CN106709424A - Optimized surveillance video storage system and equipment - Google Patents
Optimized surveillance video storage system and equipment Download PDFInfo
- Publication number
- CN106709424A CN106709424A CN201611035754.6A CN201611035754A CN106709424A CN 106709424 A CN106709424 A CN 106709424A CN 201611035754 A CN201611035754 A CN 201611035754A CN 106709424 A CN106709424 A CN 106709424A
- Authority
- CN
- China
- Prior art keywords
- face
- video
- frame
- vector
- feature vector
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
- G06F16/78—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/783—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/168—Feature extraction; Face representation
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Library & Information Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Television Signal Processing For Recording (AREA)
- Closed-Circuit Television Systems (AREA)
Abstract
The invention provides an optimized surveillance video storage system and equipment. The system and equipment comprise a video acquisition front end, a face recognition module, primary real-time storage equipment, central cloud storage equipment and a searching module, wherein the video acquisition front end is a high-definition camera, and is responsible for acquiring people flow video at an entrance of a equipment channel in real time; the face recognition module obtains an identifier indicating whether each frame of image in the video contains a face and a top-quality face picture in an image set containing the same face through performing face detection, feature extraction and face comparison on the surveillance video frame by frame; the primary real-time storage equipment stores video segments containing the face in real time; the central cloud storage equipment stores the obtained top-quality face picture in a database; and when in retrieval, a picture of a user is input to obtain a corresponding picture from the central data base and the video segments from the primary real-time storage equipment. The optimized surveillance video storage system and the equipment can guarantee that the stored picture has an evidentiary feature, and save the storage space greatly.
Description
Technical field
The invention belongs to artificial intelligence field, more particularly to a kind of monitor video optimizing memory system and relevant equipment.
Background technology
The positions such as the gateway generally for office, by surveillance video or special face and certificate ratio
To equipment such as unit guest machine etc., realization is analyzed to the face in video.
To office unit if whom clearly to find out, when enters office space, now under traditional approach
Means be that video recording inquiry is carried out by video monitoring system, but due to the video recording often storage file mistake of video monitoring system
Greatly, the writing function of dealing personnel within only supporting month, and want to find which day designated person enter office ground at
Point, it is necessary to monitoring personnel thumbs a large amount of video recordings can just be positioned manually, if not specifying the specifying informations such as time place, due to work
Amount is huge cannot almost to be realized inquiring about designated person specifically at what time into the problem condition of office.
The system is captured automatically using the human face photo that advanced artificial intelligence face recognition technology is realized into personnel
Card function is stayed, hundreds thousand of to the up to a million Historic preservation capacity of human face photo record can be reached.Usual these faces record
Capacity can be supported to realize gateway the record holding time up to even 1 to 2 years several months.And stored by equipment for customizing and held
Amount, can realize the longer record holding time such as several years.A large amount of faces not only contribute to the people of gateway by the preservation for recording
Member's Precision management, also to occurring to provide effective photographic evidence when dispute, important case.
The content of the invention
Currently, in the video surveillance applications scene for being normally applied occasion, main target is that turnover personnel are monitored,
And it is general all using traditional video storage scheme, preserve complete monitor video to facilitate user to inquire about, or investigate and collect evidence.
Such method occupies substantial amounts of memory space, causes monitoring device at most to support one to be stored to bimestrial video, and
Search is wasted time and energy during inquiry, and great inconvenience is brought to user.
In the present invention, whether, with the presence of face, the video for detecting face is only preserved by monitor video real-time detection
Section in the cloud storage of center, sets up the corresponding memory space of each Zhang Butong faces local, only retains and meets pre-conditioned
Picture frame, so greatly save memory space；Simultaneously by setting up the search engine based on face, aspect the looking into of user
Ask, greatly save query time.
In order to solve the above-mentioned technical problem, the invention provides a kind of new systems approach, including：
Video acquisition front end, gathers front-end configuration standard high-definition camera, using one or more cameras, to need into
The place of pedestrian's flow monitoring carries out monitor in real time, while the video of collection is temporarily stored among the internal memory of equipment.
Recognition of face module, carries out Face datection to the video of video acquisition front end interim storage frame by frame, detection mode or
It is depth convolutional neural networks learning algorithm, or the algorithm for other correct verification and measurement ratios higher than 95%, mark the face of each frame
Testing result；If in the testing result of same picture frame, the face number of correct detection is more than 1, then detection in the picture frame is recorded
The each face for arriving, is correctly detecting in the frame of video of face from mark, the video segmentation of face is extracted, while being regarded above-mentioned
Frequency division section is transferred to one-level real time storage facility.
From it is above-mentioned be correctly detecting face presence video segmentation in, to the video segmentation in each picture frame in it is every
One face carries out face characteristic extraction, this feature extracting method or be general Knowledge based engineering characterizing method, or be based on
The characterizing method of algebraic characteristic or statistical learning, obtains characterizing each characteristic vector of face.
In above-mentioned video segmentation, since first picture frame for having face, to each face in each picture frame
Characteristic vector matched one by one with each face of previous frame image, to meet similitude requirement face be considered same
One face, otherwise it is assumed that being new face；Characteristic vector composition one collection merging that same face will be belonged to is done accordingly
Mark, is that emerging face sets up new characteristic vector set；Until the last frame image in the video segmentation, Huo Zheda
To maximum successive image frame disposal ability of the invention.
Then in the characteristic vector set for belonging to same face, by each characteristic vector and its in addition to itself
He carries out related operation at characteristic vector, and correlation result is sued for peace, and obtains the matching value of this feature vector in above-mentioned set,
The maximum matching value that features described above vector gathers calculation acquisition of falling into a trap is optimal face matching value, corresponding face characteristic
Vector is optimal face feature vector, and picture frame corresponding with this feature vector is designated as optimal facial image frame；Or from upper
State and look for a face for maximum as optimal face in the corresponding face image set of face characteristic set, with optimal face pair
The picture frame answered is optimal facial image frame.
