CN107480624B - Permanent resident population's acquisition methods, apparatus and system, computer installation and storage medium - Google Patents
Permanent resident population's acquisition methods, apparatus and system, computer installation and storage medium Download PDFInfo
- Publication number
- CN107480624B CN107480624B CN201710671651.7A CN201710671651A CN107480624B CN 107480624 B CN107480624 B CN 107480624B CN 201710671651 A CN201710671651 A CN 201710671651A CN 107480624 B CN107480624 B CN 107480624B
- Authority
- CN
- China
- Prior art keywords
- personage
- resident population
- permanent resident
- occurrence
- frequency
- 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
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- 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
- G06V40/171—Local features and components; Facial parts ; Occluding parts, e.g. glasses; Geometrical relationships
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Human Computer Interaction (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
A kind of permanent resident population's acquisition methods, which comprises obtain pre-set video camera acquired image；It identifies personage in described image, obtains the object identity of personage in described image；The history that the object identity is obtained from history acquisition data acquires information, acquires information according to the history and obtains the frequency of occurrence of personage in described image；If the frequency of occurrence meets preset condition, it is determined that personage is permanent resident population in described image.The present invention also provides a kind of permanent resident population's acquisition device, permanent resident populations to obtain system, computer installation and storage medium.The convenience and accuracy for obtaining permanent resident population can be improved in the present invention.
Description
Technical field
The present invention relates to demographics fields, and in particular to a kind of permanent resident population's acquisition methods, apparatus and system, computer
Device and storage medium.
Background technique
The variation in terms of the size of population, composition and inhabitation in order to understand a certain area, it will usually to the normal of this area
Firmly population is counted.
Common permanent resident population's statistical method is usually taken staff and carries out investigation statistics by people's direct access inquiry from door to door, but
Be that this method takes time and effort, and if while investigating a certain resident stay out, which can be omitted, the result of statistics
And real data, there are biggish deviation, statistical method is not convenient enough.
Summary of the invention
In consideration of it, it is necessary to provide a kind of permanent resident population's acquisition methods, apparatus and system, computer installation and storages to be situated between
The convenience and accuracy for obtaining permanent resident population can be improved in matter.
One aspect of the present invention provides a kind of permanent resident population's acquisition methods, which comprises
Obtain pre-set video camera acquired image；
It identifies personage in described image, obtains the object identity of personage in described image；
The history that the object identity is obtained from history acquisition data acquires information, acquires information according to the history and obtains
The frequency of occurrence of personage into described image；
If the frequency of occurrence meets preset condition, it is determined that personage is permanent resident population in described image.
In one possible implementation, permanent resident population's acquisition methods further include:
If the frequency of occurrence meets the preset condition, judge whether the changing condition of the frequency of occurrence meets the frequency
Change condition；
If the variation of the frequency of occurrence meets frequency change condition, it is determined that personage is permanent resident population in described image.
In one possible implementation, permanent resident population's acquisition methods further include:
The information that will determine as the personage of permanent resident population is added to target database；
Permanent resident population's analysis is carried out according to the target database；
It will analyze as the result is shown in human-computer interaction interface.
In one possible implementation, described to include: according to target database progress permanent resident population's analysis
It is analyzed, is obtained according to image of the machine learning model trained to permanent resident population in the target database
The identity attribute information of permanent resident population in the target database, wherein the identity attribute information include gender information and/or
Age information；
Permanent resident population's analysis is carried out according to the identity attribute information of permanent resident population in the target database.
In one possible implementation, permanent resident population's analysis includes following one or more:
The population structure of permanent resident population is analyzed；
The volume comparison analysis of permanent resident population and non-permanent resident population；
Permanent resident population's Long-term change trend status analysis.
Another aspect of the present invention additionally provides a kind of permanent resident population's acquisition device, and described device includes:
Module is obtained, for obtaining pre-set video camera acquired image；
Identification module, personage in described image, obtains the object identity of personage in described image for identification；
Frequency of occurrence obtains module, and the history for obtaining the object identity from history acquisition data acquires information,
Information, which is acquired, according to the history obtains the frequency of occurrence of personage in described image；
Determining module, if meeting preset condition for the frequency of occurrence, it is determined that personage is permanent people in described image
Mouthful.
In one possible implementation, the determining module is also used to:
If the frequency of occurrence meets the preset condition, judge whether the changing condition of the frequency of occurrence meets the frequency
Change condition；
If the variation of the frequency of occurrence meets frequency change condition, it is determined that personage is permanent resident population in described image.
In one possible implementation, permanent resident population's acquisition device further include:
Adding module is added to target database for will determine as the information of personage of permanent resident population；
Analysis module is also used to carry out permanent resident population's analysis according to the target database；
Display module is exported, for that will analyze as the result is shown in human-computer interaction interface.
In one possible implementation, the analysis module is specifically used for:
It is analyzed, is obtained according to image of the machine learning model trained to permanent resident population in the target database
The identity attribute information of permanent resident population in the target database, wherein the identity attribute information include gender information and/or
Age information；
Permanent resident population's analysis is carried out according to the identity attribute information of permanent resident population in the target database.
In one possible implementation, permanent resident population's analysis includes following one or more:
The population structure of permanent resident population is analyzed；
The volume comparison analysis of permanent resident population and non-permanent resident population；
Permanent resident population's Long-term change trend status analysis.
Another aspect of the present invention also provides a kind of permanent resident population's acquisition system, and the system comprises multiple video cameras, service
Device end and client；
The multiple video camera is arranged in and needs the position for carrying out Image Acquisition with real-time image acquisition；
The server end, for obtaining the video camera acquired image；It identifies personage in described image, obtains institute
State the object identity of personage in image；The history that the object identity is obtained from history acquisition data acquires information, according to institute
It states history acquisition information and obtains the frequency of occurrence of personage in described image；If the frequency of occurrence meets preset condition, it is determined that
Personage is permanent resident population in described image；
The server end, the information for being also used to will determine as the personage of permanent resident population are added to target database；According to
The target database carries out permanent resident population's analysis；It will analyze as the result is shown in client；
The client, the analysis result analyzed for showing the permanent resident population that the server end is sent；
The video camera, server end and client are attached by directly or indirectly mode.
Further aspect of the present invention also provides a kind of computer installation, and the computer installation includes processor, the processing
Device is for realizing above-mentioned permanent resident population's acquisition methods when executing the computer program stored in memory.
Another aspect of the invention also provides a kind of computer readable storage medium, is stored thereon with computer instruction, described
Above-mentioned permanent resident population's acquisition methods are realized when computer instruction is executed by processor.
The present invention obtains pre-set video camera acquired image；It identifies personage in described image, obtains the figure
The object identity of personage as in；The history that the object identity is obtained from history acquisition data acquires information, is gone through according to described
History acquisition information obtains the frequency of occurrence of personage in described image；If the frequency of occurrence meets preset condition, it is determined that described
Personage is permanent resident population in image.By obtaining video camera acquired image and then analysing whether that there are permanent resident population, nothings
Permanent resident population's statistics need to be carried out by the method for people's statistics from door to door by visiting, improve the convenience for obtaining permanent resident population, and keep away
Exempt to count caused by staying out because of resident and omit, has improved the accuracy for obtaining permanent resident population.
