the second image, and above-mentioned judging result be it is no, show that face is in three-dimensional identification
Outside the visual angle of structure, field of view angle position locating for three-dimensional identification structure is improper, and processor obtains three-dimensional knowledge according to the first image
The current field angle of other structure, and the three-dimensional field of regard angle for identifying structure is determined according to current field angles and positions relationship
Degree；To generate driving signal according to field of regard angle, driving signal drives three-dimensional identification structure phase for controlling driving structure
First shell is rotated, so that three-dimensional identify structure by current field angular turn to field of regard angle, so that face
Into in the visual field of three-dimensional identification structure.
As a kind of specific embodiment, when the height of face fluctuates between 1m to 2m, the position that face is stood is from door
The distance of lock fluctuates between 0.3m to 1m, and for the height of door lock in 1.2m, the field range of door lock needs to reach 100 °, and door
The field range of lock, therefore it may only be necessary to change 1 three-dimensional identification structure and horizontal plane angle, can make generally at 60 ° to 90 °
The field of view angle of door lock is expanded to 100 °.
The scheme for only changing the angle of 1 three-dimensional identification structure and horizontal plane is described below: three-dimensional in this scenario to identify
Structure is only in two angle changes, i.e. first angle and second angle.And the first field of view angle and three-dimensional of three-dimensional identification structure
Identify that the sum of second field of view angle of structure is greater than 100 °；Wherein, the first field of view angle is that three-dimensional identification structure is located at first jiao
Field of view angle when spending, the second field of view angle are field of view angle when three-dimensional identification structure is located at second angle.
Fig. 7 is the working principle diagram based on the door lock shown in embodiment illustrated in fig. 6.As shown in fig. 7, three-dimensional identification structure is clapped
The first image is taken the photograph, processor extracts the positional relationship of face and the first image in the first image, and judges three according to positional relationship
The current field angle of dimension identification structure.When face is located at the lower section of the first image, it can be determined that three-dimensional identification structure is worked as
Preceding field of view angle is first angle α1.When face is located at the top of the first image, it can be determined that three-dimensional identifies the current of structure
Field of view angle is second angle α2。
Processor extracts the positional relationship of face and the first image in the first image.And according to positional relationship determine face with
Three-dimensional identification structure carries out the relationship of identifying processing visual field.If face is in except the visual field of three-dimensional identification structure, processor
The current field angle of three-dimensional identification structure is obtained, and three-dimensional identification structure is determined according to current field angles and positions relationship
Field of regard angle.If the current field angle of three-dimensional identification structure is first angle α1, and face is located under the first image
Side, then field of regard angle is second angle α2, executing agency's drive is three-dimensional to identify that structure turns to second angle α2.If three-dimensional
The current field angle that identification structure is is second angle α2, face is located at the top of the first image, then field of regard angle is
First angle α1, executing agency's drive is three-dimensional to identify that structure turns to first angle α1。
In door lock provided in this embodiment, three-dimensional identification structure first shoots the first image, and processor is according to the first image
It obtains face and three-dimensional identification structure carries out the relationship of identifying processing visual field.When face is in except the visual field of three-dimensional identification structure
When, then driver is controlled by processor, driver generates the movement of driving signal driving executing agency, to drive three-dimensional identification structure
It is rotated relative to the first shell, changes the field of view angle of three-dimensional identification structure, so that face is in three-dimensional identification structure and is identified
In the visual field of processing, and then expand the field range of door lock, and then the face in all ages and classes layer can be carried out at identification
Reason.
The knot of door lock in the structure and embodiment illustrated in fig. 6 of door lock shown in another exemplary embodiment provided by the invention
Structure is identical.Difference is only that: the first image of infrared sensor or RGB sensor shooting face in three-dimensional identification structure, and
First image is sent to processor, processor is extracted in above-mentioned first image and dissipated on face after receiving the first image
Spot quantity.If speckle count is more than or equal to preset quantity, driving signal is not generated.If speckle count is less than preset quantity, generate
Driving signal.Driving structure drives three-dimensional identification structure motion under the driving of driving signal, to change three-dimensional identification structure
Field of view angle, so that total speckle count is more than or equal to preset quantity on face.
