CN109035308A - Image compensation method and device, electronic equipment and computer readable storage medium - Google Patents
Image compensation method and device, electronic equipment and computer readable storage medium Download PDFInfo
- Publication number
- CN109035308A CN109035308A CN201710431823.3A CN201710431823A CN109035308A CN 109035308 A CN109035308 A CN 109035308A CN 201710431823 A CN201710431823 A CN 201710431823A CN 109035308 A CN109035308 A CN 109035308A
- Authority
- CN
- China
- Prior art keywords
- parameter
- image
- compensating
- described image
- image acquisition
- 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.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/30—Determination of transform parameters for the alignment of images, i.e. image registration
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/50—Depth or shape recovery
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
This disclosure relates to a kind of image compensation method for compensating the movement of image capture device, image compensation device, use the electronic equipment and computer readable storage medium of the image compensation method and image compensation device.Described image compensation method includes: motion sensor parameter and predetermined kinetic parameter threshold value based on described image acquisition equipment, judges described image acquisition equipment with the presence or absence of movement；When judge described image acquisition equipment deposit when moving, obtain described image acquisition equipment compensating parameter；And it is based on the compensating parameter, calculate and compensate the coordinate shift of key point in acquisition image caused by the movement of described image acquisition equipment.
Description
Technical field
This disclosure relates to field of image processing, more specifically, this disclosure relates to a kind of for compensating image capture device
Mobile image compensation method, image compensation device, using the electronic equipment of the image compensation method and image compensation device, with
And computer readable storage medium.
Background technique
When image collecting device executes the static state of subject or moving image captures, the movement of image collecting device itself
May cause subject capture image offset, it is therefore desirable to for the movement of image collecting device itself compensate so as to
Remove the offset of its caused capture image.
Recently, with the development of virtual reality (VR) technology and augmented reality (AR) technology, gesture command become user with
The important way of VR or AR electronic equipment interaction.Usually captured by the image collecting device configured in VR or AR electronic equipment
The images of gestures of user, and key point (such as finger-joint) coordinate under camera coordinates system in extraction images of gestures, with
Afterwards by the motion profile of the processing unit analysis of key point coordinate by such as central processing unit (CPU) to generate corresponding finger
It enables.In the case, if user of the image collecting device for example due to wearing the electronic equipment in VR or AR electronic equipment
Head it is mobile and move, the additional relative motion between this user gesture and image collecting device, which will lead to, is caught
The offset of key point coordinate in the images of gestures obtained, so that electronic equipment be interfered to execute correct gesture recognition process.
Summary of the invention
In view of the above problems, the disclosure provide a kind of image compensation method for compensating the movement of image capture device,
Image compensation device uses the electronic equipment and computer-readable storage medium of the image compensation method and image compensation device
Matter.
According to one embodiment of present invention, the image compensation side of the movement for compensating image capture device is provided
Method, comprising: motion sensor parameter and predetermined kinetic parameter threshold value based on described image acquisition equipment judge that described image is adopted
Collect equipment with the presence or absence of movement；When judge described image acquisition equipment deposit when moving, obtain described image acquisition equipment benefit
Repay parameter；And it is based on the compensating parameter, calculate and compensates acquisition image caused by the movement of described image acquisition equipment
The coordinate shift of middle key point.
In addition, according to the image compensation method of one embodiment of the disclosure, wherein the key point is from described image
The key point extracted in the images of gestures of acquisition equipment acquisition.
In addition, according to the image compensation method of one embodiment of the disclosure, wherein based on described image acquisition equipment
Motion sensor parameter and predetermined kinetic parameter threshold value, judging that described image acquisition equipment whether there is movement includes: acquisition figure
As the motion sensor parameter of acquisition equipment；Calculate the amount of movement product in particular directions of the motion sensor parameter instruction
Score value and differential value；It combines the integrated value and differential value obtains motion parameter on the specific direction；And compare institute
The motion parameter on specific direction and the predetermined kinetic parameter threshold value are stated, when the motion parameter on the specific direction is big
When the predetermined kinetic parameter threshold value, judge that described image acquisition equipment has movement on the specific direction.
In addition, according to the image compensation method of one embodiment of the disclosure, wherein obtain described image acquisition equipment
Compensating parameter includes: to judge that the parameter of the compensating parameter determines mode；And mode is determined based on the parameter, described in determination
Compensating parameter.
In addition, according to the image compensation method of one embodiment of the disclosure, wherein the compensating parameter includes depth ginseng
Several and radius of turn parameter, the parameter determine that mode includes sensing modes and estimation model, the judgement compensating parameter
Parameter determine that mode includes: to judge whether described image acquisition equipment is configured with corresponding biography for sensing the compensating parameter
Sensor；In the case where determining configured with the respective sensor, determine that the parameter determines that mode is the sensing modes；With
And in the case where determining without configuring the respective sensor, determine that the parameter determines that mode is the estimation model.
In addition, according to the image compensation method of one embodiment of the disclosure, wherein described to determine mould based on the parameter
Formula determines that the compensating parameter includes: to sense the depth parameter, Yi Jili using depth transducer under the sensing modes
Acceleration in particular directions is sensed with acceleration transducer, and the acceleration calculation based on sensing is described specific
The radius of turn parameter on direction；And under the estimation model, the pass in the acquisition image of successive frame is extracted
Key point coordinate calculates the institute on the specific direction based on identical key point coordinate and angular velocity data between successive frame
State radius of turn parameter and the depth parameter.
In addition, according to the image compensation method of one embodiment of the disclosure, wherein the specific direction includes pitching side
To, yaw direction and rolling direction, key point in acquisition image caused by the movement for calculating described image acquisition equipment
Coordinate shift includes: rotation angle and radius of turn, the depth based on described image acquisition equipment in the pitch orientation
First coordinate of parameter and the in the first frame key point is calculated and is bowed in the second frame by described image acquisition equipment edge
Face upward the coordinate shift amount of the key point caused by direction rotates；Equipment is acquired in the rotation of the yaw direction based on described image
Gyration and radius of turn, the depth parameter and the first coordinate of the key point in the first frame, calculate in the second frame
In by described image acquisition equipment along pitch orientation rotate caused by the key point coordinate shift amount；And it is based on the figure
As acquisition equipment the rolling direction rotation angle and radius of turn and in the first frame the key point first seat
Mark calculates the coordinate shift for rotating the caused key point along pitch orientation by described image acquisition equipment in the second frame
Amount.
