CN106525003B - A kind of attitude measurement method based on binocular vision - Google Patents
A kind of attitude measurement method based on binocular vision Download PDFInfo
- Publication number
- CN106525003B CN106525003B CN201611164992.7A CN201611164992A CN106525003B CN 106525003 B CN106525003 B CN 106525003B CN 201611164992 A CN201611164992 A CN 201611164992A CN 106525003 B CN106525003 B CN 106525003B
- Authority
- CN
- China
- Prior art keywords
- camera
- coordinate
- binocular
- binocular vision
- calibration
- 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.)
- Active
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C11/00—Photogrammetry or videogrammetry, e.g. stereogrammetry; Photographic surveying
- G01C11/02—Picture taking arrangements specially adapted for photogrammetry or photographic surveying, e.g. controlling overlapping of pictures
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C11/00—Photogrammetry or videogrammetry, e.g. stereogrammetry; Photographic surveying
- G01C11/04—Interpretation of pictures
- G01C11/30—Interpretation of pictures by triangulation
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/20—Instruments for performing navigational calculations
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Automation & Control Theory (AREA)
- Length Measuring Devices By Optical Means (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a kind of attitude measurement methods based on binocular vision, it measures and positions by calculating the slug being tracked on object using binocular vision system, include the steps that the calibration of binocular vision system, Attitude Calculation, Kalman filtering carried out to attitude data.The Kalman Filter Technology detection speed that the present invention uses is fast, can measure to human face posture without carrying out accurate initialization；Accumulated error of the present invention is small, is able to carry out prolonged tracking measurement.
Description
Technical field
The present invention relates to technical field of virtual reality, it is specifically a kind of it is based on binocular vision, be applied to it is virtual existing
To the tracking measurement method of interaction medium in human face posture measurement and interactive operation in reality.
Background technique
In virtual reality and augmented reality field, there is a large amount of face appearances measured using inertial sensor at present
State estimating system, these systems are measured using gyroscope and accelerometer, since such system is for being tracked object
Location estimation there is accumulated errors, so not can be carried out for a long time use；Furthermore using inertial sensor measurement there is also
It must suitably be initialized, otherwise whole system cisco unity malfunction.
Drawbacks described above is worth solving.
Summary of the invention
In order to overcome the shortcomings of that existing technology, the present invention provide a kind of attitude measurement method based on binocular vision.
Technical solution of the present invention is as described below:
A kind of attitude measurement method based on binocular vision, which is characterized in that using binocular vision system by calculating quilt
The slug on object is tracked to measure and position, comprising the following steps:
The calibration of step 1, binocular vision system obtains the translation and rotation between the inner parameter and camera of camera
Relationship；
Step 2, Attitude Calculation carry out the measurement of three-dimensional coordinate using triangulation to mark point；
Step 3 carries out Kalman filtering to the posture rotation and translation data of measurement.
According to the present invention of above scheme, which is characterized in that the calibration process in the step 1 includes the calibration of camera internal reference
With binocular camera stereo calibration.
Further, the distortion ginseng when calibration of camera internal reference includes the focal length, optical center coordinate and camera imaging of camera
Several calibration.
Further, during binocular camera stereo calibration, the rigid body transformation relation of multiple cameras is calculated first, from
And true physical world is established to the corresponding relationship between virtual camera coordinates system, recycle the inner parameter of camera can
With the structural physical world to the corresponding relationship between camera coordinates system.