Door lock provided in this embodiment controls driving structure by processor, and driving structure generates driving signal driving and executes
Mechanism kinematic changes the field of view angle of three-dimensional identification structure, to drive three-dimensional identification structure to rotate relative to the first shell to make one
Total speckle count is more than or equal to preset quantity on the face, finally carries out recognition of face using multiple first pictures.
Fig. 8 is the structural schematic diagram for the door lock that the present invention is shown according to a further exemplary embodiment.As shown in figure 8, this reality
The door lock 300 for applying example offer includes: three-dimensional identification structure 301, driving structure 302, processor 303, memory 304 and first
Shell.Wherein, driving structure 302 includes driver 305 and electromagnet 306.Three-dimensional identification structure 301 includes second housing, red
Outer sensor, RGB sensor, structured light projector and light compensating lamp.Three-dimensional identification structure and the first housing hinge, three-dimensional identification
Structure 301 is equipped with Attraction block.Attraction block can be located inside second housing or outside second housing.The material of Attraction block is magnetic
Iron or the material that can be adsorbed by magnet.
In above-mentioned door lock, processor 303 connects with three-dimensional identification structure 301, driver 305 and memory 304 respectively
It connects, driver 305 is connect with electromagnet 306, and electromagnet 306 drives three-dimensional identification by generating electromagnetic force between Attraction block
Structure 301 moves.
When the work of above-mentioned door lock, three-dimensional identification structure shoots the first picture, and processor obtains face according to the first image
The relationship of identifying processing visual field is carried out with three-dimensional identification structure.If face is in except the visual field of three-dimensional identification structure, processing
Device controls driver, and driver makes electromagnet be powered, so as to electromagnetic force be generated between electromagnet and Attraction block, to drive three-dimensional knowledge
Other structure is rotated relative to the first shell, changes the field of view angle of three-dimensional identification structure, and face is made to be in the view of three-dimensional identification structure
In the range of field.
In door lock provided in this embodiment, executing agency is electromagnet, the electromagnetic force generated when being powered using electromagnet
Three-dimensional identification structure motion is driven, the field of view angle of three-dimensional identification structure is changed, and then expands the field angle of three-dimensional identification structure
Degree, to realize to the identifying processing of all ages and classes layer face, and electromagnet reaction block, can rapid handoff angle, save the time.
The knot of door lock in the structure and embodiment illustrated in fig. 8 of door lock shown in another exemplary embodiment provided by the invention
Structure is identical.Difference is only that: the first image of infrared sensor or RGB sensor shooting face in three-dimensional identification structure, and
First image is sent to processor, processor is extracted in above-mentioned first image and dissipated on face after receiving the first image
Spot quantity.If speckle count is more than or equal to preset quantity, driving signal is not generated.If speckle count is less than preset quantity, generate
Driving signal.Driver makes electromagnet be powered under driving signal control, so as to electromagnetic force is generated between electromagnet and Attraction block,
To drive three-dimensional identification structure to rotate relative to the first shell, change the field of view angle of three-dimensional identification structure, so as to always dissipate on face
Spot quantity is more than or equal to preset quantity.
In door lock provided in this embodiment, executing agency is electromagnet, the electromagnetic force generated when being powered using electromagnet
Three-dimensional identification structure motion is driven, changes the field of view angle of three-dimensional identification structure, improves speckle count on face, and electromagnet is anti-
Block is answered, field of view angle can be switched rapidly, save the time.
Fig. 9 is structural schematic diagram of the present invention according to the door lock shown in another exemplary embodiment.As shown in figure 9, this reality
The door lock 400 for applying example offer includes: three-dimensional identification structure 401, driving structure 402, processor 403, memory 404 and first
Shell.Wherein, driving structure 402 includes driver 405, upper electromagnet 406 and lower electromagnet 407.Three-dimensional identification structure and the
One housing hinge, three-dimensional identification structure 401 are equipped with Attraction block, and Attraction block be located at upper electromagnet 406 and lower electromagnet 407 it
Between.