According to another embodiment of the present disclosure, a kind of image benefit for compensating the movement of image capture device is provided
Repay device, comprising: mobile judging unit, for motion sensor parameter and predetermined movement ginseng based on described image acquisition equipment
Number threshold value judges described image acquisition equipment with the presence or absence of movement；Compensating parameter acquiring unit judges that described image is adopted for working as
Collection equipment deposits the compensating parameter for obtaining described image acquisition equipment when moving；And coordinate shift calculates compensating unit, is used for
Based on the compensating parameter, the seat of key point in acquisition image caused by the movement of described image acquisition equipment is calculated and compensated
Mark offset.
According to another embodiment of the present disclosure, a kind of computer readable storage medium is provided, it is described computer-readable
Storage medium is stored with computer program instructions, wherein when the computer program instructions are run by processor, so that the place
Device execution is managed according to the image compensation method of previous embodiment.
According to another embodiment of the disclosure, a kind of image benefit for compensating the movement of image capture device is provided
Repay device, comprising: processor；And memory, it is configured to storage computer program instructions；Wherein, in the computer program
When instruction is run by the processor, image compensation method as described above is executed.
According to the further embodiment of the disclosure, a kind of electronic equipment is provided, comprising: image collecting device, for adopting
Collect image；Motion sensor device, for sensing the motion-sensing parameter of the electronic equipment；And image compensation device, it uses
The image shift caused by the movement for compensating the electronic equipment, wherein described image compensation device further comprises: movement is sentenced
Disconnected unit judges that the electronic equipment whether there is for being based on the motion sensor parameter and predetermined kinetic parameter threshold value
It is mobile；Compensating parameter acquiring unit, for obtaining the compensation of the electronic equipment when moving when judging that the electronic equipment is deposited
Parameter；And coordinate shift calculates compensating unit, for being based on the compensating parameter, calculates and compensates the electronic equipment
The coordinate shift of key point in acquisition image caused by mobile.
According to the image compensation method of the movement for compensating image capture device of the embodiment of the present disclosure, image compensation dress
It sets and can be used to by what is configured using electronic equipment using the electronic equipment of the image compensation method and image compensation device
Property sensor device (gyroscope, accelerometer etc.) obtain reflection electronic equipment itself movement sensing data, thus
Sensing data based on acquisition and the key point coordinate captured, compensation are used as caused by the movement of image capture device
Interference of the additional relative motion for gesture recognition process between family gesture and image collecting device.
Detailed description of the invention
The embodiment of the present invention is described in more detail in conjunction with the accompanying drawings, the above and other purposes of the present invention,
Feature and advantage will be apparent.Attached drawing is used to provide to further understand the embodiment of the present invention, and constitutes explanation
A part of book, is used to explain the present invention together with the embodiment of the present invention, is not construed as limiting the invention.In the accompanying drawings,
Identical reference label typically represents same parts or step.
Fig. 1 is to summarize the flow chart for illustrating image compensation method according to an embodiment of the present disclosure；
Fig. 2 is the schematic diagram for being illustrated schematically the application scenarios of image compensation method according to an embodiment of the present disclosure；
Fig. 3 is the flow chart for further illustrating image compensation method according to an embodiment of the present disclosure；
Fig. 4 is the process for further illustrating the mobile determining processing in image compensation method according to an embodiment of the present disclosure
Figure；
Fig. 5 is that the compensating parameter further illustrated in image compensation method according to an embodiment of the present disclosure determines processing
Flow chart；
Fig. 6 A and 6B are the signals for illustrating the offset compensation model of image compensation method according to an embodiment of the present disclosure
Figure；
Fig. 7 is the functional block diagram for illustrating image compensation device according to an embodiment of the present disclosure；
Fig. 8 is the hardware block diagram for illustrating image compensation device according to an embodiment of the present disclosure；
Fig. 9 is the block diagram for illustrating electronic equipment according to an embodiment of the present disclosure；And
Figure 10 is the schematic diagram for illustrating computer readable storage medium according to an embodiment of the present disclosure.
Specific embodiment
In order to enable the purposes, technical schemes and advantages of the disclosure become apparent, root is described in detail below with reference to accompanying drawings
According to the example embodiment of the disclosure.Obviously, described embodiment is only a part of this disclosure embodiment, rather than this public affairs
The whole embodiments opened, it should be appreciated that the disclosure is not limited by example embodiment described herein.Based on described in the disclosure
Embodiment, those skilled in the art's obtained all other embodiment in the case where not making the creative labor should all be fallen
Enter within the protection scope of the disclosure.
Hereinafter, embodiment of the disclosure will be described in detail with reference to the attached drawings.
Fig. 1 is to summarize the flow chart for illustrating image compensation method according to an embodiment of the present disclosure.Image as shown in Figure 1
Compensation method can be used for carrying out the compensation of capture image for the movement of image collecting device itself.As shown in Figure 1, according to this
The image compensation method of disclosed embodiment includes the following steps.
In step s 11, motion sensor parameter and predetermined kinetic parameter threshold value based on image capture device, judge to scheme
As acquisition equipment is with the presence or absence of movement.In one embodiment of the present disclosure, motion sensor includes but is not limited to gyroscope, adds
Speedometer etc..Image capture device for example can be non co axial 3DOF camera, can pitch orientation, rolling direction and
It is rotated on yaw direction.It will be described in detail with reference to the accompanying drawings as follows, can use and be mounted on image capture device (camera)
Three axis angular rate sensors sense the angular speed on pitch orientation, rolling direction and yaw direction.It will be by combining angular speed
Integral and differential acquired in kinematic parameter and the pre-set movement ginseng on pitch orientation, rolling direction and yaw direction
Number threshold value is compared, to judge image capture device with the presence or absence of movement, i.e., whether in pitch orientation, rolling direction and yaw
Side is rotated up.Hereafter, processing enters step S12.
In step s 12, the compensating parameter of image capture device is obtained when moving when judging that image capture device is deposited.