According to the present invention of above scheme, which is characterized in that in the step 2, specific step is as follows for Attitude Calculation:
(1) the center-of-mass coordinate Poc for three mark points that current binocular camera detects is calculated first, then by three three-dimensionals
Center-of-mass coordinate is individually subtracted in point, obtains the new coordinate under geocentric coordinate system, is set as Pc；Mass center seat is individually subtracted in three three-dimensional coordinates
New coordinate Pp of three mark points that the preceding binocular camera of mark calculating detects under its mass center Pop coordinate system；
(2) it using normal vector nc=Pc1 x Pc2 and np=Pp1 the x Pp2 of point set Pc and the Pp plane determined, utilizes
The normal vector of two planes by two Plane Rotations to approximately the same plane, using the theoretical calculation of quaternary number go out two normal vectors it
Between rotation, wherein Pc={ Pc1, Pc2, Pc3 } is three mark point three-dimensional coordinates detecting of binocular camera current time, Pp
={ Pp1, Pp2, Pp3 } is the three mark point three-dimensional coordinates detected binocular camera last moment；
(3) pass through above-mentioned steps, the plane and last moment that three mark points of current time determine are true by three mark points
Two fixed planes have been in approximately the same plane, and at this moment the z-axis of two coordinate systems is overlapped, but x, y coordinate system still remain
Rotation, the angle between vector by calculating two groups of points composition, which can calculate in face, to be rotated；
Coordinate between the mass center of (4) two group echo items is translation vector, obtains the rotation between the mark point of movement front and back
Turn and translation relation.
Further, it in the coordinate process for selecting three points, selects five corresponding points to be detected first, is stablized
Five corresponding points after take out three therein and calculated.
According to the present invention of above scheme, which is characterized in that the filtering in the step 3 includes:
(1) state transfer is carried out
1) angle of position and rotation is selected to form a state vector x,
In formula, x, y, z is respectively displacement three-dimensional coordinate,Respectively three-D displacement speed,Respectively
For three-D displacement acceleration, ψ, θ,Respectively three-dimensional rotation angle,Respectively three-dimensional rotation angular speed,Respectively three-dimensional rotation angular acceleration, T are matrix transposition,
2) state transfer is carried out using following formula
In formula, Xk is current state, Xk-1 is previous state, Wk-1 is noise, can be with using previous state
The state of prediction next time, Δ t are the time interval of preceding one-shot measurement and this measurement；
(2) it is that three-dimensional coordinate and three axis rotate angle, the translation and rotation being calculated using following formula that measurement amount, which is displacement,
In formula, Xk is current state, and vk is noise, and xk, yk, zk are the coordinates of current time (being indicated with k), remaining is
Rotate angle；
(3) obtain the stabilization data of binocular vision posture to get to data be exactly current position x, y, z and three
Rotate angle.
According to the present invention of above scheme, the beneficial effect is that, the Kalman Filter Technology that the present invention uses detects speed
Degree is fast, can measure to human face posture without carrying out accurate initialization；Accumulated error of the present invention is small, is able to carry out length
The tracking measurement of time.
Detailed description of the invention
Fig. 1 is the binocular coordinate system schematic diagram that the present invention does not demarcate.
Fig. 2 is the binocular coordinate system schematic diagram after present invention calibration.
Fig. 3 is the schematic diagram that the present invention calculates calibration coordinate.
Fig. 4 is the movement schematic diagram that present invention front and back shoots three mark points twice.
Specific embodiment
With reference to the accompanying drawing and the present invention is further described in embodiment:
A kind of attitude measurement method based on binocular vision is tracked object (people by calculating using binocular vision system
The peripheral hardware of face or user's control) on slug measure and position.Measurement process includes:
1, the calibration of binocular vision system.
As shown in Figs. 1-2, the main purpose of stereo calibration is to obtain the translation between the inner parameter and camera of camera
And rotation relationship.There are these parameters that can carry out three-dimensional correction, and the depth information of available scene to image later,
To carry out vision measurement.Binocular vision system in reality is as shown in Figure 1, have biggish deflection, and obtain between camera
To image also have biggish distortion.First of all for making binocular vision system be able to carry out measurement, it is necessary to know that these are opposite
Relationship；Secondly for the ease of carrying out disparity computation, also three-dimensional correction is carried out to image, guarantees accordingly to exercise alignment on image
, the calculating of such parallax only needs to be searched on corresponding row.