In above-mentioned door lock, processor 403 is electric with three-dimensional identification structure 401, driver 405 and memory 404 respectively
Connection, driver 405 are electrically connected with upper electromagnet 406 and lower electromagnet 407 respectively, and upper electromagnet 406 and lower electromagnet 307 are equal
Three-dimensional identification structure 301 is driven to move by electromagnetic force.
Figure 10 is the working principle diagram based on the door lock shown in embodiment illustrated in fig. 9.As shown in Figure 10, three-dimensional identification structure
The first picture is shot, processor obtains face according to the first image and three-dimensional identification structure carries out the relationship of identifying processing visual field.
If face is in except the visual field of three-dimensional identification structure, processor obtains the current field angle of three-dimensional identification structure.And root
The field of regard angle of three-dimensional identification structure is determined according to current field angles and positions relationship, and is generated according to field of regard angle
Driving signal.
If the current field angle of three-dimensional identification structure is first angle α1.Driver makes lower electromagnet be powered, so that under
Electromagnet generates electromagnetic force, to drive three-dimensional identification structure from first angle α1Move to second angle α2.And then change three-dimensional knowledge
The field of view angle of other structure is in face in the field range of three-dimensional identification structure.
If the current field angle of three-dimensional identification structure is second angle α2.Processor controls driver, and driver makes
Electromagnet is powered, so that upper electromagnet generates electromagnetic force, to drive three-dimensional identification structure from second angle α2Move to first jiao
Spend α1.And then change the field of view angle of three-dimensional identification structure, it is in face in the field range of three-dimensional identification structure.
In door lock provided in this embodiment, door lock is driven to switch in two angles by upper electromagnet and lower electromagnet,
By changing the angle of a door lock, changes the field of view angle of three-dimensional identification structure, face can be made to be in three-dimensional identification structure
Field range in, the control difficulty of processor is reduced, so that the door latch structure is simple.
Figure 11 is structural schematic diagram of the present invention according to the door lock shown in another exemplary embodiment again.As shown in figure 11,
Door lock 500 provided in this embodiment includes: three-dimensional identification structure 501, driving structure 502, processor 503 and memory 504.
Wherein, driving structure 502 includes motor 505 and gear set 506.
In above-mentioned door lock, processor 503 is connect with three-dimensional identification structure 501, motor 502 and memory 504 respectively,
The driving wheel of motor 505 and gear set 506 is mechanically connected, and the driven wheel of gear set 506 drives three-dimensional identification structure 501 to move.
Figure 12 is the working principle diagram based on the door lock shown in embodiment illustrated in fig. 11.As shown in figure 12, when above-mentioned door lock
When work, three-dimensional identification structure shoots the first picture, and processor obtains face according to the first image and three-dimensional identification structure carries out
The relationship of identifying processing visual field.If face is in except the visual field of three-dimensional identification structure, processor controls motor, motor rotation
Driving wheel rotation is driven, driving wheel drives driven wheel rotation, and driven wheel drives three-dimensional identification structure motion, changes three-dimensional identification knot
The field of view angle of structure is in face in the field range of three-dimensional identification structure.
In above-mentioned door lock, the rotational angle of driving wheel can be controlled by controlling rotation time and the revolving speed of motor,
And then control the rotational angle of three-dimensional identification structure, when processor detects that face is not in the visual field of door lock, processor
The current field angle of three-dimensional identification structure is obtained, and field of regard angle is determined according to current field angles and positions relationship,
Driving signal is generated further according to field of regard angle, to control the rotation time and revolving speed of the motor of motor.
In door lock provided in this embodiment, executing agency is gear set, be may be implemented accurately by drive gear set
By the field of view angle of three-dimensional identification module by current field angular turn to field of regard angle, face is made to be in three-dimensional identification mould
In the field range of block, to adapt to the recognition of face of all ages and classes layer.
