CN108509657A - Data distribute store method, equipment and computer readable storage medium - Google Patents
Data distribute store method, equipment and computer readable storage medium Download PDFInfo
- Publication number
- CN108509657A CN108509657A CN201810399032.1A CN201810399032A CN108509657A CN 108509657 A CN108509657 A CN 108509657A CN 201810399032 A CN201810399032 A CN 201810399032A CN 108509657 A CN108509657 A CN 108509657A
- Authority
- CN
- China
- Prior art keywords
- user
- user images
- images
- similarity
- image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/46—Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]; Salient regional features
- G06V10/462—Salient features, e.g. scale invariant feature transforms [SIFT]
-
- 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
-
- 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
- G06V40/172—Classification, e.g. identification
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Multimedia (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Human Computer Interaction (AREA)
- General Health & Medical Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a kind of data to distribute store method, including:Receive user images, the acquisition time of user images and the present position of corresponding image capture device;The user images received are subjected to similarity analysis processing, obtain the similarity between user images;Judge whether the corresponding user of each user images is same user according to the similarity between user images;If the corresponding user of each user images is same user, according to the correspondence acquisition time of each user images of same user, the present position of the corresponding image capture device of each user images builds the movement track of user;The user images as preservation are selected from the user images of same user, and the image selected and corresponding user trajectory are preserved.It is distributed the invention also discloses a kind of data and preserves equipment and readable storage medium storing program for executing.The present invention can be obtained an equitable breakdown and managed using user data, reduce memory space, convenient for inquiry user data and user trajectory.
Description
Technical field
The present invention relates to data preservation field more particularly to a kind of data distribution store method, equipment and computer-readable
Storage medium.
Background technology
With the development of society, in order to ensure the personal safety of people, maintain social stability and harmony, in public places cloth
The monitoring device set is more and more.
Currently, for the collected video of monitoring device or image, carried out generally by fixed cloud database
It preserves, or is stored in the local data base of monitoring device, but since some monitoring devices need 24 hours uninterrupted samplings,
Collected video or image are more, and database needs to preserve all data, and data volume is huge, therefore, by collected number
According to cloud database or local data base is all stored in, it is be easy to cause database corruption, and in subsequent query data, no
Convenient for inquiry, and the image preserved by single monitoring device, it can not know the movement track of user.
Invention content
It is a primary object of the present invention to propose that a kind of data distribute store method, equipment and computer-readable storage medium
Matter, it is intended to solve existing data save method, database corruption can be caused, be not easy to inquire, can not know the action of user
The technical issues of track.
To achieve the above object, the present invention provides a kind of data distribution store method, the method includes:
Receive user images, the acquisition time of the user images and the present position of corresponding image capture device;
The user images received are subjected to similarity analysis processing, obtain the similarity between user images;
Judge whether the corresponding user of each user images is same user according to the similarity between user images;
If the corresponding user of each user images is same user, according to the correspondence of each user images of same user
The present position of acquisition time and the corresponding image capture device of each user images, builds the movement track of user;
The user images as preservation are selected from the user images of same user, by the image selected and corresponding use
Family track is preserved.
Optionally, the correspondence acquisition time of each user images according to same user and each user images
The step of present position of corresponding image capture device, the movement track for building user includes:
The correspondence acquisition time of each user images of same user is extracted, and the acquisition time extracted is arranged
Sequence;
According to the sequence priority of acquisition time, the present position of the corresponding image capture device of user images is ranked up
It integrates, builds the movement track of user.
Optionally, the step of user images selected from the user images of same user as preservation include:
The quantity of the image characteristic point of user images is obtained, and the quantity of the image characteristic point of the user images is carried out
Sequence;
The user images as preservation are selected according to the quantity of the image characteristic point of user images sequence size.
Optionally, the phase that similarity analysis processing is carried out to collected user images, obtains between user images
The step of seemingly spending include:
Extract the face image feature of the user images;
The face image feature of each user images is compared, calculate each user images face image it
Between similarity;
Whether the similarity for detecting the face image of each user images is more than second threshold;
If the similarity is more than the second threshold, confirm that the user images corresponding to the similarity correspond to user
For same user.
Optionally, the step of face image feature of the extraction user includes:
Key feature point is carried out to the face image of the user;
The face image of the user is divided into several human face regions according to key feature point result;
Feature extraction is carried out to the human face region using the corresponding depth network model of the human face region;
The feature extracted from each human face region is recombinated, the image of the face image of the user images is obtained
Feature.