Detailed description of the invention
Technical solution in order to illustrate the embodiments of the present invention more clearly, below will be to needed in embodiment description
Attached drawing is briefly described, it should be apparent that, drawings in the following description are some embodiments of the invention, general for this field
For logical technical staff, without creative efforts, it is also possible to obtain other drawings based on these drawings.
Fig. 1 is a kind of flow chart of permanent resident population's acquisition methods provided in an embodiment of the present invention；
Fig. 2 is the schematic diagram that video camera is arranged in video camera between several residential buildings of a certain cell in the embodiment of the present invention；
Fig. 3 is the schematic diagram that a kind of permanent resident population provided in an embodiment of the present invention obtains system；
Fig. 4 is a kind of functional block diagram of permanent resident population's acquisition device provided in an embodiment of the present invention；
Fig. 5 is a kind of schematic diagram of computer installation provided in an embodiment of the present invention.
The present invention that the following detailed description will be further explained with reference to the above drawings.
Specific embodiment
To better understand the objects, features and advantages of the present invention, with reference to the accompanying drawing and specific real
Applying example, the present invention will be described in detail.It should be noted that in the absence of conflict, embodiments herein and embodiment
In feature can be combined with each other.
In the following description, numerous specific details are set forth in order to facilitate a full understanding of the present invention, described embodiment is only
It is only a part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, ordinary skill
Personnel's every other embodiment obtained without making creative work, shall fall within the protection scope of the present invention.
Unless otherwise defined, all technical and scientific terms used herein and belong to technical field of the invention
The normally understood meaning of technical staff is identical.Term as used herein in the specification of the present invention is intended merely to description tool
The purpose of the embodiment of body, it is not intended that in the limitation present invention.
Embodiment
Fig. 1 is the schematic flow diagram of permanent resident population's acquisition methods provided in an embodiment of the present invention.As shown in Figure 1, permanent people
Mouth acquisition methods can comprise the following steps that
S101: pre-set video camera acquired image is obtained.
From the point of view of the application vector of the method, permanent resident population's acquisition methods can be applied to desktop computer, notebook
The electronic equipments such as computer, server.
From the point of view of the network architecture that the method is applied, permanent resident population's acquisition methods can be applied to server end,
It can be applied to client.The server end is also referred to as the end server, can carry out a large amount of data processing；The client is also referred to as
For the end client, can be used for showing information by graphical user interface program.Usually under client server network framework, visitor
Family end sends the request instruction for obtaining data to server end, and server end returns to number to client according to the request instruction
According to, meanwhile, server end actively can also send message to client, so that client is received and shown.
When method of the present invention is applied to server end, data processing can be carried out in server end, in client
End displays data；When method of the present invention is applied to client, data processing and number can be carried out in client
According to display.
Above-mentioned pre-set video camera is for acquiring image.Specifically, above-mentioned video camera can for digital camera or
Person is analog video camera；Above-mentioned video camera may be visible light camera either infrared camera；Above-mentioned video camera is also
It can be infrared ray and the dual-purpose video camera of visible light, infrared camera, which can facilitate, carries out Image Acquisition at night.It is above-mentioned to take the photograph
Camera only the face to collected personage or collected personage can carry out image preservation, also when acquiring image
Collected each frame complete image can be saved.
Meanwhile the setting position of above-mentioned pre-set video camera can according to need and be configured, specifically because of acquisition
Place and it is different.Above-mentioned pre-set number of cameras can be either multiple for one.
As shown in Fig. 2, Fig. 2 is the schematic diagram that video camera is arranged in video camera between several residential buildings of a certain cell.In Fig. 2
Middle video camera can carry out the acquisition of image with real-time image acquisition or every preset time, pass through the video camera 1 of setting to camera shooting
Machine 8 can get the people that each building unit passes in and out in real time and not have to pass in and out the people in building in cell.
Specifically, video camera 1 may be mounted at one unit import and export of cell, disengaging can be collected by video camera 1
The people of cell Unit one；Video camera 2 may be mounted on the road between cell Unit one and cell Unit two, pass through video camera
2 can collect the people passed through between cell Unit one and cell Unit two；Video camera 8 may be mounted at cell Unit two with it is small
On road between Unit three, area, the people passed through between cell Unit one and cell Unit four can be collected by video camera 8.
Video camera 1 to 8 acquired image of video camera can be uploaded to server end by network, so that server can basis
Processing is further analyzed in the image got.
The above-mentioned pre-set video camera acquired image of acquisition can be the pre-set video camera of acquisition and adopt in real time
The all images collected are also possible to obtain a part in the collected all images of video camera.Such as it obtains and presets
Video camera in 7 points to 10 acquired images of the morning and pre-set video camera, at 5 points in afternoon is extremely in same number of days
8 acquired images are the rush hours of people's trip since aforesaid intervals are to go to school and leave school and rush hour on and off duty,
Flow of the people is larger in this time, therefore can obtain more comprehensive data as far as possible.The fetching portion period is collected
Image can operation efficiency reduces to avoid excessive data redundancy, and caused by avoiding the problem that because of data redundancy；Or it obtains
Take in multiple pre-set video cameras different cameras in different time sections acquired image, it is pre- due to multiple video cameras
The position that is first arranged may be different, thus can be according to the setting position of video camera and different selection different period collects
Image；It can also be in video camera acquired image only including the image of personage.
S102: personage in identification described image obtains the object identity of personage in described image.
After getting video camera acquired image, personage in image is identified.When the image got does not include personage
When, this image can not be analyzed.Personage can be a people either multiple people in above-mentioned image, can identify respectively each
The object identity of personage in image.
The object identity of personage is for marking whose mark personage is in above-mentioned image.A certain people is being got for the first time
When object, if this personage be it is first occur, can by newly create the personage is carried out in a manner of either new creation number of title etc. it is unique
Mark, and record the appearance information (time of occurrence, place, number of personage etc.) of the personage, wherein the mark is the personage
Object identity.If this personage occurs again, the appearance information of the personage can be obtained by object identity, and to the personage
Frequency of occurrence be updated.
Further, in an alternative embodiment of the invention, step S102 can include:
Obtain the characteristic information of personage in described image；Clustering is carried out to the characteristic information of personage in described image,
Obtain the object identity of personage in described image.
The characteristic information of personage can specifically include the characteristic information of character facial, such as the face of personage in above-mentioned image
Shape, the eyes of personage, the ear of personage, the mouth of personage, the nose of personage, the eyebrow of personage and their combination etc..
The method of the specific characteristic information for extracting personage can select to use from existing feature extraction algorithm.Example
Such as, principal component analysis (Principal Component Analysis) algorithm can be used, since Principal Component Analysis Algorithm exists
It is available in the prior art, therefore be not described herein.
In obtaining image after the characteristic information of personage, clustering is carried out to the characteristic information.Specifically, can adopt
Clustering is carried out with existing cluster algorithm, clustering can determine pair of personage according to the characteristic information of personage
As mark.If characteristic information is the characteristic information of at least two people, each characteristic information pair can be obtained by clustering
The object identity answered, to identify the quantity of the personage in image and whom each personage is respectively.