The corresponding face feature vector of optimal facial image frame and the face feature vector storehouse in the cloud storage of center are carried out
Compare, if the face feature vector is more than δ with certain the face feature vector similarity in the database for comparing, then it is assumed that this two
Open face and belong to same person, otherwise it is assumed that the characteristic vector for being compared belongs to different faces；If in the presence of multiple face characteristics
Higher than similarity δ, then it is assumed that the face feature vector belongs to same with similarity highest face feature vector in database
Face；Then it is stored in the cloud storage database of center from by the picture frame and its character pair vector, otherwise, Deictic Center
Cloud storage is that the face creates new memory space and unique mark.
If in above-mentioned optimized image frame, comprising optimal face number more than 1, then by each optimal face feature vector with
Face feature vector storehouse in the cloud storage of center is compared, if there is the face feature vector of matching, by the picture frame and
Corresponding characteristic vector is stored in the memory space of the face, otherwise for the face sets up a new memory space and only
One mark.
One-level real time storage facility, during storage video, is correctly detecting in the frame of video of face from mark, extracts face
Video segmentation；The beginning picture frame of each video segmentation is the first two field picture for detecting the presence of face, or according to the actual requirements
N1 frames storage in advance；The end of each video segmentation is the last frame for detecting the presence of face, records each video segmentation
Monitoring date and time, is then combined into a file set in advance by video segmentation one by one according to time order and function order.
Center cloud storage equipment, according to the actual requirements or sets up the characteristic vector storehouse of face and other essential information,
Or the base index information of face storage is set up according to the self-defined mode of system；
Then judge whether the face is existing people in database according to the face feature vector comparison result for extracting
Face, if so, then storing described face feature vector, and the optimized image frame of the face, records the picture frame
Date of formation and time, and its characteristic vector；
If it is not, then for the face sets up new unique index mark and memory space according to the rule that system is defined,
Store the corresponding optimized image frame of the face, the date of formation and time of optimized image frame, and its characteristic vector.
Search module, the image of user or input containing face is inquired about, and system is used according to the image of user input
The method same with above-mentioned Face datection, carries out Face datection, then extracts its characteristic vector, by the face characteristic be stored in
Facial image characteristic vector in one-level real time storage facility and center cloud storage equipment is compared, and is found matched
All face video-frequency bands or image, feed back to search front end.If without suitable result, user or abandoning search, or provide new
Image inquired about, or inputting date is scanned for the time period, obtains corresponding feedback result.
During search, acquiescence first inquires about the video-frequency band of one-level real time storage facility, if having qualified, from one-level storage
Center feedback result is to user.Then the view data of Help Center's cloud storage equipment.
Such scheme of the invention at least has the advantages that：
Efficiently solve current video monitoring data storage amount huge, and be difficult the problem of inquiry.The present invention provide be
The system storage valid data that system can will be normally applied rank are greatly promoted, and search for simple and convenient, enormously simplify general field
The video storage of scape application and query process.
A large amount of faces not only contribute to personnel's Precision management of gateway by the preservation for recording, also to there is dispute, weight
Effective photographic evidence is provided during causae majores.
Brief description of the drawings
Accompanying drawing described herein is used for providing a further understanding of the present invention, constitutes the part of the application, this hair
Bright schematic description and description does not constitute inappropriate limitation of the present invention for explaining the present invention.In the accompanying drawings：
Fig. 1 represents the systems approach basic structure schematic diagram of the embodiment of the present invention；
Fig. 2 represents the process step flow chart of the embodiment of the present invention；
The process chart of the step of Fig. 3 represents the embodiment of the present invention 2；
Specific embodiment
The following description and drawings fully show specific embodiments of the present invention, to enable those skilled in the art to
Put into practice them.Other embodiments can include structure, logic, process and other changes.Embodiment is only represented
Possible change.Unless explicitly requested, otherwise single components and functionality is optional, and the order for operating can change.
The part of some embodiments and feature can be included in or replace part and the feature of other embodiments.Reality of the invention
Apply the gamut of the scope including claims of scheme, and claims all obtainable equivalent.At this
Wen Zhong, these embodiments of the invention can individually or generally be represented that this is just for the sake of side with term " invention "
Just, and if in fact disclosing the invention more than, the scope for being not meant to automatically limit the application is any single
Invention or inventive concept.
As shown in figure 1, in embodiments of the invention, including：
Video acquisition front end 101, gathers front-end configuration standard high-definition camera, using one or more cameras, to needing
The place for entering pedestrian stream monitoring carries out monitor in real time, while the video of collection is temporarily stored among the internal memory of equipment.
In the above embodiment of the present invention, also include：
Recognition of face module 102, the video to video acquisition front end interim storage carries out Face datection, detection mode frame by frame
Or be depth convolutional neural networks algorithm, such as：Depth is 9 layers, or the algorithm for the correct verification and measurement ratio of other algorithms higher than 95%,
Such as：Face recognition technology based on Gaussian process；Record the Face datection result of each frame；If the detection knot of same picture frame
In fruit, the face number of correct detection is more than 1, then record each face detected in the picture frame, from the correct detection of mark
To in the frame of video of face, the video segmentation of face is extracted, while above-mentioned video segmentation is transferred into one-level real time storage facility.
Further, from it is above-mentioned be correctly detecting face presence video segmentation in, to the video segmentation in each figure
Each face in as frame carries out face characteristic extraction, this feature extracting method or be general Knowledge based engineering sign side
Method, or be the characterizing method based on algebraic characteristic or statistical learning, obtain characterizing each characteristic vector of face, it is designated asWherein fiI-th floating-point element of vector is characterized, N is characterized the element sum of vector.
Further, in above-mentioned video segmentation, since first picture frame for having face, to every in each picture frame
One characteristic vector of face is matched one by one with each face of previous frame image, the face to meeting similitude requirement
Same face is considered, otherwise it is assumed that being new face；The same characteristic vector of face will be belonged to and constitute a collection merging
Corresponding mark is done, is that emerging face sets up new characteristic vector set；Until the last frame figure in the video segmentation
Picture, or reach the successive image frame disposal ability of maximum of the invention.
