CN110147759A - Target identification method, system, target identification management method and storage medium - Google Patents
Target identification method, system, target identification management method and storage medium Download PDFInfo
- Publication number
- CN110147759A CN110147759A CN201910414312.XA CN201910414312A CN110147759A CN 110147759 A CN110147759 A CN 110147759A CN 201910414312 A CN201910414312 A CN 201910414312A CN 110147759 A CN110147759 A CN 110147759A
- Authority
- CN
- China
- Prior art keywords
- target identification
- video camera
- server
- target
- recognized
- 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
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/14—Session management
- H04L67/141—Setup of application sessions
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Studio Devices (AREA)
Abstract
The embodiment provides a kind of target identification method, system, target identification management method and storage mediums.The target identification method is used for video camera, and the target identification method includes: foundation and the connection of server；Obtain images to be recognized；Target identification is carried out for the images to be recognized；And the identifier of the target in the output images to be recognized is to the server.The computing capability that above-mentioned technical proposal takes full advantage of video camera itself carries out target identification, reduces the requirement to server performance and network, extends convenient for system.
Description
Technical field
The present invention relates to technical field of image processing, relate more specifically to target identification method, target identification system, target
Identify management method and storage medium.
Background technique
Target identification is that an important direction in artificial intelligence field has in many fields and widely answers in recent years
With, such as security protection, traffic is new to be sold, campus etc..With gradually going deep into for application, many scenes constantly propose target identification
Higher requirement out.
Currently, common target identification technology scheme is to capture images to be recognized by video camera and be transmitted to server, by
Server carries out target identification for images to be recognized.Since the data volume of network transmission images to be recognized is big, server is caused
Object recognition task it is heavy.Firstly, this is more demanding to server performance, it is easy to cause server expensive；Secondly, limit
The quantity for having made access video camera causes the extension of system difficult.
Summary of the invention
The present invention is proposed in view of the above problem.The present invention provides target identification method, target identification system, mesh
Identify other management method and storage medium.
According to an aspect of the present invention, a kind of method of target identification is provided, the target identification method is used for video camera,
The target identification method includes:
Establish the connection with server；
Obtain images to be recognized；
Target identification is carried out for the images to be recognized；And
The identifier of the target in the images to be recognized is exported to the server.
Illustratively, described to include: for images to be recognized progress target identification
Target detection is carried out for the images to be recognized；
The clarification of objective in the images to be recognized is extracted based on the testing result to the images to be recognized；And
Comparison result based on the feature in the clarification of objective and feature database in the images to be recognized carries out target knowledge
Not.
Illustratively, before the progress target identification for the images to be recognized, the target identification method is also
Include:
Latest features library is obtained from the server, to be used for target identification.
Illustratively, the target identification method further include:
Both the identifier of the video camera and the check code of the feature database are sent to the server, by described
Server verifies whether the video camera is stored with latest features library；
It is described to include: from server acquisition latest features library
In the case where the video camera not yet stores latest features library, latest features library is obtained from the server.
Illustratively, described to include: from server acquisition latest features library
The latest features library of the server active push is received, wherein the server creates or have updated feature database.
Illustratively, the target identification method further include:
Receive the reference picture that the server is sent；
Target detection is carried out for the reference picture；
The clarification of objective in the reference picture is extracted based on the testing result to the reference picture；
Clarification of objective in the reference picture is sent to the server, for server creation or more
New feature library.
Illustratively, before the progress target identification for the images to be recognized, the target identification method is also
Include:
Target identification strategy is obtained from the server, to carry out target identification according to the target identification strategy.
Illustratively, the feature database is stored in the storage device of the video camera.
Another aspect according to the present invention additionally provides a kind of target identification management method, the target identification management method
For server, the server is used to manage the video camera for executing above-mentioned target identification method, the target identification pipe
Reason method includes:
The connection request of the video camera is received, the connection with the video camera is established；
Receive the identifier of the target in the images to be recognized.
Illustratively, the target identification management method further include:
Latest features library is sent to the video camera, to carry out target identification for the video camera.
Illustratively, the target identification management method further include:
The check code of the identifier of the video camera and the feature database of video camera storage is received from the video camera；
Utilize video camera described in the verification code check of the identifier of the video camera and the feature database of video camera storage
Whether latest features library is stored with；
The transmission latest features library is to the video camera, comprising:
In the case where the video camera not yet stores latest features library, latest features library is sent to the video camera.
Illustratively, the transmission latest features library to the video camera includes:
In the case where creating or having updated feature database, active push latest features library to the video camera.
Illustratively, the target identification management method further include:
Reference picture is sent to the video camera, extracts feature to be based on the reference picture by the video camera；
Receive the clarification of objective in the extracted reference picture of the video camera；
Based on the clarification of objective creation in the reference picture or update feature database.
Illustratively, the target identification management method further include:
By the reference pictures store in image data base；
After the identifier for receiving the target in the images to be recognized, according to the target of the images to be recognized
Identifier retrieval described image database；
Desired operation is executed according to search result.
Illustratively, the target identification management method further include:
Target identification strategy is sent to the video camera, to carry out mesh according to the target identification strategy by the video camera
Mark is other.
According to a further aspect of the invention, a kind of target identification system is additionally provided, the target identification system includes camera shooting
Machine and server, the video camera is for executing above-mentioned target identification method, and the server is for managing the video camera.
According to a further aspect of the present invention, a kind of storage medium is additionally provided, program is stored on said storage and refers to
It enables, described program instruction is at runtime for executing above-mentioned target identification method and/or above-mentioned target identification management method.
Above-mentioned technical proposal according to an embodiment of the present invention, the computing capability for taking full advantage of video camera itself carry out target
Identification, enhances the real-time of target identification, reduces the requirement to server performance and network, extends convenient for system.
The above description is only an overview of the technical scheme of the present invention, in order to better understand the technical means of the present invention,
And it can be implemented in accordance with the contents of the specification, and in order to allow above and other objects of the present invention, feature and advantage can
It is clearer and more comprehensible, the followings are specific embodiments of the present invention.