In addition, to achieve the above object, the present invention also provides a kind of data to distribute preservation equipment, the data distribution preserves
Equipment includes data distribution save routine, and the data distribution save routine is distributed to preserve when equipment executes by the data and be realized
The step of data distribution store method as described above.
In addition, to achieve the above object, it is described computer-readable the present invention also provides a kind of computer readable storage medium
Data distribution save routine is stored on storage medium, the data distribution save routine realizes institute as above when being executed by processor
The step of data distribution store method stated.
Data distribution store method, equipment and computer readable storage medium proposed by the present invention, by receiving user's figure
The present position of picture, the acquisition time of the user images and corresponding image capture device;By the user images received into
The processing of row similarity analysis, obtains the similarity between user images;Judge each use according to the similarity between user images
Whether image corresponding user in family is same user;If the corresponding user of each user images is same user, according to same
The correspondence acquisition time of each user images of user and the residing position of the corresponding image capture device of each user images
It sets, builds the movement track of user;The user images as preservation are selected from the user images of same user, the figure that will be selected
Picture and corresponding user trajectory are preserved, by the above-mentioned means, so that data are obtained an equitable breakdown and managed, convenient for inquiry
User data and user movement track, and collected all image datas need not be preserved, it is empty to reduce storage
Between.
Description of the drawings
Fig. 1 is the flow diagram that data of the present invention distribute store method first embodiment;
Fig. 2 is that data of the present invention are distributed in store method second embodiment to collected user images progress similarity point
Analysis handle, obtain user images between similarity the step of refinement flow diagram;
Fig. 3 is that data of the present invention distribute in store method 3rd embodiment the people for being more than first threshold using recognition accuracy
Face recognizer extracts the refinement flow diagram of the step of face image feature of the user;
Fig. 4 is pair that data of the present invention distribute each user images according to same user in store method fourth embodiment
The present position for answering acquisition time and the corresponding image capture device of each user images, builds the movement track of user
The refinement flow diagram of step;
Fig. 5 is to select conduct from the user images of same user in data of the present invention distribution the 5th embodiment of store method
The refinement flow diagram of the step of user images of preservation;
Fig. 6 is the device structure schematic diagram for the hardware running environment that the embodiment of the present invention is related to.
The embodiments will be further described with reference to the accompanying drawings for the realization, the function and the advantages of the object of the present invention.
Specific implementation mode
It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, it is not intended to limit the present invention.
The primary solutions of the embodiment of the present invention are:By the acquisition time for receiving user images, the user images
And the present position of corresponding image capture device;The user images received are subjected to similarity analysis processing, obtain user
Similarity between image;Judge whether the corresponding user of each user images is same according to the similarity between user images
User;If the corresponding user of each user images is same user, adopted according to the correspondence of each user images of same user
The present position for collecting time and the corresponding image capture device of each user images, builds the movement track of user;From same
The user images as preservation are selected in the user images of user, and the image selected and corresponding user trajectory are protected
It deposits, by the above-mentioned means, so that data are obtained an equitable breakdown and are managed, convenient for inquiry user data and user movement track,
And collected all image datas need not be preserved, reduce memory space.
The embodiment of the present invention is it is considered that currently, for the collected video of monitoring device or image, generally by solid
Fixed cloud database is preserved, or is stored in the local data base of monitoring device, but since some monitoring devices need
24 hours uninterrupted samplings are wanted, collected video or image are more, and database needs to preserve all data, and data volume is huge
Greatly, therefore, collected data are all stored in cloud database or local data base, be easy to cause database corruption, and
And it in subsequent query data, is not easy to inquire.
For this purpose, the embodiment of the present invention proposes that a kind of data distribute store method, by receiving user images, the user schemes
The present position of the acquisition time of picture and corresponding image capture device;The user images received are carried out at similarity analysis
Reason obtains the similarity between user images;Judge the corresponding use of each user images according to the similarity between user images
Whether family is same user;If the corresponding user of each user images is same user, according to each user of same user
The correspondence acquisition time of image and the present position of the corresponding image capture device of each user images, build the row of user
Dynamic rail mark;The user images as preservation are selected from the user images of same user, by the image selected and corresponding use
Family track is preserved, by the above-mentioned means, so that data are obtained an equitable breakdown and managed, convenient for inquiry user data and use
Family movement track, and collected all image datas need not be preserved, reduce memory space.
The present invention provides a kind of data distribution store method.
Referring to Fig.1, Fig. 1 is the flow diagram that data of the present invention distribute store method first embodiment.