The knot of door lock in the structure and embodiment illustrated in fig. 9 of door lock shown in another exemplary embodiment provided by the invention
Structure is identical.Difference is only that: processor extracts in above-mentioned first image speckle number on face after receiving the first image
Amount.If speckle count is more than or equal to preset quantity, driving signal is not generated.If speckle count is less than preset quantity, driving is generated
Signal.Driving signal control rotates motor, and then is rotated by motor driven driving wheel, and driving wheel drives driven wheel rotation,
Driven wheel drives three-dimensional identification structure motion, changes the field of view angle of three-dimensional identification structure, so that total speckle count is big on face
In being equal to preset quantity, recognition of face finally is carried out using multiple first pictures.
Figure 13 is the schematic diagram of present invention recognition methods shown according to an exemplary embodiment.As shown in figure 13, this reality
The recognition methods for applying example offer is applied to door lock, and door lock includes: three-dimensional identification structure.The recognition methods includes the following steps:
S601, the first image for obtaining the face that three-dimensional identification structure is shot.
S602, judge whether the first image meets default identification condition；If the determination result is YES, into S603, otherwise, into
Enter S604.
More specifically, when default identification condition is that face is within the visual field that three-dimensional identification structure carries out identifying processing
When.It obtains in the following way and obtains face and the three-dimensional relationship for identifying structure and carrying out the visual field of identifying processing:
Obtain the first image of the face of three-dimensional identification structure shooting
The first image for obtaining the face of three-dimensional identification structure shooting, extracts the area size of the face in the first image,
If having 2/3 face in the first image, it may determine that face in the visual field of door lock.Or further extract face
Five features, five features is judged whether in the first image, if five features may determine that in the first image
Feature is in the visual field of door lock.Or it extracts the area size of face and extracts the five features of face, and judge five
Official's feature judges there is 2/3 face in the first image in the first image, then may determine that feature in the visual field of door lock
It is interior.
When whether total speckle count meets preset quantity to the behaviour of default identification condition on the face.It extracts in every first image
Speckle count on face, and speckle count on face is counted in multiple first images, to obtain total speckle count on face.
S603, move driving structure, to drive three-dimensional identification structure motion, so that the first image meets default identification item
Part.
More specifically, making three-dimensional identification structure motion, to change the field of view angle of three-dimensional identification structure, so that face is in
In the visual field of three-dimensional identification structure.
S604, identifying processing is carried out using the first image.
In method provided in this embodiment, the present embodiment provides in door lock, the three-dimensional identification structure of processor judgement is clapped
Whether the first image taken the photograph meets default identification condition, when the first image is unsatisfactory for default identification condition, then changes three-dimensional knowledge
The field of view angle of other structure, so that the first image meets default identification condition.It is provided in this embodiment compared to existing door lock
Door lock can adjust the field of view angle of three-dimensional identification structure, and three-dimensional identification structure is enabled to shoot the default identification condition of satisfaction
Picture.
Figure 14 is the schematic diagram for the recognition methods that the present invention is shown according to another exemplary embodiment.When the height of face exists
It is fluctuated between 1m to 2m, the position that face is stood is fluctuated between 0.2m to 1m with a distance from door lock, and the height of door lock is in 1.2m
When, the field range of door lock needs to reach 100 °, and the field range of door lock is at 60 ° to 90 °, therefore it may only be necessary to change 1 door
Lock and horizontal plane angle, can make the field of view angle of door lock be expanded to 100 °.
As shown in figure 14, recognition methods provided in this embodiment includes the following steps:
S701, the first image for obtaining the face that three-dimensional identification structure is shot.
S702, judge whether the first image meets default identification condition；If the determination result is YES, into S707, otherwise, into
Enter S703.
S703, the current field angle for obtaining three-dimensional identification structure.
More specifically, in the present embodiment, the current field angle of three-dimensional identification structure is determined according to second position relationship.