For example, containing two faces in such as the first two field picture, F is designated as respectively1,1And F1,2, its corresponding feature to
Measure and beWithAlso contain two faces in second two field picture, F is designated as respectively2,1And F2,2, its corresponding characteristic vector is
WithFour matching degree ∏ of face are calculated respectivelyI, j：
Wherein,It is standard correlation function,It is random length identical vector.
If ∏1,1>=β, wherein β are similarity threshold value, then it is assumed that F1,1And F2,1It is same face, otherwise it is assumed that F1,1
And F2,1Belong to different faces.
If ∏2,1＜ β and ∏2,2＜ β, then it is assumed that F2,2Belong to emerging face.
Further, in the above-mentioned characteristic vector set for belonging to same face, by each characteristic vector and except its sheet
Other characteristic vectors outside body carry out related operationObtain the similarity measure values vector of characteristic vectorAnd
By similarity measure values vector all elements summation, obtain the matching value of this feature vector in above-mentioned set, features described above to
The maximum matching value that acquisition is calculated in duration set is optimal face matching value, and corresponding face feature vector is optimal
Face feature vector, be designated as optimal facial image frame with this feature corresponding picture frame of vector；Or from above-mentioned face characteristic
Gathering look for a face for maximum as optimal face in corresponding face image set, and picture frame corresponding with optimal face is
It is optimal facial image frame.
Illustrate, it is assumed that the set of eigenvectors for belonging to same face is combined intoWherein νiFor this
I-th characteristic vector of element in set, M is set element sum；The similarity measure values vector of characteristic vector is designated asWhereinThe then corresponding matching of similarity measure values vector
It is worth and isFurther, optimum matching point m is obtained from above-mentioned result of calculationopt=max (m0, m1..., mM),
Wherein,To ask vector maximization computing, the corresponding characteristic vector of optimum matching point is optimal face, optimal face
Corresponding image is then optimal facial image frame.
Further, it is the corresponding face feature vector of above-mentioned optimal facial image frame and face in the cloud storage of center is special
Levy vectorial storehouse to compare, comparison method is the correlation for calculating characteristic vector, using said process identical correlation functionIf certain the face feature vector similarity ∏ in the face feature vector and the database for comparingI, jMore than δ, then
Think that this two faces belong to same person, otherwise it is assumed that the characteristic vector for being compared belongs to different faces；If in the presence of multiple
Face characteristic is higher than similarity δ, then it is assumed that the face feature vector and similarity highest face feature vector category in database
In same face；Then it is stored in the cloud storage database of center from by the picture frame and its character pair vector, otherwise,
Deictic Center cloud storage is that the face creates new memory space and unique mark.Such as：Memory space includes only space
Mark ID, unique ID of each image, the corresponding characteristic vector of each image, the generation time of picture, the personalized letter of face
Breath：Name, age, sex etc..
Further, if in above-mentioned optimized image frame, comprising optimal face number more than 1, then by each optimal face
Characteristic vector is compared with the face feature vector storehouse in the cloud storage of center, if there is the face feature vector of matching, should
Picture frame and corresponding characteristic vector are stored in the memory space of the face, otherwise for the face sets up a new storage
Space and unique mark.
In the above embodiment of the present invention, also include：
One-level real time storage facility 103, during storage video, is correctly detecting in the frame of video of face from mark, extracts people
The video segmentation of face；The beginning picture frame of each video segmentation is the first two field picture for detecting the presence of face, or according to reality
Demand shifts to an earlier date the storage of N1 frames, such as N1=5；The end of each video segmentation is the last frame for detecting the presence of face, record
The monitoring date and time of each video segmentation, is then combined into one in advance by video segmentation one by one according to time order and function order
The file of setting, such as daily segmentation file is stored.
In the above embodiment of the present invention, also include：
Center cloud storage equipment 104, according to the actual requirements or sets up the feature database and other essential informations of face, than
Such as：It is basic that the human face photo of white list or blacklist, typing white list people and blacklist, name, sex, age etc. are set
Information；Or the base index information of face storage is set up according to the self-defined mode of system.
Further, judge whether the face is existing in database according to the face feature vector comparison result for extracting
Face, if so, then storing described face feature vector, and the optimized image frame of the face, record the image
The date of formation and time of frame, and its characteristic vector.
If it is not, then for the face sets up new unique index mark and memory space according to the rule that system is defined,
Store the corresponding optimized image frame of the face, the date of formation and time of optimized image frame, and its characteristic vector.
In the above embodiment of the present invention, also include：
Search module 105, the image of user or input containing face is inquired about, system according to the image of user input,
Using the method same with the Face datection described in above-described embodiment, carry out Face datection, then extract its face characteristic to
Amount, the face characteristic is carried out with the face feature vector in being stored in one-level real time storage facility and center cloud storage equipment
Compare, find matched all face video-frequency bands or image, feed back to search front end.Such as：Feedback result includes owning
The facial image of matching, the unique ID of image, characteristic vector, characteristic vector ID, the date of formation and time of image；It is all comprising
Video file with face, video file ID, face appears in the initial time in video file, end time.If without conjunction
Suitable result, user or abandons search, or provides new image and inquired about, or inputting date is scanned for the time period, is obtained
To corresponding feedback result.
Further, during search, acquiescence first inquires about the video-frequency band of one-level real time storage facility, if having qualified,
From one-level storage center feedback result to user.Then the view data of Help Center's cloud storage equipment again.
The concrete operations flow of above-mentioned functions module or equipment is illustrated with reference to Fig. 2, Fig. 3：
Step one, video monitoring collection and interim storage, gather front-end configuration standard high-definition camera, using one or many
Individual camera, to needing to carry out monitor in real time into the place of pedestrian stream monitoring, while the video of collection is temporarily stored in described
Among the internal memory of equipment.