In the present embodiment, this method includes:
Step S100 receives user images, the acquisition time of the user images and the institute of corresponding image capture device
Locate position;
The user images received are carried out similarity analysis processing by step S200, similar between acquisition user images
Degree;
In the present embodiment, user images, the acquisition time of the user images and corresponding figure are received by database
As the present position of collecting device, after receive the user images that each image capture device is sent, i.e., to receiving
User images carry out similarity analysis, and specifically, the face recognition algorithms for using recognition accuracy to be more than first threshold first carry
Take the face image feature of the user images;Then the face image feature of each user images is compared, calculates institute
State the similarity between the face image of each user images;It can be obtained the similarity between user images.
Step S300 judges whether the corresponding user of each user images is same according to the similarity between user images
User;
After obtaining user images similarity, you can judge each user images according to the similarity between user images
Whether corresponding user is same user;Specifically, whether the similarity for detecting the face image of each user images is big
In second threshold;If the similarity is more than the second threshold, confirm that the user images corresponding to the similarity correspond to
User is same user.
Step S400, if the corresponding user of each user images is same user, according to each user of same user
The correspondence acquisition time of image and the present position of the corresponding image capture device of each user images, build the row of user
Dynamic rail mark;
If the corresponding user of each user images is same user, according to the correspondence of each user images of same user
The present position of acquisition time and the corresponding image capture device of each user images, builds the movement track of user, specifically
The correspondence acquisition time of each user images of same user is extracted, and the acquisition time extracted is ranked up in ground;Then
According to the sequence priority of acquisition time, the present position of the corresponding image capture device of user images is ranked up integration, structure
Build the movement track of user.
Step S500 selects the user images as preservation from the user images of same user, by the image selected with
And corresponding user trajectory is preserved.
The user images as preservation are selected from the user images of same user, by the image selected and corresponding use
Family track is preserved, and can specifically be selected as preservation according to the clarity of user images or the quantity of characteristic point
Image, when the quantity of the characteristic point of user images is selected the image as preservation, first obtain user images figure
It is ranked up as the quantity of characteristic point, and by the quantity of the image characteristic point of the user images;According to the user images
The most preceding user images of the image characteristic point quantity sequence of user images are selected conduct by the quantity sequence size of image characteristic point
The user images of preservation.
The present embodiment propose data distribute store method, by receive user images, the user images acquisition when
Between and corresponding image capture device present position;The user images received are subjected to similarity analysis processing, are used
Similarity between the image of family;Then whether the corresponding user of each user images is judged according to the similarity between user images
For same user;If the corresponding user of each user images is same user, according to each user images of same user
The present position of corresponding acquisition time and the corresponding image capture device of each user images, builds the movement track of user,
The movement track of user is can be obtained, consequently facilitating being monitored to the movement track of user in public places;Again from same use
The user images as preservation are selected in the user images at family, and the image selected and corresponding user trajectory are preserved,
Without being preserved to collected all image datas, memory space is reduced.
Further, with reference to Fig. 2, data point of the present invention are proposed based on data of the present invention distribution store method first embodiment
With store method second embodiment.
In the present embodiment, the step S400 includes:
Step S410, extracts the correspondence acquisition time of each user images of same user, and will extract acquisition when
Between be ranked up;
Step S420, according to the sequence priority of acquisition time, by the residing position of the corresponding image capture device of user images
It sets and is ranked up integration, build the movement track of user.
In the present embodiment, specifically it can build corresponding user's according to the acquisition time of the user images of same user
The corresponding acquisition time of the user images of same user is specifically ranked up by movement track according to the priority of acquisition time,
Then the image capture device of corresponding user images is extracted according to sequence, and is ranked up according to each Image Acquisition present position
It integrates, for example assumes that the collected corresponding image capture devices of image in 10 points of user morning are in Nanshan District, 11 points of user morning
The collected corresponding image capture device of image is in Baoan District, then can be integrated position according to acquisition time, can be with
Know that the movement track of user is from Nanshan District to Baoan District.
Further, with reference to Fig. 3, data point of the present invention are proposed based on data of the present invention distribution store method first embodiment
With store method 3rd embodiment.
In the present embodiment, the step S500 includes:
Step S510, obtains the quantity of the image characteristic point of user images, and by the image characteristic point of the user images
Quantity be ranked up;
Step S520 selects the user as preservation according to the quantity of the image characteristic point of user images sequence size
Image.