When face is located at the top edge of the first image, current field angle is second angle.When face is located at the following of the first image
When edge, current field angle is first angle.
There are two the locating angles of three-dimensional identification structure: first angle or second angle.First angle and second jiao
Degree.First field of view angle is field of view angle when three-dimensional identification structure is located at first angle, and the second field of view angle is three-dimensional identification
Structure is located at field of view angle when second angle.Second view of the first field of view angle of three-dimensional identification structure and three-dimensional identification structure
The sum of rink corner degree is greater than 100 °.
S704, the positional relationship for extracting face and the first image in the first image.
More specifically, positional relationship includes face position and face area size in the first image in the first image.
Face position in the first image can be divided into middle position and marginal position.Area size can be in the first image for face
Are as follows: the key area of face area size in the first image.Or the whole area size in the first image of face.Such as:
These key areas of eyes, nose, mouth.
S705, the field of regard angle that three-dimensional identification structure is determined according to current field angles and positions relationship.
More specifically, face is located at the lower edge of the first image, field of regard if current field angle is first angle
Angle is second angle.If current field angle is second angle, face is located at the first image top edge, then field of regard angle
For first angle.
S706, three-dimensional identification structure motion is driven, so that three-dimensional identification structure is regarded by current field angular movement to target
Rink corner degree, so that the first image meets default identification condition.
S707, recognition of face is carried out using the first image.
In recognition methods provided in this embodiment, three-dimensional is switched in two angles by structure, primary by changing
The field of view angle of three-dimensional identification structure can be such that face is in the field range of three-dimensional identification structure, reduce recognition methods
Difficulty, so that the door latch structure is simple.
It will appreciated by the skilled person that the door lock in text is other than the door lock that ordinary family user installs,
It can also refer to all kinds of gate inhibition's door-locking systems of public place installation.
Those of ordinary skill in the art will appreciate that: realize that all or part of the steps of above-mentioned each method embodiment can lead to
The relevant hardware of program instruction is crossed to complete.Program above-mentioned can be stored in a computer readable storage medium.The journey
When being executed, execution includes the steps that above-mentioned each method embodiment to sequence；And storage medium above-mentioned include: ROM, RAM, magnetic disk or
The various media that can store program code such as person's CD.
Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention., rather than its limitations；To the greatest extent
Pipe present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that: its according to
So be possible to modify the technical solutions described in the foregoing embodiments, or to some or all of the technical features into
Row equivalent replacement；And these are modified or replaceed, various embodiments of the present invention technology that it does not separate the essence of the corresponding technical solution
The range of scheme.
Claims (15)
1. a kind of door lock characterized by comprising
Three-dimensional identification structure, for shooting the first image of face；
Processor, for generating driving signal when the first image does not meet default identification condition；
Driving structure, for driving the three-dimensional identification structure motion under driving signal driving, to change the three-dimensional
The field of view angle for identifying structure, so that the first image meets the default identification condition.
2. door lock according to claim 1, which is characterized in that the first image of the face does not meet default identification condition
It specifically includes:
The relationship for the visual field that the face and the three-dimensional identification structure carry out identifying processing is that the face is in the visual field
Except.
3. door lock according to claim 1, which is characterized in that the face is in except the visual field and specifically includes:
The ratio of face part and the face in the visual field is less than default value；And/or
The key component of the face is in the visual field.
4. door lock according to claim 1, which is characterized in that the first image of the face does not meet default identification condition
It specifically includes:
Total speckle count on the face is less than preset quantity.
5. door lock according to claim 4, which is characterized in that count dissipating on face described in multiple the first images
Spot quantity, to obtain total speckle count.
6. door lock according to any one of claims 1 to 5, which is characterized in that the door lock further include: the first shell；Institute
State three-dimensional identification structure and first housing hinge.
7. door lock according to claim 6, which is characterized in that the driving structure includes driver and electromagnet, described
Three-dimensional identification structure is equipped with Attraction block；
The driver, which is controlled by the driving signal, makes the electromagnet be powered so that the electromagnet and the Attraction block it
Between generate electromagnetic force, to drive the three-dimensional identification structure motion.