Step 2, video human face detection, feature extraction and comparison, to the video of video acquisition front end interim storage frame by frame
Face datection is carried out, the Face datection result of each frame is recorded；If in the testing result of same picture frame, the face of correct detection
Number is more than 1, then record each face detected in the picture frame, is correctly detecting in the frame of video of face from mark, carries
The video segmentation of face is taken, while above-mentioned video segmentation is transferred into one-level real time storage facility 103.
Meanwhile, from it is above-mentioned be correctly detecting face presence video segmentation in, to the video segmentation in each picture frame
In each face carry out face characteristic extraction, obtain characterize each characteristic vector of face, be designated asWherein fiI-th floating-point element of vector is characterized, N is characterized the element sum of vector.
In above-mentioned video segmentation, since first picture frame for having face, to each face in each picture frame
Characteristic vector matched one by one with each face of previous frame image, to meet similitude requirement face be considered same
One face, otherwise it is assumed that being new face；Characteristic vector composition one collection merging that same face will be belonged to is done accordingly
Mark, is that emerging face sets up new characteristic vector set；Until the last frame image in the video segmentation, or
Reach the successive image frame disposal ability of maximum of the invention.
In the above-mentioned characteristic vector set for belonging to same face, by each characteristic vector and its in addition to itself
He carries out related operation at characteristic vectorObtain the similarity measure values vector of characteristic vectorAnd by the similarity measurements
Magnitude vector all elements are sued for peace, and obtain the matching value of this feature vector in above-mentioned set, and features described above vector gathers calculation of falling into a trap
The maximum matching value of acquisition is optimal face matching value, corresponding face feature vector be optimal face characteristic to
Amount, picture frame corresponding with this feature vector is designated as optimal facial image frame；Or from the corresponding people of above-mentioned face characteristic set
Look for a face for maximum as optimal face in face image set, picture frame corresponding with optimal face is optimal face figure
As frame.
By the face feature vector storehouse in the corresponding face feature vector of above-mentioned optimal facial image frame and center cloud storage
Compare, comparison method is the correlation for calculating characteristic vector, using said process identical correlation functionIf
Certain face feature vector similarity ∏ in the face feature vector and the database for comparingI, jMore than δ, then it is assumed that this two
Face belongs to same person, otherwise it is assumed that the characteristic vector for being compared belongs to different faces；If high in the presence of multiple face characteristics
In similarity δ, then it is assumed that the face feature vector belongs to same people with similarity highest face feature vector in database
Face；Then it is stored in the cloud storage database of center from by the picture frame and its character pair vector, otherwise, Deictic Center cloud
It is stored as the face and creates new memory space and unique mark.
If in above-mentioned optimized image frame, comprising optimal face number more than 1, then by each optimal face feature vector with
Face feature vector storehouse in the cloud storage of center is compared, if there is the face feature vector of matching, by the picture frame and
Corresponding characteristic vector is stored in the memory space of the face, otherwise for the face sets up a new memory space and only
One mark.Its handling process is as shown in Figure 3.
Step 3, real-time storage video-frequency band during storage video, is correctly detecting in the frame of video of face from mark, is extracted
The video segmentation of face；The beginning picture frame of each video segmentation is the first two field picture for detecting the presence of face, or according to reality
Border demand shifts to an earlier date the storage of N1 frames；The end of each video segmentation is the last frame for detecting the presence of face, records each video
The monitoring date and time of segmentation, is then combined into a text set in advance by video segmentation one by one according to time order and function order
Part, such as daily segmentation file is stored.
Step 4, cloud storage matching image and feature, according to the actual requirements or set up face feature database and its
His essential information, such as：The human face photo of setting white list or blacklist, typing white list people and blacklist, name,
The essential informations such as sex, age；Or the base index information of face storage is set up according to the self-defined mode of system.
Then judge whether the face is existing people in database according to the face feature vector comparison result for extracting
Face, if so, then storing described face feature vector, and the optimized image frame of the face, records the picture frame
Date of formation and time, and its characteristic vector.
If it is not, then for the face sets up new unique index mark and memory space according to the rule that system is defined,
Store the corresponding optimized image frame of the face, the date of formation and time of optimized image frame, and its characteristic vector.
Step 5, is input into search condition, obtains Search Results, according to the image of user input, using with above-described embodiment
Described in the same method of Face datection, carry out Face datection, then extract its face feature vector, by the face characteristic with
The face feature vector being stored in one-level real time storage facility and center cloud storage equipment is compared, and is found matched
All face video-frequency bands or image, feed back to search front end.Such as：Feedback result includes that the facial image of all matchings is schemed
As unique ID, characteristic vector, characteristic vector ID, the date of formation and time of image；All video files comprising matching face,
Video file ID, the face appears in the initial time in video file, end time.If without suitable result, user or putting
Search is abandoned, or new image is provided and inquired about, or inputting date is scanned for the time period, obtains corresponding feedback result.
During search, acquiescence first inquires about the video-frequency band of one-level real time storage facility, if having qualified, from one-level storage
Center feedback result is to user.Then the view data of Help Center's cloud storage equipment again.
The above is the preferred embodiment of the present invention, it is noted that for those skilled in the art
For, on the premise of principle of the present invention is not departed from, some improvements and modifications can also be made, these improvements and modifications
Should be regarded as protection scope of the present invention.
Claims (10)
1. the monitor video storage system and equipment of a kind of optimization, it is characterised in that including：
, by video acquisition front end, recognition of face module, one-level real time storage facility, center cloud storage sets for the system and relevant equipment
Standby, search module is constituted；
People's stream video of Real-time Collection feeder connection is responsible in video acquisition front end, and the video of collection is temporarily stored in into the collection
Among headend equipment internal memory；
Recognition of face module carries out Face datection to the video of interim storage frame by frame, and feature extraction, face alignment marks each frame
Whether image contains face, will meet the predefined optimal human face photo of system and is stored in the cloud storage equipment of center, will include
The continuous videos section for having face is stored among one-level real time storage facility.