The process entirely demarcated is divided into the calibration of camera internal reference and binocular camera stereo calibration.
The internal reference calibration of camera is an inner parameter for calculating camera, the focal length including camera, optical center coordinate and camera
Distortion parameter when imaging.These parameters are constant in the use process of camera, so the inner parameter of referred to as camera.
The stereo calibration of binocular camera, the purpose of stereo calibration is the rigid body transformation relation for calculating multiple cameras, to build
True physical world is found to the corresponding relationship between virtual camera coordinates system, recycles the inner parameter of camera can structure
Physical world is made to the corresponding relationship between camera coordinates system, so that us be allow to calculate the actual physical of certain point on image
Coordinate.
2, Attitude Calculation.
As shown in figure 3, utilizing formulaAfter being demarcated to biocular systems
The measurement that three-dimensional coordinate can be carried out to mark point is directly surveyed using triangle in the binocular vision system having had corrected that
Amount can calculate the coordinate of calibration, and in formula, b refers to the distance between two cameras, and Z is the Z coordinate value of object point P, xT
It is position of the object point P on the right on camera photos, xRIt is position of the object P on the right on camera photos, f is the coke of camera
Away from d is parallax (d=xR-xT)。
The kinematic parameter between two frame of front and back of object can be solved using three pairs of matched three-dimensional points, but due to reality
The operation of border of requirement in to(for) stability and ease for use, is generally detected using five corresponding points, it is right to obtain stable five
Three therein are taken out after should putting to be calculated.
As shown in figure 4, can be carried out Attitude Calculation later by the three-dimensional coordinate that above-mentioned steps measure slug.Tool
The step of body, is as follows:
(1) the center-of-mass coordinate Poc for three mark points that current binocular camera detects is calculated first, then by three three-dimensionals
Center-of-mass coordinate is individually subtracted in point, obtains the new coordinate under geocentric coordinate system, is set as Pc；It is primary double before being calculated using same method
New coordinate Pp of three mark points that mesh camera detects under its mass center Pop coordinate system.
(2) it using normal vector nc=Pc1 x Pc2 and np=Pp1 the x Pp2 of point set Pc and the Pp plane determined, utilizes
The normal vector of two planes by two Plane Rotations to approximately the same plane, using the theoretical calculation of quaternary number go out two normal vectors it
Between rotation, wherein Pc={ Pc1, Pc2, Pc3 } is three mark point three-dimensional coordinates detecting of binocular camera current time, Pp
={ Pp1, Pp2, Pp3 } is the three mark point three-dimensional coordinates detected binocular camera last moment.
(3) it has been in approximately the same plane by two planes of above-mentioned steps, at this moment the z-axis of two coordinate systems is overlapped, but
It is that xy coordinate system still remains rotation, at this moment the angle in calculating figure between two groups of point vectors can be calculated in face and be rotated.
The quaternary number for the rotation that two planes can be calculated to this.Plane after rotation is in the same face, so
It is rotated in using you can get it the face of the angled relationships between two coordinate vectors afterwards.
Coordinate between the mass center of (4) two group echo items is translation vector.
So far, so that it may calculate the mobile posture of each marked body, be exactly rotation between the mark point of movement front and back and
Translation relation
3, Kalman filtering is carried out to attitude data.
Since measuring system itself is due to various interference, so the attitude data surveyed contains noise, so as to cause
There is violent shake in attitude data, so finally also needing to be filtered the rotation and translation data of measurement.At this
In we select using commonplace Kalman filter.
1) state shifts
The angle of position and rotation is selected to form a state vector, the variable in x is followed successively by displacement three-dimensional coordinate, is displaced
Speed, displacement acceleration rotate angle, angular velocity of rotation, rotating angular acceleration.
In formula, x, y, z is respectively displacement three-dimensional coordinate,Respectively three-D displacement speed,Respectively
For three-D displacement acceleration, ψ, θ,Respectively three-dimensional rotation angle,Respectively three-dimensional rotation angular speed,Respectively three-dimensional rotation angular acceleration, T are matrix transposition.