8. door lock according to claim 7, which is characterized in that the electromagnet includes: upper electromagnet and lower electromagnet；
The Attraction block is between the upper electromagnet and the lower electromagnet.
9. door lock according to claim 6, which is characterized in that the driving structure includes gear set and motor；Described three
Dimension identification structure passes through articulated shaft and first housing hinge；
Gear in the gear set in end is installed on the articulated shaft, gearset motions described in the motor driven,
So that three-dimensional described in the gear set drive identifies structure motion.
10. a kind of recognition methods, which is characterized in that be applied to door lock, the door lock includes: three-dimensional identification structure and driving knot
Structure；The described method includes:
Obtain the first image of the face of the three-dimensional identification structure shooting；
Judge whether the first image meets default identification condition；
If judging result be it is no, move the driving structure, to drive the three-dimensional identification structure motion, so that described first
Image meets the default identification condition；
Identifying processing is carried out using the first image.
11. according to the method described in claim 10, it is characterized in that, described judge whether the first image meets default knowledge
Other condition, specifically includes:
Judge that the face carries out whether the relationship of the visual field of identifying processing is that the face is in the three-dimensional identification structure
The three-dimensional identification structure carries out within the visual field of identifying processing.
12. according to the method for claim 11, which is characterized in that the face is in except the visual field and specifically includes:
The ratio of face part and the face in the visual field is less than default value；And/or
The key component of the face is in the visual field.
13. method according to claim 11 or 12, which is characterized in that it is described to move the driving structure, to drive
The three-dimensional identification structure motion, specifically includes:
The three-dimensional, which is obtained, according to the first image identifies current field angle locating for structure；
Extract the positional relationship of face and the first image in the first image；
The field of regard angle of the three-dimensional identification structure is determined according to the current field angle and the positional relationship；
The driving structure drives the three-dimensional identification structure, so that the three-dimensional identification structure is transported by the current field angle
It moves to the field of regard angle.
14. according to the method for claim 13, which is characterized in that the current field angle is first angle or second
Angle；The field of regard angle is the first angle or the second angle；And the field of regard angle and described
Current field angle is not identical.
15. according to the method for claim 14, which is characterized in that the sum of the first field of view angle and the second field of view angle are greater than
100°；
Wherein, first field of view angle is field of view angle when the three-dimensional identification structure is located at the first angle, described
Second field of view angle is field of view angle when the three-dimensional identification structure is located at the second angle.
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| PCT/CN2019/093876 WO2020258304A1 (en) | 2019-06-28 | 2019-06-28 | Door lock and recognition method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110462693A true CN110462693A (en) | 2019-11-15 |
| CN110462693B CN110462693B (en) | 2022-04-22 |
Family
ID=68492784
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201980001121.9A Active CN110462693B (en) | 2019-06-28 | 2019-06-28 | Door lock and identification method |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN110462693B (en) |
