CN110197134A - A kind of human action detection method and device - Google Patents
A kind of human action detection method and device Download PDFInfo
- Publication number
- CN110197134A CN110197134A CN201910393401.0A CN201910393401A CN110197134A CN 110197134 A CN110197134 A CN 110197134A CN 201910393401 A CN201910393401 A CN 201910393401A CN 110197134 A CN110197134 A CN 110197134A
- Authority
- CN
- China
- Prior art keywords
- human body
- key position
- image
- motion track
- sample data
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/246—Analysis of motion using feature-based methods, e.g. the tracking of corners or segments
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Data Mining & Analysis (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Psychiatry (AREA)
- Social Psychology (AREA)
- Human Computer Interaction (AREA)
- Image Analysis (AREA)
Abstract
The application provides a kind of human action detection method and device.Wherein, method includes: the video image that real-time acquisition includes the human body, is detected by the convolutional neural networks model that training is completed to the key position for the human body for including in the video image, and obtain the location information of the key position;Based on the location information of the obtained key position, the motion track of the key position is determined;The determining motion track is compared with preset standard trajectory, judges whether the motion track of the key position closes rule.In this way, may be implemented whether to meet specification to the motion track of human body key position.
Description
Technical field
This application involves technical field of image detection, in particular to a kind of human action detection method and device.
Background technique
Raising with user to the quality requirements of display screen, display screen manufacturer are going out the display screen of production
It needs to carry out strict inspection before factory, so that display screen can just introduce to the market after meeting quality standard.
Currently, needing to visually observe display screen display effect by staff for the detection of the partial properties of display screen
Fruit searches defect, flaw existing for display screen etc..And artificial detection depends on the subjective judgement of staff, however by
It in the diversity of operator work habit, is easy to appear and does not observe position, it is not careful to detect, and acts nonstandard situation, finally
The problem of leading to erroneous detection, missing inspection.
For display screen testing staff and work habit diversity, display screen testing staff how is accurately examined to examine dynamic
The normalization of work is of great significance for the quality for promoting display screen.
Summary of the invention
In view of this, the application provides a kind of human action detection method and device, with the rule of the movement to the human body
Plasticity is detected.
Specifically, the application is achieved by the following technical solution:
In a first aspect, providing a kind of human action detection method in the embodiment of the present application, which comprises
Acquisition in real time includes the video image of the human body, and the convolutional neural networks model completed by training is to the view
The key position for the human body for including in frequency image is detected, and obtains the location information of the key position;
Based on the location information of the obtained key position, the motion track of the key position is determined;
The determining motion track is compared with preset standard trajectory, judges the moving rail of the key position
Whether mark closes rule.
Second aspect, the embodiment of the present application provide a kind of human action detection device, comprising:
Detection module passes through the convolutional Neural net of training completion for acquiring the video image comprising the human body in real time
Network model detects the key position for the human body for including in the video image, and obtains the position letter of the key position
Breath;
Determining module determines the movement of the key position for the location information based on the obtained key position
Track;
Judgment module judges the pass for the motion track determined to be compared with preset standard trajectory
Whether the motion track at key position closes rule.
The third aspect, the embodiment of the present application provide a kind of computer readable storage medium, are stored thereon with computer journey
Sequence, when described program is executed by processor realize as described in relation to the first aspect method the step of.
Fourth aspect, the embodiment of the present application provide a kind of computer equipment, including memory, processor and are stored in institute
The computer program that can be run on memory and on the processor is stated, the processor executes real when the computer program
The step of method described in existing above-mentioned first aspect.
A kind of human action detection method and device provided in the embodiment of the present application, can accurate detection go out it is monitored
The movement of personnel, and judge whether the movement of human body meets specification.
Detailed description of the invention
Fig. 1 is a kind of flow diagram of human action detection method shown in one exemplary embodiment of the application;
Fig. 2 is the flow diagram of the training neural network shown in one exemplary embodiment of the application;
Fig. 3 is a kind of structural schematic diagram of human action detection device shown in one exemplary embodiment of the application.
Specific embodiment
Example embodiments are described in detail here, and the example is illustrated in the accompanying drawings.Following description is related to
When attached drawing, unless otherwise indicated, the same numbers in different drawings indicate the same or similar elements.Following exemplary embodiment
Described in embodiment do not represent all embodiments consistent with the application.On the contrary, they be only with it is such as appended
The example of the consistent device and method of some aspects be described in detail in claims, the application.
It is only to be not intended to be limiting the application merely for for the purpose of describing particular embodiments in term used in this application.
It is also intended in the application and the "an" of singular used in the attached claims, " described " and "the" including majority
Form, unless the context clearly indicates other meaning.It is also understood that term "and/or" used herein refers to and wraps
It may be combined containing one or more associated any or all of project listed.
It will be appreciated that though various information, but this may be described using term first, second, third, etc. in the application
A little information should not necessarily be limited by these terms.These terms are only used to for same type of information being distinguished from each other out.For example, not departing from
In the case where the application range, the first information can also be referred to as the second information, and similarly, the second information can also be referred to as
One information.Depending on context, word as used in this " if " can be construed to " ... when " or " when ...
When " or " in response to determination ".
Fig. 1 shows a kind of flow diagram of human action detection method of the application one embodiment offer.Reference
Shown in Fig. 1, this method comprises the following steps S101-S103:
S101, in real time acquisition include the video image of the human body, the convolutional neural networks model pair completed by training
The key position for the human body for including in the video image is detected, and obtains the location information of the key position.
Referring to embodiment shown in Fig. 2, the above-mentioned convolutional neural networks model completed in training is in the video image
Before the key position for the human body for including is detected, need first to obtain the convolutional neural networks model of training completion, the convolution
Neural network model is through the following steps that S201-S202 training was completed:
The markup information for each sample image that S201, generation sample data set and the sample data are concentrated.
Specifically, the image comprising human body and image not comprising human body are obtained under target scene as training data,
The sample data set is generated, trained yolo model detects to wrap from the sample data of magnanimity in coco data set
Image containing human body, head, hand key point to the image labeling testing staff.
It is for display screen detects scene by the target scene, above-mentioned training data mainly includes under display screen detection environment
There are testing staff and the image data without testing staff, the image for being adapted under scene, and other scenes of part with and without people
Data are used for lift scheme Shandong nation property and compatibility.It is collected image data, length and width dimensions and mark after training data
Key point coordinate both maps on 0 to 1, eliminate data between, between coordinate dimension influence so that between each data target
It in the same order of magnitude, is comparable, and guarantees that back-propagation gradient towards the direction of minimum value, guarantees model instruction always
Accelerate convergence when practicing.
In the case where being directed to display screen detection scene, the normalization of the key position of testing staff is detected, above-mentioned people
The key position of body can be include: human body head and hand.
Above-mentioned target scene is also possible to such as in the field that the sitting posture normalization of student before screen is detected
Scape;At this point, the key position of above-mentioned human body can be including human body head and trunk portion.
The markup information of S202, each sample image concentrated according to the sample data and each sample image are trained
The convolutional neural networks of foundation obtain the convolutional layer of the convolutional neural networks and the parameter of batch normalization layer.
In one embodiment of the application, gives the Recognition with Recurrent Neural Network model that the above-mentioned training of an application is completed and calculate human body pass
The method of the position at key position is as follows:
Step A, the position proposal when human detection result has deviation is adjusted using symmetric space converting network, obtained
To the feature F of refine0。
Step B, a single Attitude estimation network is constructed, by the feature F after refine0It is input to single posture network
In, and the former space of Feature Mapping go back to (space before symmetric space transformation) will be exported and obtain feature F1, it is therefore an objective to work as human testing
In the case where frame inaccuracy, single Attitude estimation network still has good effect.
Step C, by F1Using non-maxima suppression eliminate redundancy posture, obtain to the end, hand key point.
Wherein, the elimination redundancy formula that non-maxima suppression uses is defined as:
d(Pi,Pj| Λ)=Ksim(Pi,Pj|σ1)+λHsim(Pi,Pj|σ2)
Wherein, λ is weight coefficient, Ksim(Pi,Pj|σ1) it is posture distance metric, indicate of different parts between posture
With number, for measuring the similarity between posture, eliminate off closer and more similar posture, Hsim(Pi,Pj|σ2) be posture it
Between different parts space length.
Posture distance and space length are defined as follows:
PiAnd PjIndicate F1Redundancy different response point posture coordinates, σ1And σ2Indicate standard deviation criteria,WithIt indicates
The response of n-th of characteristic point,WithIndicate the image coordinate of n-th of characteristic point, i and j are the key point index of head, hand.
When obtained non-maxima suppression result is greater than threshold value η, the head as detected, hand position key point.
S102, the location information based on the obtained key position, determine the motion track of the key position.
In the present embodiment, head, the hand position coordinate of each frame image detection personnel are calculated with trained model, uses Kalman
Tracking obtains smooth track;
S103, the determining motion track is compared with preset standard trajectory, judges the key position
Whether motion track closes rule.
In the present embodiment, according to following publicity calculate the consolidation path between standard operation track and the motion track of determination away from
From:
D (i, j)=Dist (i, j)+min [D (i-1, j), D (i, j-1), D (i-1, j-1)]
Wherein, D (i, j) indicates that length is the distance between two track sets of i and j, Dist (wki,wkj) indicate Europe
Distance, w are obtained in severalkiAnd wkjI-th of coordinate points for respectively indicating standard trajectory detect j-th of coordinate points of track.
Optionally, the above embodiments of the present application are can be in practical applications when detecting that human action does not conform to specification
It can be by way of providing prompt, staff prompted to carry out posture correction.
Method provided by the embodiments of the present application, when being applied to the detection operation normalization of display screen testing staff, first
The detection operation video for acquiring display screen testing staff extracts the head of testing staff, the position rail of hand by deep learning algorithm
Mark is judged the accuracy of current trial movement further according to the standard operation track accessed in advance, is finally worked as according to threshold decision
The qualification of preceding detection operation.
Referring to embodiment shown in Fig. 3, a kind of human action detection device is provided in the present embodiment, comprising:
Detection module 301 passes through the convolutional Neural of training completion for acquiring the video image comprising the human body in real time
Network model detects the key position for the human body for including in the video image, and obtains the position of the key position
Information;
Determining module 302 determines the shifting of the key position for the location information based on the obtained key position
Dynamic rail mark;
Judgment module 303, for the motion track determined to be compared with preset standard trajectory, described in judgement
Whether the motion track of key position closes rule.
Optionally, above-mentioned device, further includes:
Generation module, the markup information of each sample image for generating sample data set and sample data concentration;
Training module, the markup information of each sample image and each sample image for being concentrated according to the sample data
The convolutional neural networks of foundation are trained, the convolutional layer of the convolutional neural networks and the parameter of batch normalization layer are obtained.
Optionally, above-mentioned generation module, is specifically used for:
The image comprising human body is obtained under target scene and the image not comprising human body generates the sample data set, is used
Trained yolo model detects the image comprising human body from the sample data of magnanimity in coco data set, is somebody's turn to do to described
The head of image labeling testing staff, hand key point.
Optionally, the key position of the human body includes: head and the hand of human body.
Optionally, above-mentioned judgment module, is specifically used for:
The consolidation path distance between standard trajectory and the detection track is calculated, is preset when the regular path distance meets
When threshold range, judge that the motion track of the key position closes rule.
Installation practice can also be realized by software realization by way of hardware or software and hardware combining.
The function of each unit and the realization process of effect are specifically detailed in the above method and correspond to step in above-mentioned apparatus
Realization process, details are not described herein.
The third aspect, the embodiment of the present application provide a kind of computer readable storage medium, are stored thereon with computer journey
Sequence, the step of a kind of human action detection method is realized when described program is executed by processor.
Fourth aspect, the embodiment of the present application provide a kind of computer equipment, including memory, processor and are stored in institute
The computer program that can be run on memory and on the processor is stated, the processor executes real when the computer program
A kind of the step of existing above-mentioned human action detection method.
For device embodiment, since it corresponds essentially to embodiment of the method, so related place is referring to method reality
Apply the part explanation of example.The apparatus embodiments described above are merely exemplary, wherein described be used as separation unit
The unit of explanation may or may not be physically separated, and component shown as a unit can be or can also be with
It is not physical unit, it can it is in one place, or may be distributed over multiple network units.It can be according to actual
The purpose for needing to select some or all of the modules therein to realize application scheme.Those of ordinary skill in the art are not paying
Out in the case where creative work, it can understand and implement.
It is suitable for storing computer program instructions and the computer-readable medium of data including the non-volatile of form of ownership
Memory, medium and memory devices, for example including semiconductor memory devices (such as EPROM, EEPROM and flash memory device),
Disk (such as internal disk or removable disk), magneto-optic disk and CD ROM and DVD-ROM disk.Processor and memory can be by special
It is supplemented or is incorporated in dedicated logic circuit with logic circuit.
Although this specification includes many specific implementation details, these are not necessarily to be construed as the model for limiting any invention
It encloses or range claimed, and is primarily used for describing the feature of the specific embodiment of specific invention.In this specification
Certain features described in multiple embodiments can also be combined implementation in a single embodiment.On the other hand, individually implementing
Various features described in example can also be performed separately in various embodiments or be implemented with any suitable sub-portfolio.This
Outside, although feature can work in certain combinations as described above and even initially so be claimed, institute is come from
One or more features in claimed combination can be removed from the combination in some cases, and claimed
Combination can be directed toward the modification of sub-portfolio or sub-portfolio.
Similarly, although depicting operation in the accompanying drawings with particular order, this is understood not to require these behaviour
Make the particular order shown in execute or sequentially carry out or require the operation of all illustrations to be performed, to realize desired knot
Fruit.In some cases, multitask and parallel processing may be advantageous.In addition, the various system modules in above-described embodiment
Separation with component is understood not to be required to such separation in all embodiments, and it is to be understood that described
Program assembly and system can be usually integrated in together in single software product, or be packaged into multiple software product.
The specific embodiment of theme has been described as a result,.Other embodiments are within the scope of the appended claims.?
In some cases, the movement recorded in claims can be executed in different order and still realize desired result.This
Outside, the processing described in attached drawing and it is nonessential shown in particular order or sequential order, to realize desired result.In certain realities
In existing, multitask and parallel processing be may be advantageous.
The foregoing is merely the preferred embodiments of the application, not to limit the application, all essences in the application
Within mind and principle, any modification, equivalent substitution, improvement and etc. done be should be included within the scope of the application protection.
Claims (10)
1. a kind of human action detection method, which is characterized in that the described method includes:
Acquisition in real time includes the video image of the human body, and the convolutional neural networks model completed by training is to the video figure
The key position for the human body for including as in is detected, and obtains the location information of the key position;
Based on the location information of the obtained key position, the motion track of the key position is determined;
The determining motion track is compared with preset standard trajectory, judges that the motion track of the key position is
No conjunction rule.
2. the method according to claim 1, wherein in the real-time video image of the acquisition comprising the human body
Before, comprising:
Generate the markup information of each sample image of sample data set and sample data concentration;
The markup information of each sample image and each sample image concentrated according to the sample data is trained foundation
Convolutional neural networks obtain the convolutional layer of the convolutional neural networks and the parameter of batch normalization layer.
3. according to the method described in claim 2, it is characterized in that, the generation sample data set and the sample data are concentrated
Each sample image markup information, specifically include:
The image comprising human body is obtained under target scene and the image not comprising human body generates the sample data set, is used in
Trained yolo model detects the image comprising human body from the sample data of magnanimity in coco data set, to the described figure
Head, hand key point as mark testing staff.
4. the method according to claim 1, wherein the key position of the human body include: human body head and
Hand.
5. the method according to claim 1, wherein described by the determining motion track and preset standard
Track is compared, and judges whether the motion track of the key position closes rule, comprising:
The consolidation path distance between standard trajectory and the detection track is calculated, when the regular path distance meets preset threshold
When range, judge that the motion track of the key position closes rule.
6. a kind of human action detection device characterized by comprising
Detection module passes through the convolutional neural networks mould of training completion for acquiring the video image comprising the human body in real time
Type detects the key position for the human body for including in the video image, and obtains the location information of the key position;
Determining module determines the motion track of the key position for the location information based on the obtained key position;
Judgment module judges the key portion for the motion track determined to be compared with preset standard trajectory
Whether the motion track of position closes rule.
7. device according to claim 6, which is characterized in that further include:
Generation module, the markup information of each sample image for generating sample data set and sample data concentration;
The markup information of training module, each sample image and each sample image for being concentrated according to the sample data carries out
The convolutional neural networks that training is established obtain the convolutional layer of the convolutional neural networks and the parameter of batch normalization layer.
8. device according to claim 7, which is characterized in that the generation module is specifically used for:
The image comprising human body is obtained under target scene and the image not comprising human body generates the sample data set, is used in
Trained yolo model detects the image comprising human body from the sample data of magnanimity in coco data set, to the described figure
Head, hand key point as mark testing staff.
9. device according to claim 6, which is characterized in that the key position of the human body include: human body head and
Hand.
10. device according to claim 6, which is characterized in that the judgment module is specifically used for:
The consolidation path distance between standard trajectory and the detection track is calculated, when the regular path distance meets preset threshold
When range, judge that the motion track of the key position closes rule.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910393401.0A CN110197134A (en) | 2019-05-13 | 2019-05-13 | A kind of human action detection method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910393401.0A CN110197134A (en) | 2019-05-13 | 2019-05-13 | A kind of human action detection method and device |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110197134A true CN110197134A (en) | 2019-09-03 |
Family
ID=67752638
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910393401.0A Pending CN110197134A (en) | 2019-05-13 | 2019-05-13 | A kind of human action detection method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110197134A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111091057A (en) * | 2019-11-15 | 2020-05-01 | 腾讯科技(深圳)有限公司 | Information processing method and device and computer readable storage medium |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106774894A (en) * | 2016-12-16 | 2017-05-31 | 重庆大学 | Interactive teaching methods and interactive system based on gesture |
CN108038469A (en) * | 2017-12-27 | 2018-05-15 | 百度在线网络技术(北京)有限公司 | Method and apparatus for detecting human body |
CN108216252A (en) * | 2017-12-29 | 2018-06-29 | 中车工业研究院有限公司 | A kind of subway driver vehicle carried driving behavior analysis method, car-mounted terminal and system |
-
2019
- 2019-05-13 CN CN201910393401.0A patent/CN110197134A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106774894A (en) * | 2016-12-16 | 2017-05-31 | 重庆大学 | Interactive teaching methods and interactive system based on gesture |
CN108038469A (en) * | 2017-12-27 | 2018-05-15 | 百度在线网络技术(北京)有限公司 | Method and apparatus for detecting human body |
CN108216252A (en) * | 2017-12-29 | 2018-06-29 | 中车工业研究院有限公司 | A kind of subway driver vehicle carried driving behavior analysis method, car-mounted terminal and system |
Non-Patent Citations (2)
Title |
---|
HAOSHU FANG 等: ""RMPE: Regional Multi-person Pose Estimation"", 《ARXIV》 * |
STAN SALVADOR等: ""FastDTW: Toward Accurate Dynamic Time Warping in Linear Time and Space"", 《RESEARCHGATE》 * |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111091057A (en) * | 2019-11-15 | 2020-05-01 | 腾讯科技(深圳)有限公司 | Information processing method and device and computer readable storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Du et al. | Articulated multi-instrument 2-D pose estimation using fully convolutional networks | |
US20160042652A1 (en) | Body-motion assessment device, dance assessment device, karaoke device, and game device | |
CN109816624B (en) | Appearance inspection device | |
CN109241829B (en) | Behavior identification method and device based on space-time attention convolutional neural network | |
CN110245623A (en) | A kind of real time human movement posture correcting method and system | |
CN110009614A (en) | Method and apparatus for output information | |
Hanson et al. | Improving walking in place methods with individualization and deep networks | |
CN108205654A (en) | A kind of motion detection method and device based on video | |
CN109978870A (en) | Method and apparatus for output information | |
CN108354578A (en) | A kind of capsule endoscope positioning system | |
CN115880558A (en) | Farming behavior detection method and device, electronic equipment and storage medium | |
CN112037263A (en) | Operation tool tracking system based on convolutional neural network and long-short term memory network | |
KR20180064907A (en) | 3d body information recognition apparatus, apparatus and method for visualizing of health state | |
GB2596387A (en) | Anonymisation apparatus, monitoring device, method, computer program and storage medium | |
CN115138059A (en) | Pull-up standard counting method, pull-up standard counting system and storage medium of pull-up standard counting system | |
CN114550027A (en) | Vision-based motion video fine analysis method and device | |
CN110119768A (en) | Visual information emerging system and method for vehicle location | |
CN110197134A (en) | A kind of human action detection method and device | |
CN115359558A (en) | Automatic body test judging method, device, system and medium based on computer vision | |
CN113283334B (en) | Classroom concentration analysis method, device and storage medium | |
CN108549899A (en) | A kind of image-recognizing method and device | |
KR102251704B1 (en) | Method and Apparatus for Detecting Object Using Relational Query | |
CN116740618A (en) | Motion video action evaluation method, system, computer equipment and medium | |
Sharma et al. | Digital Yoga Game with Enhanced Pose Grading Model | |
Komiya et al. | Head pose estimation and movement analysis for speech scene |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190903 |