When user needs retrieval, any photo of object is searched in input, and search engine carries out Face datection to the photo, and feature is carried
Take, compare with the face characteristic in cloud storage device databases or one-level real time storage facility, so as to obtain corresponding
Photo and associated video.
2. the method for claim 1 and system, it is characterised in that including：
Recognition of face module, carries out Face datection to the video of video acquisition front end interim storage frame by frame, detection mode or be depth
Degree convolutional neural networks learning algorithm, or the algorithm for other correct verification and measurement ratios higher than 95%, mark the Face datection of each frame
As a result；If in the testing result of same picture frame, the face number of correct detection is more than 1, then record what is detected in the picture frame
Each face, is correctly detecting in the frame of video of face from mark, extracts the video segmentation of face, while above-mentioned video is divided
Section is transferred to one-level real time storage facility.
3. method as claimed in claim 2, its feature also includes：
From it is above-mentioned be correctly detecting face presence video segmentation in, to the video segmentation in each picture frame in each
Face carries out face characteristic extraction, this feature extracting method or be general Knowledge based engineering characterizing method, or is based on algebraically
The characterizing method of feature or statistical learning, obtains characterizing each characteristic vector of face.
Since first picture frame for having face, to each characteristic vector of face in each picture frame and previous frame image
Each face matched one by one, to meet similitude requirement face be considered same face, otherwise it is assumed that being new
Face；Corresponding mark is done in characteristic vector composition one collection merging that same face will be belonged to, and is that emerging face is built
Vertical new characteristic vector set；Until the last frame image in the video segmentation, or the sequential chart for reaching maximum of the invention
As frame disposal ability.
4. method as claimed in claim 2, it is characterised in that including：
In the characteristic vector set for belonging to same face, by each characteristic vector with addition to itself other features to
Amount carries out related operation, and correlation result is sued for peace, and obtains the matching value of this feature vector in above-mentioned set, features described above
The maximum matching value that vector gathers calculation acquisition of falling into a trap is optimal face matching value, and corresponding face feature vector is for most
Good face feature vector, picture frame corresponding with this feature vector is designated as optimal facial image frame.Or from above-mentioned face characteristic
Gathering look for a face for maximum as optimal face in corresponding face image set, and picture frame corresponding with optimal face is
It is optimal facial image frame.
5. method as claimed in claim 2, its feature also being, including：
The corresponding face feature vector of optimal facial image frame and the face feature vector storehouse in the cloud storage of center are compared,
If the face feature vector is more than δ with certain the face feature vector similarity in the database for comparing, then it is assumed that this two people
Face belongs to same person, otherwise it is assumed that the characteristic vector for being compared belongs to different faces；If being higher than in the presence of multiple face characteristics
Similarity δ, then it is assumed that the face feature vector belongs to same face with similarity highest face feature vector in database；
Then it is stored in the cloud storage database of center from by the picture frame and its character pair vector, otherwise, Deictic Center cloud is deposited
Store up as the face creates new memory space and unique mark.
6. method as claimed in claim 2, its feature also being, including：
If in above-mentioned optimized image frame, comprising optimal face number more than 1, then by each optimal face feature vector and center
Face feature vector storehouse in cloud storage is compared, if there is the face feature vector of matching, by the picture frame and correspondence
Characteristic vector be stored in the memory space of the face, otherwise for the face sets up a new memory space and unique mark
Know.
7. the method for claim 1 and system, are further characterized in that, including：
One-level real time storage facility, during storage video, is correctly detecting in the frame of video of face from mark, extracts the video of face
Segmentation；The beginning picture frame of each video segmentation is the first two field picture for detecting the presence of face, or is shifted to an earlier date according to the actual requirements
N1 frames are stored；The end of each video segmentation is the last frame for detecting the presence of face, records the monitoring of each video segmentation
Date and time, is then combined into a file set in advance by video segmentation one by one according to time order and function order.
8. the method for claim 1 and system, are further characterized in that, including：
Center cloud storage equipment, according to the actual requirements or sets up the feature database and other essential information of face, or according to being
Self-defined mode of uniting sets up the base index information of face storage.
9. method and system as claimed in claim 8, is further characterized in that, including：
Then judge whether the face is existing face in database according to the face feature vector comparison result for extracting, if
It is that then by described face feature vector, and the optimized image frame of the face is stored, records the generation day of the picture frame
Phase and time, and its characteristic vector；
If it is not, then for the face sets up new unique index mark and memory space, storage according to the rule that system is defined
The corresponding optimized image frame of the face, the date of formation and time of optimized image frame, and its characteristic vector.
10. the method for claim 1 and system, it is characterised in that including：
Search module, the image of user or input containing face is inquired about, system according to the image of user input, using with it is upper
State the same method of Face datection, carry out Face datection, then extract its characteristic vector, by the face characteristic be stored in one-level
Facial image characteristic vector in real time storage facility and center cloud storage equipment is compared, and is found matched all
Face video section or image, feed back to search front end.If without suitable result, user or abandoning search, or provide new image
Inquired about, or inputting date is scanned for the time period, obtains corresponding feedback result.