| WO (1) | WO2020258304A1 (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114046718A (en) * | 2022-01-14 | 2022-02-15 | 深圳市创腾智能电子有限公司 | Swing gate swing angle detection equipment and detection method based on image |
Citations (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH08329213A (en) * | 1995-05-31 | 1996-12-13 | Yazaki Corp | Detector and counter for passing object |
| CN104077804A (en) * | 2014-06-09 | 2014-10-01 | 广州嘉崎智能科技有限公司 | Method for constructing three-dimensional human face model based on multi-frame video image |
| JP2017122376A (en) * | 2016-01-08 | 2017-07-13 | 日本電産リード株式会社 | Iris authentication device for door and iris authentication system |
| CN107093230A (en) * | 2017-03-28 | 2017-08-25 | 上海斐讯数据通信技术有限公司 | The cloud management method and its system of a kind of intelligent video camera head |
| CN107146305A (en) * | 2017-05-02 | 2017-09-08 | 上海灵至科技有限公司 | Unlocking method and door lock based on recognition of face |
| CN108052506A (en) * | 2017-12-28 | 2018-05-18 | 广东欧珀移动通信有限公司 | Natural language processing method, apparatus, storage medium and electronic equipment |
| CN207586943U (en) * | 2017-11-14 | 2018-07-06 | 南京甄视智能科技有限公司 | For the 3D face identification devices with automatic regulation function of bank |
| WO2018133027A1 (en) * | 2017-01-20 | 2018-07-26 | 深圳大学 | Grayscale constraint-based method and apparatus for integer-pixel search for three-dimensional digital speckle pattern |
| CN108549867A (en) * | 2018-04-12 | 2018-09-18 | Oppo广东移动通信有限公司 | Image processing method, device, computer readable storage medium and electronic equipment |
| CN109086694A (en) * | 2018-07-17 | 2018-12-25 | 北京量子光影科技有限公司 | A kind of face identification system and method |
| CN109087382A (en) * | 2018-08-01 | 2018-12-25 | 宁波发睿泰科智能科技有限公司 | A kind of three-dimensional reconstruction method and 3-D imaging system |
| CN109184358A (en) * | 2018-10-09 | 2019-01-11 | 芜湖市越泽机器人科技有限公司 | Intelligent door lock system with recognition of face |
| CN109284597A (en) * | 2018-11-22 | 2019-01-29 | 北京旷视科技有限公司 | A kind of face unlocking method, device, electronic equipment and computer-readable medium |
| CN208488784U (en) * | 2018-07-06 | 2019-02-12 | 北京驭光科技发展有限公司 | It enters control system |
| CN109359648A (en) * | 2018-12-08 | 2019-02-19 | 佛山市伟邦电子科技有限公司 | A kind of system for carrying out recognition of face to people of different heights |
| CN109501722A (en) * | 2017-09-15 | 2019-03-22 | 南京志超汽车零部件有限公司 | A kind of optical module of vehicle anti-theft 3D face identification system |
| CN109903328A (en) * | 2017-12-11 | 2019-06-18 | 宁波盈芯信息科技有限公司 | A kind of device and method that the object volume applied to smart phone measures |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107590454A (en) * | 2017-09-04 | 2018-01-16 | 江苏非寻信息技术有限公司 | A kind of safety check detection means with iris recognition technology |
-
2019
- 2019-06-28 WO PCT/CN2019/093876 patent/WO2020258304A1/en active Application Filing
- 2019-06-28 CN CN201980001121.9A patent/CN110462693B/en active Active
Patent Citations (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH08329213A (en) * | 1995-05-31 | 1996-12-13 | Yazaki Corp | Detector and counter for passing object |
| CN104077804A (en) * | 2014-06-09 | 2014-10-01 | 广州嘉崎智能科技有限公司 | Method for constructing three-dimensional human face model based on multi-frame video image |
| JP2017122376A (en) * | 2016-01-08 | 2017-07-13 | 日本電産リード株式会社 | Iris authentication device for door and iris authentication system |
| WO2018133027A1 (en) * | 2017-01-20 | 2018-07-26 | 深圳大学 | Grayscale constraint-based method and apparatus for integer-pixel search for three-dimensional digital speckle pattern |
| CN107093230A (en) * | 2017-03-28 | 2017-08-25 | 上海斐讯数据通信技术有限公司 | The cloud management method and its system of a kind of intelligent video camera head |
| CN107146305A (en) * | 2017-05-02 | 2017-09-08 | 上海灵至科技有限公司 | Unlocking method and door lock based on recognition of face |
| CN109501722A (en) * | 2017-09-15 | 2019-03-22 | 南京志超汽车零部件有限公司 | A kind of optical module of vehicle anti-theft 3D face identification system |