In one embodiment of the present disclosure, the compensating parameter includes depth parameter and radius of turn parameter.As follows with reference to the accompanying drawings
Detailed description, it can directly be sensed by depth transducer in described image acquisition equipment (camera) configured with depth transducer
Obtain the depth parameter；And the case where described image acquisition equipment (camera) is configured with three axis linear acceleration sensors
Under, and can be by linear acceleration that three axis linear acceleration sensors sense and by three axis angular rate sensor senses
The corresponding angular speed measured determines the rotation in respective direction by radius of turn and linear acceleration and angular speed direct relation
Turn radius.On the contrary, there is no configurable deep sensor and three axis acceleration sensings in described image acquisition equipment (camera)
In the case where device, by extracting the key point coordinate of successive frame acquired in image, and based on identical pass between successive frame
Key point coordinate and angular velocity data, calculate depth parameter in particular directions and radius of turn.Hereafter, processing enters step
S13。
In step s 13, it is based on the compensating parameter, caused by the movement for calculating and compensating described image acquisition equipment
Acquire the coordinate shift of key point in image.In one embodiment of the present disclosure, based on the compensating parameter and in first frame
Described in key point the first coordinate, calculate in the second frame by described image acquisition equipment pitch orientation, rolling direction and
The coordinate shift amount of the key point caused by being rotated on yaw direction.Second coordinate of the key point in the second frame is moved
Except the coordinate shift amount, it can the true coordinate of the key point in the second frame is obtained, to be directed to image collecting device
The compensation deals of the mobile realization capture image of itself.
More than, the image compensation method according to an embodiment of the present disclosure described referring to Fig.1 can be usually used for being directed to
The movement of image collecting device itself carries out the compensation of capture image.The capture image can be by image collecting device capture
The image of any subject.Hereinafter, will be described with image compensation method according to an embodiment of the present disclosure be applied to for
The concrete application scene that images of gestures compensates.
Fig. 2 is the schematic diagram for being illustrated schematically the application scenarios of image compensation method according to an embodiment of the present disclosure.?
In embodiment shown in Fig. 2, the application scenarios of image compensation method according to an embodiment of the present disclosure are electronic equipment for catching
The compensation of the user gesture image obtained.
As shown in Fig. 2, electronic equipment 20 can VR the or AR electronics of such as intelligent glasses, head-mounted display (HMD) set
It is standby.On the electronic equipment 20, configured with the image collecting device 201 for capturing image.Described image acquisition device 201
It can be used for capturing and tracking the gesture of user.Electronic equipment 20 can be according to the figure captured by described image acquisition device 201
The gesture feature (such as joint, color in image etc.) as in extracts the coordinate of gesture key point 203, by for successive frame
Gesture key point 203 coordinate determination, identify the gesture of user.If the head for dressing the user of electronic equipment 20 occurs
Rotation on pitch orientation, rolling direction and yaw direction, then according to by 201 captured image institute of described image acquisition device
Additional offset will occur in the coordinate of determining gesture key point 203, interfere the identification of the gesture for user.
Fig. 3 is the flow chart for further illustrating image compensation method according to an embodiment of the present disclosure.Image shown in Fig. 3
Compensation method is used to be directed to application scenarios shown in Fig. 2, executes the compensation deals of images of gestures.As shown in figure 3, according to the disclosure
The image compensation method of embodiment include the following steps.
In step S301, images of gestures is acquired.In one embodiment of the present disclosure, electronic equipment as shown in Figure 2
The images of gestures of the user of 201 successive frame of image collecting device on 20.Hereafter, processing enters step S302.
In step s 302, the key point in images of gestures is extracted.In one embodiment of the present disclosure, according to by described
Gesture feature (such as joint, color in image etc.) in 201 captured image of image collecting device extracts gesture key point
203 coordinate.The two-dimensional coordinate under image coordinate system be can use to indicate key point.Hereafter, processing enters step S303.
In step S303, judge image capture device (for example, electronic equipment 20 as shown in Figure 2) with the presence or absence of shifting
It is dynamic.The determining processing of image capture device whether moved is identical as the step S11 described above with reference to Fig. 1.That is, utilizing installation
The three axis angular rate sensor (not shown) on electronic equipment 20 sense on pitch orientation, rolling direction and yaw direction
Angular speed.Will by combination angular speed integral and differential acquired in kinematic parameter with pitch orientation, rolling direction and partially
Boat direction on pre-set kinematic parameter threshold value be compared, with judge electronic equipment 20 with the presence or absence of movement, i.e., whether
It is rotated on pitch orientation, rolling direction and yaw direction.
In step S303 obtain positive result in the case where, i.e., electronic equipment 20 is deposited in the case of movement, handle into
To step S304.
In step s 304, the compensating parameter of image capture device is obtained.At the compensating parameter acquisition of image capture device
It manages identical as the step S12 described above with reference to Fig. 1.It can be direct that is, being configured with depth transducer in the electronic equipment 20
The depth parameter is obtained by depth transducer sensing；And it is passed in the electronic equipment 20 configured with three axis linear accelerations
In the case where sensor, and can be by linear acceleration that three axis linear acceleration sensors sense and by three shaft angles speed
The corresponding angular speed that degree sensor senses, it is corresponding with the determination of angular speed direct relation to linear acceleration by radius of turn
Radius of turn on direction.On the contrary, being passed in the electronic equipment 20 without configurable deep sensor and three axis linear accelerations
In the case where sensor, by extracting the key point coordinate of successive frame acquired in image, and based on identical between successive frame
Key point coordinate and angular velocity data calculate depth parameter in particular directions and radius of turn.Hereafter, processing enters step
S305。
In step S305, the coordinate shift of key point in acquisition image is calculated and compensated.The coordinate shift of key point
Compensation deals are identical as the step S13 described above with reference to Fig. 1.Namely based on the compensating parameter and the pass in the first frame
First coordinate x of key point1, calculate in the second frame by described image acquisition equipment in pitch orientation, rolling direction and yaw side
The coordinate shift amount Δ x of the key point caused by being rotated up.By the second coordinate x of the key point in the second frame2' move
Except coordinate shift amount Δ x, it can obtain the true coordinate x of the key point in the second frame2, to be directed to Image Acquisition
The compensation deals of the mobile realization capture image of device itself.More specifically, for determining the coordinate shift amount of the key point
The parameter that is related to of processing include rotation angle, key point coordinate, depth parameter and radius of turn between two frames, pass through utilization
Above-mentioned parameter calculates the offset of key point between two frames.In another embodiment of the present disclosure, multi-frame processing can also be accumulated
As a result and the smooth of result is carried out, smooth value is used in the compensation calculation of the offset between two frames.Hereinafter, will be referring to attached
Figure detailed description is using rotation angle, key point coordinate, depth parameter and the radius of turn between two frames for closing between two frames
The calculation processing of the offset of key point.Hereafter, processing enters step S306.
