CN106339428B - Suspect's personal identification method and device based on video big data - Google Patents
Suspect's personal identification method and device based on video big data Download PDFInfo
- Publication number
- CN106339428B CN106339428B CN201610677700.3A CN201610677700A CN106339428B CN 106339428 B CN106339428 B CN 106339428B CN 201610677700 A CN201610677700 A CN 201610677700A CN 106339428 B CN106339428 B CN 106339428B
- Authority
- CN
- China
- Prior art keywords
- suspect
- information
- moving target
- characteristic information
- video
- 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.)
- Active
Links
Classifications
-
- 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
- G06F16/7837—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content using objects detected or recognised in the video content
- G06F16/784—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content using objects detected or recognised in the video content the detected or recognised objects being people
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/20—Movements or behaviour, e.g. gesture recognition
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Library & Information Science (AREA)
- Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Health & Medical Sciences (AREA)
- Psychiatry (AREA)
- Social Psychology (AREA)
- Human Computer Interaction (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Image Analysis (AREA)
Abstract
The present invention provides a kind of suspect's personal identification methods and device based on video big data, comprising: receives suspect's characteristic information that user sends;The moving target that Clustering Retrieval and suspect's characteristic information match from moving target property data base, and extract the corresponding characteristic information of moving target;According to the characteristic information of extraction, the base station data in the corresponding scope of activities of characteristic information is obtained;According to the base station data in the corresponding scope of activities of characteristic information, the suspect's identity information to match with moving target is extracted from identity information stage apparatus;It combines many-sided resource such as resident demographic data in moving target property data base, base station data and identity information stage apparatus to carry out comprehensive collision retrieval, accurate video suspect identity information can be obtained, the accuracy rate and success rate of the identification of suspect's identity information are substantially increased;Also, big data analysis processing technique is used, a large amount of, high speed, changeable complex scene can be handled, timeliness is preferable.
Description
Technical field
The present invention relates to technical field of video processing, in particular to a kind of suspicion person based on video big data
Part recognition methods and device.
Background technique
In recent years, with the reinforcement of ruling by law dynamics, each important common point in China city has been respectively mounted monitoring
Camera, for obtaining the video data in its monitoring range in real time and being stored, to assist the detection case of public security organ
Part, to guarantee the living safety of resident.In society now, the main means of public security organ's clear up a criminal case call place of committing a crime
The video monitoring information of surrounding, and suspect's clue of Related Cases is found and positioned accordingly.And in above-mentioned clear up a criminal case process
In, carrying out identification positioning to the identity information of the suspect in associated video is particularly important.
Currently, relatively advanced video suspect's identity information recognition methods relies on face recognition technology.Above-mentioned face
Identification technology is individual to distinguish organism to the biological characteristic of organism (generally refering in particular to people) itself.Specifically, first determining whether
Then need to calculate position, size and the people of each face if there is face with the presence or absence of face in corresponding monitor video
The location information and characteristic information of each major facial organ in face further extract every then according to the above- mentioned information obtained
The identity characteristic contained in a face finally carries out pre-stored face feature in the identity characteristic of extraction and Relational database pair
Than to identify the corresponding identity information of each face.
But above by the knowledge of recognition of face progress video suspect identity information, method for distinguishing can there are the following problems:
First, due to the shooting angle problem of camera, the collected video data of video monitoring system may not include human face data
(or only including a part of human face data), so that video suspect identity information can not be carried out by above-mentioned face recognition technology
Identification.Second, the shooting location of video monitoring system and video camera clarity, exposure problem all can be to collected faces
The precision of data causes very big deviation.
Summary of the invention
In view of this, the embodiment of the present invention is designed to provide a kind of suspect's identification based on video big data
Method and apparatus, to improve the accuracy of identification of identity information.
In a first aspect, the embodiment of the invention provides a kind of suspect's personal identification method based on video big data, institute
The method of stating includes:
Receive suspect's characteristic information that user sends;Suspect's characteristic information includes at least the following letter of suspect
Breath: activity time range, motion video point information and figure and features characteristic information;
The moving target that Clustering Retrieval and suspect's characteristic information match from moving target property data base, and
Extract the corresponding space-time characteristic information of the moving target;The space-time characteristic information includes at least the following letter of moving target
Breath: activity time and video point information;
According to the space-time characteristic information of the moving target of extraction, the corresponding movable model of the space-time characteristic information is obtained
Enclose interior base station data;
According to the base station data in the corresponding scope of activities of the space-time characteristic information, mentioned from identity information stage apparatus
Take the suspect's identity information to match with the moving target.
With reference to first aspect, the embodiment of the invention provides the first possible embodiments of first aspect, wherein institute
The moving target that Clustering Retrieval and suspect's characteristic information match from moving target property data base is stated, and extracts institute
State the corresponding space-time characteristic information of moving target, comprising:
According to the activity time range of suspect and motion video point information, from the moving target property data base
Load matched moving target characteristic information;
According to the figure and features characteristic information of suspect, matched movement is searched from the moving target characteristic information of load
Target, and determine that the moving target is suspect's target;
Extract the space-time characteristic information of suspect's target.
The possible embodiment of with reference to first aspect the first, the embodiment of the invention provides second of first aspect
Possible embodiment, wherein the space-time characteristic information of the moving target according to extraction obtains the space-time characteristic
Base station data in the corresponding scope of activities of information, comprising:
According to the sequencing of suspect's activity time, the space-time characteristic information of suspect's target of extraction is carried out
Sequence processing, obtains suspect's trace information sample;
According to the corresponding latitude and longitude information of suspect's motion video point information, the suspect track is drawn on map
The corresponding suspect's activity trajectory information of information sample;
According to suspect's activity trajectory information, obtain in the corresponding scope of activities of suspect's activity trajectory information
All base station point information.
The possible embodiment of second with reference to first aspect, the embodiment of the invention provides the third of first aspect
Possible embodiment, wherein the base station data according in the corresponding scope of activities of the space-time characteristic information, from identity
The suspect's identity information to match with the moving target is extracted in information platform device, comprising:
Within the activity time of the suspect, obtains the movement accessed in each described base station point information and set
It is standby;
From all mobile devices of acquisition, the mobile device and the movement for accessing all base station point information are searched
Equipment accesses the turn-on time of each base station point information;
The mobile device to match with suspect's activity trajectory information is filtered out from lookup result;
According to the identification information of the mobile device, it is corresponding that the mobile device is searched in mobile device operator platform
Authentication information;
According to the authentication information, matched suspect's identity information is searched in public security big data platform.
The third possible embodiment with reference to first aspect, the embodiment of the invention provides the 4th kind of first aspect
Possible embodiment, wherein the moving target property data base is established previously according to following methods:
Receive the video data that image acquisition device is sent;
The characteristic information of the moving target and the moving target in each frame video image is extracted respectively;
The characteristic information of the moving target and the moving target is stored in database, the movement mesh is obtained
Mark property data base.