| CN207586943U (en) * | 2017-11-14 | 2018-07-06 | 南京甄视智能科技有限公司 | For the 3D face identification devices with automatic regulation function of bank |
| CN109903328A (en) * | 2017-12-11 | 2019-06-18 | 宁波盈芯信息科技有限公司 | A kind of device and method that the object volume applied to smart phone measures |
| CN108052506A (en) * | 2017-12-28 | 2018-05-18 | 广东欧珀移动通信有限公司 | Natural language processing method, apparatus, storage medium and electronic equipment |
| CN108549867A (en) * | 2018-04-12 | 2018-09-18 | Oppo广东移动通信有限公司 | Image processing method, device, computer readable storage medium and electronic equipment |
| CN208488784U (en) * | 2018-07-06 | 2019-02-12 | 北京驭光科技发展有限公司 | It enters control system |
| CN109086694A (en) * | 2018-07-17 | 2018-12-25 | 北京量子光影科技有限公司 | A kind of face identification system and method |
| CN109087382A (en) * | 2018-08-01 | 2018-12-25 | 宁波发睿泰科智能科技有限公司 | A kind of three-dimensional reconstruction method and 3-D imaging system |
| CN109184358A (en) * | 2018-10-09 | 2019-01-11 | 芜湖市越泽机器人科技有限公司 | Intelligent door lock system with recognition of face |
| CN109284597A (en) * | 2018-11-22 | 2019-01-29 | 北京旷视科技有限公司 | A kind of face unlocking method, device, electronic equipment and computer-readable medium |
| CN109359648A (en) * | 2018-12-08 | 2019-02-19 | 佛山市伟邦电子科技有限公司 | A kind of system for carrying out recognition of face to people of different heights |
Non-Patent Citations (1)
| Title |
|---|
| 付星斗: ""三维人脸真实感及动态数据获取与应用"", 《中国博士学位论文全文数据库 (信息科技辑)》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114046718A (en) * | 2022-01-14 | 2022-02-15 | 深圳市创腾智能电子有限公司 | Swing gate swing angle detection equipment and detection method based on image |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110462693B (en) | 2022-04-22 |
| WO2020258304A1 (en) | 2020-12-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Chenney et al. | Simulating cartoon style animation | |
| Peris et al. | Towards a simulation driven stereo vision system | |
| Franco et al. | Fusion of multiview silhouette cues using a space occupancy grid | |
| Deng et al. | Amodal detection of 3d objects: Inferring 3d bounding boxes from 2d ones in rgb-depth images | |
| CN112771539A (en) | Using three-dimensional data predicted from two-dimensional images using neural networks for 3D modeling applications | |
| CN105704475A (en) | Three-dimensional stereo display processing method of curved-surface two-dimensional screen and apparatus thereof | |
| US9067320B2 (en) | Robotic texture | |
| CN107111866A (en) | Method and apparatus for generating extrapolated image based on object detection | |
| CN110462693A (en) | Door lock and recognition methods | |
| Tsukamoto et al. | Detection and pose estimation of human face with synthesized image models | |
| US20030146922A1 (en) | System and method for diminished reality | |
| Vodopivec et al. | Fine hand segmentation using convolutional neural networks | |
| US10099644B2 (en) | Virtual head mounted video camera system | |
| Sullivan | Model-based vision for traffic scenes using the ground-plane constraint | |
| CA2634933C (en) | Group tracking in motion capture | |
| Papachristos et al. | Aerial robotic tracking of a generalized mobile target employing visual and spatio-temporal dynamic subject perception | |
| Gu et al. | Information extraction from image sequences of real-world facial expressions | |
| Argelaguet et al. | Automatic speed graph generation for predefined camera paths | |
| Wang et al. | Efficient visual tracking by probabilistic fusion of multiple cues | |
| Menezes et al. | Towards human motion capture from a camera mounted on a mobile robot | |
| Bergasa et al. | Guidance of a wheelchair for handicapped people by face tracking | |
| CN111219940B (en) | Method and device for controlling light in refrigerator and refrigerator | |
| Argyros et al. | Tracking skin-colored objects in real-time | |
| Brolly et al. | Model-based head pose estimation for air-traffic controllers | |
| Bobick et al. | Controlling view-based algorithms using approximate world models and action information |
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 |