In step S306, identifies gesture and execute corresponding instruction.Electronic equipment 20 is based on holding in step S305
It has gone the truthful data of migration, has identified the gesture path in images of gestures, it is associated with gesture path in advance to execute
Corresponding instruction.
Return step S303, in the case where negative decision is obtained in step S303, i.e., there is no movements for electronic equipment 20
In the case where, then processing enters step S306, to identify gesture and to execute corresponding instruction.
By the image compensation method according to an embodiment of the present disclosure described above by reference to Fig. 3, can be set by electronics
It is standby to execute in gesture recognition process, the offset of the images of gestures as caused by the movement of electronic equipment is judged whether there is, and
Corresponding compensation deals are executed in the case where there is offset, so that it is guaranteed that electronic equipment executes correct gesture recognition process.
Fig. 4 is the process for further illustrating the mobile determining processing in image compensation method according to an embodiment of the present disclosure
Figure.As shown in figure 4, the mobile determining processing in image compensation method according to an embodiment of the present disclosure includes the following steps.
In step S401, the motion sensor parameter of image capture device is acquired.In embodiment of the disclosure, it utilizes
Three axis angular rate sensors being mounted on image capture device (camera) are sensed in pitch orientation, rolling direction and yaw direction
On angular speed.Hereafter, processing enters step S402.
In step S402, the amount of movement integrated value in particular directions and differential of the instruction of motion sensor parameter are calculated
Value.In one embodiment of the present disclosure, θ and Δ ω respectively indicates amount of movement (that is, angular velocity of rotation) in particular directions
Integrated value and differential value.Wherein, the integrated value of amount of movement indicates overall movement degree, and the differential value of amount of movement indicates to move
Dynamic variation degree.Hereafter, processing enters step S403.
In step S403, combinatorial product score value and differential value obtain the motion parameter on specific direction.In the disclosure
In one embodiment, combinatorial product score value and differential value obtain the motion parameter on specific direction and are indicated by following formula (1):
Wherein, Tp、Tr、TyThe motion parameter being illustrated respectively on pitch orientation, rolling direction and yaw direction, 1 > α
>β>0.Hereafter, processing enters step S404.
In step S404, judge whether motion parameter is greater than predetermined kinetic parameter threshold value.Agreed in step s 404
In the case where determining result, i.e., motion parameter is greater than predetermined kinetic parameter threshold value, then processing enters step S405.In step S405
In, determine there is movement in particular directions.On the contrary, that is, movement is joined in the case where obtaining negative decision in step s 404
Numerical value is not more than predetermined kinetic parameter threshold value, then processing enters step S406.In step S406, determine in particular directions not
There are movements.
It is real by referring to the mobile determining processing in the image compensation method according to an embodiment of the present disclosure of Fig. 4 description
Show and has accurately judged image capture device with the presence or absence of movement in particular directions using motion sensor parameter.
Fig. 5 is that the compensating parameter further illustrated in image compensation method according to an embodiment of the present disclosure determines processing
Flow chart.As shown in figure 5, the compensating parameter in image compensation method according to an embodiment of the present disclosure determines that processing includes following
Step.
In step S501, it is determined whether configured with the respective sensor for sensing and compensating parameter.In the reality of the disclosure
It applies in example, compensating parameter includes depth parameter and radius of turn parameter.Respective sensor for sensing and compensating parameter includes deep
Spend sensor and three axis linear acceleration sensors.
In the case where obtaining positive result in step S501, i.e., configured with the depth transducer for sensing and compensating parameter
With three axis linear acceleration sensors, processing enters step S502.In step S502, determine that parameter determines mode for sensing mould
Formula.Hereafter, processing enters step S503.
In step S503, depth parameter is sensed using depth transducer.Hereafter, processing enters step S504.
In step S504, using the acceleration of acceleration transducer sensing in particular directions, and based on sensing
The radius of turn parameter of acceleration calculation in particular directions.In one embodiment of the present disclosure, acceleration transducer is utilized
The linear acceleration of sensing in particular directions is expressed as a.Based between linear acceleration, angular velocity of rotation and radius of turn
Relationship r=a/ Δ ω, can be calculated radius of turn parameter in particular directions.
Return step S501 is not configured to sensing and compensating in the case where obtaining negative decision in step S501
The depth transducer of parameter and three axis linear acceleration sensors, processing enter step S505.In step S505, parameter is determined
Determine that mode is estimation model.Hereafter, processing enters step S506.
In step S506, the key point coordinate in the acquisition image of successive frame is extracted.In one embodiment of the disclosure
In, it can indicate that hand is placed on immediately ahead of image capture device and is remain stationary by user, hereafter respectively along pitching, rolling and yaw
Direction rotates image capture device, and keeps records of the continuous frame information of user's hand, thus each from the successive frame information extraction
Gesture key point coordinate in frame.Hereafter, processing enters step S507.
In step s 507, it based on identical key point coordinate and angular velocity data between successive frame, calculates in certain party
Upward radius of turn parameter and depth parameter.It in one embodiment of the present disclosure, can be based on identical pass between two continuous frames
The coordinate of key point and the output data of angular-rate sensor calculate image capture device in the rotation of pitching, rolling and yaw direction
Turn radius.And it is possible to which the output of coordinate and angular-rate sensor based on key point between two continuous frames, calculates gesture ginseng
Examine depth.Further, by the reference depth of each frame gesture and the distance between key point two-by-two, depth-key point is established
Gesture depth information after distance equation is used for is estimated.
At the compensating parameter in image compensation method according to an embodiment of the present disclosure described by referring to Fig. 5 determines
Reason, the case where there is the respective sensor for sensing and compensating parameter or be not used in the respective sensor of sensing and compensating parameter
Under, it can realize and the compensating parameter in image compensation method is determined.