During search, acquiescence first inquires about the video-frequency band of one-level real time storage facility, if having qualified, from one-level storage center
Feedback result is to user.Then the view data of Help Center's cloud storage equipment.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611035754.6A CN106709424B (en) | 2016-11-19 | 2016-11-19 | Optimized monitoring video storage system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611035754.6A CN106709424B (en) | 2016-11-19 | 2016-11-19 | Optimized monitoring video storage system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106709424A true CN106709424A (en) | 2017-05-24 |
| CN106709424B CN106709424B (en) | 2022-11-11 |
Family
ID=58940179
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611035754.6A Active CN106709424B (en) | 2016-11-19 | 2016-11-19 | Optimized monitoring video storage system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106709424B (en) |
Cited By (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108733819A (en) * | 2018-05-22 | 2018-11-02 | 深圳云天励飞技术有限公司 | A kind of personnel's archives method for building up and device |
| CN108881816A (en) * | 2017-10-12 | 2018-11-23 | 北京旷视科技有限公司 | Generation method, device and the computer storage medium of video file |
| CN108875512A (en) * | 2017-12-05 | 2018-11-23 | 北京旷视科技有限公司 | Face identification method, device, system, storage medium and electronic equipment |
| CN109241378A (en) * | 2018-08-29 | 2019-01-18 | 北京旷视科技有限公司 | Archives method for building up, device, equipment and storage medium |
| CN109241299A (en) * | 2018-09-25 | 2019-01-18 | 腾讯科技（深圳）有限公司 | Multimedia resource searching method, device, storage medium and equipment |
| CN109815371A (en) * | 2019-01-30 | 2019-05-28 | 无锡华云数据技术服务有限公司 | Video monitoring data stores access system |
| CN110266953A (en) * | 2019-06-28 | 2019-09-20 | Oppo广东移动通信有限公司 | Image processing method, device, server and storage medium |
| CN110267007A (en) * | 2019-06-28 | 2019-09-20 | Oppo广东移动通信有限公司 | Image processing method, device, server and storage medium |
| CN110263704A (en) * | 2019-06-18 | 2019-09-20 | 浙江宇视科技有限公司 | Human face data acquisition method, device, server, video collector and medium |
| CN110866491A (en) * | 2019-11-13 | 2020-03-06 | 腾讯科技（深圳）有限公司 | Target retrieval method, device, computer readable storage medium and computer equipment |
| CN111295875A (en) * | 2018-05-07 | 2020-06-16 | 合刃科技（武汉）有限公司 | Shooting control method and electronic device |
| CN111385440A (en) * | 2018-12-27 | 2020-07-07 | 芜湖潜思智能科技有限公司 | Monitoring camera with face recording and inquiring functions |
| CN111414517A (en) * | 2020-03-26 | 2020-07-14 | 成都市喜爱科技有限公司 | Video face analysis method and device and server |
| CN111723242A (en) * | 2020-05-21 | 2020-09-29 | 深圳信息职业技术学院 | Customer portrait drawing method, customer portrait drawing device, terminal equipment and medium |
| CN111831742A (en) * | 2020-05-25 | 2020-10-27 | 佛山市华全电气照明有限公司 | Smart city video positioning method and system |
| CN112597961A (en) * | 2020-12-30 | 2021-04-02 | 上海大学 | Interest target extraction method and system based on big data |
| CN113098642A (en) * | 2021-04-22 | 2021-07-09 | 浙江万里学院 | Logistics management method based on Beidou satellite positioning technology |
| CN113343842A (en) * | 2021-06-04 | 2021-09-03 | 中山大学 | Self-adaptive face recognition method |
| CN113779309A (en) * | 2021-09-01 | 2021-12-10 | 杭州视洞科技有限公司 | Video screening method based on face recognition |
| CN114333119A (en) * | 2021-12-31 | 2022-04-12 | 上海商汤临港智能科技有限公司 | Vehicle unlocking method, vehicle management method, terminal, vehicle unlocking system, vehicle unlocking device, and storage medium |
| CN117111858A (en) * | 2023-10-23 | 2023-11-24 | 深圳萨尔浒网络科技有限公司 | Computer file data matching system |
Citations (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040183951A1 (en) * | 2003-03-06 | 2004-09-23 | Lee Hyeok-Beom | Image-detectable monitoring system and method for using the same |
| JP2007300456A (en) * | 2006-05-01 | 2007-11-15 | Nippon Telegr & Teleph Corp <Ntt> | Video monitoring system and its index generation method |
| CN101299812A (en) * | 2008-06-25 | 2008-11-05 | 北京中星微电子有限公司 | Method, system for analyzing, storing video as well as method, system for searching video |
| CN101505412A (en) * | 2009-03-11 | 2009-08-12 | 上海伯里春贸易有限公司 | Human face collecting identification monitoring system and method for hotel, office building and public place for entertainment |
| CN101546377A (en) * | 2009-04-28 | 2009-09-30 | 上海银晨智能识别科技有限公司 | Human face image capture system and human face image capture method |
| CN101763388A (en) * | 2008-12-25 | 2010-06-30 | 北京中星微电子有限公司 | Method for searching video, system therefor and device therefor as well as video storing method and system thereof |
| CN102170563A (en) * | 2011-03-24 | 2011-08-31 | 杭州海康威视软件有限公司 | Intelligent person capture system and person monitoring management method |
| CN102609729A (en) * | 2012-02-14 | 2012-07-25 | 中国船舶重工集团公司第七二六研究所 | Method and system for recognizing faces shot by multiple cameras |
| CN102665054A (en) * | 2012-05-10 | 2012-09-12 | 江苏友上科技实业有限公司 | Network video recorder system for fast face retrieval |
| CN102799877A (en) * | 2012-09-11 | 2012-11-28 | 上海中原电子技术工程有限公司 | Method and system for screening face images |
| CN102929903A (en) * | 2012-07-04 | 2013-02-13 | 北京中盾安全技术开发公司 | Rapid video retrieval method based on layered structuralized description of video information |
| CN103258028A (en) * | 2013-05-08 | 2013-08-21 | 林凡 | Video hierarchical and partitioned storage system based on content features |