The 4th kind of possible embodiment with reference to first aspect, the embodiment of the invention provides the 5th kind of first aspect
Possible embodiment, wherein the characteristic information by the moving target and the moving target is stored in database
In, comprising:
According to the characteristic information of the moving target, the feature tag for corresponding to each moving target is generated;Institute
It states feature tag to include at least: activity time label, video point information labels and figure and features characteristic information label;
Each feature tag of generation is added in the corresponding moving target;
All moving targets for carrying the feature tag are stored in database.
Second aspect, the embodiment of the invention also provides a kind of suspect's identity recognition device based on video big data,
Described device includes:
First receiving module, for receiving suspect's characteristic information of user's transmission;Suspect's characteristic information is at least
Following information including suspect: activity time range, motion video point information and figure and features characteristic information;
Clustering Retrieval module, for Clustering Retrieval and suspect's characteristic information phase from moving target property data base
Matched moving target, and extract the corresponding space-time characteristic information of the moving target;The space-time characteristic information includes at least
The following information of moving target: activity time and video point information;
Module is obtained, for the space-time characteristic information according to the moving target of extraction, obtains the space-time characteristic letter
Cease the base station data in corresponding scope of activities;
First extraction module, for according to the base station data in the corresponding scope of activities of the space-time characteristic information, from body
The suspect's identity information to match with the moving target is extracted in part information platform device.
In conjunction with second aspect, the embodiment of the invention provides the first possible embodiments of second aspect, wherein institute
State Clustering Retrieval module, comprising:
Loading unit, for the activity time range and motion video point information according to suspect, from the movement mesh
Matched moving target characteristic information is loaded in mark property data base;
Searching unit, for the figure and features characteristic information according to suspect, from the moving target characteristic information of load
Matched moving target is searched, and determines that the moving target is suspect's target;
Extraction unit, for extracting the space-time characteristic information of suspect's target.
In conjunction with the first possible embodiment of second aspect, the embodiment of the invention provides second of second aspect
Possible embodiment, wherein the acquisition module, comprising:
Sequencing unit, for the sequencing according to suspect's activity time, to suspect's target of extraction when
Empty characteristic information is ranked up processing, obtains suspect's trace information sample;
Drawing unit, for being drawn on map according to the corresponding latitude and longitude information of suspect's motion video point information
The corresponding suspect's activity trajectory information of suspect's trace information sample;
First acquisition unit, for obtaining suspect's activity trajectory letter according to suspect's activity trajectory information
Cease all base station point information in corresponding scope of activities.
In conjunction with second of possible embodiment of second aspect, the embodiment of the invention provides the third of second aspect
Possible embodiment, wherein first extraction module, comprising:
Second acquisition unit, within the activity time of the suspect, obtaining each described base station point
The mobile device accessed in information;
First searching unit, for searching the shifting for accessing all base station point information from all mobile devices of acquisition
Dynamic equipment and the mobile device access the turn-on time of each base station point information;
Subelement is screened, for filtering out the movement to match with suspect's activity trajectory information from lookup result
Equipment;
Second searching unit is looked into mobile device operator platform for the identification information according to the mobile device
Look for the corresponding authentication information of the mobile device;
Third searching unit, for searching matched suspicion in public security big data platform according to the authentication information
Doubt people's identity information.
In conjunction with the third possible embodiment of second aspect, the embodiment of the invention provides the 4th kind of second aspect
Possible embodiment, wherein above-mentioned suspect's identity recognition device based on video big data, further includes:
Second receiving module, for receiving the video data of image acquisition device transmission;
Second extraction module, for extracting the spy of moving target and the moving target in each frame video image respectively
Reference breath;
Memory module, for the characteristic information of the moving target and the moving target to be stored in database,
Obtain the moving target property data base.
In conjunction with the 4th kind of possible embodiment of second aspect, the embodiment of the invention provides the 5th kind of second aspect
Possible embodiment, wherein the memory module, comprising:
Generation unit generates for the characteristic information according to the moving target and corresponds to each described moving target
Feature tag;The feature tag includes at least: activity time label, video point information labels and figure and features characteristic information mark
Label;
Adding unit, for each feature tag generated to be added in the corresponding moving target;
Storage unit, for all moving targets for carrying the feature tag to be stored in database.
A kind of suspect's personal identification method and device based on video big data provided in an embodiment of the present invention, comprising:
Receive suspect's characteristic information that user sends;Clustering Retrieval and suspect's characteristic information phase from moving target property data base
Matched moving target, and extract the corresponding characteristic information of moving target;According to the characteristic information of extraction, characteristic information pair is obtained
The base station data in scope of activities answered;It is flat from identity information according to the base station data in the corresponding scope of activities of characteristic information
The suspect's identity information to match with moving target is extracted in platform device;
Compared with the video suspect's identity information identification carried out in the prior art by recognition of face mode is undesirable,
In conjunction with many-sided resource such as resident demographic data in moving target property data base, base station data and identity information stage apparatus
Comprehensive collision retrieval is carried out, the accurate information of video suspect's identity can be obtained, substantially increases the knowledge of suspect's identity information
Other accuracy rate and success rate;Also, big data analysis processing technique is used, a large amount of, high speed, changeable complicated field can be handled
Scape, timeliness are preferable.
Further, a kind of suspect's personal identification method and dress based on video big data provided in an embodiment of the present invention
It sets, analyzes result generalization, video suspect's identity accurate information can be not only provided, moreover it is possible to which comprehensive offer suspect commits a crime
The motion track information of front and back, cellphone information, personage's portrait information of the completions such as permanent information, trip information are more advantageous to the people
Police handles a case.
To enable the above objects, features and advantages of the present invention to be clearer and more comprehensible, preferred embodiment is cited below particularly, and cooperate
Appended attached drawing, is described in detail below.
Detailed description of the invention
In order to illustrate the technical solution of the embodiments of the present invention more clearly, below will be to needed in the embodiment attached
Figure is briefly described, it should be understood that the following drawings illustrates only certain embodiments of the present invention, therefore is not construed as pair
The restriction of range for those of ordinary skill in the art without creative efforts, can also be according to this
A little attached drawings obtain other relevant attached drawings.
Fig. 1 shows a kind of suspect's personal identification method based on video big data provided by the embodiment of the present invention
Flow chart;
Big data retrieval technique is utilized Fig. 2 shows a kind of provided by the embodiment of the present invention, from moving target characteristic
The moving target to match according to Clustering Retrieval in library and suspect's characteristic information, and extract the moving target it is corresponding when
The flow chart of empty characteristic information;
Fig. 3 shows a kind of space-time characteristic letter of the moving target according to extraction provided by the embodiment of the present invention
Breath, obtains the flow chart of the base station data in the corresponding scope of activities of the space-time characteristic information;
Fig. 4 shows a kind of according in the corresponding scope of activities of the space-time characteristic information provided by the embodiment of the present invention
Base station data, the process of the suspect's identity information to match with the moving target is extracted from identity information stage apparatus
Figure;
Fig. 5 shows a kind of video data foundation movement according to image acquisition device acquisition provided by the embodiment of the present invention
The flow chart of target characteristic database;
Fig. 6 shows a kind of suspect's identity recognition device based on video big data provided by the embodiment of the present invention
Structural schematic diagram;
Fig. 7 is shown in a kind of suspect's identity recognition device based on video big data provided by the embodiment of the present invention
Clustering Retrieval module and the structural schematic diagram for obtaining module;
Fig. 8 is shown in a kind of suspect's identity recognition device based on video big data provided by the embodiment of the present invention
The structural schematic diagram of first extraction module and memory module;
Fig. 9 shows suspect identity recognition device of the another kind provided by the embodiment of the present invention based on video big data
Structural schematic diagram.
Major Symbol explanation:
10, the first receiving module;20, Clustering Retrieval module;30, module is obtained;40, the first extraction module;50, it second connects
Receive module;60, the second extraction module;70, memory module;201, loading unit;202, the first searching unit;203, it extracts single
Member;301, sequencing unit;302, drawing unit;303, first acquisition unit;401, second acquisition unit;402, second list is searched
Member;403, subelement is screened;404, third searching unit;405, the 4th searching unit;701, generation unit;702, addition is single
Member;703, storage unit.
Specific embodiment
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
Middle attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is only
It is a part of the embodiment of the present invention, instead of all the embodiments.The present invention being usually described and illustrated herein in the accompanying drawings is real
The component for applying example can be arranged and be designed with a variety of different configurations.Therefore, of the invention to what is provided in the accompanying drawings below
The detailed description of embodiment is not intended to limit the range of claimed invention, but is merely representative of selected reality of the invention
Apply example.Based on the embodiment of the present invention, those skilled in the art institute obtained without making creative work
There are other embodiments, shall fall within the protection scope of the present invention.
Social now, the main means that public security is solved a case are believed by the video monitoring checked around place of committing a crime
Breath finds positioning Related Cases suspect clue.But a generally existing at present problem is people's police according to suspect's video
The true identity and its activity trajectory of the suspect occurred in image analysing computer video, needs to take considerable time, man power and material,
In conjunction with the true identity for showing the means of surveying and finally positioning suspect of various complexity.
In view of be at present by recognition of face carry out video suspect identity information know method for distinguishing can exist it is as follows
Problem: first, due to the shooting angle problem of camera, the collected video data of video monitoring system may not include face
Data (or only including a part of human face data), so that video suspect identity can not be carried out by above-mentioned face recognition technology
Information identification.Second, the shooting location of video monitoring system and video camera clarity, exposure problem all can be to collected
The precision of human face data causes very big deviation;Third, since recognition of face is the facial image for arriving video acquisition and public affairs
Pacify local suspect library face picture to be compared, and public security local face database data are limited, cause lower than middle possibility.It is logical
Suspect's identity information can not finally be determined by crossing this means.Based on this, it is big based on video that the embodiment of the invention provides one kind
The suspect's personal identification method and device of data, are described below by embodiment.
The embodiment of the invention provides a kind of suspect's personal identification method based on video big data, the method is based on
Big data platform executes, and with reference to Fig. 1, the method specifically comprises the following steps:
S101, suspect's characteristic information that user sends is received;Suspect's characteristic information includes at least suspect's
Following information: activity time range, motion video point information and figure and features characteristic information.
Method provided in an embodiment of the present invention is mainly handled a case use for people's police;Firstly, being done by big data platform reception
The characteristic information of the suspect that commits a crime of case people's police input, features described above information include at least: the figure and features feature of suspect, such as body
High, shape (such as: long hair, has scar at bob on the face) and clothing etc., the activity time range of suspect, that is, need to retrieve
Time;And motion video point information, that is, the video point information for needing to retrieve.
S102, the movement mesh that Clustering Retrieval and suspect's characteristic information match from moving target property data base
Mark, and extract the corresponding space-time characteristic information of above-mentioned moving target;Above-mentioned space-time characteristic information include at least moving target with
Lower information: activity time and video point information.
Specifically, being previously stored with the video data of magnanimity structuring, above-mentioned view in above-mentioned moving target property data base
Frequency is according to being front-end image collector, and big data platform is to the moving target progress structuring processing in above-mentioned video data
Afterwards, the moving target that processing obtains is stored in moving target property data base, wherein above-mentioned moving target is corresponding with multiple
Label, such as time of occurrence, video point information (number of the image acquisition device where i.e., the number are corresponding with collecting location)
With the figure and features feature (height and five official ranks of such as people) of moving target.
Then, suspect's characteristic information is inputted in big data platform according to policeman in charge of the case, big data platform is then according to upper
Suspect's characteristic information is stated, the fortune that Clustering Retrieval and suspect's characteristic information match in its moving target property data base
Moving-target, meanwhile, extract the corresponding space-time characteristic information of above-mentioned moving target, comprising: activity time and video point information.
S103, the space-time characteristic information according to the moving target of extraction, it is corresponding to obtain the space-time characteristic information
Base station data in scope of activities.
In this step, big data platform can be drawn according to the activity time of the suspect of extraction and video point information to be disliked
The activity trajectory of people is doubted, the mobile device base station data on the activity trajectory periphery of suspect is then extracted;Wherein, above-mentioned suspect
The range on activity trajectory periphery can be configured in advance.
S104, according to the base station data in the corresponding scope of activities of the space-time characteristic information, filled from identity information platform
Set suspect's identity information that middle extraction matches with the moving target.
In this step, big data platform is located in the activity time range of suspect according to all base station datas of acquisition
Interior, then the mobile device for accessing above-mentioned all base stations according to the above-mentioned mobile device of positioning, connects in advance in big data platform
The suspect's identity information to match with the moving target extracted is extracted in the identity information stage apparatus entered.Wherein, above-mentioned body
Part information platform device can be mobile device operator platform and public security big data platform;It is also possible to access above-mentioned movement and sets
The third-party platform of standby operator's platform and public security big data platform.
Wherein, the corresponding phone number of network, the above-mentioned mobile phone of its operation are stored in above-mentioned mobile device operator platform
Number the base station that preset time accesses number and, the associated mobile device sequence number of above-mentioned phone number and user's
ID card information;Big data platform then passes through all base station datas of acquisition, from above-mentioned mobile device operator platform, obtains
The ID card information of suspect.
The essential information data that mobile device holds each user are previously stored in above-mentioned public security big data platform;On
The database for being divided into multiple classifications in the database of public security big data platform in advance is stated, such as population essential information library, fugitive people
Member library, personnel concerning the case library, trip record storehouse, hotel hotel library etc., also, be stored in each above-mentioned database corresponding
Personal information.
Big data platform is then according to the ID card information of the suspect of acquisition, in the database of above-mentioned public security big data platform
In collision comparison is carried out to the ID card information of above-mentioned suspect, with the full identity information of the case-involving suspect of positioning video: packet
Include the identification card number of suspect, name, home address, permanent address, whether be previous conviction personnel, whether be fugitive personnel, commit a crime
Front and back have which trip record (such as sitting which train, aircraft and automobile), firmly which hotel, hotel, finally, according to upper
The full identity information for stating suspect draws the complete personage's portrait of suspect, so that policeman in charge of the case can be violated with fast track
Case suspect.
All comparisons, analytical technology are all made of backstage big data cluster environment and transport automatically in 101~step 104 of above-mentioned steps
It calculates and completes.Wherein, the process for carrying out above-mentioned operation uses distributed treatment, concurrent operation mass data, and comparison result second grade is returned
It returns, suspect's identity can be pushed to policeman in charge of the case in a very short period of time as a result, accelerating efficiency of solving a case.
A kind of suspect's personal identification method based on video big data provided in an embodiment of the present invention, and in the prior art
The video suspect's identity information identification carried out by recognition of face mode is undesirable to be compared, in conjunction with moving target characteristic
The various aspects resource such as resident demographic data in library, base station data and identity information stage apparatus carries out comprehensive collision retrieval, energy
The accurate information for accessing video suspect's identity substantially increases the accuracy rate and success rate of the identification of suspect's identity information;
Also, big data analysis processing technique is used, a large amount of, high speed, changeable complex scene can be handled, timeliness is preferable.
Further, with reference to Fig. 2, above-mentioned steps 102 are using big data retrieval technique, from moving target property data base
The moving target that middle Clustering Retrieval and suspect's characteristic information match, and it is special to extract the corresponding space-time of the moving target
Reference breath, specifically comprises the following steps:
S201, activity time range and motion video point information according to suspect, from the moving target characteristic
According to loading matched moving target characteristic information in library.
Big data retrieval technique in the embodiment of the present invention is using Spark and HDFS distributed file system;Wherein, on
State the universal parallel frame that Spark is the class Hadoop MapReduce that UC Berkeley AMP lab is increased income.
Specifically, big data platform utilizes above-mentioned big data retrieval technique, when according to the activity of the suspect of people's police's input
Between range and the motion video point information of suspect search condition, from moving target property data base screening meet above-mentioned inspection
The video structural data of rope condition, and above-mentioned video structural data are loaded into SPARK distributed elastic memory.
S202, the figure and features characteristic information according to suspect search matching from the moving target characteristic information of load
Moving target, and determine the moving target be suspect's target.
Specifically, according to the moving target loaded in the figure and features characteristic information of the suspect of people's police's input and step 201
Figure and features feature tag compares, and the retrieval item of people's police's input is met if there is the description of the figure and features feature tag of moving target
Part, it is determined that corresponding moving target is suspect's target.
S203, the space-time characteristic information for extracting suspect's target.
Specifically, in the suspect's characteristic information inputted according to people's police, after located suspect's target, from above-mentioned movement mesh
The video point and time of occurrence that above-mentioned suspect's target occurs are extracted in mark property data base.
Further, with reference to Fig. 3, in above-mentioned steps 103, according to the space-time characteristic information of the moving target of extraction,
Obtain the base station data in the corresponding scope of activities of the space-time characteristic information, comprising:
S301, according to the sequencing of suspect's activity time, to suspect's clarification of objective information of extraction into
Row sequence processing, obtains suspect's trace information sample.
Specifically, all results that meet of the space-time characteristic information for the suspect's target extracted in step 202 are converged
Always, it while according to the sequencing of suspect's activity time, resequences to above-mentioned space-time characteristic information, generates suspect
Trace information sample, if suspect's activity time can be 1:00,2:00 and 3:00;It is corresponding, the image acquisition device at place
Point information is A point, B point and C point;Therefore suspect's trace information sample after sorting is as follows: 1:00 (A point)->
2:00 (B point)-> 3:00 (C point).
S302, according to the corresponding latitude and longitude information of suspect's motion video point information, the suspicion is drawn on map
The corresponding suspect's activity trajectory information of people's trace information sample.
Specifically, the image acquisition device of each number is corresponding with its default pickup area, suspect's activity view is obtained
The corresponding latitude and longitude information of frequency point position information, then according to the latitude and longitude information in PGIS (Police Geographic
Information System, Police Geographic Information System) the complete space-time trajectory information of the suspect is portrayed in map (i.e. should
Activity trajectory information of the suspect based on time and space).
S303, according to suspect's activity trajectory information, obtain the corresponding activity of suspect's activity trajectory information
All base station point information in range.
Specifically, searching all base station points within the scope of this according to the latitude and longitude information of suspect's complete active range first
Information, when then pulling suspect from the base station information library of public security big data platform according to specific base sites bit number and occurring
Between front and back all mobile devices (in all mobile devices i.e. including suspect mobile device) connection base station specific letter
Breath.
Further, with reference to Fig. 4, in above-mentioned suspect's personal identification method based on video big data, step 104, root
According to the base station data in the corresponding scope of activities of the space-time characteristic information, extracted and the fortune from identity information stage apparatus
Suspect's identity information that moving-target matches, comprising:
S401, within the activity time of the suspect, obtain and access in each described base station point information
Mobile device.
S402, from all mobile devices of acquisition, search the mobile device for accessing all base station point information and institute
State the turn-on time that mobile device accesses each base station point information.
S403, the mobile device to match with suspect's activity trajectory information is filtered out from lookup result.
S404, according to the identification information of the mobile device, search the movement in mobile device operator platform and set
Standby corresponding authentication information.
Wherein, the identification information of above-mentioned mobile device is the sequence number of mobile device, and above-mentioned authentication information can be
The ID card information of suspect, i.e. ID card No.;Specifically, can be with slave mobile device according to the sequence number of above-mentioned mobile device
The corresponding phone number of the mobile device is found in operator's platform, then by searching for the mobile device of the suspect arrived
Phone number you can learn that suspect ID card No..
S405, according to the authentication information, matched suspect's identity information is searched in public security big data platform.
In conjunction with above-mentioned steps 401 to step 405, which is being searched according to the latitude and longitude information of suspect's complete active range
After enclosing interior all base station point information, according to specific base sites bit number, from identity information stage apparatus, (such as public security is big first
Data platform) in base station information library in pull before and after suspect's time of occurrence all mobile devices (all movements are set
Standby includes the mobile device of suspect) specifying information of connection base station, the specifying information include mobile device sequence number and
The information such as number, the time of base station of mobile device access;
Then, according to the above-mentioned specifying information of acquisition, to above-mentioned collected base station mobile device data information using big
Data collision analytical technology finds out the phone number of suspect.Specific implementation includes:
1, the base station data extracted is loaded into spark elasticity memory.
2, by spark clustering technique, using cell-phone number as statistical dimension, counting each mobile device, (such as mobile phone is set
It is standby) which base station point appeared in.
3, statistical data in 2 is further screened, the mobile device for appearing in all base station points is filtered out, as mobile phone is set
Standby sequence number, time of cell phone apparatus appearance etc..
4, the result filtered out in 3 and suspect's activity trajectory time are compared, finishing screen, which is selected, meets suspect
The cell phone apparatus of activity trajectory, then according to the cell phone apparatus filtered out, directly or indirectly slave mobile device operator platform is obtained
Get authentication information (such as identity card of the corresponding phone number of the mobile device and the corresponding suspect of the phone number
Number);
5, finally, according to the identification card number of suspect, matched suspect's identity letter is searched in public security big data platform
Breath.
In addition, carrying out suspect's identity information in the prior art to know method for distinguishing being the number directly from surveillance video
According to " video point information " that middle positioning suspect occurs, the program is complicated and time-consuming and laborious.It is right first in the embodiment of the present invention
The monitor video data of image acquisition device acquisition carry out structuring processing, and the result that structuring is handled is stored to movement
In target characteristic database, then according to policeman in charge of the case input suspect's characteristic information in moving target property data base into
Row retrieval.Specifically, being to establish moving target characteristic according to the video data of image acquisition device acquisition in the embodiment of the present invention
According to library, with reference to Fig. 5, specific method for building up is as follows:
S501, the video data that image acquisition device is sent is received.
Specifically, the image acquisition device of front end is accessed big data platform, image acquisition device first with TCP/UDP agreement
Collected monitor video data are then sent to big data platform in a manner of video flowing.
S502, the space-time characteristic information for extracting moving target and the moving target in each frame video image respectively.
Specifically, big data platform, which as unit of video frame, analyzes each frame image in video flowing, there are all movement mesh
Mark and the corresponding characteristic information of each moving target (such as activity time, video point information and figure and features characteristic information).
S503, the space-time characteristic information of the moving target and the moving target is stored in database, is obtained
The moving target property data base.
Specifically, the space-time characteristic information of the above-mentioned moving target obtained according to analysis, generates and corresponds to described in each
The feature tag of moving target;The feature tag includes at least: activity time label, video point information labels and figure and features are special
Levy information labels;Then, each feature tag of generation is added in the corresponding moving target;By all carryings
There is the moving target of the feature tag to be stored in database.Wherein, figure and features characteristic information label can also include multiple
Subtab, such as figure, the colour of skin, clothing, local feature, wherein more more retrievals for the more becoming the more subsequent progress of label setting.This
In inventive embodiments, with the activity time range of moving target+motion video point information (i.e. space time information) position for key, with
Other features (such as figure and features characteristic information) of moving target are value, and above-mentioned moving target and corresponding label storage are arrived
In HDFS distributed file system.Subsequent, according to suspect's characteristic information that user inputs, in moving target property data base
After middle Clustering Retrieval to matched moving target, then return the moving target key (moving target appearance video point with
And time of occurrence), i.e. the characteristic information of suspect.
A kind of suspect's personal identification method based on video big data provided in an embodiment of the present invention, and in the prior art
The video suspect's identity information identification carried out by recognition of face mode is undesirable to be compared, in conjunction with moving target characteristic
The various aspects resource such as resident demographic data in library, base station data and identity information stage apparatus carries out comprehensive collision retrieval, energy
The accurate information for accessing video suspect's identity substantially increases the accuracy rate and success rate of the identification of suspect's identity information;
Also, big data analysis processing technique is used, a large amount of, high speed, changeable complex scene can be handled, timeliness is preferable.
Further, a kind of suspect's personal identification method based on video big data provided in an embodiment of the present invention,
Result generalization is analyzed, video suspect's identity accurate information can be not only provided, moreover it is possible to before and after comprehensive offer suspect commits a crime
Motion track information, cellphone information, the personages of the completions such as permanent information, trip information draws a portrait information, is more advantageous to people's police and does
Case.
The embodiment of the invention also provides a kind of suspect's identity recognition device based on video big data, described device is used
In executing above-mentioned suspect's personal identification method based on video big data, with reference to Fig. 6, described device, that is, big data platform,
It specifically includes:
First receiving module 10, for receiving suspect's characteristic information of user's transmission;Suspect's characteristic information at least wraps
Include the following information of suspect: activity time range, motion video point information and figure and features characteristic information;
Clustering Retrieval module 20, for the Clustering Retrieval from moving target property data base and suspect's characteristic information
The moving target to match, and extract the corresponding space-time characteristic information of the moving target;The space-time characteristic information is at least wrapped
Include the following information of moving target: activity time and video point information;
Module 30 is obtained, for the space-time characteristic information according to the moving target of extraction, obtains the space-time characteristic
Base station data in the corresponding scope of activities of information;
First extraction module 40, for according to the base station data in the corresponding scope of activities of the space-time characteristic information, from
The suspect's identity information to match with the moving target is extracted in identity information stage apparatus.
Further, with reference to Fig. 7, in above-mentioned suspect's identity recognition device based on video big data, Clustering Retrieval module
20, comprising:
Loading unit 201, for the activity time range and motion video point information according to suspect, from moving target
Matched moving target characteristic information is loaded in property data base;
First searching unit 202, for the figure and features characteristic information according to suspect, from the moving target characteristic information of load
It is middle to search matched moving target, and determine that the moving target is suspect's target;
Extraction unit 203, for extracting the space-time characteristic information of suspect's target.
Further, with reference to Fig. 7, in above-mentioned suspect's identity recognition device based on video big data, module 30, packet are obtained
It includes:
Sequencing unit 301, for the sequencing according to suspect's activity time, to suspect's target of extraction
Space-time characteristic information is ranked up processing, obtains suspect's trace information sample;
Drawing unit 302, for being drawn on map according to the corresponding latitude and longitude information of suspect's motion video point information
Make the corresponding suspect's activity trajectory information of suspect's trace information sample;
First acquisition unit 303, for obtaining suspect's activity trajectory according to suspect's activity trajectory information
All base station point information in the corresponding scope of activities of information.
Further, with reference to Fig. 8, in above-mentioned suspect's identity recognition device based on video big data, the first extraction module
40, comprising:
Second acquisition unit 401, within the activity time of suspect, obtaining in each base station point information
The mobile device of access;
Second searching unit 402, for searching and accessing all base station point information from all mobile devices of acquisition
Mobile device and mobile device access the turn-on time of each base station point information;
Subelement 403 is screened, for filtering out the movement to match with suspect's activity trajectory information from lookup result
Equipment;
Third searching unit 404 is searched in mobile device operator platform for the identification information according to mobile device
The corresponding authentication information of mobile device;
4th searching unit 405, for being searched in public security big data platform matched according to the authentication information
Suspect's identity information.
Further, with reference to Fig. 9, above-mentioned suspect's identity recognition device based on video big data further include:
Second receiving module 50, for receiving the video data of image acquisition device transmission;
Second extraction module 60, for extracting the space-time of moving target and moving target in each frame video image respectively
Characteristic information;
Memory module 70 is obtained for the space-time characteristic information of moving target and moving target to be stored in database
To moving target property data base.
Further, with reference to Fig. 8, in above-mentioned suspect's identity recognition device based on video big data, memory module 70, packet
It includes:
Generation unit 701 generates for the space-time characteristic information according to moving target and corresponds to each moving target
Feature tag;Feature tag includes at least: activity time label, video point information labels and figure and features characteristic information label;
Adding unit 702, for each feature tag generated to be added in corresponding moving target;
Storage unit 703, for all moving targets for carrying feature tag to be stored in database.
A kind of suspect's identity recognition device based on video big data provided in an embodiment of the present invention, and in the prior art
The video suspect's identity information identification carried out by recognition of face mode is undesirable to be compared, in conjunction with moving target characteristic
The various aspects resource such as resident demographic data in library, base station data and identity information stage apparatus carries out comprehensive collision retrieval, energy
The accurate information for accessing video suspect's identity substantially increases the accuracy rate and success rate of the identification of suspect's identity information;
Also, big data analysis processing technique is used, a large amount of, high speed, changeable complex scene can be handled, timeliness is preferable.
Further, a kind of suspect's identity recognition device based on video big data provided in an embodiment of the present invention,
Result generalization is analyzed, video suspect's identity accurate information can be not only provided, moreover it is possible to before and after comprehensive offer suspect commits a crime
Motion track information, cellphone information, the personages of the completions such as permanent information, trip information draws a portrait information, is more advantageous to people's police and does
Case.
The device of suspect's identification based on video big data provided by the embodiment of the present invention can be in equipment
Specific hardware or the software being installed in equipment or firmware etc..Device provided by the embodiment of the present invention, realization principle
And the technical effect generated is identical with preceding method embodiment, to briefly describe, Installation practice part does not refer to place, can join
Corresponding contents in embodiment of the method are stated before examination.It is apparent to those skilled in the art that for description convenience and
Succinctly, the specific work process of the system of foregoing description, device and unit, the correspondence during reference can be made to the above method embodiment
Process, details are not described herein.
In embodiment provided by the present invention, it should be understood that disclosed device and method, it can be by others side
Formula is realized.The apparatus embodiments described above are merely exemplary, for example, the division of the unit, only one kind are patrolled
Function division is collected, there may be another division manner in actual implementation, in another example, multiple units or components can combine or can
To be integrated into another system, or some features can be ignored or not executed.Another point, shown or discussed is mutual
Coupling, direct-coupling or communication connection can be INDIRECT COUPLING or communication link by some communication interfaces, device or unit
It connects, can be electrical property, mechanical or other forms.
The unit as illustrated by the separation member may or may not be physically separated, aobvious as unit
The component shown may or may not be physical unit, it can and it is in one place, or may be distributed over multiple
In network unit.It can select some or all of unit therein according to the actual needs to realize the mesh of this embodiment scheme
's.
In addition, each functional unit in embodiment provided by the invention can integrate in one processing unit, it can also
To be that each unit physically exists alone, can also be integrated in one unit with two or more units.
It, can be with if the function is realized in the form of SFU software functional unit and when sold or used as an independent product
It is stored in a computer readable storage medium.Based on this understanding, technical solution of the present invention is substantially in other words
The part of the part that contributes to existing technology or the technical solution can be embodied in the form of software products, the meter
Calculation machine software product is stored in a storage medium, including some instructions are used so that a computer equipment (can be a
People's computer, server or network equipment etc.) it performs all or part of the steps of the method described in the various embodiments of the present invention.
And storage medium above-mentioned includes: that USB flash disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), arbitrary access are deposited
The various media that can store program code such as reservoir (RAM, Random Access Memory), magnetic or disk.
It should also be noted that similar label and letter indicate similar terms in following attached drawing, therefore, once a certain Xiang Yi
It is defined in a attached drawing, does not then need that it is further defined and explained in subsequent attached drawing, in addition, term " the
One ", " second ", " third " etc. are only used for distinguishing description, are not understood to indicate or imply relative importance.
Finally, it should be noted that embodiment described above, only a specific embodiment of the invention, to illustrate the present invention
Technical solution, rather than its limitations, scope of protection of the present invention is not limited thereto, although with reference to the foregoing embodiments to this hair
It is bright to be described in detail, those skilled in the art should understand that: anyone skilled in the art
In the technical scope disclosed by the present invention, it can still modify to technical solution documented by previous embodiment or can be light
It is readily conceivable that variation or equivalent replacement of some of the technical features;And these modifications, variation or replacement, do not make
The essence of corresponding technical solution is detached from the spirit and scope of technical solution of the embodiment of the present invention.Should all it cover in protection of the invention
Within the scope of.Therefore, protection scope of the present invention should be based on the protection scope of the described claims.
Claims (8)
1. a kind of suspect's personal identification method based on video big data, which is characterized in that the described method includes:
Receive suspect's characteristic information that user sends;Suspect's characteristic information includes at least the following information of suspect:
Activity time range, motion video point information and figure and features characteristic information;
The moving target that Clustering Retrieval and suspect's characteristic information match from moving target property data base, and extract
The corresponding space-time characteristic information of the moving target;The space-time characteristic information includes at least the following information of moving target: living
Dynamic time and video point information;
According to the space-time characteristic information of the moving target of extraction, obtain in the corresponding scope of activities of the space-time characteristic information
Base station data;
According to the base station data in the corresponding scope of activities of the space-time characteristic information, extracted from identity information stage apparatus with
Suspect's identity information that the moving target matches;
The moving target that the Clustering Retrieval from moving target property data base and suspect's characteristic information match, and
Extract the corresponding space-time characteristic information of the moving target, comprising:
According to the activity time range of suspect and motion video point information, loaded from the moving target property data base
Matched moving target characteristic information;
According to the figure and features characteristic information of suspect, matched movement mesh is searched from the moving target characteristic information of load
Mark, and determine that the moving target is suspect's target;
Extract the space-time characteristic information of suspect's target;
The space-time characteristic information of the moving target according to extraction obtains the corresponding movable model of the space-time characteristic information
Enclose interior base station data, comprising:
According to the sequencing of suspect's activity time, the space-time characteristic information of suspect's target of extraction is ranked up
Processing, obtains suspect's trace information sample;
According to the corresponding latitude and longitude information of suspect's motion video point information, suspect's trace information is drawn on map
The corresponding suspect's activity trajectory information of sample;
According to suspect's activity trajectory information, the institute in the corresponding scope of activities of suspect's activity trajectory information is obtained
There is base station point information.
2. suspect's personal identification method according to claim 1 based on video big data, which is characterized in that described
According to the base station data in the corresponding scope of activities of the space-time characteristic information, extracted and the fortune from identity information stage apparatus
Suspect's identity information that moving-target matches, comprising:
Within the activity time of the suspect, the mobile device accessed in each described base station point information is obtained;
From all mobile devices of acquisition, the mobile device and the mobile device for accessing all base station point information are searched
Access the turn-on time of each base station point information;
The mobile device to match with suspect's activity trajectory information is filtered out from lookup result;
According to the identification information of the mobile device, the corresponding body of the mobile device is searched in mobile device operator platform
Part authentication information;
According to the authentication information, matched suspect's identity information is searched in public security big data platform.
3. suspect's personal identification method according to claim 2 based on video big data, which is characterized in that the fortune
Moving-target property data base is established previously according to following methods:
Receive the video data that image acquisition device is sent;
The characteristic information of the moving target and the moving target in each frame video image is extracted respectively;
The characteristic information of the moving target and the moving target is stored in database, it is special to obtain the moving target
Levy database.
4. suspect's personal identification method according to claim 3 based on video big data, which is characterized in that described to incite somebody to action
The characteristic information of the moving target and the moving target is stored in database, comprising:
According to the characteristic information of the moving target, the feature tag for corresponding to each moving target is generated;The spy
Sign label includes at least: activity time label, video point information labels and figure and features characteristic information label;
Each feature tag of generation is added in the corresponding moving target;
All moving targets for carrying the feature tag are stored in database.
5. a kind of suspect's identity recognition device based on video big data, which is characterized in that described device includes:
First receiving module, for receiving suspect's characteristic information of user's transmission;Suspect's characteristic information includes at least
The following information of suspect: activity time range, motion video point information and figure and features characteristic information;
Clustering Retrieval module, for from moving target property data base Clustering Retrieval match with suspect's characteristic information
Moving target, and extract the corresponding space-time characteristic information of the moving target;The space-time characteristic information includes at least movement
The following information of target: activity time and video point information;
Module is obtained, for the space-time characteristic information according to the moving target of extraction, obtains the space-time characteristic information pair
The base station data in scope of activities answered;
First extraction module, for being believed from identity according to the base station data in the corresponding scope of activities of the space-time characteristic information
The suspect's identity information to match with the moving target is extracted in breath stage apparatus;
The Clustering Retrieval module, comprising:
Loading unit, it is special from the moving target for the activity time range and motion video point information according to suspect
Matched moving target characteristic information is loaded in sign database;
First searching unit, for the figure and features characteristic information according to suspect, from the moving target characteristic information of load
Matched moving target is searched, and determines that the moving target is suspect's target;
Extraction unit, for extracting the space-time characteristic information of suspect's target;
The acquisition module, comprising:
Sequencing unit, it is special to the space-time of suspect's target of extraction for the sequencing according to suspect's activity time
Reference breath is ranked up processing, obtains suspect's trace information sample;
Drawing unit, described in being drawn on map according to the corresponding latitude and longitude information of suspect's motion video point information
The corresponding suspect's activity trajectory information of suspect's trace information sample;
First acquisition unit, for obtaining suspect's activity trajectory information pair according to suspect's activity trajectory information
All base station point information in the scope of activities answered.
6. suspect's identity recognition device according to claim 5 based on video big data, which is characterized in that described
One extraction module, comprising:
Second acquisition unit, within the activity time of the suspect, obtaining each described base station point information
The mobile device of middle access;
Second searching unit, the movement for from all mobile devices of acquisition, searching all base station point information of access are set
The standby and described mobile device accesses the turn-on time of each base station point information;
Subelement is screened, is set for filtering out the movement to match with suspect's activity trajectory information from lookup result
It is standby;
Third searching unit searches institute in mobile device operator platform for the identification information according to the mobile device
State the corresponding authentication information of mobile device;
4th searching unit, for searching matched suspect in public security big data platform according to the authentication information
Identity information.
7. suspect's identity recognition device according to claim 6 based on video big data, which is characterized in that also wrap
It includes:
Second receiving module, for receiving the video data of image acquisition device transmission;
Second extraction module, the feature for extracting moving target and the moving target in each frame video image respectively are believed
Breath;
Memory module is obtained for the characteristic information of the moving target and the moving target to be stored in database
The moving target property data base.
8. suspect's identity recognition device according to claim 7 based on video big data, which is characterized in that described to deposit
Store up module, comprising:
Generation unit generates the spy for corresponding to each moving target for the characteristic information according to the moving target
Levy label;The feature tag includes at least: activity time label, video point information labels and figure and features characteristic information label;
Adding unit, for each feature tag generated to be added in the corresponding moving target;
Storage unit, for all moving targets for carrying the feature tag to be stored in database.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610677700.3A CN106339428B (en) | 2016-08-16 | 2016-08-16 | Suspect's personal identification method and device based on video big data |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610677700.3A CN106339428B (en) | 2016-08-16 | 2016-08-16 | Suspect's personal identification method and device based on video big data |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106339428A CN106339428A (en) | 2017-01-18 |
CN106339428B true CN106339428B (en) | 2019-08-23 |
Family
ID=57824208
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610677700.3A Active CN106339428B (en) | 2016-08-16 | 2016-08-16 | Suspect's personal identification method and device based on video big data |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106339428B (en) |
Families Citing this family (28)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107480246B (en) * | 2017-08-10 | 2021-03-12 | 北京中航安通科技有限公司 | Method and device for identifying associated personnel |
CN108053354A (en) * | 2017-11-06 | 2018-05-18 | 国政通科技股份有限公司 | A kind of quick personnel's technique for delineating and device |
CN108427930B (en) * | 2018-03-20 | 2022-04-01 | 佛山市云立方互动科技有限公司 | Method and system for establishing identity recognition information association relation based on mathematical statistics |
CN108595606A (en) * | 2018-04-20 | 2018-09-28 | 广东亿迅科技有限公司 | Public security case space-time analysis method and device based on carrier data |
CN108556764A (en) * | 2018-05-03 | 2018-09-21 | 李建营 | The police vehicle-mounted office system of one kind and method |
CN109034055B (en) * | 2018-07-24 | 2021-10-01 | 北京旷视科技有限公司 | Portrait drawing method and device and electronic equipment |
CN109086829A (en) * | 2018-08-14 | 2018-12-25 | 东方网力科技股份有限公司 | A kind of method and device that social population administers |
CN110942619B (en) * | 2018-09-21 | 2024-03-08 | 杭州海康威视系统技术有限公司 | Vehicle determination method, device, system and electronic equipment |
CN109359570A (en) * | 2018-09-30 | 2019-02-19 | 广东司法警官职业学院 | A kind of method of video personage identification |
CN111209446A (en) * | 2018-11-22 | 2020-05-29 | 深圳云天励飞技术有限公司 | Method and device for presenting personnel retrieval information and electronic equipment |
CN109598223A (en) * | 2018-11-26 | 2019-04-09 | 北京洛必达科技有限公司 | Method and apparatus based on video acquisition target person |
CN109615573B (en) * | 2018-12-05 | 2023-05-05 | 武汉烽火众智数字技术有限责任公司 | Foreign personnel flow channeling analysis method and system based on big data |
CN111368106B (en) * | 2018-12-26 | 2024-04-26 | 中兴通讯股份有限公司 | Method and device for processing wild advertisement and computer readable storage medium |
CN110175217A (en) * | 2019-05-16 | 2019-08-27 | 武汉数矿科技股份有限公司 | It is a kind of for determining the perception data analysis method and device of suspect |
CN112182055A (en) * | 2019-07-02 | 2021-01-05 | 中国移动通信集团贵州有限公司 | Suspect determination method, apparatus, device and storage medium |
CN110399525A (en) * | 2019-07-27 | 2019-11-01 | 广州伽利略网络科技有限公司 | A kind of people based on image recognition technology, object motion profile method for quickly retrieving |
CN110659580A (en) * | 2019-08-29 | 2020-01-07 | 深圳市新系区块链技术有限公司 | Method and device for quickly authenticating identity information |
CN110825893A (en) * | 2019-09-18 | 2020-02-21 | 北京旷视科技有限公司 | Target searching method, device, system and storage medium |
CN111367955B (en) * | 2019-10-09 | 2024-03-26 | 杭州海康威视系统技术有限公司 | Target object identification method, target object identification device, electronic equipment and storage medium |
CN110650322A (en) * | 2019-10-29 | 2020-01-03 | 北京枭龙科技有限公司 | Security and protection system based on cloud service, Internet of things and AR security and protection glasses |
CN111079524A (en) * | 2019-11-05 | 2020-04-28 | 联通系统集成有限公司贵州省分公司 | Target identity recognition method and system based on operator base station |
CN110856115B (en) * | 2019-11-28 | 2021-02-12 | 北京明略软件系统有限公司 | Identification method and identification device for fraud organization offence area and electronic equipment |
CN111935450A (en) * | 2020-07-15 | 2020-11-13 | 长江大学 | Intelligent suspect tracking method and system and computer readable storage medium |
CN111898572A (en) * | 2020-08-05 | 2020-11-06 | 杭州云栖智慧视通科技有限公司 | Case intelligent serial-parallel method based on shape recognition |
CN112256667B (en) * | 2020-09-16 | 2024-03-22 | 珠海市新德汇信息技术有限公司 | Multi-biological characteristic normalization method |
CN112364683A (en) * | 2020-09-22 | 2021-02-12 | 苏州千视通视觉科技股份有限公司 | Case evidence fixing method and device |
CN112347296B (en) * | 2020-11-16 | 2022-06-17 | 罗普特科技集团股份有限公司 | Person and case association analysis method and device based on face recognition |
CN112800176B (en) * | 2020-12-23 | 2024-02-06 | 电信科学技术第十研究所有限公司 | Organization member mining method and device based on identity and terminal identification |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
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 |
CN103716878A (en) * | 2013-12-12 | 2014-04-09 | 深圳先进技术研究院 | Method for locating with the use of mobile phone and video monitoring equipment |
CN103914532A (en) * | 2014-03-31 | 2014-07-09 | 安徽新华博信息技术股份有限公司 | Analyzing method for automatically troubleshooting suspects |
CN104034316A (en) * | 2013-03-06 | 2014-09-10 | 深圳先进技术研究院 | Video analysis-based space positioning method |
CN104243926A (en) * | 2014-09-23 | 2014-12-24 | 深圳先进技术研究院 | Multi-source big data collection system for police |
CN105427221A (en) * | 2015-12-09 | 2016-03-23 | 北京中科云集科技有限公司 | Cloud platform-based police affair management method |
-
2016
- 2016-08-16 CN CN201610677700.3A patent/CN106339428B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
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 |
CN104034316A (en) * | 2013-03-06 | 2014-09-10 | 深圳先进技术研究院 | Video analysis-based space positioning method |
CN103716878A (en) * | 2013-12-12 | 2014-04-09 | 深圳先进技术研究院 | Method for locating with the use of mobile phone and video monitoring equipment |
CN103914532A (en) * | 2014-03-31 | 2014-07-09 | 安徽新华博信息技术股份有限公司 | Analyzing method for automatically troubleshooting suspects |
CN104243926A (en) * | 2014-09-23 | 2014-12-24 | 深圳先进技术研究院 | Multi-source big data collection system for police |
CN105427221A (en) * | 2015-12-09 | 2016-03-23 | 北京中科云集科技有限公司 | Cloud platform-based police affair management method |
Also Published As
Publication number | Publication date |
---|---|
CN106339428A (en) | 2017-01-18 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106339428B (en) | Suspect's personal identification method and device based on video big data | |
CN104915351B (en) | Picture sort method and terminal | |
US10810870B2 (en) | Method of processing passage record and device | |
CN109993125A (en) | Model training method, face identification method, device, equipment and storage medium | |
CN111461089A (en) | Face detection method, and training method and device of face detection model | |
US10725737B2 (en) | Address information-based account mapping method and apparatus | |
CN110188209A (en) | Cross-module state Hash model building method, searching method and device based on level label | |
CN103984738A (en) | Role labelling method based on search matching | |
EP4174716A1 (en) | Pedestrian tracking method and device, and computer readable storage medium | |
CN111930868A (en) | Big data behavior trajectory analysis method based on multi-dimensional data acquisition | |
CN102868983B (en) | Data interactive method and system | |
CN109829072A (en) | Construct atlas calculation and relevant apparatus | |
CN110427542A (en) | Sorter network training and data mask method and device, equipment, medium | |
CN112770265B (en) | Pedestrian identity information acquisition method, system, server and storage medium | |
CN106537387B (en) | Retrieval/storage image associated with event | |
CN108985190A (en) | Target identification method and device, electronic equipment, storage medium, program product | |
CN105518644A (en) | Method for processing and displaying real-time social data on map | |
CN111832658B (en) | Point-of-interest information processing method and device, electronic equipment and storage medium | |
CN113255477A (en) | Comprehensive management system and method for pedestrian video images | |
CN110493363A (en) | A kind of discrimination system and method for smart phone random MAC address | |
CN112258254A (en) | Internet advertisement risk monitoring method and system based on big data architecture | |
CN112925899B (en) | Ordering model establishment method, case clue recommendation method, device and medium | |
CN106355537A (en) | Smart analysis method and system for interrelated cases | |
CN109857829A (en) | A kind of geographic information data fusion system | |
CN116778306A (en) | Fake object detection method, related device and storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant | ||
PP01 | Preservation of patent right | ||
PP01 | Preservation of patent right |
Effective date of registration: 20220726 Granted publication date: 20190823 |