Fig. 6 A and 6B are the signals for illustrating the offset compensation model of image compensation method according to an embodiment of the present disclosure
Figure.It is had been described above above with reference to flow chart, utilizes rotation angle, key point coordinate, depth parameter and the rotation between two frames
Radius calculates the offset of key point between two frames.Specifically, Fig. 6 A shows the offset compensation in pitching or yaw direction
Model, and Fig. 6 B shows the offset compensation model in rolling direction.
As shown in Figure 6A, it is assumed that B' point is imaging of the B point in first frame image, x1It is B' point in first frame image
Coordinate.B " point is imaging of the B point in the second frame image, x2" the coordinate o'clock in the second frame image for B.Then Δ x=x2-x1Table
Show that camera pitching (or yaw) direction rotates key point offset under caused image coordinate system.That is, when finding out x2It can count
Calculate the offset of object in image coordinate caused by camera rotation.
If θ indicates the rotation angle of camera, α indicates that the angle between camera optical axis and BB' point line, f indicate camera
Focal length,Indicate the angle of BB " and camera plane.O1 and O2 is respectively image center point.
γ is defined by following expression formula (2):
Wherein r indicates radius of turn, and d indicates gesture depth.
It can then acquire:
It can be acquired by expression formula (3) and (4) two formulas:
It can further be acquired by expression formula (5):
It can then acquire:
As required x2Value.
As shown in Figure 6B, for camera when rolling direction rotates, if first frame picture centre point C, the second frame image
Center point coordinate be D.For A point, the coordinate on first frame image can be expressed as (x, y), and A point is in the second frame figure
As upper coordinate is (x', y').It can be seen that by geometrical relationship in figure, only require to obtain the length of AD and the value of angle beta, it can find out
(x', y'), further finds out offset:
(x'-x,y'-y) (8)
It can be found out by geometrical relationship:
Then exist:
It in addition can be in the hope of by geometrical relationship:
Known AC2=x2+y2, so:
By the value of the length of AD and angle beta that are shown by expression formula (10)-(12), that is, it can determine offset.
Fig. 7 is the functional block diagram for illustrating image compensation device according to an embodiment of the present disclosure.According to the reality of the disclosure
The image compensation device 70 for applying example can be only fitted to in image capture device, or can be only fitted to image collector
In the electronic equipment set.As shown in fig. 7, image compensation device 70 includes: mobile judging unit 701, compensating parameter acquiring unit
702 and coordinate shift calculate compensating unit 703.Described each unit can be executed respectively above in conjunction with Fig. 1 to Fig. 6 B description
Each step/function of image compensation method.Therefore, below only to the major function of each unit of the image compensation device 70 into
Row description, and omit the detail content having been described above.
The mobile judging unit 701 is used for motion sensor parameter and predetermined kinetic parameter based on image capture device
Threshold value judges described image acquisition equipment with the presence or absence of movement.The compensating parameter acquiring unit 702, which is used to work as, judges the figure
It is deposited when moving as acquiring equipment, obtains the compensating parameter that described image acquires equipment.The coordinate shift calculates compensating unit
703 for being based on the compensating parameter, calculates and compensates and closes in acquisition image caused by the movement of described image acquisition equipment
The coordinate shift of key point.
Described image compensation device 70 can be that by above-mentioned mobile judging unit 701, compensating parameter acquiring unit
702 and coordinate shift calculate any device with processing capacity of 703 function of compensating unit, such as it can be and be designed for
Carry out the general processor, digital signal processor (DSP), ASIC, field programmable gate array signal of function described herein
(FPGA) or other programmable logic device (PLD), discrete gate or transistor logics, discrete hardware component or its any group
It closes.
Fig. 8 is the hardware block diagram for illustrating image compensation device according to an embodiment of the present disclosure.As shown in figure 8, according to this
The image compensation device 80 of disclosed embodiment includes processor 801 and memory 802.It is configured to deposit in the memory 802
Computer program instructions are stored up, the computer program instructions are executed when being run by processor 801 and retouched above with reference to Fig. 1 to Fig. 6 B
The image compensation method stated.
Fig. 9 is the block diagram for illustrating electronic equipment according to an embodiment of the present disclosure.Electronics according to an embodiment of the present disclosure
Equipment 90 can have the image compensation function above with reference to Fig. 1 to Fig. 6 B description.Electronic equipment 90 can be to be adopted with image
Any electronic equipment of collection ability, the including but not limited to VR or AR equipment of such as intelligent glasses, head-mounted display or all
Such as the portable electronic device of smart phone.
As shown in figure 9, electronic equipment 90 according to an embodiment of the present disclosure specifically includes: image collecting device 901, movement
Sensor device 902 and image compensation device 903.Described image acquisition device 901 is for acquiring image.At one of the disclosure
In embodiment, described image acquisition device 901 is used for the images of gestures that user's hand executes.The motion sensor device 902
For sensing the motion-sensing parameter of the electronic equipment.In one embodiment of the present disclosure, the motion sensor device
902 include but is not limited to gyroscope, three axis angular rate sensors, three axis linear acceleration sensors, depth transducer etc..It is described
Image compensation device 903 is for compensating image shift caused by the movement of the electronic equipment.
Further, described image compensation device 903 includes mobile judging unit 9031, compensating parameter acquiring unit 9032
Compensating unit 9033 is calculated with coordinate shift.Described each unit can execute the figure above in conjunction with Fig. 1 to Fig. 6 B description respectively
As each step/function of compensation method.The mobile judging unit 9031 is used for the motion-sensing based on image capture device
Device parameter and predetermined kinetic parameter threshold value judge described image acquisition equipment with the presence or absence of movement.The compensating parameter obtains single
Member 9032 judges that described image acquisition equipment is deposited when moving for working as, the compensating parameter of acquisition described image acquisition equipment.Institute
It states coordinate shift and calculates compensating unit 9033 for based on the compensating parameter, calculating and compensating described image acquisition equipment
The coordinate shift of key point in acquisition image caused by mobile.
Figure 10 is the schematic diagram for illustrating the computer readable storage medium according to the embodiment of the present disclosure.As shown in Figure 10, root
Computer program instructions 1001 are stored thereon with according to the computer readable storage medium 1000 of the embodiment of the present disclosure.When the calculating
When machine program instruction 1001 is run by processor, the image compensation according to the embodiment of the present disclosure referring to the figures above description is executed
Method.