Detailed description of the invention
The embodiment of the present invention is described in more detail in conjunction with the accompanying drawings, the above and other purposes of the present invention,
Feature and advantage will be apparent.Attached drawing is used to provide to further understand the embodiment of the present invention, and constitutes explanation
A part of book, is used to explain the present invention together with the embodiment of the present invention, is not construed as limiting the invention.In the accompanying drawings,
Identical reference label typically represents same parts or step.
Fig. 1 shows the schematic flow chart of target identification method according to an embodiment of the invention；
Fig. 2 shows the schematic flow charts of the target identification method of another embodiment according to the present invention；
Fig. 3 shows the schematic flow chart of target identification management method according to an embodiment of the invention；
Fig. 4 shows the schematic flow chart of the target identification management method of another embodiment according to the present invention.
Specific embodiment
In order to enable the object, technical solutions and advantages of the present invention become apparent, root is described in detail below with reference to accompanying drawings
According to example embodiments of the present invention.Obviously, described embodiment is only a part of the embodiments of the present invention, rather than this hair
Bright whole embodiments, it should be appreciated that the present invention is not limited by example embodiment described herein.Based on described in the present invention
The embodiment of the present invention, those skilled in the art's obtained all other embodiment in the case where not making the creative labor
It should all fall under the scope of the present invention.
In order to solve the above problem in the prior art, according to an embodiment of the present invention, a kind of target identification is provided
Method.The target identification method is used for video camera, and the computing capability of video camera is made full use of to carry out target identification.The video camera
It can be used for connecting server.And for the server, it can connect video camera as one or more.Server
It is operated without the target identification for images to be recognized, but the video camera by being connected realizes that target identification operates.
Fig. 1 shows the schematic flow chart of target identification method 100 according to an embodiment of the invention.Such as Fig. 1 institute
Show, method 100 includes the following steps.
Step S110 establishes the connection of video camera and server.
Server can be used for managing the video camera for being used for target identification concentratedly.For example, server can manage one or
Multiple video cameras can also carry out distributed management one or more video camera by multiple servers.
It is appreciated that video camera actively can send connection request to server after actuation, confirms in server and connect
In the case where, establish the connection with server.To ensure that video camera can be communicated with server, to receive server
Management.
It is appreciated that above-mentioned connection can be any wired or wireless connection type.
Step S120 obtains images to be recognized.
Images to be recognized can be image that is any suitable, needing to carry out target identification.It can obtain by various modes
Take images to be recognized.For example, images to be recognized can be acquired by the shooting operation of video camera.Images to be recognized, which can be, to be taken the photograph
The collected original image of camera is also possible to the image obtained after being pre-processed to original image.The pretreatment operation
It may include for all operations of clearer identification target.For example, pretreatment operation may include the denoisings such as filtering operation.
Step S130 carries out target identification for images to be recognized, with the mark of the target in the determination images to be recognized
Know symbol.
Target identification technology is the technology identified based on clarification of objective information.Target identification technology for determine to
Identify which specific objective is the target in image be specifically.Object identifier is for uniquely identifying target.Pass through target identification
Operation, can determine the identifier of the target in images to be recognized, that is, be determined which specific objective is target be specifically.
It is appreciated that the target that target identification technology is identified can be interested any target, example in application scenarios
Such as face.Using face recognition technology, can determine which people the pedestrian in images to be recognized is specifically, for example, Zhang San.
Illustratively, target identification utilizes neural fusion, such as convolutional neural networks.Convolutional neural networks can be protected
Demonstrate,prove the accuracy of target identification.
The target identification technology that this step can use any existing or following research and development realizes that the application does not limit this
System.
Step S140 exports the identifier of the target in the images to be recognized to the server.
Video camera can export the object identifier to server.Server can be true according to object identifier as a result,
The fixed target then can execute relevant operation for the target according to preset rules.
It is appreciated that can also notify to service by video camera in the case where that can not identify the target in images to be recognized
Device.It is specific for example, video camera can export the message of recognition failures to server.Optionally, can also export can not for video camera
The images to be recognized of identification is to server, other processing are recorded, store or carried out by server.
Above-mentioned target identification method according to an embodiment of the present invention, the computing capability for taking full advantage of video camera itself carry out
Target identification reduces the requirement to server performance and network, extends convenient for system.In addition, also adding target identification
Real-time.
Illustratively, above-mentioned steps S130 for the images to be recognized carry out target identification specifically includes the following steps:
Step S131 carries out target detection for images to be recognized.
Target detection is used to find out the target in images to be recognized, determines position and the size of target.
In one example, by carrying out target detection for images to be recognized, the bounding box of target can be obtained
(bounding box).The bounding box of the target can be rectangle frame.Optionally, bounding box can use a vertex of rectangle
The length and width of coordinate value and rectangle indicates.Alternatively, bounding box can also be at least three vertex of rectangle come table
Show.
The target detection technique of any existing or following research and development be can use to realize step S131, the application is to this
Without limitation.By target detection, the redundancy in images to be recognized can be effectively reduced, treatment effeciency and processing are improved
Precision.
Step S132 extracts the clarification of objective in the images to be recognized based on the testing result to images to be recognized.
In the examples described above, clarification of objective can be extracted based on the bounding box of target obtained.Specifically, according to
The pixel value of each pixel in the bounding box of images to be recognized, to extract clarification of objective.For example, for recognition of face side
Method can extract the feature of face.The characteristic point of the multiple dimensions of the feature of face such as face, such as 128 dimensional features point.
Optionally, by the initial data of images to be recognized and information input about bounding box to feature extraction nerve net
Network.Alternatively, being split first to images to be recognized according to its testing result, by the image in images to be recognized inside bounding box
Data are input to feature extraction neural network.Then, the spy of target in feature extraction neural computing images to be recognized is utilized
Levy data.Neural network is suitable for handling calculating that is complicated, can not simply being handled with function.And images to be recognized itself is not only
Data volume is big, and data can preferably extract the spy of target using feature extraction neural network without simple regularity
Sign, effectively to represent target itself with it.
Feature extraction neural network can be convolutional neural networks.