S103: the history that the object identity is obtained from history acquisition data acquires information, is acquired according to the history
Information obtains the frequency of occurrence of personage in described image.
Above-mentioned history acquisition data are that the image that this obtains video camera acquisition passes through the collected data of video camera before,
The information of collected personage before having recorded current time, in specific implementation, the lasting acquisition data of video camera.If current
Data acquisition is carried out for the first time for video camera, then history acquisition data are sky.If a certain personage is to collect for the first time, the personage's
It is sky that history, which acquires information, can create object identity corresponding with the personage for the personage, and record the people by object identity
The history of object acquires information.
Above-mentioned frequency of occurrence may include the frequency of occurrences and/or frequency of occurrence.The specific can be that a period of time or multiple
Frequency of occurrence and/or the frequency of occurrences in period.
Video camera acquired image information before being due to history acquisition data, history acquires to be had recorded in data
The information of the passing personage occurred can also acquire the history acquisition information that object identity is obtained in data from history.
Above-mentioned steps S101 can according to need to step S103 and be used for multiple times whithin a period of time.For example, according to step
The method of S101 to step S103 was either counted in three months at one month, then the frequency of occurrence of each personage can basis
Actual result is constantly updated, and the statistical result obtained from is more accurate.Also, such method is without manually repeatedly visiting
Statistics, saves human cost and time cost.
S104: if the frequency of occurrence meets preset condition, it is determined that personage is permanent resident population in described image.
It is default that above-mentioned preset condition can be more than or equal to first for the frequency of occurrence of the personage in image whithin a period of time
Number.For example, judging whether frequency of occurrence of the personage in one month in image is greater than 60 times, if any personage in image
Frequency of occurrence in one month is greater than 60 times, it is determined that personage is permanent resident population in image.
Above-mentioned preset condition, which can also be, is greater than the second preset times in the sum of frequency of occurrence of certain periods, and above-mentioned the
One preset times and the second preset times can be identical or different, and occurrence can be set as needed.For example, above-mentioned second is default
Number is 50 times, judges 4 points to 9 points of the morning 7 point to 10 point of frequency of occurrence of the personage in image in one month and afternoon
The sum of frequency of occurrence whether be greater than 50 times, if any personage in image went out occurrence for 7 points to 10 points of the morning in one month
The sum of several and 4 points to 9 points frequency of occurrence in afternoon is greater than 50 times, it is determined that personage is permanent resident population in image.
Meanwhile specific preset condition can be set as needed, and the frequency of occurrence of different personages can be selected
Different preset conditions is taken to be judged.
If the frequency of occurrence of personage meets preset condition in image, it is determined that personage is permanent resident population in image.Meanwhile if
The frequency of occurrence of personage is unsatisfactory for above-mentioned preset condition in image, personage in image can be determined as non-permanent resident population.
Further, in another embodiment, permanent resident population's acquisition methods further include:
If the frequency of occurrence meets the preset condition, judge whether the changing condition of the frequency of occurrence meets the frequency
Change condition；If the changing condition of the frequency of occurrence meets frequency change condition, it is determined that personage is permanent in described image
Population.
When frequency of occurrence meets preset condition, the changing condition of frequency of occurrence is judged, specifically can be to out
The changing condition of existing frequency and/or the changing condition of frequency of occurrence are judged.
Above-mentioned frequency change condition can be set as needed.For example, the changing condition of above-mentioned frequency of occurrence is in image
Personage's frequency of occurrences whithin a period of time changing condition, specifically, the frequency of occurrences is the frequency of occurrence in a period of time
With the ratio of time.In July to August, certain personage in image is 3 times/day in the frequency of occurrences of certain cell, but other months,
Do not get the image of the personage, the frequency of occurrences 0, then may the personage in image due to summer time to ground tourism,
Although during this period of time, the frequency of occurrences of the personage may be higher, it can determine that the personage is not permanent resident population.
Since above step can persistently carry out obtaining information and analysis for the period either multiple periods
Judgement, thus it is a certain personal after somewhere is determined as permanent resident population, it may be true by it again due to the variation of its frequency of occurrence
After the non-permanent resident population or a certain people for being set to this area are determined as non-permanent resident population in somewhere, due to its frequency of occurrence
Variation determine it as the permanent resident population on the ground.Since population has mobility, permanent resident population is carried out by the method
Acquisition it is more convenient, and accuracy is higher, to further improve the acquisition efficiency of permanent resident population.
In another embodiment of the invention, permanent resident population's acquisition methods may also include that
The information that will determine as the personage of permanent resident population is added to target database；
Permanent resident population's analysis is carried out according to the target database；
It will analyze as the result is shown in human-computer interaction interface.
After determining that the personage in image is permanent resident population, which is added to target database.Above-mentioned number of targets
According to the database that library is for saving the information of permanent resident population.
It is determined as the information of permanent resident population due to saving in the target database, it can be according to the target database
Carry out permanent resident population's analysis, for example, in permanent resident population teenager, adult and the elderly ratio.
Above-mentioned human-computer interaction interface is typically as client, if this method is applied to server end, server end will divide
It analyses result and client is sent to by network, so that client shows the analysis result；If this method is applied to client, directly
It is locally obtaining analysis result and is showing.Specifically, can receive analysis result check instruction when, in human-computer interaction interface
It is shown.Specific display format can have line chart, column diagram, cake chart etc..
The present invention human-computer interaction interface show permanent resident population analysis analysis result can be used family intuitively understand it is permanent
The situation of population.
Further, in another embodiment of the invention, described that permanent resident population point is carried out according to the target database
Analysis can include:
It is analyzed, is obtained according to image of the machine learning model trained to permanent resident population in the target database
The identity attribute information of permanent resident population in the target database, wherein the identity attribute information include gender information and/or
Age information；Permanent resident population's analysis is carried out according to the identity attribute information of permanent resident population in the target database.
The above-mentioned machine learning model trained is the model obtained with the method training of machine learning.Using training
Machine learning model specific method that the image of permanent resident population in target database is analyzed be, will be in target database
Any image of permanent resident population is input to the machine learning model trained, output image in permanent resident population identity attribute
Information.
Above-mentioned identity attribute information can include but is not limited to gender information and/or age information.It can also specifically obtain
It is different because of the machine learning model trained to which identity attribute information.
The above-mentioned machine learning model trained can pre-establish by the following method:
(1) great amount of images is obtained in advance establish training set, above-mentioned training set can be the characteristic information of great amount of images, and
The corresponding identity attribute information of this feature information (gender information of personage in such as image, the age information of personage in image).
(2) determine that machine learning model, machine learning model are pre-set function models, which includes not
Know parameter.
(3) according in training set characteristic information and identity attribute to this include unknown parameter function model instruct
Practice, obtain the value of the unknown parameter, then the function model of the value including the unknown parameter is the machine learning model trained.
After having obtained the machine learning model of trained mistake by above method, if obtaining the spy of personage in new image again
After reference breath, the characteristic information of the personage in new image is input to the machine learning model trained, the machine learning mould
Type can according to before training export the image in identity of personage attribute information, for example, in image the gender of personage and
The age of personage in image.
Therefore in the present invention, permanent people in target database can be obtained according to the machine learning model that this was trained
Then the identity attribute information of mouth carries out resident population analysis according to the identity attribute information of obtained permanent resident population, for example, point
Analyse male to female ratio, the age composition of permanent resident population etc. of permanent resident population.
Further, in another embodiment, above-mentioned permanent resident population's analysis may include following one or more:
The population structure of permanent resident population is analyzed；
The volume comparison analysis of permanent resident population and non-permanent resident population；
Permanent resident population's Long-term change trend status analysis.
The population structure analysis of above-mentioned permanent resident population may include the sex structure of permanent resident population.In human-computer interaction interface
In, the sex structure of permanent resident population can be shown according to time or place.Such as show the sex ratio of sometime permanent resident population
Example, wherein the sex ratio of permanent resident population can be shown in the form of cake chart.
The population structure analysis of above-mentioned permanent resident population can also include the age composition of permanent resident population.Then in human-computer interaction circle
In face, the age composition of permanent resident population can be shown according to time or place.For example, display sometime permanent resident population's is small
The population composition of child, young man, a middle-aged person, the elderly, wherein the age composition of permanent resident population can be in the form of histogram
Existing, different age people can be with identical or different color identifier.
The quantity of population and permanent resident population other than permanent resident population is compared, can be obtained permanent resident population with it is non-permanent
The quantitative comparison of population.The permanent resident population of a certain position current slot and the ratio of non-permanent resident population can be shown with cake chart
Example.Specifically, can also show population, permanent resident population's sum and non-permanent population.
Above-mentioned permanent resident population's Long-term change trend situation is to calculate the population of different time points, to obtain population
Changing condition.For example, a certain position permanent resident population quantity changing condition figure in six months is shown using line chart, so as to anti-
Reflect ground permanent resident population's quantity variation tendency be increase, reduce or it is constant.
Further, human-computer interaction interface can also show the history acquisition information of a certain permanent resident population and show.For example,
If receiving the inquiry instruction for inquiring a certain permanent resident population, is shown in the form of time shaft in human-computer interaction interface and collected every time
The time of the permanent resident population and image.
Meanwhile the present invention be not limited in the information that human-computer interaction interface is shown it is more above-mentioned, it is permanent collecting
After the image of population and preservation, the analysis result of permanent resident population's analysis can be showed with any diagrammatic form.
The embodiment of the present invention obtains pre-set video camera acquired image；It identifies personage in described image, obtains
The object identity of personage in described image；The history that the object identity is obtained from history acquisition data acquires information, according to
The history acquisition information obtains the frequency of occurrence of personage in described image；If the frequency of occurrence meets preset condition, really
Determining personage in described image is permanent resident population.By obtaining video camera acquired image and then analysing whether that there are permanent people
Mouthful, without improving the convenience for obtaining permanent resident population by the method progress permanent resident population's statistics counted from door to door by people of visiting,
And avoid stay out because of resident caused by count omit, improve obtain permanent resident population accuracy.
It is the detailed description carried out to method provided by the present invention above.According to different requirements, in shown flow chart
The execution sequence of box can change, and certain boxes can be omitted, and the acquisition methods of permanent resident population can also be in above-mentioned permanent people
It is selective in mouth acquisition methods to be applied in combination, or be applied in combination with other above-mentioned unmentioned permanent resident population's acquisition methods.
Embodiment
Fig. 3 is the schematic diagram that permanent resident population provided by the invention obtains system, as shown in figure 3, permanent resident population's system can be with
It include: multiple video cameras, server end and client.
The multiple video camera is arranged on the position for needing to acquire image with real-time image acquisition, such as shown in Figure 2
Some cell each building unit inlet and outlet perhaps cell each entrance perhaps each front door of hospital or
Each entrance at scenic spot or railway station, each entrance at harbour etc..
The image of acquisition is directly or indirectly transferred to server end by network by the video camera.Such as in the present embodiment
In, the video camera can give the image transmitting of acquisition to the server end by interchanger.
The server end is the computer installation with mass data processing, including processor and memory.The clothes
Device end be engaged in after receiving the video camera acquired image, carries out operation, identifies the personage in described image, obtains described
The object identity of personage in image；And the history that the object identity is obtained from history acquisition data acquires information, according to institute
It states history acquisition information and obtains the frequency of occurrence of personage in described image.
Meanwhile the server end is also used to will determine as the information of the personage of permanent resident population and is added to target database；
Permanent resident population's analysis is carried out according to the target database；It will analyze as the result is shown in client.
The client is used to show the analysis result for permanent resident population's analysis that the server end is sent.
In permanent resident population's acquisition system, for video camera for acquiring image, the quantity of video camera can be one or more,
Generally for the accuracy that permanent resident population obtains, multiple video cameras are set, the quantity of the video camera in Fig. 3 is only a kind of possible
Example, do not represent is only 2 in practice, and the actual quantity of video camera can be any amount.
The embodiment of the present invention obtains pre-set video camera acquired image by server end；Identify described image
Middle personage obtains the object identity of personage in described image；The history that the object identity is obtained from history acquisition data is adopted
Collect information, information is acquired according to the history and obtains the frequency of occurrence of personage in described image；If the frequency of occurrence meets pre-
If condition, it is determined that personage is permanent resident population in described image.The present invention be not necessarily to by visit from door to door by people statistics method into
Row permanent resident population statistics, improve obtain permanent resident population convenience, and avoid stay out because of resident caused by count omit,
Improve the accuracy for obtaining permanent resident population.And it can be easily in multiple clients using the framework mode of server client
It is displayed data on end, and since server-side hardware configuration is usually higher, data-handling capacity is stronger, and processing speed is more
Fastly, more efficient, it more rapidly can accurately obtain permanent resident population.
Embodiment
Fig. 4 is the structure chart of permanent resident population's acquisition device provided in an embodiment of the present invention, as shown in figure 4, permanent resident population obtains
Taking device may include: to obtain module 210, identification module 220, frequency of occurrence to obtain module 230 and determining module 240.
Module 210 is obtained, for obtaining pre-set video camera acquired image.
From the point of view of the application vector of described device, permanent resident population's acquisition device can be applied to desktop computer, notebook
The electronic equipments such as computer, server.
From the point of view of the network architecture that described device is applied, permanent resident population's acquisition device can be applied to server end,
It can be applied to client.The server end is also referred to as the end server, can carry out a large amount of data processing；The client is also referred to as
For the end client, can be used for showing information by graphical user interface program.Usually under client server network framework, visitor
Family end sends the request instruction for obtaining data to server end, and server end returns to number to client according to the request instruction
According to, meanwhile, server end actively can also send message to client, so that client is received and shown.
When device of the present invention is applied to server end, data processing can be carried out in server end, in client
End displays data；When device of the present invention is applied to client, data processing and number can be carried out in client
According to display.
Above-mentioned pre-set video camera is for acquiring image.Specifically, above-mentioned video camera can for digital camera or
Person is analog video camera；Above-mentioned video camera may be visible light camera either infrared camera；Above-mentioned video camera is also
It can be infrared ray and the dual-purpose video camera of visible light, infrared radiation machine, which can facilitate, carries out Image Acquisition at night.It is above-mentioned to take the photograph
Camera only the face to collected personage or collected personage can carry out image preservation, also when acquiring image
Collected each frame complete image can be saved.
Meanwhile the setting position of above-mentioned pre-set video camera can according to need and be configured, specifically because of acquisition
Place and it is different.Above-mentioned pre-set number of cameras can be either multiple for one.
As shown in Fig. 2, Fig. 2 is the schematic diagram that video camera is arranged in video camera between several residential buildings of a certain cell.In Fig. 2
Middle video camera can carry out the acquisition of image with real-time image acquisition or every preset time, pass through the video camera 1 of setting to camera shooting
Machine 8 can get the people that each building unit passes in and out in real time and not have to pass in and out the people in building in cell.
Specifically, video camera 1 may be mounted at one unit import and export of cell, disengaging can be collected by video camera 1
The people of cell Unit one；Video camera 2 may be mounted on the road between cell Unit one and cell Unit two, pass through video camera
2 can collect the people passed through between cell Unit one and cell Unit two；Video camera 8 may be mounted at cell Unit two with it is small
On road between Unit three, area, the people passed through between cell Unit one and cell Unit four can be collected by video camera 8.
Video camera 1 to 8 acquired image of video camera can be uploaded to server end by network, so that server can basis
Processing is further analyzed in the image got.
The above-mentioned pre-set video camera acquired image of acquisition can be the pre-set video camera of acquisition and adopt in real time
The all images collected are also possible to obtain a part in the collected all images of video camera.Such as it obtains and presets
Video camera in 7 points to 10 acquired images of the morning and pre-set video camera, at 5 points in afternoon is extremely in same number of days
8 acquired images are the rush hours of people's trip since aforesaid intervals are to go to school and leave school and rush hour on and off duty,
Flow of the people is larger in this time, therefore can obtain more comprehensive data as far as possible.The fetching portion period is collected
Image can operation efficiency reduces to avoid excessive data redundancy, and caused by avoiding the problem that because of data redundancy；Or it obtains
Take in multiple pre-set video cameras different cameras in different time sections acquired image, it is pre- due to multiple video cameras
The position that is first arranged may be different, thus can be according to the setting position of video camera and different selection different period collects
Image；It can also be in video camera acquired image only including the image of personage.
Identification module 220, personage in described image, obtains the object identity of personage in described image for identification.
After acquisition module 210 gets video camera acquired image, identification module 220 identifies personage in image.When obtaining
When the image got does not include personage, this image can not be analyzed.Personage can be for a people either in above-mentioned image
Multiple people can identify the object identity of personage in each image respectively.
The object identity of personage is for marking whose mark personage is in above-mentioned image.A certain people is being got for the first time
When object, if this personage be it is first occur, can by newly create the personage is carried out in a manner of either new creation number of title etc. it is unique
Mark, and record the appearance information (time of occurrence, place, number of personage etc.) of the personage.If this personage occurs again, can
To obtain the appearance information of the personage by object identity, and the frequency of occurrence of the user is updated.
Further, in an alternative embodiment of the invention, identification module 220 is specifically used for:
Obtain the characteristic information of personage in described image；Clustering is carried out to the characteristic information of personage in described image,
Obtain the object identity of personage in described image.
The characteristic information of personage can specifically include the characteristic information of character facial, such as the face of personage in above-mentioned image
Shape, the eyes of personage, the ear of personage, the mouth of personage, the nose of personage, the eyebrow of personage and their combination etc..
The method of the specific characteristic information for extracting personage can select to use from existing feature extraction algorithm.Example
Such as, principal component analysis (Principal Component Analysis) algorithm can be used, since Principal Component Analysis Algorithm exists
It is available in the prior art, therefore be not described herein.
In obtaining image after the characteristic information of personage, clustering is carried out to the characteristic information.Specifically, can adopt
Clustering is carried out with existing cluster algorithm, clustering can determine pair of personage according to the characteristic information of personage
As mark.If characteristic information is the characteristic information of at least two people, each characteristic information pair can be obtained by clustering
The object identity answered, to identify the quantity of the personage in image and whom each personage is respectively.
Frequency of occurrence obtains module 230, for obtaining the history acquisition letter of the object identity from history acquisition data
Breath acquires information according to the history and obtains the frequency of occurrence of personage in described image.
Above-mentioned history acquisition data are that the image that this obtains video camera acquisition passes through the collected data of video camera before,
The information of collected personage before having recorded current time, in specific implementation, the lasting acquisition data of video camera.If current
Data acquisition is carried out for the first time for video camera, then history acquisition data are sky.If a certain personage is to collect for the first time, the personage's
It is sky that history, which acquires information, can create object identity corresponding with the personage for the personage, and record the people by object identity
The history of object acquires information.
Above-mentioned frequency of occurrence may include the frequency of occurrences and/or frequency of occurrence.The specific can be that a period of time or multiple
Frequency of occurrence and/or the frequency of occurrences in period.
Video camera acquired image information before being due to history acquisition data, history acquires to be had recorded in data
The information of the passing people occurred can also acquire the history acquisition information that object identity is obtained in data from history.
Above-mentioned acquisition module 210, identification module 220 and frequency of occurrence module 230 can according to need whithin a period of time
It is performed a plurality of times.For example, either being counted in three months at one month, then the frequency of occurrence of each personage can be according to practical knot
Fruit is constantly updated, and the statistical result obtained from is more accurate.Also, such method is not necessarily to statistics of manually repeatedly visiting,
Save human cost and time cost.
Determining module 240, if meeting preset condition for the frequency of occurrence, it is determined that personage is permanent in described image
Population.
It is default that above-mentioned preset condition can be more than or equal to first for the frequency of occurrence of the personage in image whithin a period of time
Number.For example, judging whether frequency of occurrence of the personage in one month in image is greater than 60 times, if any personage in image
Frequency of occurrence in one month is greater than 60 times, it is determined that personage is permanent resident population in image.
Above-mentioned preset condition, which can also be, is greater than the second preset times in the sum of frequency of occurrence of certain periods, and above-mentioned the
One preset times and the second preset times can be identical or different, and occurrence can be set as needed.For example, above-mentioned second is default
Number is 50 times, judges 4 points to 9 points of the morning 7 point to 10 point of frequency of occurrence of the personage in image in one month and afternoon
The sum of frequency of occurrence whether be greater than 50 times, if any personage in image went out occurrence for 7 points to 10 points of the morning in one month
The sum of several and 4 points to 9 points frequency of occurrence in afternoon is greater than 50 times, it is determined that personage is permanent resident population in image.
Meanwhile specific preset condition can be set as needed, and the frequency of occurrence of different personages can be selected
Different preset conditions is taken to be judged.
If the frequency of occurrence of personage meets preset condition in image, it is determined that module 240 determines that personage is permanent in image
Population.Meanwhile if the frequency of occurrence of personage is unsatisfactory for above-mentioned preset condition in image, personage in image can be determined as very
Firmly population.
Further, in another embodiment, the determining module is also used to:
If the frequency of occurrence meets the preset condition, judge whether the changing condition of the frequency of occurrence meets the frequency
Change condition；If the changing condition of the frequency of occurrence meets frequency change condition, it is determined that personage is permanent in described image
Population.