More than, describe the image of the movement for compensating image capture device according to the embodiment of the present disclosure with reference to the accompanying drawings
Compensation method, image compensation device and benefit can be passed through using the electronic equipment of the image compensation method and image compensation device
Reflection electronic equipment itself movement is obtained with the inertial sensor device (gyroscope, accelerometer etc.) of electronics device configuration
Sensing data compensate due to Image Acquisition thus the sensing data based on acquisition and the key point coordinate captured
Additional relative motion caused by the movement of equipment between user gesture and image collecting device is for gesture recognition process
Interference.The reliability of the unrelated gesture identification task of background and accurate is improved according to the image compensation method of the embodiment of the present disclosure
Property.More specifically, passing through the threshold calculations for judging whether camera rotates according to the image compensation method of the embodiment of the present disclosure
Provide reliable and real-time camera rotation monitoring.It can be evaluated whether to calculate offset according to the image compensation method of the embodiment of the present disclosure
Relevant parameter needed for amount, provides flexible and high-precision parameter Estimation.According to the image compensation method of the embodiment of the present disclosure
The coordinate shift for calculating and compensating for gesture key point provides flexible and accurate offset compensation method, improves gesture
The precision of migration.
Basic principle of the invention is described in conjunction with specific embodiments above, however, it is desirable to, it is noted that in the disclosure
The advantages of referring to, advantage, effect etc. are only exemplary rather than limitation, must not believe that these advantages, advantage, effect etc. are of the invention
Each embodiment is prerequisite.In addition, detail disclosed above is merely to exemplary effect and the work being easy to understand
With, rather than limit, above-mentioned details is not intended to limit the present invention as that must realize using above-mentioned concrete details.
Device involved in the disclosure, device, equipment, system block diagram only as illustrative example and be not intended to
It is required that or hint must be attached in such a way that box illustrates, arrange, configure.As those skilled in the art will appreciate that
, it can be connected by any way, arrange, configure these devices, device, equipment, system.Such as "include", "comprise", " tool
" etc. word be open vocabulary, refer to " including but not limited to ", and can be used interchangeably with it.Vocabulary used herein above
"or" and "and" refer to vocabulary "and/or", and can be used interchangeably with it, unless it is not such that context, which is explicitly indicated,.Here made
Vocabulary " such as " refers to phrase " such as, but not limited to ", and can be used interchangeably with it.
Step flow chart and above method description in the disclosure only as illustrative example and are not intended to require
Or imply the step of must carrying out each embodiment according to the sequence that provides, certain steps can it is parallel, independently of one another or according to
Other sequences appropriate execute.In addition, such as " thereafter ", " then ", " following " etc. word be not intended to limit step
Sequentially；These words are only used for the description that guidance reader reads over these methods.
In addition, as used herein, the "or" instruction separation used in the enumerating of the item started with "at least one"
It enumerates, so that enumerating for such as " at least one of A, B or C " means A or B or C or AB or AC or BC or ABC (i.e. A and B
And C).In addition, wording " exemplary " does not mean that the example of description is preferred or more preferable than other examples.
It may also be noted that in the apparatus and method of the present invention, each component or each step are can to decompose and/or again
Combination nova.These, which decompose and/or reconfigure, should be regarded as equivalent scheme of the invention.
For those of ordinary skill in the art, it is to be understood that whole or any portions of disclosed method and device
Point, can in any computing device (including processor, storage medium etc.) or the network of computing device, with hardware, firmware,
Software or their combination are realized.The hardware can be using being designed to carry out the logical of function described herein
With processor, digital signal processor (DSP), ASIC, field programmable gate array signal (FPGA) or other programmable logic devices
Part (PLD), discrete gate or transistor logic, discrete hardware component or any combination thereof.General processor can be micro- place
Device is managed, but as an alternative, the processor can be any commercially available processor, controller, microcontroller or shape
State machine.Processor is also implemented as calculating the combination of equipment, such as the combination of DSP and microprocessor, multi-microprocessor, with
The one or more microprocessors of DSP core cooperation or any other such configuration.The software can reside in any form
Computer-readable tangible media in.It by example rather than limits, such computer-readable tangible storage is situated between
Matter may include RAM, ROM, EEPROM, CD-ROM or other optical disc storages, disk storage or other magnetic memory devices or can
For carrying or the desired program code of store instruction or data structure form and can be accessed by computer any
Other tangible mediums.As used herein, disk include compact disk (CD), laser disk, CD, digital versatile disc (DVD), floppy disk and
Blu-ray disc.
Intelligent control technology disclosed by the invention can also be by running a program or one on any computing device
Program is organized to realize.The computing device can be well known fexible unit.Intellectual technology disclosed in this invention can also be only
Only by providing the program product comprising realizing the method perhaps program code of device to realize or by being stored with this
Any storage medium of the program product of sample is realized.
The technology instructed defined by the appended claims can not departed from and carried out to the various of technology described herein
Change, replace and changes.In addition, the scope of the claims of the disclosure is not limited to process described above, machine, manufacture, thing
Composition, means, method and the specific aspect of movement of part.Can use carried out to corresponding aspect described herein it is essentially identical
Function or realize essentially identical result there is currently or later to be developed processing, machine, manufacture, event group
At, means, method or movement.Thus, appended claims include such processing, machine, manufacture, event within its scope
Composition, means, method or movement.
The above description of disclosed aspect is provided so that any person skilled in the art can make or use this
Invention.Various modifications in terms of these are readily apparent to those skilled in the art, and are defined herein
General Principle can be applied to other aspect without departing from the scope of the present invention.Therefore, the present invention is not intended to be limited to
Aspect shown in this, but according to principle disclosed herein and the consistent widest range of novel feature.
In order to which purpose of illustration and description has been presented for above description.In addition, this description is not intended to reality of the invention
It applies example and is restricted to form disclosed herein.Although already discussed above multiple exemplary aspects and embodiment, this field skill
Its certain modifications, modification, change, addition and sub-portfolio will be recognized in art personnel.
Claims (11)
1. a kind of for compensating the image compensation method of the movement of image capture device, comprising:
Based on the motion sensor parameter and predetermined kinetic parameter threshold value of described image acquisition equipment, judge that described image acquisition is set
It is standby to whether there is movement；
When judge described image acquisition equipment deposit when moving, obtain described image acquisition equipment compensating parameter；And
Based on the compensating parameter, calculates and compensate key point in acquisition image caused by the movement of described image acquisition equipment
Coordinate shift.
2. image compensation method as described in claim 1, wherein the key point is acquired from described image acquisition equipment
The key point extracted in images of gestures.
3. image compensation method as claimed in claim 1 or 2, wherein the motion sensor based on described image acquisition equipment
Parameter and predetermined kinetic parameter threshold value judge that described image acquisition equipment includes: with the presence or absence of movement
Acquire the motion sensor parameter of image capture device；
Calculate the amount of movement integrated value in particular directions and differential value of motion sensor parameter instruction；
It combines the integrated value and differential value obtains motion parameter on the specific direction；And
Compare the motion parameter on the specific direction and the predetermined kinetic parameter threshold value, the fortune on the specific direction
When dynamic parameter value is greater than the predetermined kinetic parameter threshold value, judges that described image acquisition equipment exists on the specific direction and move
It is dynamic.
4. image compensation method as claimed in claim 1 or 2, wherein obtain the compensating parameter packet of described image acquisition equipment
It includes:
Judge that the parameter of the compensating parameter determines mode；And
Mode is determined based on the parameter, determines the compensating parameter.
5. image compensation method as claimed in claim 4, wherein the compensating parameter includes depth parameter and radius of turn ginseng
Number, the parameter determine that mode includes sensing modes and estimation model, and the parameter of the judgement compensating parameter determines mode
Include:
Judge whether described image acquisition equipment is configured with the respective sensor for sensing the compensating parameter；
In the case where determining configured with the respective sensor, determine that the parameter determines that mode is the sensing modes；With
And
In the case where determining without configuring the respective sensor, determine that the parameter determines that mode is the estimation model.
6. image compensation method as claimed in claim 5, wherein it is described to determine mode based on the parameter, determine the benefit
Repaying parameter includes:
The depth parameter is sensed using depth transducer under the sensing modes, and is existed using acceleration transducer sensing
Acceleration on specific direction, and the radius of turn of the acceleration calculation based on sensing on the specific direction
Parameter；And
Under the estimation model, the key point coordinate in the acquisition image of successive frame is extracted, based on phase between successive frame
Same key point coordinate and angular velocity data calculates the radius of turn parameter and depth ginseng on the specific direction
Number.
7. image compensation method as claimed in claim 6, wherein the specific direction include pitch orientation, yaw direction and
Rolling direction, the coordinate shift that key point in image is acquired caused by the movement for calculating described image acquisition equipment include:
Based on described image acquisition equipment the rotation angle and radius of turn of the pitch orientation, the depth parameter and
First coordinate of the key point in the first frame is calculated and is rotated in the second frame by described image acquisition equipment along pitch orientation
The coordinate shift amount of the caused key point；
Based on described image acquisition equipment the rotation angle and radius of turn of the yaw direction, the depth parameter and
First coordinate of the key point in the first frame is calculated and is rotated in the second frame by described image acquisition equipment along pitch orientation
The coordinate shift amount of the caused key point；And
Based on described image acquisition equipment in the rotation angle and radius of turn in the rolling direction and described in the first frame
First coordinate of key point calculates and rotates the caused key along pitch orientation by described image acquisition equipment in the second frame
The coordinate shift amount of point.
8. a kind of for compensating the image compensation device of the movement of image capture device, comprising:
Mobile judging unit, for acquiring the motion sensor parameter and predetermined kinetic parameter threshold value of equipment based on described image,
Judge described image acquisition equipment with the presence or absence of movement；
Compensating parameter acquiring unit judges that described image acquisition equipment is deposited when moving for working as, obtains described image acquisition and sets
Standby compensating parameter；And
Coordinate shift calculates compensating unit, for being based on the compensating parameter, calculating and compensating described image acquisition equipment
The coordinate shift of key point in acquisition image caused by mobile.
9. a kind of computer readable storage medium, the computer-readable recording medium storage has computer program instructions, wherein
When the computer program instructions are run by processor, so that the processor is executed as described in any one of claims 1 to 7
Image compensation method.
10. a kind of for compensating the image compensation device of the movement of image capture device, comprising:
Processor；And
Memory is configured to storage computer program instructions；
Wherein, when the computer program instructions are run by the processor, any one institute such as claims 1 to 7 is executed
The image compensation method stated.