Transfer process is
In formula, Xk is current state, Xk-1 is previous state, Wk-1 is noise, can be with using previous state
The state of prediction next time, Δ t are the time interval of preceding one-shot measurement and this measurement.
2) measurement process
Measurement amount is that displacement is that three-dimensional coordinate and three axis rotate angle, is exactly the translation and rotation being calculated every time.
In formula, Xk is current state, and Vk is noise, and xk, yk, zk are the coordinates of current time (being indicated with k), remaining is
Rotate angle.
3) more stable data can be obtained with Kalman filtering progress data filtering by model above to get arriving
Data be exactly current position x, y, z and three rotation angles, totally 6 variables.
It should be understood that for those of ordinary skills, it can be modified or changed according to the above description,
And all these modifications and variations should all belong to the protection domain of appended claims of the present invention.
Illustrative description has been carried out to the invention patent above in conjunction with attached drawing, it is clear that the realization of the invention patent not by
The limitation of aforesaid way, if the method concept of the invention patent and the various improvement of technical solution progress are used, or without
It improves and the conception and technical scheme of the invention patent is directly applied into other occasions, be within the scope of the invention.
Claims (5)
1. a kind of attitude measurement method based on binocular vision, which is characterized in that using binocular vision system by calculate by with
Slug on track object is measured and is positioned, comprising the following steps:
The calibration of step 1, binocular vision system obtains the translation and rotation relationship between the inner parameter and camera of camera；
Step 2, Attitude Calculation carry out the measurement of three-dimensional coordinate using triangulation to mark point；
Step 3 carries out Kalman filtering to the posture rotation and translation data of measurement；
In the step 2, specific step is as follows for Attitude Calculation:
(1) the center-of-mass coordinate Poc for three mark points that current binocular camera detects is calculated first, then by three three-dimensional points point
Center-of-mass coordinate is not subtracted, the new coordinate under geocentric coordinate system is obtained, is set as Pc；Center-of-mass coordinate meter is individually subtracted in three three-dimensional coordinates
New coordinate Pp of three mark points that the preceding binocular camera of calculation detects under its mass center Pop coordinate system；
(2) using normal vector nc=Pc1 x Pc2 and np=Pp1 the x Pp2 of point set Pc and the Pp plane determined, two are utilized
The normal vector of plane goes out two Plane Rotations to approximately the same plane between two normal vectors using the theoretical calculation of quaternary number
Rotation, wherein Pc={ Pc1, Pc2, Pc3 } is the three mark point three-dimensional coordinates detected at binocular camera current time, Pp=
{ Pp1, Pp2, Pp3 } is the three mark point three-dimensional coordinates detected binocular camera last moment；
(3) pass through above-mentioned steps, what the plane and last moment that three mark points of current time determine were determined by three mark points
Two planes have been in approximately the same plane, and at this moment the z-axis of two coordinate systems is overlapped, but x, y coordinate system still remain rotation,
The angle between vector by calculating two groups of points composition, which can calculate in face, to be rotated；
Coordinate between the mass center of (4) two group echo items is translation vector, obtain movement front and back mark point between rotation and
Translation relation.
2. the attitude measurement method according to claim 1 based on binocular vision, which is characterized in that in the step 1
Calibration process includes the calibration of camera internal reference and binocular camera stereo calibration.
3. the attitude measurement method according to claim 2 based on binocular vision, which is characterized in that camera internal reference calibration packet
The calibration of distortion parameter when including the focal length, optical center coordinate and camera imaging of camera.
4. the attitude measurement method according to claim 2 based on binocular vision, which is characterized in that in binocular camera solid
In calibration process, the rigid body transformation relation of multiple cameras is calculated first, to establish true physical world to virtual camera
Corresponding relationship between coordinate system, recycle camera inner parameter can the structural physical world between camera coordinates system
Corresponding relationship.