When frequency of occurrence meets preset condition, the changing condition of frequency of occurrence is judged, specifically can be to out
The changing condition of existing frequency and/or the changing condition of frequency of occurrence are judged.
Above-mentioned frequency change condition can be set as needed.For example, the changing condition of above-mentioned frequency of occurrence is in image
Personage's frequency of occurrences whithin a period of time changing condition, specifically, the frequency of occurrences is the frequency of occurrence in a period of time
With the ratio of time.In July to August, certain personage in image is 3 times/day in the frequency of occurrences of certain cell, but other months,
Do not get the image of the personage, the frequency of occurrences 0, then may the personage in image due to summer time to ground tourism,
Although during this period of time, the frequency of occurrences of the personage may be higher, it can determine that the personage is not permanent resident population.
Due to can persistently carry out obtaining information and analysis for the period either multiple periods with upper module
Judgement, thus it is a certain personal after somewhere is determined as permanent resident population, it may be true by it again due to the variation of its frequency of occurrence
After the non-permanent resident population or a certain people for being set to this area are determined as non-permanent resident population in somewhere, due to its frequency of occurrence
Variation determine it as the permanent resident population on the ground.Since population has mobility, permanent resident population is carried out by the method
Acquisition it is more convenient, and accuracy is higher, to further improve the acquisition efficiency of permanent resident population.
In another embodiment of the invention, permanent resident population's acquisition device may also include that
Adding module is added to target database for will determine as the information of personage of permanent resident population；
Analysis module, for carrying out permanent resident population's analysis according to the target database；
Display module is exported, for that will analyze as the result is shown in human-computer interaction interface.
After determining that the personage in image is permanent resident population, which is added to target database.Above-mentioned number of targets
According to the database that library is for saving the information of permanent resident population.
It is determined as the information of permanent resident population due to saving in the target database, it can be according to the target database
Carry out permanent resident population's analysis, for example, in permanent resident population teenager, adult and the elderly ratio.
Above-mentioned human-computer interaction interface is typically as client, if the present apparatus is applied to server end, server end will divide
It analyses result and client is sent to by network, so that client shows the analysis result；If this method is applied to client, directly
It is locally obtaining analysis result and is showing.Specifically, can receive analysis result check instruction when, in human-computer interaction interface
It is shown.Specific display format can have line chart, column diagram, cake chart etc..
The present invention human-computer interaction interface show permanent resident population analysis analysis result can be used family intuitively understand it is permanent
The situation of population.
Further, in another embodiment of the invention, the analysis module is specifically used for:
It is analyzed, is obtained according to image of the machine learning model trained to permanent resident population in the target database
The identity attribute information of permanent resident population in the target database, wherein the identity attribute information include gender information and/or
Age information；Permanent resident population's analysis is carried out according to the identity attribute information of permanent resident population in the target database.
The above-mentioned machine learning model trained is the model obtained with the method training of machine learning.Using training
Machine learning model specific method that the image of permanent resident population in target database is analyzed be, will be in target database
Any image of permanent resident population is input to the machine learning model trained, output image in permanent resident population identity attribute
Information.
Above-mentioned identity attribute information can include but is not limited to gender information and/or age information.It can also specifically obtain
It is different because of the machine learning model trained to which identity attribute information.
The above-mentioned machine learning model trained can pre-establish by the following method:
(1) great amount of images is obtained in advance establish training set, above-mentioned training set can be the characteristic information of great amount of images, and
The corresponding identity attribute information of this feature information (gender information of personage in such as image, the age information of personage in image).
(2) determine that machine learning model, machine learning model are pre-set function models, which includes not
Know parameter.
(3) according in training set characteristic information and identity attribute to this include unknown parameter function model instruct
Practice, obtain the value of the unknown parameter, then the function model of the value including the unknown parameter is the machine learning model trained.
After having obtained the machine learning model of trained mistake by above method, if obtaining the spy of personage in new image again
After reference breath, the characteristic information of the personage in new image is input to the machine learning model trained, the machine learning mould
Type can according to before training export the image in identity of personage attribute information, for example, in image the gender of personage and
The age of personage in image.
Therefore in the present invention, permanent people in target database can be obtained according to the machine learning model that this was trained
Then the identity attribute information of mouth carries out resident population analysis according to the identity attribute information of obtained permanent resident population, for example, point
Analyse male to female ratio, the age composition of permanent resident population etc. of permanent resident population.
Further, in another embodiment, above-mentioned permanent resident population's analysis may include following one or more:
The population structure of permanent resident population is analyzed；
The volume comparison analysis of permanent resident population and non-permanent resident population；
Permanent resident population's Long-term change trend status analysis.
The population structure analysis of above-mentioned permanent resident population may include the sex structure of permanent resident population.In human-computer interaction interface
In, the sex structure of permanent resident population can be shown according to time or place.Such as show the sex ratio of sometime permanent resident population
Example, wherein the sex ratio of permanent resident population can be shown in the form of cake chart.
The population structure analysis of above-mentioned permanent resident population can also include the age composition of permanent resident population.Then in human-computer interaction circle
In face, the age composition of permanent resident population can be shown according to time or place.For example, display sometime permanent resident population's is small
The population composition of child, young man, a middle-aged person, the elderly, wherein the age composition of permanent resident population can be in the form of histogram
Existing, different age people can be with identical or different color identifier.
The quantity of population and permanent resident population other than permanent resident population is compared, can be obtained permanent resident population with it is non-permanent
The quantitative comparison of population.The permanent resident population of a certain place current slot and the ratio of non-permanent resident population can be shown with cake chart
Example.Specifically, can also show population, permanent resident population's sum and non-permanent population.
Above-mentioned permanent resident population's Long-term change trend situation is to calculate the population of different time points, to obtain population
Changing condition.For example, a certain position permanent resident population quantity changing condition figure in six months is shown using line chart, so as to anti-
Reflect ground permanent resident population's quantity variation tendency be increase, reduce or it is constant.
Further, human-computer interaction interface can also show the history acquisition information of a certain permanent resident population and show.For example,
If receiving the inquiry instruction for inquiring a certain permanent resident population, the permanent resident population is shown in the form of time shaft in human-computer interaction interface
Each collected time and picture.
Meanwhile the present invention be not limited in the information that human-computer interaction interface is shown it is more above-mentioned, it is permanent collecting
After the image of population and preservation, the analysis result of permanent resident population's analysis can be showed with any diagrammatic form.
The embodiment of the present invention obtains pre-set video camera acquired image；It identifies personage in described image, obtains
The object identity of personage in described image；The history that the object identity is obtained from history acquisition data acquires information, according to
The history acquisition information obtains the frequency of occurrence of personage in described image；If the frequency of occurrence meets preset condition, really
Determining personage in described image is permanent resident population.By obtaining video camera acquired image and then analysing whether that there are permanent people
Mouthful, without improving the convenience for obtaining permanent resident population by the method progress permanent resident population's statistics counted from door to door by people of visiting,
And avoid stay out because of resident caused by count omit, improve obtain permanent resident population accuracy.