| CN103530652A (en) * | 2013-10-23 | 2014-01-22 | 北京中视广信科技有限公司 | Face clustering based video categorization method and retrieval method as well as systems thereof |
| CN104239881A (en) * | 2013-06-08 | 2014-12-24 | 杭州海康威视数字技术股份有限公司 | Method and system for automatically finding and registering target in surveillance video |
| CN204156985U (en) * | 2014-08-29 | 2015-02-11 | 上海智达商投资管理合伙企业(有限合伙) | There is high-definition camera equipment and the supervisory control system of face recognition comparison function |
| CN204859420U (en) * | 2015-08-19 | 2015-12-09 | 江苏联禹智能工程有限公司 | Intelligent building video monitor system |
| CN105243160A (en) * | 2015-10-28 | 2016-01-13 | 西安美林数据技术股份有限公司 | Mass data-based distributed video processing system |
| CN105357475A (en) * | 2015-10-28 | 2016-02-24 | 小米科技有限责任公司 | Video playing method and device |
| CN105373626A (en) * | 2015-12-09 | 2016-03-02 | 深圳融合永道科技有限公司 | Distributed face recognition track search system and method |
| CN205566477U (en) * | 2016-02-17 | 2016-09-07 | 成都理工大学 | Low -power consumption people face watch -dog |
| CN106060442A (en) * | 2016-05-20 | 2016-10-26 | 浙江宇视科技有限公司 | Video storage method, device and system |
-
2016
- 2016-11-19 CN CN201611035754.6A patent/CN106709424B/en active Active
Patent Citations (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040183951A1 (en) * | 2003-03-06 | 2004-09-23 | Lee Hyeok-Beom | Image-detectable monitoring system and method for using the same |
| JP2007300456A (en) * | 2006-05-01 | 2007-11-15 | Nippon Telegr & Teleph Corp <Ntt> | Video monitoring system and its index generation method |
| CN101299812A (en) * | 2008-06-25 | 2008-11-05 | 北京中星微电子有限公司 | Method, system for analyzing, storing video as well as method, system for searching video |
| CN101763388A (en) * | 2008-12-25 | 2010-06-30 | 北京中星微电子有限公司 | Method for searching video, system therefor and device therefor as well as video storing method and system thereof |
| CN101505412A (en) * | 2009-03-11 | 2009-08-12 | 上海伯里春贸易有限公司 | Human face collecting identification monitoring system and method for hotel, office building and public place for entertainment |
| CN101546377A (en) * | 2009-04-28 | 2009-09-30 | 上海银晨智能识别科技有限公司 | Human face image capture system and human face image capture method |
| CN102170563A (en) * | 2011-03-24 | 2011-08-31 | 杭州海康威视软件有限公司 | Intelligent person capture system and person monitoring management method |
| CN102609729A (en) * | 2012-02-14 | 2012-07-25 | 中国船舶重工集团公司第七二六研究所 | Method and system for recognizing faces shot by multiple cameras |
| CN102665054A (en) * | 2012-05-10 | 2012-09-12 | 江苏友上科技实业有限公司 | Network video recorder system for fast face retrieval |
| CN102929903A (en) * | 2012-07-04 | 2013-02-13 | 北京中盾安全技术开发公司 | Rapid video retrieval method based on layered structuralized description of video information |
| CN102799877A (en) * | 2012-09-11 | 2012-11-28 | 上海中原电子技术工程有限公司 | Method and system for screening face images |
| CN103258028A (en) * | 2013-05-08 | 2013-08-21 | 林凡 | Video hierarchical and partitioned storage system based on content features |
| CN104239881A (en) * | 2013-06-08 | 2014-12-24 | 杭州海康威视数字技术股份有限公司 | Method and system for automatically finding and registering target in surveillance video |
| CN103530652A (en) * | 2013-10-23 | 2014-01-22 | 北京中视广信科技有限公司 | Face clustering based video categorization method and retrieval method as well as systems thereof |
| CN204156985U (en) * | 2014-08-29 | 2015-02-11 | 上海智达商投资管理合伙企业(有限合伙) | There is high-definition camera equipment and the supervisory control system of face recognition comparison function |
| CN204859420U (en) * | 2015-08-19 | 2015-12-09 | 江苏联禹智能工程有限公司 | Intelligent building video monitor system |
| CN105243160A (en) * | 2015-10-28 | 2016-01-13 | 西安美林数据技术股份有限公司 | Mass data-based distributed video processing system |
| CN105357475A (en) * | 2015-10-28 | 2016-02-24 | 小米科技有限责任公司 | Video playing method and device |
| CN105373626A (en) * | 2015-12-09 | 2016-03-02 | 深圳融合永道科技有限公司 | Distributed face recognition track search system and method |
| CN205566477U (en) * | 2016-02-17 | 2016-09-07 | 成都理工大学 | Low -power consumption people face watch -dog |
| CN106060442A (en) * | 2016-05-20 | 2016-10-26 | 浙江宇视科技有限公司 | Video storage method, device and system |
Non-Patent Citations (4)
| Title |
|---|
| MANEESH UPMANYU 等: "Efficient privacy preserving video surveillance", 《2009 IEEE 12TH INTERNATIONAL CONFERENCE ON COMPUTER VISION》 * |
| YAN LI 等: "Face Video Retrieval with Image Query via Hashing across Euclidean Space and Riemannian Manifold", 《CVPR 2015》 * |
| 无: "智能化人脸检测存储 全球互联网即时访问——杭州智诺ZN-DVR6104系列嵌入式人脸检测硬盘录像机评测", 《中国公共安全》 * |
| 杨强 等: "视频检索技术中"人物"语义的提取方法", 《苏州科技学院学报(工程技术版)》 * |
Cited By (28)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108881816A (en) * | 2017-10-12 | 2018-11-23 | 北京旷视科技有限公司 | Generation method, device and the computer storage medium of video file |
| CN108875512A (en) * | 2017-12-05 | 2018-11-23 | 北京旷视科技有限公司 | Face identification method, device, system, storage medium and electronic equipment |
| CN111295875A (en) * | 2018-05-07 | 2020-06-16 | 合刃科技（武汉）有限公司 | Shooting control method and electronic device |
| CN108733819B (en) * | 2018-05-22 | 2021-07-06 | 深圳云天励飞技术有限公司 | Personnel archive establishing method and device |
| CN108733819A (en) * | 2018-05-22 | 2018-11-02 | 深圳云天励飞技术有限公司 | A kind of personnel's archives method for building up and device |
| CN109241378A (en) * | 2018-08-29 | 2019-01-18 | 北京旷视科技有限公司 | Archives method for building up, device, equipment and storage medium |
| CN109241299A (en) * | 2018-09-25 | 2019-01-18 | 腾讯科技（深圳）有限公司 | Multimedia resource searching method, device, storage medium and equipment |