Feature in clarification of objective and feature database in images to be recognized is compared step S133, with based on than
The identifier of the target in images to be recognized is determined to result.
It is appreciated that storing the feature of existing object and the identifier of the existing object in feature database.Show at one
In example, each object has a unique corresponding feature therewith.The feature and identifier of multiple objects are stored in feature database.Base
It can be compared respectively with the feature in feature database in the feature that step S130 is extracted.Extracted feature is confirmed by comparing
It is similar with which feature in feature database.Target is identified based on comparison result, that is, determines the identifier of target.For example, base
The comparison result of the feature in clarification of objective and feature database in images to be recognized, determines the target in images to be recognized
Similarity between the feature of Zhang San in feature and feature database is higher than threshold value, it is determined that the target in images to be recognized is
Three.By with aspect ratios all in feature database to that can not confirm target, it is believed that target can not identify.
Above-mentioned technical proposal carries out target detection first, extracts clarification of objective based on testing result and based on extracted
Feature carries out target identification, avoids interference of the redundant data in images to be recognized to target identification, enhances target identification
Accuracy.
Illustratively, it is stored in the storage device of video camera for the feature database of target identification.
The storage device of the video camera can be realized using any suitable storage medium.Illustratively, the camera shooting
The storage device of machine can be realized using nonvolatile memory and/or volatile memory, for example may include read-only storage
Device (ROM), Erasable Programmable Read Only Memory EPROM (EPROM), portable compact disc read-only memory (CD-ROM), USB storage
Any combination of one of device, random access memory (RAM) or above-mentioned storage medium.
Feature database is stored in the storage device of video camera, is facilitated video camera to obtain the feature in feature database and is carried out target knowledge
Not, and reduce the network flow between server.
Illustratively, before step S130 carries out target identification for images to be recognized, above-mentioned target identification method is also
Including obtaining latest features library from server, to be used for target identification.
It is appreciated that the feature database for video camera to carry out target identification can be by server centered management.Due to feature
Object involved in library may change, therefore feature therein can change with the variation of object, i.e., feature database adapts to
Update to property.For example, the object in feature database increases or decreases, then feature therein also will be accordingly increased or be reduced.
In another example the object itself in feature database is changed, specifically, feature database is face characteristic library, object Zhang San therein
It grows up, then the feature of Zhang San will change, the feature in feature database will also change as a result,.In order to standard
Target identification really is carried out, video camera can obtain newest feature database from server, using the newest feature database as currently
The basis of target identification.
Video camera obtains latest features library from server, it can be ensured that the accuracy of video camera target identification.
Illustratively, above-mentioned target identification method further include send video camera identifier and feature database check code this two
Person is to the server, to verify whether the video camera is stored with latest features library by the server.
It is appreciated that server can manage one or more features library, the target identification of different scenes is respectively corresponded.
Video camera can store a set of in features described above library target identification for a special scenes.It is appreciated that video camera
For identifier for identifying current camera, the identifier based on video camera, server can retrieve the identifier pair with video camera
The latest features library answered.The check code of feature database can be the start context of feature database, for identifying the history of the feature database
The information of update.The check code of the feature database of check code and Lai Si video camera based on latest features library can determine on video camera
Whether the feature database of storage is latest features library.
Since video camera is after starting and connecting server, in order to determine stored on server it is corresponding with the video camera
Feature database whether made update, video camera can send the check code of the feature database on the identifier and video camera of the video camera
To server, to verify whether described feature database is latest features library according to both by server.
It is verified by server, it, can not in the case where confirming the feature database on current camera is latest features library
Do any further operation.In the case where determining that current camera not yet stores latest features library, video camera can be from clothes
Business device obtains latest features library.Specifically for example, server is according to the identifier determination of current camera and current camera first
Corresponding latest features library, then video camera obtains latest features library from server, to update stored feature database.
The case where server admin according to an embodiment of the invention multiple feature databases are described below in detail.In certain research and development
In the target identification system of unit, 3 feature databases of server admin, this 3 feature databases are respectively white list library 1, white list library
2, blacklist library 1.There are 3 video cameras (respectively video camera 1, video camera 2 and video camera 3) to be separately mounted to the unit simultaneously
Research and development building entrance (installation video camera 1), Research and development chamber inlet (installation video camera 2) and unit gate entry (install
Video camera 3).Wherein, video camera 1 stores white list library 1, and video camera 2 stores white list library 2, and video camera 3 stores blacklist library 1.
Video camera 1 and video camera 2 in this way can be used for gate inhibition, the personnel in corresponding white list of only letting pass, and by the target of identification
Identifier is sent to server, to be recorded by server；Video camera 3 is for identification into the people in the blacklist at unit gate
Member, and the identifier of the target of identification is sent to server, alarm signal is generated to be recorded by server or according to setting.
The identifier and check information that video camera is sent by video camera ensure that the spy that target identification is used on video camera
Sign library is required latest features library, it is ensured that the accuracy of target identification.
Illustratively, obtaining latest features library from the server includes creating or having updated the feelings of feature database in server
Under condition, the latest features library of server active push is received.
In some instances, the creation and update of feature database execute on the server, so video camera is in the process of running,
It can not learn in time whether feature database updates.In the case where server creates or has updated feature database, once it is built with video camera
Connection has been stood, the check code of feature database is sent without waiting for video camera, i.e., by the newest feature database of server active push to taking the photograph
Camera.
It is appreciated that server is for wherein one in the case where the multiple feature databases of server admin and multiple video cameras
It, can be the feature database as described in server active push extremely one corresponding with the feature database or more after a feature database is updated
A video camera.
By server active push latest features library to video camera, the operation without video camera can ensure that be used on video camera
In target identification feature database be latest features library, it is ensured that the accuracy of target identification.
Illustratively, above-mentioned target identification method further includes the feature that reference picture is extracted by video camera.Specifically include as
Lower step.
Step S151 receives the reference picture that server is sent.
The reference picture is believable target image.The clarification of objective extracted from reference picture can be used for to
The clarification of objective extracted in identification image is compared, to carry out target identification.In one example, reference picture can be
The image for each object that system manager stores in the server.In the example of above-mentioned research and development unit, reference picture can be with
It is the facial image of each object in white list or blacklist, it can be by system manager or object oneself (such as white name
People in list) it is input in server.