In the present embodiment, specifically the user as preservation can be selected according to the quantity of user images characteristic point
Specifically the face that the user images are extracted in recognition accuracy more than the face recognition algorithms of first threshold may be used in image
Portion's characteristics of image;For example combine bayesian algorithm, you can the quantity of the image characteristic point of user images is obtained, then by the use
The quantity of the image characteristic point of family image is ranked up, such as positive sequence sequence;According to the image characteristic point of the user images
Quantity sequence size selects the user images as preservation, specifically can be last by sequence when sort method is positive sequence, i.e., special
The most user images of sign point quantity are as the user images preserved.
Further, with reference to Fig. 4, data point of the present invention are proposed based on data of the present invention distribution store method first embodiment
With store method fourth embodiment.
In the present embodiment, the step S200 includes:
Step S210 extracts the face image feature of the user images;
Step S220 compares the face image feature of each user images, calculates each user images
Similarity between face image;
Whether step S230, the similarity for detecting the face image of each user images are more than second threshold;
Step S240 confirms user's figure corresponding to the similarity if the similarity is more than the second threshold
As corresponding user is same user.
In the present embodiment, the characteristics of image that specifically can extract the face image of user by combining bayesian algorithm,
Then the characteristics of image of the face image of the user extracted is matched, calculates separately the phase between the face image of user
Like degree;The similarity between user images is can be obtained, it is possible to further continue the face image that user is calculated in detection
Between similarity whether have more than second threshold, if detect the face image of user similarity be more than second threshold face
Portion's image then confirms that the user images that similarity is more than second threshold are the image of same user.
Further, with reference to Fig. 5, data point of the present invention are proposed based on data of the present invention distribution store method fourth embodiment
With the 5th embodiment of store method.
In the present embodiment, the step S210 includes:
Step S211 carries out key feature point to the face image of the user;
The face image of the user is divided into several face areas by step S212 according to key feature point result
Domain;
Step S213 carries out feature to the human face region using the corresponding depth network model of the human face region and carries
It takes;
Step S214 recombinates the feature extracted from each human face region, obtains the face of the user images
The characteristics of image of image.
In the present embodiment, key feature point is carried out to the face image of user first, it is fixed according to key feature points
The face image of user is divided into several human face regions by position result, for each human face region, using the human face region
Corresponding depth network carries out feature extraction to the human face region, and the feature extracted from each human face region is then carried out weight
Group, you can the characteristics of image of the facial image for the user that obtains registering.Key feature points in facial image refer in face such as
The characteristic point at the centers of eyes, nose, the both sides corners of the mouth etc.Positioning feature point result can be used characteristic point vector and be indicated,
Characteristic point vector includes the coordinate of each characteristic point.For each different human face region, corresponding depth is respectively trained in advance
Spend network model.Depth volume can be used for extracting characteristics of image, depth network model from human face region in depth network model
Product neural network Convolutional Neural Networks, CNNs).In embodiments of the present invention, using based on depth
The face recognition algorithms of habit obtain the characteristics of image of facial image, compared to other face recognition algorithms, recognition accuracy higher.
In addition, being directed to different human face regions (such as ocular, nasal area, mouth region), corresponding depth is respectively trained
Network model is spent, and feature extraction is carried out using corresponding depth network model, substantially ensures the accuracy of feature extraction.
The data that the present embodiment proposes distribute store method, and it is fixed to carry out characteristic point to the face image of the user first
Position;Then the face image of the user is divided by several human face regions according to positioning feature point result;It uses again described
The corresponding depth network model of human face region carries out feature extraction to the human face region;The spy that will be extracted from each human face region
Sign is recombinated, you can obtains the characteristics of image of the face image of the user that registers, it is ensured that the accuracy of feature extraction.
The embodiment of the present invention further provides for a kind of data distribution preservation equipment.
With reference to Fig. 6, Fig. 6 is the device structure schematic diagram for the hardware running environment that the embodiment of the present invention is related to.
As shown in fig. 6, data distribution preservation equipment may include:Processor 1001, such as CPU, network interface 1002,
User interface 1003, memory 1004.Connection communication between these components can be realized by communication bus.Network interface
1002 may include optionally wireline interface (for connecting cable network), wireless interface (such as WI-FI interfaces, the bluetooth of standard
Interface, infrared interface etc., for connecting wireless network).User interface 1003 may include display screen (Display), input
Unit such as keyboard (Keyboard), optional user interface 1003 can also include the wireline interface of standard (such as connecting
Wired keyboard, wire mouse etc.) and/or wireless interface (such as connecting Wireless Keyboard, wireless mouse).Memory 1004 can
Can also be stable memory (non-volatile memory), such as magnetic disk storage to be high-speed RAM memory.It deposits
Reservoir 1004 optionally can also be the storage device independently of aforementioned processor 1001.
Optionally, it can also include camera, RF (Radio Frequency, radio frequency) electricity that data distribution, which preserves equipment,
Road, sensor, voicefrequency circuit, WiFi module etc..
It will be understood by those skilled in the art that data distribution shown in figure preserves device structure not structure paired data point
May include either combining certain components or different portions than illustrating more or fewer components with the restriction for preserving equipment
Part is arranged.
As shown in fig. 6, as may include that operating system, network are logical in a kind of memory 1004 of computer storage media
Believe that module, Subscriber Interface Module SIM and data distribute save routine.Wherein, operating system is that management and control data distribution preserve
The program of device hardware and software resource, support network communication module, Subscriber Interface Module SIM, data distribution save routine and its
The operation of his program or software;Network communication module is for managing and controlling network interface 1002;Subscriber Interface Module SIM is for managing
Reason and control user interface 1003.
Data distribution shown in Fig. 6 preserves in equipment, and network interface 1002 is mainly used for connecting database, with database
Into row data communication;User interface 1003 is mainly used for connecting client (can be understood as user terminal), with client into line number
According to communication, information is such as shown to client by window, or receives the operation information that client is sent;And processor 1001 can
Save routine is distributed for executing the data stored in memory 1004, to realize following steps:
Receive user images, the acquisition time of the user images and the present position of corresponding image capture device;
The user images received are subjected to similarity analysis processing, obtain the similarity between user images;
Judge whether the corresponding user of each user images is same user according to the similarity between user images;
If the corresponding user of each user images is same user, according to the correspondence of each user images of same user
The present position of acquisition time and the corresponding image capture device of each user images, builds the movement track of user;
The user images as preservation are selected from the user images of same user, by the image selected and corresponding use
Family track is preserved.
Further, the processor 1001 is additionally operable to execute the data distribution save routine stored in memory 1004,
To realize following steps:
The correspondence acquisition time of each user images of same user is extracted, and the acquisition time extracted is arranged
Sequence;
According to the sequence priority of acquisition time, the present position of the corresponding image capture device of user images is ranked up
It integrates, builds the movement track of user.
Further, the processor 1001 is additionally operable to execute the data distribution save routine stored in memory 1004,
To realize following steps:
The quantity of the image characteristic point of user images is obtained, and the quantity of the image characteristic point of the user images is carried out
Sequence;
The user images as preservation are selected according to the quantity of the image characteristic point of user images sequence size.
Further, the processor 1001 is additionally operable to execute the data distribution save routine stored in memory 1004,
To realize following steps:
Extract the face image feature of the user images;
The face image feature of each user images is compared, calculate each user images face image it
Between similarity;
Whether the similarity for detecting the face image of each user images is more than second threshold;
If the similarity is more than the second threshold, confirm that the user images corresponding to the similarity correspond to user
For same user.
Further, the processor 1001 is additionally operable to execute the data distribution save routine stored in memory 1004,
To realize following steps:
Key feature point is carried out to the face image of the user;
The face image of the user is divided into several human face regions according to key feature point result;
Feature extraction is carried out to the human face region using the corresponding depth network model of the human face region;
The feature extracted from each human face region is recombinated, the image of the face image of the user images is obtained
Feature.
The specific embodiment and above-mentioned data distribution each embodiment of store method of data distribution preservation equipment of the present invention are basic
Identical, therefore not to repeat here.
The present invention also provides a kind of computer readable storage medium, there are one the computer-readable recording medium storages
Or multiple programs, one or more of programs can be executed by one or more processor, to realize following steps:
Receive user images, the acquisition time of the user images and the present position of corresponding image capture device;
The user images received are subjected to similarity analysis processing, obtain the similarity between user images;
Judge whether the corresponding user of each user images is same user according to the similarity between user images;
If the corresponding user of each user images is same user, according to the correspondence of each user images of same user
The present position of acquisition time and the corresponding image capture device of each user images, builds the movement track of user;
The user images as preservation are selected from the user images of same user, by the image selected and corresponding use
Family track is preserved.
Further, one or more of programs can be executed by one or more of processors, also realize with
Lower step:
The correspondence acquisition time of each user images of same user is extracted, and the acquisition time extracted is arranged
Sequence;
According to the sequence priority of acquisition time, the present position of the corresponding image capture device of user images is ranked up
It integrates, builds the movement track of user.
Further, one or more of programs can be executed by one or more of processors, also realize with
Lower step:
The quantity of the image characteristic point of user images is obtained, and the quantity of the image characteristic point of the user images is carried out
Sequence;
The user images as preservation are selected according to the quantity of the image characteristic point of user images sequence size.
Further, one or more of programs can be executed by one or more of processors, also realize with
Lower step:
Extract the face image feature of the user images;
The face image feature of each user images is compared, calculate each user images face image it
Between similarity;
Whether the similarity for detecting the face image of each user images is more than second threshold;
If the similarity is more than the second threshold, confirm that the user images corresponding to the similarity correspond to user
For same user.
Further, one or more of programs can be executed by one or more of processors, also realize with
Lower step:
Key feature point is carried out to the face image of the user;
The face image of the user is divided into several human face regions according to key feature point result;
Feature extraction is carried out to the human face region using the corresponding depth network model of the human face region;
The feature extracted from each human face region is recombinated, the image of the face image of the user images is obtained
Feature.
The specific embodiment of computer readable storage medium of the present invention is distributed with above-mentioned data distribution store method and data
Preservation each embodiment of equipment is essentially identical, and therefore not to repeat here.
It should also be noted that, herein, the terms "include", "comprise" or its any other variant are intended to non-
It is exclusive to include, so that process, method, article or device including a series of elements include not only those elements,
But also include other elements that are not explicitly listed, or further include solid by this process, method, article or device
Some elements.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that including
There is also other identical elements in the process of the element, method, article or device.
Through the above description of the embodiments, those skilled in the art can be understood that above-described embodiment side
Method can add the mode of required general hardware platform to realize by software, naturally it is also possible to by hardware, but in many cases
The former is more preferably embodiment.Based on this understanding, technical scheme of the present invention substantially in other words does the prior art
Going out the part of contribution can be expressed in the form of software products, which is stored in a storage medium
In (such as ROM/RAM, magnetic disc, CD), including some instructions are used so that a station terminal equipment (can be mobile phone, computer, clothes
Be engaged in device, air conditioner or the network equipment etc.) method that executes each embodiment of the present invention.
It these are only the preferred embodiment of the present invention, be not intended to limit the scope of the invention, it is every to utilize this hair
Equivalent structure or equivalent flow shift made by bright specification and accompanying drawing content is applied directly or indirectly in other relevant skills
Art field, is included within the scope of the present invention.
Claims (10)
1. a kind of data distribute store method, which is characterized in that the described method comprises the following steps:
Receive user images, the acquisition time of the user images and the present position of corresponding image capture device;
The user images received are subjected to similarity analysis processing, obtain the similarity between user images;
Judge whether the corresponding user of each user images is same user according to the similarity between user images;
If the corresponding user of each user images is same user, corresponding according to each user images of same user acquires
The present position of time and the corresponding image capture device of each user images, builds the movement track of user;
The user images as preservation are selected from the user images of same user, by the image selected and corresponding user's rail
Mark is preserved.
2. data as described in claim 1 distribute store method, which is characterized in that each user according to same user
The correspondence acquisition time of image and the present position of the corresponding image capture device of each user images, build the row of user
The step of dynamic rail mark includes:
The correspondence acquisition time of each user images of same user is extracted, and the acquisition time extracted is ranked up;
According to the sequence priority of acquisition time, the present position of the corresponding image capture device of user images is ranked up whole
It closes, builds the movement track of user.
3. data as described in claim 1 distribute store method, which is characterized in that described from the user images of same user
The step of selecting the user images as preservation include:
The quantity of the image characteristic point of user images is obtained, and the quantity of the image characteristic point of the user images is arranged
Sequence;
The user images as preservation are selected according to the quantity of the image characteristic point of user images sequence size.
4. data as described in claim 1 distribute store method, which is characterized in that described to carry out the user images received
Similarity analysis processing, obtain user images between similarity the step of include:
Extract the face image feature of the user images;
The face image feature of each user images is compared, between the face image for calculating each user images
Similarity;
Whether the similarity for detecting the face image of each user images is more than second threshold;
If the similarity is more than the second threshold, it is same to confirm that the user images corresponding to the similarity correspond to user
One user.
5. data as claimed in claim 4 distribute store method, which is characterized in that the face image of the extraction user
The step of feature includes:
Key feature point is carried out to the face image of the user;
The face image of the user is divided into several human face regions according to key feature point result;
Feature extraction is carried out to the human face region using the corresponding depth network model of the human face region;
The feature extracted from each human face region is recombinated, the image for obtaining the face image of the user images is special
Sign.
6. a kind of distribution of data preserves equipment, which is characterized in that it includes that processor, network connect that the data distribution, which preserves equipment,
Mouthful, user interface and memory, be stored with data distribution save routine in the memory;The processor is described for executing
Data distribute save routine, to realize following steps:
Receive user images, the acquisition time of the user images and the present position of corresponding image capture device;
The user images received are subjected to similarity analysis processing, obtain the similarity between user images;
Judge whether the corresponding user of each user images is same user according to the similarity between user images;
If the corresponding user of each user images is same user, corresponding according to each user images of same user acquires
The present position of time and the corresponding image capture device of each user images, builds the movement track of user;
The user images as preservation are selected from the user images of same user, by the image selected and corresponding user's rail
Mark is preserved.
7. data distribution as claimed in claim 6 preserves equipment, which is characterized in that the processor is additionally operable to execute the number
According to distribution save routine, to realize following steps:
The correspondence acquisition time of each user images of same user is extracted, and the acquisition time extracted is ranked up;
According to the sequence priority of acquisition time, the present position of the corresponding image capture device of user images is ranked up whole
It closes, builds the movement track of user.
8. data distribution as claimed in claim 6 preserves equipment, which is characterized in that the processor is additionally operable to execute the number
According to distribution save routine, to realize following steps:
The quantity of the image characteristic point of user images is obtained, and the quantity of the image characteristic point of the user images is arranged
Sequence;
The user images as preservation are selected according to the quantity of the image characteristic point of user images sequence size.
9. data distribution as claimed in claim 6 preserves equipment, which is characterized in that the processor is additionally operable to execute the number
According to distribution save routine, to realize following steps:
Extract the face image feature of the user images;
The face image feature of each user images is compared, between the face image for calculating each user images
Similarity;
Whether the similarity for detecting the face image of each user images is more than second threshold;
If the similarity is more than the second threshold, it is same to confirm that the user images corresponding to the similarity correspond to user
One user.
10. a kind of computer readable storage medium, which is characterized in that be stored with data point on the computer readable storage medium
With save routine, the data distribution save routine is realized when being executed by processor as described in any one of claim 1 to 5
Data distribute the step of store method.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810399032.1A CN108509657A (en) | 2018-04-27 | 2018-04-27 | Data distribute store method, equipment and computer readable storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810399032.1A CN108509657A (en) | 2018-04-27 | 2018-04-27 | Data distribute store method, equipment and computer readable storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108509657A true CN108509657A (en) | 2018-09-07 |
Family
ID=63399349
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810399032.1A Pending CN108509657A (en) | 2018-04-27 | 2018-04-27 | Data distribute store method, equipment and computer readable storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108509657A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109829355A (en) * | 2018-12-05 | 2019-05-31 | 深圳市北斗智能科技有限公司 | A kind of dynamic trajectory generation method and system, equipment, storage medium |
CN111639689A (en) * | 2020-05-20 | 2020-09-08 | 杭州海康威视系统技术有限公司 | Face data processing method and device and computer readable storage medium |
Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101228555A (en) * | 2005-07-07 | 2008-07-23 | 独创目标实验室公司 | System for 3D monitoring and analysis of motion behavior of targets |
US20080211907A1 (en) * | 2003-06-04 | 2008-09-04 | Model Software Corporation | Video surveillance system |
CN106022220A (en) * | 2016-05-09 | 2016-10-12 | 西安北升信息科技有限公司 | Method for performing multi-face tracking on participating athletes in sports video |
KR101721980B1 (en) * | 2016-08-22 | 2017-03-31 | 정정주 | Method for sharing photo image using time and location information, server and computer-readable recording media using the same |
CN106650652A (en) * | 2016-12-14 | 2017-05-10 | 黄先开 | Trajectory tracking system and method based on face recognition technology |
CN107016374A (en) * | 2017-04-12 | 2017-08-04 | 电子科技大学 | Intelligent Measurement tracking and the generation method of space-time track towards specific objective |
CN107153824A (en) * | 2017-05-22 | 2017-09-12 | 中国人民解放军国防科学技术大学 | Across video pedestrian recognition methods again based on figure cluster |
CN107315755A (en) * | 2016-04-27 | 2017-11-03 | 杭州海康威视数字技术股份有限公司 | The orbit generation method and device of query object |
CN107437075A (en) * | 2017-07-29 | 2017-12-05 | 安徽博威康信息技术有限公司 | A kind of risk alarm system based on daily behavior track |
CN107479703A (en) * | 2017-08-07 | 2017-12-15 | 深圳天珑无线科技有限公司 | Automatic speech gives the correct time method, equipment and computer-readable recording medium |
CN107871111A (en) * | 2016-09-28 | 2018-04-03 | 苏宁云商集团股份有限公司 | A kind of behavior analysis method and system |
-
2018
- 2018-04-27 CN CN201810399032.1A patent/CN108509657A/en active Pending
Patent Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20080211907A1 (en) * | 2003-06-04 | 2008-09-04 | Model Software Corporation | Video surveillance system |
CN101228555A (en) * | 2005-07-07 | 2008-07-23 | 独创目标实验室公司 | System for 3D monitoring and analysis of motion behavior of targets |
CN107315755A (en) * | 2016-04-27 | 2017-11-03 | 杭州海康威视数字技术股份有限公司 | The orbit generation method and device of query object |
CN106022220A (en) * | 2016-05-09 | 2016-10-12 | 西安北升信息科技有限公司 | Method for performing multi-face tracking on participating athletes in sports video |
KR101721980B1 (en) * | 2016-08-22 | 2017-03-31 | 정정주 | Method for sharing photo image using time and location information, server and computer-readable recording media using the same |
CN107871111A (en) * | 2016-09-28 | 2018-04-03 | 苏宁云商集团股份有限公司 | A kind of behavior analysis method and system |
CN106650652A (en) * | 2016-12-14 | 2017-05-10 | 黄先开 | Trajectory tracking system and method based on face recognition technology |
CN107016374A (en) * | 2017-04-12 | 2017-08-04 | 电子科技大学 | Intelligent Measurement tracking and the generation method of space-time track towards specific objective |
CN107153824A (en) * | 2017-05-22 | 2017-09-12 | 中国人民解放军国防科学技术大学 | Across video pedestrian recognition methods again based on figure cluster |
CN107437075A (en) * | 2017-07-29 | 2017-12-05 | 安徽博威康信息技术有限公司 | A kind of risk alarm system based on daily behavior track |
CN107479703A (en) * | 2017-08-07 | 2017-12-15 | 深圳天珑无线科技有限公司 | Automatic speech gives the correct time method, equipment and computer-readable recording medium |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109829355A (en) * | 2018-12-05 | 2019-05-31 | 深圳市北斗智能科技有限公司 | A kind of dynamic trajectory generation method and system, equipment, storage medium |
CN109829355B (en) * | 2018-12-05 | 2023-01-17 | 深圳市北斗智能科技有限公司 | Dynamic track generation method, system, equipment and storage medium |
CN111639689A (en) * | 2020-05-20 | 2020-09-08 | 杭州海康威视系统技术有限公司 | Face data processing method and device and computer readable storage medium |
CN111639689B (en) * | 2020-05-20 | 2023-07-25 | 杭州海康威视系统技术有限公司 | Face data processing method and device and computer readable storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
TWI786313B (en) | Method, device, storage medium, and apparatus of tracking target | |
CN107066983B (en) | Identity verification method and device | |
WO2020199926A1 (en) | Image recognition network model training method, image recognition method and device | |
US9763055B2 (en) | Travel and activity capturing | |
US11501514B2 (en) | Universal object recognition | |
EP3335412B1 (en) | Method and electronic apparatus for providing service associated with image | |
CN106446950B (en) | Image processing method and device | |
CN108304758A (en) | Facial features tracking method and device | |
WO2018120426A1 (en) | Personal health status evaluation method, apparatus and device based on location service, and storage medium | |
US11821742B2 (en) | Travel based notifications | |
CN108764051B (en) | Image processing method and device and mobile terminal | |
CN109063558A (en) | A kind of image classification processing method, mobile terminal and computer readable storage medium | |
WO2020047921A1 (en) | Deep metric learning method based on hierarchical triplet loss function, and apparatus thereof | |
CN114722937A (en) | Abnormal data detection method and device, electronic equipment and storage medium | |
CN110765924A (en) | Living body detection method and device and computer-readable storage medium | |
CN107665232A (en) | Detect the method for similar application and its electronic installation of adaptation | |
CN108509657A (en) | Data distribute store method, equipment and computer readable storage medium | |
US20180276696A1 (en) | Association method, and non-transitory computer-readable storage medium | |
CN103745223A (en) | Face detection method and apparatus | |
WO2015102711A2 (en) | A method and system of enforcing privacy policies for mobile sensory devices | |
KR102617756B1 (en) | Apparatus and Method for Tracking Missing Person based on Attribute | |
JP2019109556A (en) | Identity authentication method using behavior history | |
KR102383284B1 (en) | System for providing business fieldtrip service using metaverse | |
CN111797874A (en) | Behavior prediction method, behavior prediction device, storage medium and electronic equipment | |
CN112995757B (en) | Video clipping method and device |
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: 20180907 |