11. a kind of electronic equipment, comprising:
Image collecting device, for acquiring image；
Motion sensor device, for sensing the motion-sensing parameter of the electronic equipment；And
Image compensation device, image shift caused by the movement for compensating the electronic equipment,
Wherein, described image compensation device further comprises:
Mobile judging unit judges that the electronics is set for being based on the motion sensor parameter and predetermined kinetic parameter threshold value
It is standby to whether there is movement；
Compensating parameter acquiring unit, for obtaining the compensation of the electronic equipment when moving when judging that the electronic equipment is deposited
Parameter；And
Coordinate shift calculates compensating unit, for being based on the compensating parameter, calculates and compensate the movement of the electronic equipment
The coordinate shift of key point in caused acquisition image.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710431823.3A CN109035308A (en) | 2017-06-09 | 2017-06-09 | Image compensation method and device, electronic equipment and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710431823.3A CN109035308A (en) | 2017-06-09 | 2017-06-09 | Image compensation method and device, electronic equipment and computer readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109035308A true CN109035308A (en) | 2018-12-18 |
Family
ID=64628771
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710431823.3A Pending CN109035308A (en) | 2017-06-09 | 2017-06-09 | Image compensation method and device, electronic equipment and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109035308A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110023833A (en) * | 2016-11-30 | 2019-07-16 | 株式会社理光 | Equipment for inhibiting of vibration and electronic equipment |
| CN113352998A (en) * | 2021-06-01 | 2021-09-07 | 地平线征程(杭州)人工智能科技有限公司 | Setting direction adjusting method and device and computer readable storage medium |
| CN113496171A (en) * | 2020-04-03 | 2021-10-12 | 北京小米移动软件有限公司 | Gesture detection method and device, mobile terminal and storage medium |
| CN113793244A (en) * | 2021-05-14 | 2021-12-14 | 黑蜂智造(深圳)科技有限公司 | Image data processing method, electronic device, and computer-readable storage medium |
| CN114356082A (en) * | 2021-12-20 | 2022-04-15 | 歌尔光学科技有限公司 | Image optimization method and device of augmented reality equipment, electronic equipment and system |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102016711A (en) * | 2008-04-15 | 2011-04-13 | Opto电子有限公司 | Method and apparatus to compensate for movement of an imaging apparatus |
| US8233664B2 (en) * | 2008-11-12 | 2012-07-31 | Eastman Kodak Company | Determining relative depth of points in multiple videos |
| CN103841298A (en) * | 2014-02-25 | 2014-06-04 | 浙江理工大学 | Video image stabilization method based on color constant and geometry invariant features |
| CN106507965B (en) * | 2013-08-30 | 2014-10-22 | 中国科学院电子学研究所 | A kind of various dimensions synthetic aperture radar kinematic error is extracted and compensation method |
| US20160300367A1 (en) * | 2015-04-10 | 2016-10-13 | Kabushiki Kaisha Toshiba | Method and apparatus of resampling and averaging to obtain tilted thick-slice computed tomography images |
-
2017
- 2017-06-09 CN CN201710431823.3A patent/CN109035308A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102016711A (en) * | 2008-04-15 | 2011-04-13 | Opto电子有限公司 | Method and apparatus to compensate for movement of an imaging apparatus |
| US8233664B2 (en) * | 2008-11-12 | 2012-07-31 | Eastman Kodak Company | Determining relative depth of points in multiple videos |
| CN106507965B (en) * | 2013-08-30 | 2014-10-22 | 中国科学院电子学研究所 | A kind of various dimensions synthetic aperture radar kinematic error is extracted and compensation method |
| CN103841298A (en) * | 2014-02-25 | 2014-06-04 | 浙江理工大学 | Video image stabilization method based on color constant and geometry invariant features |
| US20160300367A1 (en) * | 2015-04-10 | 2016-10-13 | Kabushiki Kaisha Toshiba | Method and apparatus of resampling and averaging to obtain tilted thick-slice computed tomography images |
Non-Patent Citations (1)
| Title |
|---|
| 殷继彬 等: "《笔+触控交互界面的设计策略与研究》", 30 June 2016, 云南大学出版社 * |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110023833A (en) * | 2016-11-30 | 2019-07-16 | 株式会社理光 | Equipment for inhibiting of vibration and electronic equipment |
| CN110023833B (en) * | 2016-11-30 | 2021-11-02 | 株式会社理光 | Vibration suppression device and electronic apparatus |
| US11421749B2 (en) | 2016-11-30 | 2022-08-23 | Ricoh Company, Ltd. | Vibration damper and electronic device |
| CN113496171A (en) * | 2020-04-03 | 2021-10-12 | 北京小米移动软件有限公司 | Gesture detection method and device, mobile terminal and storage medium |
| CN113793244A (en) * | 2021-05-14 | 2021-12-14 | 黑蜂智造(深圳)科技有限公司 | Image data processing method, electronic device, and computer-readable storage medium |
| CN113793243A (en) * | 2021-05-14 | 2021-12-14 | 黑蜂智造(深圳)科技有限公司 | Image data processing method, electronic device, and computer-readable storage medium |
| CN113352998A (en) * | 2021-06-01 | 2021-09-07 | 地平线征程(杭州)人工智能科技有限公司 | Setting direction adjusting method and device and computer readable storage medium |
| CN114356082A (en) * | 2021-12-20 | 2022-04-15 | 歌尔光学科技有限公司 | Image optimization method and device of augmented reality equipment, electronic equipment and system |
| WO2023116016A1 (en) * | 2021-12-20 | 2023-06-29 | 歌尔股份有限公司 | Image optimization method, apparatus and system for augmented reality device, and electronic device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109035308A (en) | Image compensation method and device, electronic equipment and computer readable storage medium | |
| Zubizarreta et al. | A framework for augmented reality guidance in industry | |
| CN106352877B (en) | A kind of mobile device and its localization method | |
| CN102346859B (en) | Character recognition device | |
| JP6038417B1 (en) | Robot teaching apparatus and robot control program creating method | |
| CN112484719B (en) | Systems and methods for enhancing non-inertial tracking systems using inertial constraints | |
| CN101976330B (en) | Gesture recognition method and system | |
| CN107478220A (en) | Unmanned plane indoor navigation method, device, unmanned plane and storage medium | |
| US20160210761A1 (en) | 3d reconstruction | |
| CN109559330A (en) | Visual tracking method, device, electronic equipment and the storage medium of moving target | |
| CN102831378A (en) | Method and system for detecting and tracking human object | |
| CN112798010A (en) | Initialization method and device for VIO system of visual inertial odometer | |
| CN114485640A (en) | Monocular vision inertia synchronous positioning and mapping method and system based on point-line characteristics | |
| CN112907633B (en) | Dynamic feature point identification method and application thereof | |
| CN112731503A (en) | Pose estimation method and system based on front-end tight coupling | |
| CN111385813A (en) | System and method for cycle duration measurement in repetitive activity sequences | |
| US20220218230A1 (en) | System and method of detecting walking activity using waist-worn inertial sensors | |
| KR101987308B1 (en) | Method and apparatus for recognizing motion to be considered noise | |
| CN106502380A (en) | A kind of method and apparatus for judging target following effect | |
| JP2017227687A (en) | Camera assembly, finger shape detection system using camera assembly, finger shape detection method using camera assembly, program implementing detection method, and recording medium of program | |
| CN110428452A (en) | Detection method, device, electronic equipment and the storage medium of non-static scene point | |
| Chen et al. | An integrated sensor network method for safety management of construction workers | |
| KR101958334B1 (en) | Method and apparatus for recognizing motion to be considered noise | |
| CN118209101B (en) | Multi-sensor fusion SLAM method and system applied to dynamic environment | |
| CN107765841A (en) | Method and apparatus for gesture operation identification |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181218 |
|
| RJ01 | Rejection of invention patent application after publication |