| CN111385440A (en) * | 2018-12-27 | 2020-07-07 | 芜湖潜思智能科技有限公司 | Monitoring camera with face recording and inquiring functions |
| CN109815371A (en) * | 2019-01-30 | 2019-05-28 | 无锡华云数据技术服务有限公司 | Video monitoring data stores access system |
| CN110263704A (en) * | 2019-06-18 | 2019-09-20 | 浙江宇视科技有限公司 | Human face data acquisition method, device, server, video collector and medium |
| CN110263704B (en) * | 2019-06-18 | 2021-07-20 | 浙江宇视科技有限公司 | Face data acquisition method, device, server, video acquisition device and medium |
| CN110267007A (en) * | 2019-06-28 | 2019-09-20 | Oppo广东移动通信有限公司 | Image processing method, device, server and storage medium |
| CN110266953B (en) * | 2019-06-28 | 2021-05-07 | Oppo广东移动通信有限公司 | Image processing method, image processing apparatus, server, and storage medium |
| CN110266953A (en) * | 2019-06-28 | 2019-09-20 | Oppo广东移动通信有限公司 | Image processing method, device, server and storage medium |
| CN110866491A (en) * | 2019-11-13 | 2020-03-06 | 腾讯科技（深圳）有限公司 | Target retrieval method, device, computer readable storage medium and computer equipment |
| CN110866491B (en) * | 2019-11-13 | 2023-11-24 | 腾讯科技（深圳）有限公司 | Target retrieval method, apparatus, computer-readable storage medium, and computer device |
| CN111414517A (en) * | 2020-03-26 | 2020-07-14 | 成都市喜爱科技有限公司 | Video face analysis method and device and server |
| CN111414517B (en) * | 2020-03-26 | 2023-05-19 | 成都市喜爱科技有限公司 | Video face analysis method, device and server |
| CN111723242A (en) * | 2020-05-21 | 2020-09-29 | 深圳信息职业技术学院 | Customer portrait drawing method, customer portrait drawing device, terminal equipment and medium |
| CN111831742A (en) * | 2020-05-25 | 2020-10-27 | 佛山市华全电气照明有限公司 | Smart city video positioning method and system |
| CN112597961A (en) * | 2020-12-30 | 2021-04-02 | 上海大学 | Interest target extraction method and system based on big data |
| CN113098642B (en) * | 2021-04-22 | 2023-05-09 | 浙江万里学院 | Logistics management method based on Beidou satellite positioning technology |
| CN113098642A (en) * | 2021-04-22 | 2021-07-09 | 浙江万里学院 | Logistics management method based on Beidou satellite positioning technology |
| CN113343842A (en) * | 2021-06-04 | 2021-09-03 | 中山大学 | Self-adaptive face recognition method |
| CN113779309A (en) * | 2021-09-01 | 2021-12-10 | 杭州视洞科技有限公司 | Video screening method based on face recognition |
| CN114333119A (en) * | 2021-12-31 | 2022-04-12 | 上海商汤临港智能科技有限公司 | Vehicle unlocking method, vehicle management method, terminal, vehicle unlocking system, vehicle unlocking device, and storage medium |
| CN117111858A (en) * | 2023-10-23 | 2023-11-24 | 深圳萨尔浒网络科技有限公司 | Computer file data matching system |
| CN117111858B (en) * | 2023-10-23 | 2024-04-02 | 深圳萨尔浒网络科技有限公司 | Computer file data matching system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106709424B (en) | 2022-11-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106709424A (en) | Optimized surveillance video storage system and equipment | |
| CN105488478B (en) | Face recognition system and method | |
| CN107292240B (en) | Person finding method and system based on face and body recognition | |
| CN109284729B (en) | Method, device and medium for acquiring face recognition model training data based on video | |
| US9176987B1 (en) | Automatic face annotation method and system | |
| CN105279480A (en) | Method of video analysis | |
| CN105631430A (en) | Matching method and apparatus for face image | |
| CN110532970B (en) | Age and gender attribute analysis method, system, equipment and medium for 2D images of human faces | |
| CN101300588A (en) | Determining a particular person from a collection | |
| US20150055879A1 (en) | Method, Server and System for Setting Background Image | |
| JPWO2018180588A1 (en) | Face image matching system and face image search system | |
| US10037467B2 (en) | Information processing system | |
| CN101976356A (en) | Face identification method for surfing identification policy, and identification system thereof | |
| CN105659279B (en) | Information processing apparatus, information processing method, and computer program | |
| CN102486793A (en) | Method and system for searching target user | |
| US20130266194A1 (en) | System and method for associating a photo with a data structure node | |
| CN110827432B (en) | Class attendance checking method and system based on face recognition | |
| EP3573327B1 (en) | Method and device for displaying target object | |
| CN103258222A (en) | Cell intelligent logistic management system | |
| CN106713859A (en) | Image visual monitoring search system and search method thereof | |
| CN109359689B (en) | Data identification method and device | |
| US11244185B2 (en) | Image search device, image search system, and image search method | |
| WO2023093241A1 (en) | Pedestrian re-identification method and apparatus, and storage medium | |
| CN106485221A (en) | A kind of method that benchmark photograph is replaced automatically according to similar concentration degree | |
| Yadav et al. | Attendance Management System Based on Face Recognition Using Haar-Cascade |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20180702 Address after: 519085 the E3 unit of the second level nursery of A plant, No. 1, Port Road, Tangjia Bay, Zhuhai high tech Zone, Guangdong. Applicant after: Guangdong Zhongke human intelligence technology Co.,Ltd. Address before: No. 1, No. 19 Building, jasmine garden, A-1416, northwest of Haidian District, Beijing. Applicant before: BEIJING ZHONGKE AIR-WORLD TECHNOLOGY CO.,LTD. |
|
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |