CN105069421B - A kind of human body standing behavior automatic testing method and device based on image - Google Patents
A kind of human body standing behavior automatic testing method and device based on image Download PDFInfo
- Publication number
- CN105069421B CN105069421B CN201510453651.0A CN201510453651A CN105069421B CN 105069421 B CN105069421 B CN 105069421B CN 201510453651 A CN201510453651 A CN 201510453651A CN 105069421 B CN105069421 B CN 105069421B
- Authority
- CN
- China
- Prior art keywords
- image
- label object
- label
- human body
- spokesman
- 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/20—Movements or behaviour, e.g. gesture recognition
Landscapes
- Engineering & Computer Science (AREA)
- Human Computer Interaction (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Health & Medical Sciences (AREA)
- Psychiatry (AREA)
- Social Psychology (AREA)
- Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
- Closed-Circuit Television Systems (AREA)
- Studio Devices (AREA)
Abstract
The present invention relates to a kind of human body standing behavior automatic testing method and device based on image, it applies in education recorded broadcast, video conference or intelligent monitor system, its simple installation is not easy to touch, is unrelated with standing person's height, and human body standing state is detected according to detection marker.A device is arranged in the present invention, which includes video camera, label object and image analysis module;Label level is fixed on the seat of spokesman in the coverage of video camera, and label object is blocked when spokesman sits down, and when standing, label object then reveals;When spokesman sits down, video camera can not take or can only take the label object of the corresponding seat of small part, but when spokesman's standing, and camera shooting function takes the label object of the corresponding seat of all or most;Whether Image Real-time Transmission to image analysis module, image analysis module operation image algorithm, automatic decision are had standing target by video camera.
Description
Technical field
The present invention relates to a kind of human body standing behavior automatic testing method and device based on image is applied and is recorded in education
It broadcasts, in video conference or intelligent monitor system.
Background technology
In education recorded broadcast classroom, meeting room or Indoor Video, it usually needs a kind of to detect standing spokesman automatically
Device.The image device of existing automatic detection standing spokesman, both sides respectively fill a camera shooting typically before classroom
Machine, height of head is slightly higher when video camera mounting height is than people's sitting, and in the image of video camera, a horizontal firing line is arranged.
When people stands, human height is more than horizontal firing line, thus detects human body standing activities.Such as application No. is
201410610741.1, a kind of Chinese patent of entitled student trace localization method based on principal and subordinate's video camera uses class
As method.
But the method have the shortcomings that it is several bigger, first, camera installation locations both sides usually before classroom, this
The many occasions in position are all windowpanes, it is difficult to be installed;Second is that video camera mounting height is relatively low, student is easy arbitrarily to adjust it
Whole or destruction causes detection inaccurate or can not detect;Third, being difficult to picture to the occasion that student's height height differs meets condition
Firing line;Fourth, can't resolve primary grades pupil standing height and sitting height the problem of being not much different, needless to say stand
The vertical height situation also lower or fair than sitting height.
Invention content
It is an object of the invention to overcome above-mentioned deficiency existing in the prior art, and provide a kind of reasonable design based on
The human body standing behavior automatic testing method and device of image, simple installation are not easy to touch, are unrelated with standing person's height, according to
Human body standing state is detected according to detection marker.
Technical solution is used by the present invention solves the above problems:
A kind of human body standing behavior automatic testing method based on image, it is characterised in that:One device is set, the device packet
Include video camera, label object and image analysis module;Label level is fixed on spokesman's in the coverage of video camera
On seat, label object is blocked when spokesman sits down, and when standing, label object then reveals;When spokesman sits down, take the photograph
Camera can not take or can only take the label object of the corresponding seat of small part, but when spokesman's standing, video camera
The label object of the corresponding seat of all or most can be taken;Video camera by Image Real-time Transmission to image analysis module,
Whether image analysis module operation image algorithm, automatic decision have standing target;
The image algorithm includes the following steps:
Step 1 obtains a frame image by video camera, is sent into image analysis module;
Step 2 retains pixel identical with label object color in image, removes the pixel of other colors;
Step 3, to step 2 treated image carries out expansion and etch state filtering, and carry out connected domain analysis, go
Except small block of pixels, non-interconnected region is disconnected, filling region cavity removes connected domain burrs on edges;
Step 4, to each connected domain edge in the image after step 3 into row label object form fit;
The coincidence ratio of step 5, digital simulation pattern curve and connected domain actual edge;
Step 6 overlaps the region that ratio is less than certain threshold value, it is believed that is non-label object, removes this region;
Step 7 records size and location information of the coincidence ratio more than the region of threshold value in step 6, and verifies area
The size in domain, location information, and information is put into buffering area;
Step 8, at regular intervals time sample new piece image, repeat step 1-6, obtain new piece image acceptance of the bid
It signs the size and location information of object area and is stored in buffering area;
Step 9, buffering area maintain the size and location information of the label object area of multiple image always;
Step 10, when buffering area is full, according to first in first out, abandon the information of oldest frame image;
Step 11, the size variation for judging the label object area of continuous multiple frames image close positions in buffering area, if certain
Area label object size from scratch, or from small becomes larger, then judges someone's standing herein;If certain area label object size from
Have to nothing, or from becoming smaller greatly, then judges to take down herein.
The present invention is provided centrally with small label the label object, added between the step 6 and step 7 as
Lower step 6b:The small label Verification of label object, if without small label, it is believed that non-label object removes this region;In step 8, weight
Multiple step 1-6b.
Label object of the present invention is multiple, and the equal fixed placement in the seat of each spokesman one is opened.
Label object of the present invention uses unified color.
Label object of the present invention uses unified shape.
The color of label object of the present invention is the color of monotone.
The shape of label object of the present invention is circle.
The present invention in step 2, using hsv color space judges the color of label object:First, image is converted
To hsv color space, when pixel H meets 360-Dev<H<360 or 0<H<When Dev, which is considered red;Work as picture
Vegetarian refreshments H meets 120-Dev<H<When 120+Dev, which is considered green;When pixel H meets 240-Dev<H<240+
When Dev, which is considered blue;Wherein Dev takes 5~10.
A kind of human body standing behavior automatic detection device based on image, it is characterised in that:Including video camera, label object and
Image analysis module;Label level is fixed on the seat of spokesman in the coverage of video camera, and spokesman sits down
When label object be blocked, and when standing, label object then reveals;When spokesman sits down, video camera can not take or
Person can only take the label object of the corresponding seat of small part, but when spokesman stands, camera shooting function take all or
The label object of most corresponding seat;Video camera runs Image Real-time Transmission to image analysis module, image analysis module
Whether image algorithm, automatic decision have standing target.
Compared with prior art, the present invention haing the following advantages and effect:1, video camera can be ceiling mounted, will not
The case where appearance can not install;2, mounting height is high, is not easy to be touched and destroyed by audience;3, audience's height is adapted to differ or even deposit
In the situation of very big gap;4, it adapts to audience's standing height and sitting height is not much different or even the feelings also lower than sitting height
Shape;5, algorithm robustness is good, and reliability is high;6, it is not necessarily to that standing firing line is arranged according to audience's height in video camera, without
Be concerned about the height height of audience, only need to according to the variation of special sign thing, image algorithm can automatic decision go out whether audience stands
It stands or whether sits down, algorithm is simple, and it is convenient to realize, as a result reliably.
Description of the drawings
Fig. 1 is the structural schematic diagram of the embodiment of the present invention.
Fig. 2 is the structural schematic diagram of head assembly of embodiment of the present invention bottom.
Fig. 3 is the structural schematic diagram of base assembly of the embodiment of the present invention.
Fig. 4 is the structural schematic diagram of CCD camera assembly of the embodiment of the present invention.
Fig. 5 is that label object of the embodiment of the present invention is fixed on the schematic diagram on seat.
Fig. 6 is the label object of video camera of embodiment of the present invention shooting from the small change schematic diagram to become larger.
Fig. 7 is the schematic diagram of step 4 label object fitting result of the embodiment of the present invention.
Fig. 8 is image algorithm flow chart of the present invention.
Specific implementation mode
The present invention is described in further detail below in conjunction with the accompanying drawings and by embodiment, and following embodiment is to this hair
Bright explanation and the invention is not limited in following embodiments.
Referring to Fig. 1~Fig. 8, the human body standing behavior automatic detection device the present invention is based on image includes video camera, label
Object 5 and image analysis module.
Video camera includes base assembly 1, head assembly 2 and CCD camera assembly 3.
Base assembly 1 includes pedestal upper casing 4 and pedestal lower casing 6.Pedestal upper casing 4 and pedestal lower casing 6 are fixed together.
Head assembly 2 includes holder pedestal 9, holder holder 10 and drive component.9 horizontal left-right rotation of holder pedestal connects
At the top of pedestal upper casing 4, such head assembly 2 is connected to regard to horizontal left-right rotation on base assembly 1, and horizontal left-right rotation is
Refer to left-right rotation in the horizontal direction.
Holder holder 10 is fixed on 9 top of holder pedestal.
CCD camera assembly 3 includes camera 12 and camera shell.Camera 12 is fixed in casing of pick-up head body.Camera
Shell is vertically rotatably connected on holder holder 10, and such CCD camera assembly 3 is just vertically rotatably connected on holder group
On part 2, vertically rotation refers to vertically rotating upwardly and downwardly.
Camera shell includes camera upper casing 11, camera lower casing 8 and camera front housing 7.Camera upper casing 11, camera shooting
Head lower casing 8, camera front housing 7 are fixed together.
Drive component is connect with holder pedestal 9 and camera shell, can drive 2 horizontal left-right rotation of head assembly and camera shooting
Head assembly 3 vertically rotates.
Image analysis module is connect with video camera.
Label object 5 is located in the coverage of video camera.5 level of label object, which is pasted, to be fixed on seat, and spokesman sits down
When label object 5 be blocked, and when standing, label object 5 then reveals.
Label object 5 is multiple, and the equal fixed placement in the seat of each spokesman one is opened;These label objects 5 use unified face
Color and unified shape;Color generally chooses the color of the monotones such as red, green or blue, it is not easy to it is influenced by brightness,
Color is facilitated to compare and judge;Shape generally chooses circle, can preferably resist certain affine of the rotation of label object, label object
Transformation and the interference of a large amount of straight lines of background.
In order to improve jamproof ability, there are one small small labels for label object 5 centrally disposed, for label object 5
Verification.The color of small label is black.
In the present embodiment, label object 5 is red and is round, diameter 20cm, and circle centre position is that the black circle of diameter 2cm is small
Label.
Video camera lifts on the ceiling, and video camera shoots bed rearrangement position and audience with depression angle.When spokesman sits down,
Video camera can not take or take the label object 5 of the corresponding seat of small part, but when spokesman's standing, image function
Take the label object 5 of the corresponding seat of all or most.Camera review is real-time transmitted to image analysis module, image
Analysis module is analyzed, and standing target is judged whether there is.
One frame image of camera acquisition, image analysis module analyze this frame image.It can be analyzed as follows(This
Analysis is a kind of embodiment):If 5 size of label object of continuous multiple frames image close positions is from scratch, or from small change
Greatly, then judge someone's standing herein;If certain 5 size of area label object is from having to nothing, or from becoming smaller greatly, then judges have herein
People sits down.
According to room-size, to make camera shooting function be detected all markers 5, can be installed on overhead room
Multiple cameras.In the present embodiment, one video camera is installed into row label analyte detection per two rows of, four row audiences.
Image analysis module operation image algorithm the step of be:
Step 1 obtains a frame image by video camera, is sent into image analysis module, image analysis module is i.e. to this frame figure
As carrying out image algorithm processing;
Step 2 retains pixel identical with 5 color of label object in image, removes the pixel of other colors;
It needs to carry out color identification to label object 5 in the step, present invention employs hsv color spaces to be judged:It is first
First, image is transformed into hsv color space, when pixel H meets 360-Dev<H<360 or 0<H<When Dev, which recognizes
To be red;When pixel H meets 120-Dev<H<When 120+Dev, which is considered green;When pixel H meets
240-Dev<H<When 240+Dev, which is considered blue;Wherein Dev generally takes 5~10;
Step 3, the noise spot to remove smaller, carry out morphological erosion operation to image first;For the area of connection fracture
Domain and removal burrs on edges, morphological dilations operation is carried out to the image after erosion operation;Using connected domain analysis method, to expansion
Cavity in the region of image after operation is filled operation;
Step 4, to each connected domain edge in the image after step 3 into 5 form fit of row label object;Such as this reality
It applies in example, due to camera angles relationship, elliptical shape may be presented in the circular tag object on seat in the picture, therefore to even
Image after logical domain analysis carries out ellipse fitting;Ellipse fitting uses quick random Hough change algorithm;
The coincidence ratio of step 5, digital simulation pattern curve and connected domain actual edge;In the present embodiment, in image
The interfering object of non-ellipse is there may be, therefore using the coincidence factor conduct of ellipse fitting line and connected domain actual edge line
Mark removes interfering object;
Step 6 overlaps the region that ratio is less than certain threshold value, it is believed that is non-label object 5, removes this region;
The small label Verification of step 7, label object 5, if without small label, it is believed that non-label object removes this region;Such as this
In embodiment, with the presence of the interfering object of small probability ellipse in the image of complex scene, therefore using the label object black center of circle
It is verified, removes interfering object;The brightness of circle centre position is less than certain threshold value, then is verified;Otherwise, this region is removed;It should
Threshold value can take 30;
Step 8 records size and location information of the coincidence ratio more than the region of threshold value in step 6, and by small
The size and location information in label Verification region, and information is put into buffering area;
Step 9, at regular intervals time sample new piece image, repeat step 1-7, obtain new piece image acceptance of the bid
The size and location information in 5 region of label object is simultaneously stored in buffering area;In the present embodiment, time interval is 400 milliseconds;
Step 10, buffering area maintain the size and location information in 5 region of label object of multiple image always;
Step 11, when buffering area is full, according to first in first out, abandon the information of oldest frame image, be added newest
The label object information of one frame image;
Step 12, judge continuous multiple frames image close positions in buffering area 5 region of label object size variation, if certain
5 size of area label object from scratch, or from small becomes larger, then judges someone's standing herein;If certain 5 size of area label object
From having to nothing, or from becoming smaller greatly, then judge to take down herein.
Furthermore, it is necessary to illustrate, the specific embodiment described in this specification, the shape of parts and components is named
Claiming etc. can be different, described in this specification above content is only to structure of the invention example explanation.
Claims (8)
1. a kind of human body standing behavior automatic testing method based on image, it is characterised in that:One device is set, which includes
Video camera, label object and image analysis module;Label level is fixed on the seat of spokesman in the coverage of video camera
On position, label object is blocked when spokesman sits down, and when standing, label object then reveals;When spokesman sits down, camera shooting
Machine can not take or can only take the label object of the corresponding seat of small part, but when spokesman's standing, image function
Take the label object of the corresponding seat of all or most;Video camera schemes Image Real-time Transmission to image analysis module
As analysis module operation image algorithm, whether automatic decision has standing target;
The image algorithm includes the following steps:
Step 1 obtains a frame image by video camera, is sent into image analysis module;
Step 2 retains pixel identical with label object color in image, removes the pixel of other colors;
Step 3 filters step 2 treated image carries out expansion and etch state, and carries out connected domain analysis, removes small
Block of pixels, disconnect non-interconnected region, filling region cavity removes connected domain burrs on edges;
Step 4, to each connected domain edge in the image after step 3 into row label object form fit;
The coincidence ratio of step 5, digital simulation pattern curve and connected domain actual edge;
Step 6 overlaps the region that ratio is less than certain threshold value, it is believed that is non-label object, removes this region;
Step 7 records size and location information of the coincidence ratio more than the region of threshold value in step 6, and validation region
Size, location information, and information is put into buffering area;
Step 8, at regular intervals time sample new piece image, repeat step 1-6, obtain label object in new piece image
The size and location information in region is simultaneously stored in buffering area;
Step 9, buffering area maintain the size and location information of the label object area of multiple image always;
Step 10, when buffering area is full, according to first in first out, abandon the information of oldest frame image;
Step 11, the size variation for judging the label object area of continuous multiple frames image close positions in buffering area, if certain region
Label object size from scratch, or from small becomes larger, then judges someone's standing herein;If certain area label object size from have to
Nothing, or from becoming smaller greatly, then judge to take down herein.
2. the human body standing behavior automatic testing method according to claim 1 based on image, it is characterised in that:Described
Label object be provided centrally with small label, add following steps 6b between the step 6 and step 7:Label object it is small
Label Verification, if without small label, it is believed that non-label object removes this region;In step 8, step 1-6b is repeated.
3. the human body standing behavior automatic testing method according to claim 1 based on image, it is characterised in that:Described
Label object is multiple, and the equal fixed placement in the seat of each spokesman one is opened.
4. the human body standing behavior automatic testing method according to claim 3 based on image, it is characterised in that:Described
Label object uses unified color.
5. the human body standing behavior automatic testing method according to claim 3 based on image, it is characterised in that:Described
Label object uses unified shape.
6. the human body standing behavior automatic testing method according to claim 4 based on image, it is characterised in that:Described
The color of label object is the color of monotone.
7. the human body standing behavior automatic testing method according to claim 3 based on image, it is characterised in that:Described
The shape of label object is circle.
8. the human body standing behavior automatic testing method according to claim 1 or 4 based on image, it is characterised in that:
In step 2, the color of label object is judged using hsv color space:First, image is transformed into hsv color space, when
Pixel H meets 360-Dev<H<360 or 0<H<When Dev, which is considered red;When pixel H meets 120-Dev
<H<When 120+Dev, which is considered green;When pixel H meets 240-Dev<H<When 240+Dev, which thinks
It is blue;Wherein Dev takes 5~10.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510453651.0A CN105069421B (en) | 2015-07-29 | 2015-07-29 | A kind of human body standing behavior automatic testing method and device based on image |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510453651.0A CN105069421B (en) | 2015-07-29 | 2015-07-29 | A kind of human body standing behavior automatic testing method and device based on image |
Publications (2)
Publication Number | Publication Date |
---|---|
CN105069421A CN105069421A (en) | 2015-11-18 |
CN105069421B true CN105069421B (en) | 2018-09-25 |
Family
ID=54498783
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510453651.0A Active CN105069421B (en) | 2015-07-29 | 2015-07-29 | A kind of human body standing behavior automatic testing method and device based on image |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105069421B (en) |
Families Citing this family (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107172383B (en) * | 2016-03-02 | 2019-11-22 | 杭州海康威视数字技术股份有限公司 | A kind of Obj State detection method and device |
CN106227092B (en) * | 2016-08-09 | 2018-12-21 | 大连理工大学 | Intelligent elderly service robot |
CN107480607B (en) * | 2017-07-28 | 2020-04-07 | 青岛大学 | Method for detecting and positioning standing face in intelligent recording and broadcasting system |
CN109920079B (en) * | 2018-12-18 | 2021-03-23 | 国网浙江桐乡市供电有限公司 | Safety configuration data collection method for power equipment |
CN110458808B (en) * | 2019-07-10 | 2021-06-15 | 山东仕达思生物产业有限公司 | Female genital tract pathogen identification method based on morphology and YOLO algorithm |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5825924A (en) * | 1993-05-07 | 1998-10-20 | Nippon Telegraph And Telephone Corporation | Method and apparatus for image processing |
CN102354378A (en) * | 2011-05-20 | 2012-02-15 | 北京理工大学 | Classroom management system based on image identification and network |
CN102495997A (en) * | 2011-10-30 | 2012-06-13 | 南京师范大学 | Reading room intelligent management system based on video detection and GIS (geographic information system) image visualization |
CN102646297A (en) * | 2012-04-27 | 2012-08-22 | 徐汉阳 | Intelligent theatre chain attendance statistical system and intelligent theatre chain attendance statistical method |
CN102867188A (en) * | 2012-07-26 | 2013-01-09 | 中国科学院自动化研究所 | Method for detecting seat state in meeting place based on cascade structure |
-
2015
- 2015-07-29 CN CN201510453651.0A patent/CN105069421B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5825924A (en) * | 1993-05-07 | 1998-10-20 | Nippon Telegraph And Telephone Corporation | Method and apparatus for image processing |
CN102354378A (en) * | 2011-05-20 | 2012-02-15 | 北京理工大学 | Classroom management system based on image identification and network |
CN102495997A (en) * | 2011-10-30 | 2012-06-13 | 南京师范大学 | Reading room intelligent management system based on video detection and GIS (geographic information system) image visualization |
CN102646297A (en) * | 2012-04-27 | 2012-08-22 | 徐汉阳 | Intelligent theatre chain attendance statistical system and intelligent theatre chain attendance statistical method |
CN102867188A (en) * | 2012-07-26 | 2013-01-09 | 中国科学院自动化研究所 | Method for detecting seat state in meeting place based on cascade structure |
Also Published As
Publication number | Publication date |
---|---|
CN105069421A (en) | 2015-11-18 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105069421B (en) | A kind of human body standing behavior automatic testing method and device based on image | |
US8773464B2 (en) | Methods and systems for collaborative-writing-surface image formation | |
CN106843460B (en) | Multiple target position capture positioning system and method based on multi-cam | |
CN103716594B (en) | Panorama splicing linkage method and device based on moving target detecting | |
US10121069B2 (en) | Method of switching video images and surveillance system | |
CN106162146B (en) | The method and system of automatic identification and playing panoramic video | |
CN108230343A (en) | A kind of image processing method and device | |
CN103957387B (en) | A kind of security protection channel sundries detection method and detection system | |
CN104732219B (en) | A kind of room for individual study room querying method and device based on image recognition | |
CN106339657B (en) | Crop straw burning monitoring method based on monitor video, device | |
CN101209207A (en) | Eyelid detecting apparatus, eyelid detecting method and program thereof | |
Rougier et al. | Fall detection using 3d head trajectory extracted from a single camera video sequence | |
CN106469312A (en) | Weld seam visual identity method based on region growing label | |
EP1798688A3 (en) | Method of locating a human eye in a video image | |
CN110059611A (en) | A kind of intelligence vacant seat recognition methods in classroom | |
CN105709434A (en) | Educational toy suite and reflector position detecting method thereof | |
CN112016482B (en) | Method and device for distinguishing false face and computer equipment | |
CN102360424A (en) | Glare prevention method based on shadow image cutting algorithm | |
WO2018000786A1 (en) | Method and device for automatically moving suspended menu | |
CN106845378A (en) | It is a kind of to in image recognize human body target method | |
CN106941580A (en) | Method and system of the teacher student from motion tracking is realized based on single detective camera lens | |
CN102663350A (en) | Road tunnel fire detection method based on video | |
CN104616277B (en) | Pedestrian's localization method and its device in video structural description | |
CN210645067U (en) | Camera module for identifying basketball track | |
CN108876824A (en) | Method for tracking target, device, system and ball machine |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
CB02 | Change of applicant information |
Address after: 310030 4, 4, 16 West Garden Road, West Lake science and Technology Park, three pier Town, Xihu District, Hangzhou, Zhejiang. Applicant after: Hangzhou morning Ann Polytron Technologies Inc Address before: 310030 4, 4, 16 West Garden Road, West Lake science and Technology Park, three pier Town, Xihu District, Hangzhou, Zhejiang. Applicant before: Hangzhou Chingan Vision Digital Technology Co., Ltd. |
|
CB02 | Change of applicant information | ||
GR01 | Patent grant | ||
GR01 | Patent grant |