Referring to figure 5., Fig. 5 is the schematic diagram of computer installation 11 provided in an embodiment of the present invention.The computer installation
11 include memory 20, processor 30 and are stored in the calculating that can be run in the memory 20 and on the processor 30
Machine program 40, such as permanent resident population obtain program.The processor 30 is realized above-mentioned permanent when executing the computer program 40
Step in population acquisition methods embodiment, such as step S101~S104 shown in FIG. 1.Alternatively, the processor 30 executes
The function of each module/unit in above-mentioned apparatus embodiment, such as module 210~240 are realized when the computer program 40.
Illustratively, the computer program 40 can be divided into one or more module/units, it is one or
Multiple module/units are stored in the memory 20, and are executed by the processor 30, to complete the present invention.Described one
A or multiple module/units can be the series of computation machine program instruction section that can complete specific function, which is used for
Implementation procedure of the computer program 40 in the computer installation 11 is described.For example, the computer program 40 can be with
It is divided into the acquisition module 210 in Fig. 4, identification module 220, frequency of occurrence and obtains module 230 and determining module 240, each mould
Block concrete function is referring to previous embodiment.
The computer installation 11 can be desktop PC, laptop, palm PC and cloud server etc.
Computer equipment.It will be understood by those skilled in the art that the schematic diagram 5 is only the example of computer installation 11, not structure
The restriction of pairs of computer installation 11 may include perhaps combining certain components or not than illustrating more or fewer components
Same component, such as the computer installation 11 can also include input-output equipment, network access equipment, bus etc..
Alleged processor 30 can be central processing unit (Central Processing Unit, CPU), can also be
Other general processors, digital signal processor (Digital Signal Processor, DSP), specific integrated circuit
(Application Specific Integrated Circuit, ASIC), ready-made programmable gate array (Field-
Programmable Gate Array, FPGA) either other programmable logic device, discrete gate or transistor logic,
Discrete hardware components etc..General processor can be microprocessor or the processor 30 is also possible to any conventional processor
Deng the processor 30 is the control centre of the computer installation 11, utilizes various interfaces and the entire computer of connection
The various pieces of device 11.
The memory 20 can be used for storing the computer program 40 and/or module/unit, and the processor 30 passes through
Operation executes the computer program and/or module/unit being stored in the memory 20, and calls and be stored in memory
Data in 20 realize the various functions of the computer installation 11.The memory 20 can mainly include storing program area and
Storage data area, wherein application program needed for storing program area can store operating device, at least one function (such as sound
Playing function, image player function etc.) etc.；Storage data area, which can be stored, uses created data according to computer installation 11
(such as audio data, phone directory etc.) etc..In addition, memory 20 may include high-speed random access memory, can also include
Nonvolatile memory, such as hard disk, memory, plug-in type hard disk, intelligent memory card (Smart Media Card, SMC), safety
Digital (Secure Digital, SD) card, flash card (Flash Card), at least one disk memory, flush memory device or
Other volatile solid-state parts.
If the integrated module/unit of the computer installation 11 is realized in the form of SFU software functional unit and as independence
Product when selling or using, can store in a computer readable storage medium.Based on this understanding, of the invention
It realizes all or part of the process in above-described embodiment method, can also instruct relevant hardware come complete by computer program
At the computer program can be stored in a computer readable storage medium, which is being executed by processor
When, it can be achieved that the step of above-mentioned each embodiment of the method.Wherein, the computer program includes computer program code, described
Computer program code can be source code form, object identification code form, executable file or certain intermediate forms etc..The meter
Calculation machine readable medium may include: can carry the computer program code any entity or device, recording medium, USB flash disk,
Mobile hard disk, magnetic disk, CD, computer storage, read-only memory (ROM, Read-Only Memory), random access memory
Device (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium etc..It needs to illustrate
It is that the content that the computer-readable medium includes can be fitted according to the requirement made laws in jurisdiction with patent practice
When increase and decrease, such as in certain jurisdictions, according to legislation and patent practice, computer-readable medium does not include electric carrier wave letter
Number and telecommunication signal.
In several embodiments provided by the present invention, it should be understood that disclosed method and apparatus can also pass through
Other modes are realized.For example, the apparatus embodiments described above are merely exemplary, for example, the division of the module,
Only a kind of logical function partition, there may be another division manner in actual implementation.
Finally it should be noted that the above examples are only used to illustrate the technical scheme of the present invention and are not limiting, although reference
Preferred embodiment describes the invention in detail, those skilled in the art should understand that, it can be to of the invention
Technical solution is modified or equivalent replacement, without departing from the spirit and scope of the technical solution of the present invention.
Claims (8)
1. a kind of permanent resident population's acquisition methods, which is characterized in that the described method includes:
The pre-set video camera according to the position acquisition of pre-set video camera is in collected figure of multiple periods
Picture；
It identifies personage in described image, obtains the object identity of personage in described image, the object identity record has personage's
Time of occurrence and frequency of occurrence；
The history that the object identity is obtained from history acquisition data acquires information, acquires going out in information according to the history
Between current and frequency of occurrence directly determines frequency of occurrence of the personage within multiple periods in described image；
If the sum of the frequency of occurrence of personage within multiple periods is more than or equal to frequency threshold value in described image, described image is judged
Whether the changing condition of frequency of occurrence of the middle personage within multiple periods meets number change condition；
If the changing condition of frequency of occurrence of the personage within multiple periods meets number change condition in described image, it is determined that
Personage is permanent resident population in described image.
2. the method as described in claim 1, which is characterized in that the method also includes:
The information that will determine as the personage of permanent resident population is added to target database；
Permanent resident population's analysis is carried out according to the target database；
It will analyze as the result is shown in human-computer interaction interface.
3. method according to claim 2, which is characterized in that described to carry out permanent resident population's analysis according to the target database
Include:
It is analyzed, is obtained described according to image of the machine learning model trained to permanent resident population in the target database
The identity attribute information of permanent resident population in target database, wherein the identity attribute information includes gender information and/or age
Information；
Permanent resident population's analysis is carried out according to the identity attribute information of permanent resident population in the target database.
4. method according to claim 2, which is characterized in that permanent resident population's analysis includes following one or more:
The population structure of permanent resident population is analyzed；
The volume comparison analysis of permanent resident population and non-permanent resident population；
Permanent resident population's Long-term change trend status analysis.
5. a kind of permanent resident population's acquisition device, which is characterized in that described device includes:
Module is obtained, for the pre-set video camera according to the position acquisition of pre-set video camera in multiple times
Section acquired image；
Identification module, personage in described image, obtains the object identity of personage in described image, the object identity for identification
Record has the time of occurrence and frequency of occurrence of personage；
Frequency of occurrence obtains module, and the history for obtaining the object identity from history acquisition data acquires information, according to
Time of occurrence and frequency of occurrence in history acquisition information directly determine in described image personage within multiple periods
Frequency of occurrence；
Determining module, if the sum of the frequency of occurrence for personage in described image within multiple periods is more than or equal to number threshold
Value, judges whether the changing condition of frequency of occurrence of the personage within multiple periods in described image meets number change condition；
If the variation of frequency of occurrence of the personage within multiple periods meets number change condition in described image, it is determined that described image
Middle personage is permanent resident population.