It is appreciated that it may include image itself and image identifier that video camera, which receives the reference picture that server is sent,.
Described image identifier can be used for the feature that association is extracted, determine institute with thus incidence relation for identifying reference picture
The feature of extraction and the corresponding relationship of reference picture.
Step S152 carries out target detection for the reference picture.
Step S153 extracts the clarification of objective in the reference picture based on the testing result to the reference picture.
It is appreciated that the two steps are similar with above-mentioned steps S131 and step S132 respectively.Difference is only that operation pair
As difference.The two steps are used to be handled for the target in reference picture, to reduce redundancy, facilitate subsequent place
Reason.By the two steps, the clarification of objective in reference picture can be effectively extracted, and by the identifier and step of reference picture
The rapid extracted feature of S153 is associated.
Clarification of objective in the extracted reference picture of step S153 is sent to server, to be used for by step S154
The server creation updates feature database.
It is appreciated that server admin one or more video camera, it can be by server centered characteristics of management library.Video camera
The feature extracted in step S153 is sent to server, feature database is created or updated for server.It can according to need,
Utilize the feature database new in the extracted feature-modeling of step S153.The extracted feature of step S153 can also be added to existing
In some feature databases or using the individual features in the existing feature database of the extracted character displacement of step S153, it is somebody's turn to do with updating
Existing feature database.
In the above-mentioned technical solutions, the feature database establishd or updated using the feature of the extracted reference picture of the video camera
It not can be only used for the video camera, this feature library can also be used to the video camera that server is connected.
The feature that reference picture is extracted by video camera, efficiently utilizes the computing capability of video camera, further reduces
The consumption of server computing resource.
Illustratively, before step S130 carries out target identification for images to be recognized, above-mentioned target identification method is also
Including obtaining target identification strategy from server, to carry out target identification according to the target identification strategy.
It is appreciated that video camera can obtain target identification strategy from server before carrying out target identification.The target
Recognition strategy may include target detection strategy, feature extraction strategy or aspect ratio to one or more in strategy.Target is known
Strategy can also be including the setting information of target detection, feature extraction or one or more dependent thresholds of aspect ratio centering.
It is appreciated that better optimization aim identification can also be carried out by adjusting the policy content in target identification strategy
Method promotes the accuracy rate of target identification.
Target identification strategy is obtained from server, target identification can be preferably controlled, promote the accuracy rate of target identification
With target identification efficiency.
In order to illustrate more clearly of the application, Fig. 2 shows the target identification methods of another embodiment according to the present invention
200 schematic flow chart.As shown in Fig. 2, target identification method 200 includes the following steps.
Step S210 establishes the connection with server.
In the case where establishing successful connection, step S220 is executed.Establish connection it is failed in the case where, by camera
Determine whether to exit, thens follow the steps S280 if exited；Execute step S210 again if not exiting.
Step S220 sends both the identifier of video camera and the check code of feature database to server.
Video camera sends both check codes of its identifier and feature database to server, by server according to both come
Verify whether the feature database on the video camera is latest features library.After the completion of server verification, sends check results and take the photograph to this
Camera.In the case where server check results indicate that the feature database is latest features library, step S240 is executed, is otherwise executed
Step S230.
Step S230 obtains latest features library from server.
Step S240 obtains target identification strategy from server.
Step S250 obtains images to be recognized.
It is appreciated that video camera completes the preparation of target identification by executing above step S210 to S240, it can
To initially enter the target identification for being directed to images to be recognized.Video camera obtains images to be recognized, for carrying out to target therein
Target identification.
Step S260 carries out target identification for images to be recognized.
Step S270 exports the identifier of the target in images to be recognized to server.
After the identifier to server of the target in output images to be recognized, if video camera continues target knowledge
Not, then step S250 is executed again, it is no to then follow the steps S280.
Step S280 exits target identification operation in the case where video camera does not continue to performance objective identification.
It is appreciated that video camera no longer performance objective identifies, it can be video camera and actively exit, can also be that video camera connects
The exit instruction for receiving server transmission passively exits.
It is appreciated that target identification method 200 carries out target identification by video camera, the real-time of target identification is enhanced
Property, the requirement to server performance and network is reduced, the cost of server maintenance extension is reduced.
Another aspect according to the present invention additionally provides a kind of target identification management method, which uses
In server, the server is used to manage the video camera for executing above-mentioned target identification method.
Fig. 3 shows the schematic flow chart of target identification management method 300 according to an embodiment of the invention.Such as figure
Shown in 3, the target identification management method 300 includes the following steps.
Step S310 receives the connection request of video camera, establishes the connection with the video camera.It is appreciated that video camera
Connection request actively can be sent to server after actuation, after server receives connection request, establish the company with video camera
It connects.
Step S320 receives the identifier of the target in images to be recognized.
It is appreciated that video camera establishes the connection with the video camera for executing above-mentioned target identification method, server
Afterwards, in the successful situation of target of video camera identification images to be recognized, server can receive the to be identified of video camera transmission
The identifier of target in image is directed to the mesh even executing to determine the target according to the object identifier by server
Target respective operations.
Above-mentioned technical proposal is used for the video camera of target identification by server admin, not only ensures the real-time of target identification
Property, and reduce the performance requirement to server.In addition, the server is convenient for system extension, such as the more camera shootings of increase
Machine, to improve the processing capacity of system.
Illustratively, above-mentioned target identification management method further includes sending latest features library to video camera, for described
Video camera carries out target identification.
It is appreciated that the feature database for video camera to carry out target identification can be by server centered management.The feature
In the updated, in order to accurately carry out target identification, server can send latest features library to video camera in library.
Latest features library is sent to video camera by server, it can be ensured that the accuracy of target identification.
Illustratively, above-mentioned target identification management method further includes that identifier and the institute of the video camera are received from video camera
State the check code of the feature database of video camera storage；The feature database stored using the identifier of the video camera and the video camera
Whether video camera described in verification code check is stored with latest features library.
Identifier based on video camera, server can retrieve the latest features library suitable for the video camera.Based on most
Whether new feature library and the check code of the feature database of video camera both can verify consistent, that is, can determine the spy stored on video camera
Levy whether library is latest features library.
Verified by server, in the case where determining that current camera not yet stores latest features library, server according to
The identifier of current camera sends the latest features library for being suitable for the video camera to video camera, updates its storage by video camera
Feature database is latest features library.
It is appreciated that in the case where video camera and server establish connection, by the mark of video camera active transmission video camera
The check code of the feature database of symbol and video camera storage is known to server, can be verified the video camera in time by server and be deposited
Whether the feature database of storage is latest features library, it is ensured that the accuracy of target identification.
Illustratively, server sends the case where latest features library to video camera is included in creation or has updated feature database
Under, active push latest features library to the video camera.
It is appreciated that connect in the case where server creates or has updated feature database if established with video camera, it can
To be suitable for the latest features library of the video camera by server active push to the video camera.
It is appreciated that server can have one, can also have multiple in above-mentioned target identification management method.It is more having
In the case where a server, multiple servers can be managed collectively by distributed management system, and then be realized by server pipe
Manage video camera.In the case where there is multiple servers, the feature database on a server can be what basis was obtained from video camera
Feature-modeling or the feature database of update can also be the feature for being created or being updated according to the feature obtained from other servers
Library.
It is appreciated that server, which can manage one or more video cameras, carries out target identification, server can also pass through
The video camera is grouped, target identification is carried out based on grouping management video camera, server can send newest spy as a result,
Levy all video cameras in library to respective packets.
By the newest feature database of server active push to video camera, the feature of target identification is used on ensuring video camera
Library is latest features library, and then under the premise of ensuring the accuracy of target identification, reduces the operation of video camera.
Illustratively, above-mentioned target identification management method further includes following steps.
Step S331 sends reference picture to video camera, extracts feature to be based on the reference picture by the video camera.
It is appreciated that video camera in the feature database of target identification for being characterized in extracting from reference picture.Server is sent
Reference picture extracts wherein clarification of objective to video camera to be based on the reference picture by the video camera.
It is appreciated that the reference picture that server is sent may include image itself and image identifier, described image mark
Symbol is known for identifying reference picture.
Step S332 receives the clarification of objective in the extracted reference picture of video camera.
It is appreciated that the feature is sent out after the clarification of objective that video camera extracts in reference picture, then by video camera
Server is returned, to be received by server and manage the feature.
It is appreciated that the received feature of server includes the identifier of feature reference picture corresponding with feature itself.
It is also understood that server receives video camera and sends in images to be recognized in target identification management method
The identifier of target can be the image identifier or the object identifier and described image identifier of above-mentioned reference picture
It corresponds.
Step S333 based on the clarification of objective creation in reference picture or updates feature database.
After the clarification of objective in the reference picture that server receives video camera extraction, institute can be based on by server
It states feature-modeling or updates feature database.
The feature that reference picture is extracted by video camera, reduces the consumption of server computing resource.
Illustratively, above-mentioned target identification management method further includes server based on the target in received reference picture
Identifier executes following steps.
Step 341, by reference pictures store in image data base.
It is appreciated that server can be by reference pictures store in image data base.It can be used for according to be identified
The identifier of target in image obtains reference picture.
It is appreciated that further including the corresponding image identifier of the reference picture in image data base.Described image mark
Symbol can be above-mentioned object identifier or described image identifier and the object identifier corresponds.
Step 342, after the identifier for receiving the target in the images to be recognized, according to the images to be recognized
Target identifier retrieval described image database.It is appreciated that retrieving described image data based on the object identifier
Library, it is available to arrive reference picture corresponding with the object identifier.
Step 343, desired operation is executed according to search result.
Search result based on step 342 is available to the corresponding reference picture of target identified by video camera, in turn
Desired operation can be executed by server.Specifically for example, the desired operation may include carrying out to this target identification result
Relative recording, or can also include playing the reference picture to carry out relevant presentation.
Illustratively, above-mentioned target identification management method further includes that target identification strategy is sent by server to video camera,
To carry out target identification according to the target identification strategy by the video camera.
It is appreciated that above-mentioned target identification management method further includes by server admin target identification strategy.The target
Recognition strategy can be managed according to identification classification, and each identification classification may include one or more target identification strategy.
Video camera can be sent target identification strategy to video camera by server before carrying out target identification.
The target identification strategy can also include one or more about target detection, feature extraction or aspect ratio centering
The setting information of item dependent thresholds.
It is appreciated that server can carry out better optimization aim identification by adjusting the target identification policy content
Method promotes the accuracy rate of target identification.
Target identification strategy is sent to video camera by server, target identification can be preferably used for, promote target identification
Accuracy rate.
Those of ordinary skill in the art, can be more clearly by reading the above-mentioned associated description about target identification method
Understand the target identification management method.For sake of simplicity, details are not described herein.
In order to illustrate more clearly of the application, Fig. 4 shows the target identification management of another embodiment according to the present invention
The schematic flow chart of method 400.As shown in figure 4, target identification management method 400 includes the following steps.
Step S410 starts and initializes.
Server starting, the then initialization of performance objective identification management method.The initialization may include following son
Step.
Sub-step S411, data library initialization.The database initialization includes normal in the connection or database of database
With the cleaning and recovery of data.The database may include the feature database for storing feature, can also include for storing
The image data base of reference picture.
Sub-step S412 loads all feature databases.On the basis of sub-step S411, server can load all features
Library, with the transmission or update for subsequent characteristics library.
Step S420 waits video camera connection request.
Step S430 receives the connection request of video camera.
Step S440 receives the check code of the identifier of video camera and the feature database of video camera storage from video camera.
Step S450, calibration feature library.
According to added by the initialization of the check code and step S410 of the identifier of the received video camera of step S440 and feature database
The check code of the feature database of load, whether the feature database by server verification video camera storage is latest features library.If passing through school
The server for testing the storage of determining video camera is not to execute step S460 in the case where latest features library, no to then follow the steps S470.
Step S460 sends latest features library to video camera.
Step S470 sends target identification strategy to video camera.
Step S480 waits video camera target identification result.
Server is identified by video camera performance objective and is operated after sending target identification strategy to video camera.Server into
Enter wait state, video camera is waited to send target identification result.
Step S490 receives the identifier of the target in the images to be recognized that video camera is sent.
After the identifier of the target in the images to be recognized for receiving video camera transmission, if server allows video camera
Continue target identification work, executes step S480 again；Otherwise server can execute step S491.
Step S491 disconnects the connection with video camera.
It is appreciated that the video camera no longer performance objective identifies work after server disconnects the connection with video camera.It replaces
Generation, server, which can also be sent, disconnects instruction, receives open command by video camera, and executed by video camera and disconnect and take
The connection of business device.
It is appreciated that target identification management method 400 is used for the video camera of target identification by server admin, not only really
The real-time of target identification is protected, and reduces the consumption of server computing resource, is extended convenient for system.
Above-mentioned target identification management method 400 describes management of the server to a video camera, it will be understood that server
Can be serial or simultaneously manage to property multiple video cameras.
According to a further aspect of the present invention, a kind of target identification system is additionally provided, the target identification system includes camera shooting
Machine and server.The video camera is for executing above-mentioned target identification method.The server is used for above-mentioned by executing
Target identification management method manages the video camera.
In addition, according to a further aspect of the invention, additionally providing a kind of storage medium, storing journey on said storage
Sequence instruction makes the computer or processor execute the present invention real when described program instruction is run by computer or processor
Apply the target identification method of example and/or the corresponding steps of target identification management method, and for realizing implementing according to the present invention
The corresponding module of example being used in target identification system.The storage medium for example may include the storage card of smart phone, put down
The storage unit of plate computer, the hard disk of personal computer, read-only memory (ROM), Erasable Programmable Read Only Memory EPROM
(EPROM), portable compact disc read-only memory (CD-ROM), any combination of USB storage or above-mentioned storage medium.
The computer readable storage medium can be any combination of one or more computer readable storage mediums.
In one embodiment, when the computer program instructions are run by computer or processor, make the calculating
Machine or processor execute following steps:
Establish the connection with server；
Obtain images to be recognized；
Target identification is carried out for the images to be recognized, with the identifier of the target in the determination images to be recognized；
And
The object identifier is exported to the server.
In another embodiment, when the computer program instructions are run by computer or processor, make the meter
Calculation machine or processor execute following steps:
The connection request of the video camera is received, the connection with the video camera is established；
Receive the identifier of the target in the images to be recognized.
Those of ordinary skill in the art are by reading the phase above for target identification method and target identification management method
Close description, it is possible to understand that the specific implementation of above-mentioned target identification system and storage medium, for sake of simplicity, no longer superfluous herein
It states.
Target identification method, target identification system, target identification management method and storage according to an embodiment of the present invention are situated between
Matter enhances the real-time of target identification, reduces to server performance and network by carrying out target identification using video camera
Requirement, reduce server maintenance extension cost.
Although describing example embodiment by reference to attached drawing here, it should be understood that above example embodiment are only exemplary
, and be not intended to limit the scope of the invention to this.Those of ordinary skill in the art can carry out various changes wherein
And modification, it is made without departing from the scope of the present invention and spiritual.All such changes and modifications are intended to be included in appended claims
Within required the scope of the present invention.
Those of ordinary skill in the art may be aware that list described in conjunction with the examples disclosed in the embodiments of the present disclosure
Member and algorithm steps can be realized with the combination of electronic hardware or computer software and electronic hardware.These functions are actually
It is implemented in hardware or software, the specific application and design constraint depending on technical solution.Professional technician
Each specific application can be used different methods to achieve the described function, but this realization is it is not considered that exceed
The scope of the present invention.
In several embodiments provided herein, it should be understood that disclosed device and method can pass through it
Its mode is realized.For example, apparatus embodiments described above are merely indicative, for example, the division of the unit, only
Only a kind of logical function partition, there may be another division manner in actual implementation, such as multiple units or components can be tied
Another equipment is closed or is desirably integrated into, or some features can be ignored or not executed.
In the instructions provided here, numerous specific details are set forth.It is to be appreciated, however, that implementation of the invention
Example can be practiced without these specific details.In some instances, well known method, structure is not been shown in detail
And technology, so as not to obscure the understanding of this specification.
Similarly, it should be understood that in order to simplify the present invention and help to understand one or more of the various inventive aspects,
To in the description of exemplary embodiment of the present invention, each feature of the invention be grouped together into sometimes single embodiment, figure,
Or in descriptions thereof.However, the method for the invention should not be construed to reflect an intention that i.e. claimed
The present invention claims features more more than feature expressly recited in each claim.More precisely, such as corresponding power
As sharp claim reflects, inventive point is that the spy of all features less than some disclosed single embodiment can be used
Sign is to solve corresponding technical problem.Therefore, it then follows thus claims of specific embodiment are expressly incorporated in this specific
Embodiment, wherein each, the claims themselves are regarded as separate embodiments of the invention.
It will be understood to those skilled in the art that any combination pair can be used other than mutually exclusive between feature
All features disclosed in this specification (including adjoint claim, abstract and attached drawing) and so disclosed any method
Or all process or units of equipment are combined.Unless expressly stated otherwise, this specification (is wanted including adjoint right
Ask, make a summary and attached drawing) disclosed in each feature can be replaced with an alternative feature that provides the same, equivalent, or similar purpose.
In addition, it will be appreciated by those of skill in the art that although some embodiments described herein include other embodiments
In included certain features rather than other feature, but the combination of the feature of different embodiments mean it is of the invention
Within the scope of and form different embodiments.For example, in detail in the claims, embodiment claimed it is one of any
Can in any combination mode come using.
Various component embodiments of the invention can be implemented in hardware, or to run on one or more processors
Software module realize, or be implemented in a combination thereof.It will be understood by those of skill in the art that can be used in practice
Microprocessor or digital signal processor (DSP) realize one in target identification system according to an embodiment of the present invention
The some or all functions of a little modules.The present invention be also implemented as a part for executing method as described herein or
The program of device (for example, computer program and computer program product) of person's whole.It is such to realize that program of the invention be with
It may be stored on the computer-readable medium, or may be in the form of one or more signals.Such signal can from because
It downloads and obtains on spy's net website, be perhaps provided on the carrier signal or be provided in any other form.
It should be noted that the above-mentioned embodiments illustrate rather than limit the invention, and ability
Field technique personnel can be designed alternative embodiment without departing from the scope of the appended claims.In the claims,
Any reference symbol between parentheses should not be configured to limitations on claims.Word "comprising" does not exclude the presence of not
Element or step listed in the claims.Word "a" or "an" located in front of the element does not exclude the presence of multiple such
Element.The present invention can be by means of including the hardware of several different elements and being come by means of properly programmed computer real
It is existing.In the unit claims listing several devices, several in these devices can be through the same hardware branch
To embody.The use of word first, second, and third does not indicate any sequence.These words can be explained and be run after fame
Claim.
The above description is merely a specific embodiment or to the explanation of specific embodiment, protection of the invention
Range is not limited thereto, and anyone skilled in the art in the technical scope disclosed by the present invention, can be easily
Expect change or replacement, should be covered by the protection scope of the present invention.Protection scope of the present invention should be with claim
Subject to protection scope.
Claims (17)
1. a kind of target identification method, the target identification method is used for video camera, and the target identification method includes:
Establish the connection with server；
Obtain images to be recognized；
Target identification is carried out for the images to be recognized, with the identifier of the target in the determination images to be recognized；And
The object identifier is exported to the server.
2. target identification method as described in claim 1, wherein described to carry out target identification packet for the images to be recognized
It includes:
Target detection is carried out for the images to be recognized；
The clarification of objective in the images to be recognized is extracted based on the testing result to the images to be recognized；And
Feature in clarification of objective and feature database in the images to be recognized is compared, to be determined based on comparison result
The object identifier.
3. target identification method as claimed in claim 2, wherein the feature database is stored in the storage device of the video camera
In.
4. target identification method as claimed in claim 2, wherein carry out target identification for the images to be recognized described
Before, the target identification method further include:
Latest features library is obtained from the server, to be used for target identification.
5. target identification method as claimed in claim 4, wherein the target identification method further include:
Both the identifier of the video camera and the check code of the feature database are sent to the server, by the service
Device verifies whether the video camera is stored with latest features library；
It is described to include: from server acquisition latest features library
In the case where the video camera not yet stores latest features library, latest features library is obtained from the server.
6. target identification method as claimed in claim 4, wherein described to include: from server acquisition latest features library
The latest features library of the server active push is received, wherein the server creates or have updated feature database.
7. such as the described in any item target identification methods of claim 4 to 6, wherein the target identification method further include:
Receive the reference picture that the server is sent；
Target detection is carried out for the reference picture；
The clarification of objective in the reference picture is extracted based on the testing result to the reference picture；
Clarification of objective in the reference picture is sent to the server, to create or update special for the server
Levy library.
8. such as target identification method as claimed in any one of claims 1 to 6, wherein it is described for the images to be recognized into
Before row target identification, the target identification method further include:
Target identification strategy is obtained from the server, to carry out target identification according to the target identification strategy.
9. a kind of target identification management method, the target identification management method is used for server, and the server is for managing
For executing the video camera of any one of the claims 1-8 target identification method, the target identification management method packet
It includes:
The connection request of the video camera is received, the connection with the video camera is established；
Receive the identifier of the target in the images to be recognized.
10. target identification management method as claimed in claim 9, wherein the target identification management method further include:
Latest features library is sent to the video camera, to carry out target identification for the video camera.
11. target identification management method as claimed in claim 10, wherein the target identification management method further include:
The check code of the identifier of the video camera and the feature database of video camera storage is received from the video camera；
Whether video camera described in the verification code check of the feature database stored using the identifier of the video camera and the video camera
It is stored with latest features library；
The transmission latest features library is to the video camera, comprising:
In the case where the video camera not yet stores latest features library, latest features library is sent to the video camera.
12. target identification management method as claimed in claim 10, wherein the transmission latest features library to the video camera
Include:
In the case where creating or having updated feature database, active push latest features library to the video camera.
13. such as the described in any item target identification management methods of claim 9 to 12, wherein the target identification management method
Further include:
Reference picture is sent to the video camera, extracts feature to be based on the reference picture by the video camera；
Receive the clarification of objective in the extracted reference picture of the video camera；
Based on the clarification of objective creation in the reference picture or update feature database.
14. target identification management method as claimed in claim 13, wherein the target identification management method further include:
By the reference pictures store in image data base；
After the identifier for receiving the target in the images to be recognized, according to the mark of the target of the images to be recognized
Symbol retrieval described image database；
Desired operation is executed according to search result.
15. such as the described in any item target identification management methods of claim 9 to 12, wherein the target identification management method
Further include:
Target identification strategy is sent to the video camera, to carry out target knowledge according to the target identification strategy by the video camera
Not.
16. a kind of target identification system, the target identification system includes video camera and server, which is characterized in that
The video camera is for executing the described in any item target identification methods of the claims 1 to 8；
The server is for managing the video camera.
17. a kind of storage medium, stores program instruction on said storage, which is characterized in that described program instruction exists
For executing target identification method as claimed in any one of claims 1 to 8 and/or as claim 9 to 15 is any when operation
Target identification management method described in.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910414312.XA CN110147759A (en) | 2019-05-17 | 2019-05-17 | Target identification method, system, target identification management method and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910414312.XA CN110147759A (en) | 2019-05-17 | 2019-05-17 | Target identification method, system, target identification management method and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110147759A true CN110147759A (en) | 2019-08-20 |
Family
ID=67594273
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910414312.XA Pending CN110147759A (en) | 2019-05-17 | 2019-05-17 | Target identification method, system, target identification management method and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110147759A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111782664A (en) * | 2019-10-12 | 2020-10-16 | 西安宇视信息科技有限公司 | Camera management method, device, equipment and medium |
| CN113159000A (en) * | 2021-05-26 | 2021-07-23 | 中国工商银行股份有限公司 | Face recognition method, device and system |
| CN113286115A (en) * | 2020-02-20 | 2021-08-20 | 浙江宇视科技有限公司 | Video monitoring guide library distribution control method, device and related equipment |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101071447A (en) * | 2006-03-06 | 2007-11-14 | 索尼株式会社 | Search system, image-capturing apparatus, data storage apparatus, information processing apparatus |
| CN102721420A (en) * | 2012-06-28 | 2012-10-10 | 宇龙计算机通信科技(深圳)有限公司 | Cloud computing-based navigation error correction prompt system and method |
| CN104023252A (en) * | 2013-03-01 | 2014-09-03 | 中兴通讯股份有限公司 | OTT internet TV using record sharing method and system |
| CN105472312A (en) * | 2014-08-19 | 2016-04-06 | 北京奇虎科技有限公司 | Intelligent shooting system alarming method, intelligent shooting system and network camera |
| CN106303390A (en) * | 2015-06-02 | 2017-01-04 | 联想(北京)有限公司 | Image-pickup method and device thereof, image transfer method and device thereof |
| CN106372606A (en) * | 2016-08-31 | 2017-02-01 | 北京旷视科技有限公司 | Target object information generation method and unit identification method and unit and system |
| CN106529515A (en) * | 2016-12-26 | 2017-03-22 | 浙江宇视科技有限公司 | Facial feature library management method and system |
| CN108765823A (en) * | 2018-05-07 | 2018-11-06 | 西安艾润物联网技术服务有限责任公司 | A kind of alarm method, device and system |
| CN109002789A (en) * | 2018-07-10 | 2018-12-14 | 银河水滴科技（北京）有限公司 | A kind of face identification method applied to camera |
| CN109684961A (en) * | 2018-12-14 | 2019-04-26 | 深圳英飞拓智能技术有限公司 | Population management's method and device based on recognition of face |
-
2019
- 2019-05-17 CN CN201910414312.XA patent/CN110147759A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101071447A (en) * | 2006-03-06 | 2007-11-14 | 索尼株式会社 | Search system, image-capturing apparatus, data storage apparatus, information processing apparatus |
| CN102721420A (en) * | 2012-06-28 | 2012-10-10 | 宇龙计算机通信科技(深圳)有限公司 | Cloud computing-based navigation error correction prompt system and method |
| CN104023252A (en) * | 2013-03-01 | 2014-09-03 | 中兴通讯股份有限公司 | OTT internet TV using record sharing method and system |
| CN105472312A (en) * | 2014-08-19 | 2016-04-06 | 北京奇虎科技有限公司 | Intelligent shooting system alarming method, intelligent shooting system and network camera |
| CN106303390A (en) * | 2015-06-02 | 2017-01-04 | 联想(北京)有限公司 | Image-pickup method and device thereof, image transfer method and device thereof |
| CN106372606A (en) * | 2016-08-31 | 2017-02-01 | 北京旷视科技有限公司 | Target object information generation method and unit identification method and unit and system |
| CN106529515A (en) * | 2016-12-26 | 2017-03-22 | 浙江宇视科技有限公司 | Facial feature library management method and system |
| CN108765823A (en) * | 2018-05-07 | 2018-11-06 | 西安艾润物联网技术服务有限责任公司 | A kind of alarm method, device and system |
| CN109002789A (en) * | 2018-07-10 | 2018-12-14 | 银河水滴科技（北京）有限公司 | A kind of face identification method applied to camera |
| CN109684961A (en) * | 2018-12-14 | 2019-04-26 | 深圳英飞拓智能技术有限公司 | Population management's method and device based on recognition of face |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111782664A (en) * | 2019-10-12 | 2020-10-16 | 西安宇视信息科技有限公司 | Camera management method, device, equipment and medium |
| CN113286115A (en) * | 2020-02-20 | 2021-08-20 | 浙江宇视科技有限公司 | Video monitoring guide library distribution control method, device and related equipment |
| CN113159000A (en) * | 2021-05-26 | 2021-07-23 | 中国工商银行股份有限公司 | Face recognition method, device and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110414376B (en) | Method for updating face recognition model, face recognition camera and server | |
| CN110147759A (en) | Target identification method, system, target identification management method and storage medium | |
| CN109492128A (en) | Method and apparatus for generating model | |
| CN111523413A (en) | Method and device for generating face image | |
| CN105185121A (en) | Method for parallelly recognizing license plate via virtual checkpoint | |
| CN110162462A (en) | Test method, system and the computer equipment of face identification system based on scene | |
| CN108875328B (en) | Identity verification method, device and storage medium | |
| CN108875478A (en) | The testimony of a witness unifies checking method, device and system and storage medium | |
| CN110796269B (en) | Method and device for generating model, and method and device for processing information | |
| CN109815839B (en) | Loitering person identification method under micro-service architecture and related product | |
| CN113255685B (en) | Image processing method and device, computer equipment and storage medium | |
| CN111126411B (en) | Abnormal behavior identification method and device | |
| CN111401215A (en) | Method and system for detecting multi-class targets | |
| CN110188129A (en) | Data processing method, device, system, equipment and the medium of testimony of a witness verification terminal | |
| CN109413760A (en) | A kind of wireless connection method and equipment | |
| CN109635532A (en) | A kind of picture pick-up device and its binding method | |
| CN111860071A (en) | Method and device for identifying an item | |
| CN110119456A (en) | Retrieve the method and device of image | |
| CN112487082B (en) | Biological feature recognition method and related equipment | |
| CN112925899A (en) | Ranking model establishing method, case clue recommending device and medium | |
| CN115984977A (en) | Living body detection method and system | |
| CN112257666B (en) | Target image content aggregation method, device, equipment and readable storage medium | |
| CN104462422A (en) | Object processing method and device | |
| CN114677584A (en) | Water immersion identification method and system for power distribution station of double-attention power system | |
| CN114513653A (en) | Video processing method, device, equipment, computer program product and storage medium |
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: 20190820 |