5. the attitude measurement method according to claim 1 based on binocular vision, which is characterized in that the seat of three points of selection
During mark, select five corresponding points to be detected first, obtain taking out after five stable corresponding points three therein into
Row calculates.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611164992.7A CN106525003B (en) | 2016-12-16 | 2016-12-16 | A kind of attitude measurement method based on binocular vision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611164992.7A CN106525003B (en) | 2016-12-16 | 2016-12-16 | A kind of attitude measurement method based on binocular vision |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106525003A CN106525003A (en) | 2017-03-22 |
| CN106525003B true CN106525003B (en) | 2019-02-12 |
Family
ID=58340819
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611164992.7A Active CN106525003B (en) | 2016-12-16 | 2016-12-16 | A kind of attitude measurement method based on binocular vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106525003B (en) |
Families Citing this family (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110573917B (en) * | 2017-04-24 | 2022-08-23 | 奇跃公司 | Optical flow tracking backscattered laser speckle patterns |
| CN107289931B (en) * | 2017-05-23 | 2019-09-27 | 北京小鸟看看科技有限公司 | A kind of methods, devices and systems positioning rigid body |
| EP3447448B1 (en) * | 2017-07-24 | 2021-01-06 | Trifo, Inc. | Fault-tolerance to provide robust tracking for autonomous and non-autonomous positional awareness |
| CN107608541B (en) * | 2017-10-17 | 2021-03-05 | 宁波视睿迪光电有限公司 | Three-dimensional attitude positioning method and device and electronic equipment |
| CN107945220B (en) * | 2017-11-30 | 2020-07-10 | 华中科技大学 | Binocular vision-based reconstruction method |
| CN108408080B (en) * | 2018-03-29 | 2019-11-12 | 南昌航空大学 | A kind of aircraft wing body Butt Assembling device, method and system |
| CN108692661A (en) * | 2018-05-08 | 2018-10-23 | 深圳大学 | Portable three-dimensional measuring system based on Inertial Measurement Unit and its measurement method |
| CN108717713B (en) * | 2018-05-23 | 2021-11-30 | 南京理工大学 | Cross arm attitude measurement method based on binocular vision under complex background |
| CN109166150B (en) * | 2018-10-16 | 2021-06-01 | 海信视像科技股份有限公司 | Pose acquisition method and device storage medium |
| CN110232662B (en) * | 2019-05-10 | 2022-06-10 | 昆明理工大学 | Multi-information anti-interference filtering method under face pose collaborative system |
| CN110920824A (en) * | 2019-11-21 | 2020-03-27 | 深圳市若雅方舟科技有限公司 | Ship model attitude measurement system and method based on binocular stereo vision |
| CN112465877B (en) * | 2020-12-09 | 2022-11-18 | 北京航空航天大学 | Kalman filtering visual tracking stabilization method based on motion state estimation |
| CN114018214A (en) * | 2021-10-18 | 2022-02-08 | 武汉理工大学 | Marker binocular sub-pixel distance measurement method based on hardware acceleration system |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102339062A (en) * | 2011-07-11 | 2012-02-01 | 西北农林科技大学 | Navigation and remote monitoring system for miniature agricultural machine based on DSP (Digital Signal Processor) and binocular vision |
| DE102011122335A1 (en) * | 2011-09-30 | 2013-04-04 | Samsung Electro-Mechanics Co., Ltd. | Calibration device for a camera module |
| CN103198492A (en) * | 2013-03-28 | 2013-07-10 | 沈阳航空航天大学 | Human motion capture method |
| CN203231736U (en) * | 2013-04-18 | 2013-10-09 | 中国科学院沈阳自动化研究所 | Specular object measurement device based on binocular vision |
| CN105373266A (en) * | 2015-11-05 | 2016-03-02 | 上海影火智能科技有限公司 | Novel binocular vision based interaction method and electronic whiteboard system |
-
2016
- 2016-12-16 CN CN201611164992.7A patent/CN106525003B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102339062A (en) * | 2011-07-11 | 2012-02-01 | 西北农林科技大学 | Navigation and remote monitoring system for miniature agricultural machine based on DSP (Digital Signal Processor) and binocular vision |
| DE102011122335A1 (en) * | 2011-09-30 | 2013-04-04 | Samsung Electro-Mechanics Co., Ltd. | Calibration device for a camera module |
| CN103198492A (en) * | 2013-03-28 | 2013-07-10 | 沈阳航空航天大学 | Human motion capture method |
| CN203231736U (en) * | 2013-04-18 | 2013-10-09 | 中国科学院沈阳自动化研究所 | Specular object measurement device based on binocular vision |
| CN105373266A (en) * | 2015-11-05 | 2016-03-02 | 上海影火智能科技有限公司 | Novel binocular vision based interaction method and electronic whiteboard system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106525003A (en) | 2017-03-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106525003B (en) | A kind of attitude measurement method based on binocular vision | |
| CN107747941B (en) | Binocular vision positioning method, device and system | |
| CN106056664B (en) | A kind of real-time three-dimensional scene reconstruction system and method based on inertia and deep vision | |
| CN104718431B (en) | Gyroscope regulation and gyroscope camera alignment | |
| CN104596502B (en) | Object posture measuring method based on CAD model and monocular vision | |
| CN106980368A (en) | A kind of view-based access control model calculating and the virtual reality interactive device of Inertial Measurement Unit | |
| CN109465832A (en) | High-precision vision and the tight fusion and positioning method of IMU and system | |
| CN106989744A (en) | A kind of rotor wing unmanned aerial vehicle autonomic positioning method for merging onboard multi-sensor | |
| CN110617814A (en) | Monocular vision and inertial sensor integrated remote distance measuring system and method | |
| CN108364319A (en) | Scale determines method, apparatus, storage medium and equipment | |
| CN112649016A (en) | Visual inertial odometer method based on point-line initialization | |
| EP3379202B1 (en) | A method for determining bias in an inertial measurement unit of an image acquisition device | |
| GB2498177A (en) | Apparatus for determining a floor plan of a building | |
| CN107153369A (en) | It is a kind of to position the localization method of object, system and wear display device | |
| CN110411476A (en) | Vision inertia odometer calibration adaptation and evaluation method and system | |
| CN108733206A (en) | A kind of coordinate alignment schemes, system and virtual reality system | |
| JP6288858B2 (en) | Method and apparatus for estimating position of optical marker in optical motion capture | |
| CN108154533A (en) | A kind of position and attitude determines method, apparatus and electronic equipment | |
| CN108022302A (en) | A kind of sterically defined AR 3 d display devices of Inside-Out | |
| CN111609868A (en) | Visual inertial odometer method based on improved optical flow method | |
| CN109040525B (en) | Image processing method, image processing device, computer readable medium and electronic equipment | |
| KR20190063153A (en) | System and method for simultaneous reconsttuction of initial 3d trajectory and velocity using single camera images | |
| CN113012224A (en) | Positioning initialization method and related device, equipment and storage medium | |
| Satoh et al. | A head tracking method using bird's-eye view camera and gyroscope | |
| Nyqvist et al. | A high-performance tracking system based on camera and IMU |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | 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 | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20211227 Address after: 518107 1801 and 1802, building 1, South Taiyun chuanggu Park, Southeast of the intersection of Guangming Avenue and Dongchang Road, Tangwei community, Fenghuang street, Guangming District, Shenzhen, Guangdong Province Patentee after: Shenzhen zhilai Education Technology Co.,Ltd. Address before: No. 103, Baishan 1st Street, Shenzhen, Guangdong Province Patentee before: SHENZHEN VOXELSENSE TECHNOLOGY CO.,LTD. |