6. a kind of permanent resident population obtains system, which is characterized in that the system comprises multiple video cameras, server end and clients
End；
The multiple video camera is arranged in and needs the position for carrying out Image Acquisition with real-time image acquisition；
The server end is adopted for the multiple video camera of position acquisition according to the multiple video camera in multiple periods
The image collected；It identifies personage in described image, obtains the object identity of personage in described image, the object identity record has
The time of occurrence and frequency of occurrence of personage；The history that the object identity is obtained from history acquisition data acquires information, according to
Time of occurrence and frequency of occurrence in history acquisition information directly determine in described image personage within multiple periods
Frequency of occurrence；If the sum of the frequency of occurrence of personage within multiple periods is more than or equal to frequency threshold value in described image, institute is judged
Whether the changing condition for stating frequency of occurrence of the personage within multiple times in image meets number change condition；If in described image
The changing condition of frequency of occurrence of the personage within multiple periods meets number change condition, it is determined that personage is in described image
Permanent resident population；
The server end, the information for being also used to will determine as the personage of permanent resident population are added to target database；According to described
Target database carries out permanent resident population's analysis；It will analyze as the result is shown in client；
The client, the analysis result analyzed for showing the permanent resident population that the server end is sent；
The video camera, server end and client are attached by directly or indirectly mode.
7. a kind of computer installation, which is characterized in that the computer installation includes processor, and the processor is deposited for executing
Permanent resident population's acquisition methods as described in any one of claim 1-4 are realized when the computer program stored in reservoir.
8. a kind of computer readable storage medium, is stored thereon with computer instruction, it is characterised in that: the computer instruction quilt
Permanent resident population's acquisition methods as described in any one of claim 1-4 are realized when processor executes.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710671651.7A CN107480624B (en) | 2017-08-08 | 2017-08-08 | Permanent resident population's acquisition methods, apparatus and system, computer installation and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710671651.7A CN107480624B (en) | 2017-08-08 | 2017-08-08 | Permanent resident population's acquisition methods, apparatus and system, computer installation and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107480624A CN107480624A (en) | 2017-12-15 |
| CN107480624B true CN107480624B (en) | 2018-12-11 |
Family
ID=60599986
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710671651.7A Active CN107480624B (en) | 2017-08-08 | 2017-08-08 | Permanent resident population's acquisition methods, apparatus and system, computer installation and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107480624B (en) |
Families Citing this family (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108154457A (en) * | 2018-01-02 | 2018-06-12 | 深圳云天励飞技术有限公司 | The method and system of population analysis |
| CN110555923A (en) * | 2018-05-31 | 2019-12-10 | 杭州海康威视数字技术股份有限公司 | Personnel registration method and system |
| CN108764369B (en) * | 2018-06-07 | 2021-10-22 | 深圳市公安局公交分局 | Figure identification method and device based on data fusion and computer storage medium |
| 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 |
| CN109118413A (en) * | 2018-08-21 | 2019-01-01 | 北京深瞐科技有限公司 | Urban activity demographics method and device thereof, computer-readable medium |
| CN111275873B (en) * | 2018-11-19 | 2022-07-26 | 深圳云天励飞技术有限公司 | Traffic control management method and device, electronic equipment and storage medium |
| CN110334564B (en) * | 2019-03-18 | 2020-04-24 | 特斯联（北京）科技有限公司 | Frequent population identification method and system based on target tracking |
| CN109784321A (en) * | 2019-03-28 | 2019-05-21 | 北京深醒科技有限公司 | A kind of real population statistical classification method and apparatus based on recognition of face |
| CN111061691A (en) * | 2019-12-25 | 2020-04-24 | 秒针信息技术有限公司 | Method and device for determining fixed member |
| CN112689131B (en) * | 2021-03-12 | 2021-06-01 | 深圳市安软科技股份有限公司 | Gridding-based moving target monitoring method and device and related equipment |
| CN113537078A (en) * | 2021-07-19 | 2021-10-22 | 深圳康佳电子科技有限公司 | Personnel management method and device, intelligent terminal and computer readable storage medium |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106503631A (en) * | 2016-10-10 | 2017-03-15 | 深圳云天励飞技术有限公司 | A kind of population analysis method and computer equipment |
| CN106709840A (en) * | 2016-12-06 | 2017-05-24 | 上海云砥信息科技有限公司 | City permanent population evaluation method based on mobile network data |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7233933B2 (en) * | 2001-06-28 | 2007-06-19 | Microsoft Corporation | Methods and architecture for cross-device activity monitoring, reasoning, and visualization for providing status and forecasts of a users' presence and availability |
-
2017
- 2017-08-08 CN CN201710671651.7A patent/CN107480624B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106503631A (en) * | 2016-10-10 | 2017-03-15 | 深圳云天励飞技术有限公司 | A kind of population analysis method and computer equipment |
| CN106709840A (en) * | 2016-12-06 | 2017-05-24 | 上海云砥信息科技有限公司 | City permanent population evaluation method based on mobile network data |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107480624A (en) | 2017-12-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107480624B (en) | Permanent resident population's acquisition methods, apparatus and system, computer installation and storage medium | |
| CN102947850B (en) | Content output apparatus, content outputting method | |
| CN107798027B (en) | Information popularity prediction method, information recommendation method and device | |
| WO2021031600A1 (en) | Data collection method and apparatus, computer device, and storage medium | |
| CN107197384A (en) | The multi-modal exchange method of virtual robot and system applied to net cast platform | |
| CN105809178A (en) | Population analyzing method based on human face attribute and device | |
| CN110942055A (en) | State identification method, device and equipment for display area and storage medium | |
| CN104112209A (en) | Audience statistical method of display terminal, and audience statistical system of display terminal | |
| WO2023029574A1 (en) | Method and apparatus for acquiring passenger flow information, and computer device and storage medium | |
| CN107358471A (en) | A kind of tourist resources based on visit behavior recommends method and system | |
| US20210097556A1 (en) | Data processing | |
| CN112016485A (en) | Passenger flow statistical method and system based on face recognition | |
| TWI754456B (en) | Region arrangement method, apparatus and computer readable storage medium | |
| CN113592785A (en) | Target flow statistical method and device | |
| CN110264497B (en) | Method and device for determining tracking duration, storage medium and electronic device | |
| CN114024737B (en) | Method, apparatus and computer readable storage medium for determining live room volume | |
| TW202226114A (en) | Information processing method, device, electronic device, storage medium, and computer program | |
| CN114510641A (en) | Flow statistical method, device, computer equipment and storage medium | |
| CA2939729A1 (en) | Correlating data from satellite images with retail location performance | |
| CN112183380B (en) | Passenger flow volume analysis method and system based on face recognition and electronic equipment | |
| CN112561636A (en) | Recommendation method, recommendation device, terminal equipment and medium | |
| CN108009998A (en) | Composition method of cutting out, device, equipment and the storage medium of a kind of character image | |
| CN113822367B (en) | Regional behavior analysis method, system and medium based on human face | |
| CN111178113A (en) | Information processing method, device and storage medium | |
| WO2021103727A1 (en) | Data processing method, device, and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |