CN107563282A - For unpiloted recognition methods, electronic equipment, storage medium and system - Google Patents
For unpiloted recognition methods, electronic equipment, storage medium and system Download PDFInfo
- Publication number
- CN107563282A CN107563282A CN201710612860.4A CN201710612860A CN107563282A CN 107563282 A CN107563282 A CN 107563282A CN 201710612860 A CN201710612860 A CN 201710612860A CN 107563282 A CN107563282 A CN 107563282A
- Authority
- CN
- China
- Prior art keywords
- image data
- common
- denominator target
- identified
- target image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Landscapes
- Image Analysis (AREA)
Abstract
The invention discloses include for unpiloted recognition methods, this method：Obtain the image data on road surface；The image data is subjected to background motion removal processing, obtains image data to be identified；The image data to be identified is identified and localization process, obtains the processed image data containing common-denominator target image；Common-denominator target image in the processed image data is subjected to extraction process, obtains common-denominator target image data；The motion state of common-denominator target is calculated according to the common-denominator target image data.By gathering the image data on road surface, and background motion removal processing is carried out to image data, and localization process is identified, obtain the processed image data containing common-denominator target image, and extraction process is carried out to the common-denominator target image in processed image data, common-denominator target image data is obtained, and the motion state of common-denominator target is calculated according to common-denominator target image data.
Description
Technical field
The present invention relates to motion identification field, more particularly, to unpiloted recognition methods, electronic equipment, storage are situated between
Matter and system.
Background technology
Pilotless automobile turns into the new lover of automobile industry at present, and the dynamics of the research to pilotless automobile is also year by year
Increase.The identification technology of pedestrian or object in road pavement make the core technology of pilotless automobile.Pilotless automobile at present
The sensor used is camera, and camera mainly undertakes the important task that collection traffic information uses to back-end algorithm, back-end algorithm
The RGB information that camera is collected carries out many complicated algorithms such as vehicle identification, Lane detection, the identification of traffic sign thing.
In numerous recognizers, by the way that the information of camera collection judges pedestrian on road, the motion conditions of vehicle are extremely important
, only judge whether pedestrian moves exactly, and whether the speed of motion, vehicle move, speed of motion etc., can just make
Accurate judgement is made in next step control of the intelligence system to pilotless automobile.
But the camera on pilotless automobile is currently installed in, because road conditions are jolted, unmanned vehicle is also moving in itself
Etc. reason, even if being parked in the pedestrian not taken action in roadside, being parked in the automobile that roadside is not yet started, in the video that camera collects
In also tend to be shake (mainly road conditions jolt, caused by camera rocks up and down), or motion is (main former
Because being for ground, unmanned vehicle is motion in itself).Therefore current pilotless automobile can not accurately identify
The motion state of pedestrian.
The content of the invention
For overcome the deficiencies in the prior art, an object of the present invention is to provide for unpiloted identification side
Method, its can solve the problems, such as current pilotless automobile not can accurately identifying rows people motion state.
The two of the object of the invention are to provide a kind of electronic equipment, and it can solve current pilotless automobile can not be accurate
The problem of motion state of true identification pedestrian.
The three of the object of the invention are to provide a kind of computer-readable recording medium, and it can solve current unmanned vapour
Car not can accurately identifying rows people motion state the problem of.
The fourth object of the present invention is to provide for unpiloted identifying system, and it can solve current unmanned
Automobile not can accurately identifying rows people motion state the problem of.
An object of the present invention is realized using following technical scheme：
For unpiloted recognition methods, this method includes：
Obtain the image data on road surface；
The image data is subjected to background motion removal processing, obtains image data to be identified；
The image data to be identified is identified and localization process, obtains the processed shadow containing common-denominator target image
As data；
Common-denominator target image in the processed image data is subjected to extraction process, obtains common-denominator target image number
According to；
The motion state of common-denominator target is calculated according to the common-denominator target image data.
Further, the motion state according to common-denominator target image data calculating common-denominator target is specially：To described
Common-denominator target is tracked, and obtains real time critical target image, and the background motion is carried out to the real time critical target image
Removal is handled, and obtains the pixel value of the motion of common-denominator target, if the pixel value is identical with static threshold, the common-denominator target
To be static；If pixel value is different from static threshold, according to default pixel value and the corresponding relation of moving distance value, by described in
Pixel value is scaled actual moving distance value.
Further, it is described localization process is identified in the image data to be identified to be specially：Establish the first depth
Learning model, the image data to be identified is identified and positioned by the first deep learning model, is contained
The processed image data of common-denominator target image.
Further, the first deep learning model of establishing is specially：Using ImageNet databases as training data
Storehouse, convolution after the RGB information of the picture in the ImageNet databases is carried out multiple convolution operation and merged, is obtained
Corresponding first deep learning model.
Further, the common-denominator target image progress extraction process by the processed image data is specially：
The second deep learning model is established, the second deep learning model is carried out using ImageNet databases as tranining database
Training, obtains the 3rd deep learning model, according to the 3rd deep learning model to the pass in the processed image data
The feature memory deep learning matching of key target image, and the feature to matching carries out Non-surveillance clustering, obtains key
The object edge of target image, so as to obtain common-denominator target image data.
The second object of the present invention is realized using following technical scheme：
A kind of electronic equipment, the equipment include：Processor；
Memory；And program, wherein described program is stored in the memory, and is configured to by processor
Perform, described program includes being used to perform in the present invention to be used for unpiloted recognition methods.
The third object of the present invention is realized using following technical scheme：
A kind of computer-readable recording medium, is stored thereon with computer program, and the computer program is held by processor
It is used for unpiloted recognition methods in the row present invention.
The fourth object of the present invention is realized using following technical scheme：
For unpiloted identifying system, the system includes：Anti-shaking module, identify locating module, extraction module and
Computing module；
The anti-shaking module is used to obtain the image data on road surface；The anti-shaking module is additionally operable to the image data
Background motion removal is carried out to handle to obtain image data to be identified；
The image data to be identified is identified and localization process the identify locating module user, obtains containing relevant
The processed image data of key target image；
The extraction module is used to the common-denominator target image in the processed image data carrying out extraction process, obtains
Common-denominator target image data；The computing module calculates the motion state of common-denominator target according to the common-denominator target image data.
Further, in addition to image collecting module, the image collecting module are used to gather the image data on road surface,
The anti-shaking module obtains the upper road surface image data of the image collecting module collection.
Further, the image collecting module is camera.
Compared with prior art, the beneficial effects of the present invention are：It is used for unpiloted recognition methods in the application, leads to
The image data crossed on collection road surface, and background motion removal processing is carried out to image data, and localization process is identified,
The processed image data containing common-denominator target image is obtained, and the common-denominator target image in processed image data is carried
Processing is taken, obtains common-denominator target image data, and the motion state of common-denominator target is calculated according to common-denominator target image data.
Brief description of the drawings
Fig. 1 is the flow chart for unpiloted recognition methods of the present invention；
Fig. 2 is the module frame chart for unpiloted identifying system of the present invention；
Fig. 3 is the background dynamics movement each second figure for unpiloted recognition methods of the present invention；
Fig. 4 is the original picture in the common-denominator target image for unpiloted recognition methods of the present invention；
Fig. 5 is that the original picture in the common-denominator target image for unpiloted recognition methods of the present invention is deep by the 3rd
Degree learning model carries out the picture in the interest region that study matching obtains；
The picture to the interest region in figure for being used for unpiloted recognition methods that Fig. 6 is the present invention carries out convolution kernel
The picture that process of convolution obtains.
Embodiment
Below, with reference to accompanying drawing and embodiment, the present invention is described further, it is necessary to which explanation is, not
Under the premise of afoul, new implementation can be formed between various embodiments described below or between each technical characteristic in any combination
Example：
As shown in figure 1, the application's is used for unpiloted recognition methods, this method comprises the following steps：
Step S10：The image data on road surface is obtained, the image modalities (camera) in pilotless automobile are to nothing
Image data in front of people drives a car and on the road surface of surrounding is acquired, on the road surface that anti-shaking module gathers to camera
Image data obtained.Image data includes pedestrian's image data and automobile image data and other barrier image numbers
According to.
Step S20：Image data is subjected to background motion removal processing, image data to be identified is obtained, by image data
In video per continuous two frames component frame pair, and to each frame to carrying out pixel difference comparison, so as to the change speed of background motion
Degree forms a background motion function, according to the background motion movement value on background motion function, is moved according to background motion
The position actual value of image data is conversed, that is, eliminate influences caused by background motion, has obtained quiet containing relative ground
The image data of effect characteristicses only, obtain image data to be identified.
The above-mentioned every continuous two frames component frame pair of video by image data, and to each frame to carrying out pixel difference ratio
Compared with this process of a background motion function is formd so as to the pace of change of background motion to be：Will be per continuous two frame
Component frame pair, it is assumed that the pixel coordinate of each image is X, Y on two width figures on take M*N block of pixels, and by picture in two width figures
The coordinate of plain block carries out difference, and to going difference to remove average value, obtains the width of the average value of coordinate difference, as background motion
Degree.Illustrated below by way of concrete example：By taking the first width picture and the second width picture as an example, now M is 10, N 10；Then exist
(1/16*X, the 1/16*Y) of the picture of first width figure, (1/16*X, 15/16*Y), (15/16*X, 1/16*Y), (15/16*X, 15/
16*Y), (1/8X, 1/8Y), (7/8X, 1/8Y), (1/8X, 7/8Y), 10*10 block of pixels is taken on (7/8*X, 7/8*Y),
Sliding window searching using 10*10 and piece image identical block of pixels in two width figures, because 8 block of pixels taken all concentrate on
Image border, two images are want to carry out difference with the coordinate of block of pixels, and average value is gone to difference, obtain the flat of coordinate difference
Average S, this S are the amplitude of the frame centering background motion, are the pixel difference in background motion according to background motion amplitude, this
With the image of pilotless automobile camera 24 frames of collection per second in application, 23 frames pair are formed continuously two-by-two, by frame pair
Continue retrograde pixel difference to compare, form the broken lines by 23 values, the broken line represents background motion letter in a seconds section
Number, is illustrated in figure 3 background dynamics movement each second figure i.e. background motion functional arrangement, what is simulated in image is due to road bumps
Caused by pilotless automobile camera in background shake, can be by reverse after establishing the function model in systems
Subtract the motion that respective pixel values offset background.Caused by being directed to road bumps for shake, the function is more bent on image
Folding, caused by being moved for unmanned vehicle for background movement, the pixel displacement on image in the gentler but unit interval is bigger.
Step S30：Image data to be identified is identified and localization process, obtains the place containing common-denominator target image
Manage image data；Specially：The first deep learning model is established, image data to be identified is entered by the deep learning model
Row identification and positioning, obtain the processed image data containing common-denominator target image.
Above-mentioned first deep learning model of establishing is using ImageNet databases as tranining database, by described in
Convolution after the RGB information of picture in ImageNet databases carries out multiple convolution operation and merged, obtain corresponding to the
One deep learning model.First deep learning model be used for the corresponding image in image data to be identified is identified and
The key character of common-denominator target image is sorted out, and common-denominator target image is positioned.First deep learning model includes machine
Motor-car deep learning model, pedestrian's deep learning model, perambulator deep learning model, luggage case deep learning model, non-machine
Motor-car deep learning model and animal deep learning model.
Step S40：Common-denominator target image in the processed image data is subjected to extraction process, obtains common-denominator target
Image data；Specially：The second deep learning model is established, establishes the second deep learning model herein with being established in step S30
Method is identical, and the first and second of deep learning model is intended merely to distinguish the order of step, the first deep learning model and the
Two deep learning models are substantially identical；The second deep learning model is entered using ImageNet databases as tranining database
Row training, it is fine to carry out mark manually using 30% picture in the car in ImageNet databases and the pedestrian's database to prestore
Edge, and cut with marking the common-denominator target main body of near edge, and as the input data of deep learning model
It is trained；Trained deep learning model is the 3rd obtained deep learning model, according to the 3rd depth
Model is practised match the feature memory deep learning of the common-denominator target image in the processed image data, and to matching
The feature carries out Non-surveillance clustering, the object edge of common-denominator target image is obtained, so as to obtain common-denominator target image data.With
Exemplified by a picture in common-denominator target image, as Figure 4-Figure 6, Fig. 4 is the original picture in common-denominator target image, and Fig. 5 is process
3rd deep learning model carries out the picture in the interest region that study matching obtains, then carries out convolution kernel convolution to its interest region
Picture as shown in Figure 6 is obtained, the picture Jing Guo convolution kernel convolution is subjected to Non-surveillance clustering, obtains the edge of Target Photo,
That is, obtain common-denominator target picture.
Step S50：The motion state of common-denominator target is calculated according to common-denominator target image data.The common-denominator target is carried out
Tracking, obtains real time critical target image, carries out background motion removal processing to real time critical target image, obtains common-denominator target
Motion pixel value, if the pixel value is identical with static threshold, common-denominator target is static；If pixel value and static threshold
Difference, then according to default pixel value and the corresponding relation of moving distance value, pixel value is scaled actual moving distance value；On
The static threshold theoretical value 0 stated, but due to the shake of vehicle and image documentation equipment in reality can not possibly accomplish by it is external because
It is plain to exclude completely, therefore static threshold herein can be in certain error range, when pixel value is in this error range, i.e.,
Assert that pixel value is identical with static threshold, conversely, then different.
A kind of electronic equipment in the application, it is characterised in that including：Processor；
Memory；And program, wherein described program is stored in the memory, and is configured to by processor
Perform, described program includes being used to perform in the application to be used for unpiloted recognition methods.
A kind of computer-readable recording medium of the application, is stored thereon with computer program, it is characterised in that：The meter
Calculation machine program, which is executed by processor in the application, is used for unpiloted recognition methods.
It is used for unpiloted identifying system in the application, it is characterised in that including：Image collecting module, stabilization mould
Block, identify locating module, extraction module and computing module；
Image collecting module is used to gather the image data on road surface；Image collecting module is camera；Anti-shaking module obtains
The upper road surface image data for taking image collecting module to gather；Anti-shaking module is additionally operable to carry out image data at background motion removal
Reason obtains image data to be identified；
Image data to be identified is identified and localization process identify locating module user, obtains containing common-denominator target shadow
The processed image data of picture；
Extraction module is used to the common-denominator target image in processed image data carrying out extraction process, obtains common-denominator target
Image data；Computing module calculates the motion state of common-denominator target according to common-denominator target image data.
It is used for unpiloted recognition methods in the application, by gathering the image data on road surface, and to image number
According to progress background motion removal processing, and localization process is identified, obtains the processed image containing common-denominator target image
Data, and extraction process is carried out to the common-denominator target image in processed image data, obtain common-denominator target image data, and root
The motion state of common-denominator target is calculated according to common-denominator target image data.
It will be apparent to those skilled in the art that technical scheme that can be as described above and design, make other various
Corresponding change and deformation, and all these changes and deformation should all belong to the protection domain of the claims in the present invention
Within.
Claims (10)
1. it is used for unpiloted recognition methods, it is characterised in that including：
Obtain the image data on road surface；
The image data is subjected to background motion removal processing, obtains image data to be identified；
The image data to be identified is identified and localization process, obtains the processed image number containing common-denominator target image
According to；
Common-denominator target image in the processed image data is subjected to extraction process, obtains common-denominator target image data；
The motion state of common-denominator target is calculated according to the common-denominator target image data.
2. it is used for unpiloted recognition methods as claimed in claim 1, it is characterised in that：It is described according to common-denominator target image
Data calculate common-denominator target motion state be specially：The common-denominator target is tracked, obtains real time critical target image,
The background motion removal processing is carried out to the real time critical target image, obtains the pixel value of the motion of common-denominator target, if
The pixel value is identical with static threshold, then the common-denominator target is static；If pixel value is different from static threshold, according to pre-
If pixel value and moving distance value corresponding relation, the pixel value is scaled actual moving distance value.
3. it is used for unpiloted recognition methods as claimed in claim 1, it is characterised in that：It is described by the image to be identified
Localization process is identified in data：The first deep learning model is established, by the first deep learning model to institute
State image data to be identified to be identified and position, obtain the processed image data containing common-denominator target image.
4. it is used for unpiloted recognition methods as claimed in claim 3, it is characterised in that：It is described to establish the first deep learning
Model is specially：Using ImageNet databases as tranining database, the RGB of the picture in the ImageNet databases is believed
Convolution after breath carries out multiple convolution operation and merged, obtain corresponding first deep learning model.
5. it is used for unpiloted recognition methods as claimed in claim 1, it is characterised in that：It is described by the processed image
Common-denominator target image in data carries out extraction process：The second deep learning model is established, by ImageNet databases
The second deep learning model is trained as tranining database, obtains the 3rd deep learning model, according to described
Three deep learning models match to the feature memory deep learning of the common-denominator target image in the processed image data, and right
The feature matched carries out Non-surveillance clustering, the object edge of common-denominator target image is obtained, so as to obtain common-denominator target shadow
As data.
6. a kind of electronic equipment, it is characterised in that including：Processor；
Memory；And program, wherein described program is stored in the memory, and is configured to be held by processor
OK, described program includes being used for the method described in perform claim requirement 1-5 any one.
7. a kind of computer-readable recording medium, is stored thereon with computer program, it is characterised in that：The computer program quilt
Method of the computing device as described in claim 1-5 any one.
8. it is used for unpiloted identifying system, it is characterised in that including：Anti-shaking module, identify locating module, extraction module with
And computing module；
The anti-shaking module is used to obtain the image data on road surface；The anti-shaking module is additionally operable to carry out the image data
Background motion removal handles to obtain image data to be identified；
The image data to be identified is identified and localization process the identify locating module user, obtains containing crucial mesh
Mark the processed image data of image；
The extraction module is used to the common-denominator target image in the processed image data carrying out extraction process, obtains key
Target image data；The computing module calculates the motion state of common-denominator target according to the common-denominator target image data.
9. it is used for unpiloted identifying system as claimed in claim 8, it is characterised in that：Also include image collecting module,
The image collecting module is used to gather the image data on road surface, and the anti-shaking module obtains the image collecting module collection
Upper road surface image data.
10. it is used for unpiloted identifying system as claimed in claim 9, it is characterised in that：The image collecting module is
Camera.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710612860.4A CN107563282A (en) | 2017-07-25 | 2017-07-25 | For unpiloted recognition methods, electronic equipment, storage medium and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710612860.4A CN107563282A (en) | 2017-07-25 | 2017-07-25 | For unpiloted recognition methods, electronic equipment, storage medium and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107563282A true CN107563282A (en) | 2018-01-09 |
Family
ID=60974638
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710612860.4A Pending CN107563282A (en) | 2017-07-25 | 2017-07-25 | For unpiloted recognition methods, electronic equipment, storage medium and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107563282A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109040604A (en) * | 2018-10-23 | 2018-12-18 | Oppo广东移动通信有限公司 | Shoot processing method, device, storage medium and the mobile terminal of image |
| CN109443794A (en) * | 2018-10-26 | 2019-03-08 | 百度在线网络技术（北京）有限公司 | Evaluation method, device, computer equipment and the storage medium of automatic driving car |
| CN115147785A (en) * | 2021-03-29 | 2022-10-04 | 东风汽车集团股份有限公司 | Vehicle identification method and device, electronic equipment and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1897015A (en) * | 2006-05-18 | 2007-01-17 | 王海燕 | Method and system for inspecting and tracting vehicle based on machine vision |
| CN106295459A (en) * | 2015-05-11 | 2017-01-04 | 青岛若贝电子有限公司 | Based on machine vision and the vehicle detection of cascade classifier and method for early warning |
| CN106534614A (en) * | 2015-09-10 | 2017-03-22 | 南京理工大学 | Rapid movement compensation method of moving target detection under mobile camera |
| CN106599832A (en) * | 2016-12-09 | 2017-04-26 | 重庆邮电大学 | Method for detecting and recognizing various types of obstacles based on convolution neural network |
-
2017
- 2017-07-25 CN CN201710612860.4A patent/CN107563282A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1897015A (en) * | 2006-05-18 | 2007-01-17 | 王海燕 | Method and system for inspecting and tracting vehicle based on machine vision |
| CN106295459A (en) * | 2015-05-11 | 2017-01-04 | 青岛若贝电子有限公司 | Based on machine vision and the vehicle detection of cascade classifier and method for early warning |
| CN106534614A (en) * | 2015-09-10 | 2017-03-22 | 南京理工大学 | Rapid movement compensation method of moving target detection under mobile camera |
| CN106599832A (en) * | 2016-12-09 | 2017-04-26 | 重庆邮电大学 | Method for detecting and recognizing various types of obstacles based on convolution neural network |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109040604A (en) * | 2018-10-23 | 2018-12-18 | Oppo广东移动通信有限公司 | Shoot processing method, device, storage medium and the mobile terminal of image |
| CN109040604B (en) * | 2018-10-23 | 2020-09-15 | Oppo广东移动通信有限公司 | Shot image processing method and device, storage medium and mobile terminal |
| CN109443794A (en) * | 2018-10-26 | 2019-03-08 | 百度在线网络技术（北京）有限公司 | Evaluation method, device, computer equipment and the storage medium of automatic driving car |
| CN115147785A (en) * | 2021-03-29 | 2022-10-04 | 东风汽车集团股份有限公司 | Vehicle identification method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Ozgunalp et al. | Multiple lane detection algorithm based on novel dense vanishing point estimation | |
| Keller et al. | The benefits of dense stereo for pedestrian detection | |
| Yenikaya et al. | Keeping the vehicle on the road: A survey on on-road lane detection systems | |
| Wu et al. | Lane-mark extraction for automobiles under complex conditions | |
| Zhou et al. | Efficient road detection and tracking for unmanned aerial vehicle | |
| Li et al. | Springrobot: A prototype autonomous vehicle and its algorithms for lane detection | |
| Yuan et al. | Robust lane detection for complicated road environment based on normal map | |
| CN111801711A (en) | Image annotation | |
| Chougule et al. | Reliable multilane detection and classification by utilizing cnn as a regression network | |
| CN108364466A (en) | A kind of statistical method of traffic flow based on unmanned plane traffic video | |
| CN104299009B (en) | License plate character recognition method based on multi-feature fusion | |
| CN105457908B (en) | The sorting method for rapidly positioning and system of small size glass panel based on monocular CCD | |
| CN108052904B (en) | Method and device for acquiring lane line | |
| CN108921813B (en) | Unmanned aerial vehicle detection bridge structure crack identification method based on machine vision | |
| US9396553B2 (en) | Vehicle dimension estimation from vehicle images | |
| CN105404857A (en) | Infrared-based night intelligent vehicle front pedestrian detection method | |
| KR20150112656A (en) | Method to calibrate camera and apparatus therefor | |
| CN106778668A (en) | A kind of method for detecting lane lines of the robust of joint RANSAC and CNN | |
| CN109190483B (en) | Lane line detection method based on vision | |
| CN110110608B (en) | Forklift speed monitoring method and system based on vision under panoramic monitoring | |
| CN111738033B (en) | Vehicle driving information determination method and device based on plane segmentation and vehicle-mounted terminal | |
| CN107563282A (en) | For unpiloted recognition methods, electronic equipment, storage medium and system | |
| CN107480603A (en) | Figure and method for segmenting objects are synchronously built based on SLAM and depth camera | |
| Suddamalla et al. | A novel algorithm of lane detection addressing varied scenarios of curved and dashed lanemarks | |
| CN104200492A (en) | Automatic detecting and tracking method for aerial video target based on trajectory constraint |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180109 |
|
| RJ01 | Rejection of invention patent application after publication |