CN107564283B - A kind of macroscopical wagon flow flow detection algorithm based on WIFI signal - Google Patents
A kind of macroscopical wagon flow flow detection algorithm based on WIFI signal Download PDFInfo
- Publication number
- CN107564283B CN107564283B CN201710736719.5A CN201710736719A CN107564283B CN 107564283 B CN107564283 B CN 107564283B CN 201710736719 A CN201710736719 A CN 201710736719A CN 107564283 B CN107564283 B CN 107564283B
- Authority
- CN
- China
- Prior art keywords
- data
- extension set
- mobile terminal
- sub
- network
- 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
Landscapes
- Traffic Control Systems (AREA)
Abstract
The invention discloses a kind of macroscopical wagon flow flow detection algorithm based on WIFI signal, detection device system is disposed along traffic route, the detection device system includes multiple sub-networks, each sub-network includes a host and several extension sets, the extension set (single detection device) passes through wireless passive perceptual model, acquisition is by mobile terminal device based on the Wifi agreements broadcast data packet that environment is sent around at random, and it screens the wherein data packet with mobile terminal device id information and is retrieved, it is uploaded to host after stamping extension set label, the data being collected into are carried out unified storage and stamp time tag by host, and it is uploaded in data server and stores, and assessment detection is carried out to macroscopical wagon flow flow by data analysis.
Description
Technical field
The invention belongs to the improvement of development of Mobile Internet technology more particularly to macro-traffic information monitoring algorithm.
Background technology
Traffic flow data is the important information source of traffic operation dispatching and command system, can be command scheduling, the magnitude of traffic flow
Control and traffic guidance provide decision-making foundation.There are many existing Traffic flow detecting technologies, can be divided into contact according to mounting means
Formula detection mode and non-contact detection mode.Wherein contact measurement technology includes piezoelectricity, pressure pipe detection and loop coil
Detection.The major defect of this technology is that vehicle causes the service life of detector shorter rolling for road, is detected laying
When device, the road surface that suspends traffic, destroys is needed, therefore more difficult, use cost height is gone along with sb. to guard him in installation.Non-contact detection technology master
To be wave frequency detection and video detection.Wave frequency detection is divided into microwave, ultrasonic wave and three kinds infrared etc..Non-contact detection device can lead to
Holder installation is crossed, easy to maintain, service life is long, major defect is easily to be influenced by weather and outdoor conditions, and it is suitable that there are environment
The problems such as answering property is not strong, volume of transmitted data is big, Detection accuracy is not high and cost is higher.
With the rapid development of China's highway network, freeway traffic flow detects application demand and increases severely.In highway network
In, traffic flow information is equally important, and by flow information, highway network administrative department can understand the reality in each section in real time
When vehicle fleet size information, intuitive road network vehicle load amount is provided, accurate data is provided for the scheduling and integrated planning of road network.
But highway network has that some are special, such as highway power supply is inconvenient, information transmission is difficult, with
And fail to lay all kinds of detectors etc. in advance in process of construction, it can not accomplish concentrated type monitoring and management, need to existing detection
Device is further designed and is improved.
Invention content
In view of the problems of the existing technology, macroscopical wagon flow flow detection based on WIFI signal that the present invention provides a kind of
Algorithm, the present invention is based on the unique ID of portable mobile terminal, the macro-traffics of gathered data timestamp and detection device location information
Infomation detection algorithm has power supply convenient, and dense deployment, monitoring and management, algorithm optimization data is facilitated to be kept with truthful data
It is highly consistent, accurate Traffic Information data can be provided.
In order to solve the above technical problems, present invention employs following technical schemes：A kind of macroscopical vehicle based on WIFI signal
Flow detection algorithm is flowed, disposes detection device system along traffic route, the detection device system includes multiple sub-networks, each
Sub-network includes a host and several extension sets, and the extension set (single detection device) is adopted by wireless passive perceptual model
Collect by mobile terminal device based on the Wifi agreements broadcast data packet that environment is sent around at random, and screens wherein to carry and move
The data packet of dynamic terminal device id information is retrieved, and host, the data that host will be collected into are uploaded to after stamping extension set label
It carries out unified storage and stamps time tag, and be uploaded in data server and store, and by data analysis to macroscopical wagon flow
Flow carries out assessment detection.
Further, the analysis of the data includes the following steps：
Step 1：The data D of complete period is acquired by extension set,Wherein, DijIt indicates j-th
No. i-th extension set data of subnet；N indicates that the number of subnet, M indicate the extension set number in j-th of subnet；
Step 2：Data are sliced and extract section S and complete period (the data D&apos of T- Δs t) to be analyzed;s,D in formulaisFor the collected data of extension set that number is i under s subnets；
Step 3：Spatial match is carried out to the sub-network of deployment and corresponding practical section S, obtain sub-network host with it is corresponding
The extension set deployment scenario list of the number information in section and the sub-network；
Step 4：The data of each extension set acquisition are ranked up according to mobile terminal device ID number, establish data matrix
{Tower(i,s),t}；
Step 5：The ID data lists of foundation are classified by the number for appearing in different data matrix：For in the time
In section Δ t, what mobile terminal ID only occurred in the single extension set of sub-network, to the corresponding data of mobile terminal ID individually extract into
The follow-up efficiency analysis of row；It, should in period Δ t, mobile terminal ID occurs in sub-network two or more extension set
The corresponding data of mobile terminal ID are directly as valid data；
Step 6：For in period Δ t, mobile terminal ID is only in the single extension set appearance of sub-network, to movement end
ID corresponding data in end, which are individually extracted, carries out follow-up efficiency analysis：1, within the Δ t times, mobile terminal ID is individually dividing
Repeat in the data matrix TOWER of machine, and case above occur in multiple mobile terminal ID, mark corresponding road section is congestion shape
Condition, and such ID data is denoted as valid data；2, within the Δ t times, do not find mobile terminal ID in single extension set number
According to repeating in matrix TOWER, then traverse whether the sub-network before and after sub-network corresponding road section S identical ID number occurs,
If do not occurred, using the ID data as noise data processing, if occurred in other sub-networks, identify into significant figure
According to list；
Step 7：Step 4~6 are repeated until data processing finishes；
Step 8：Merger will be carried out by the valid data of step 5 and 6 processing gained, and according to data matrix TOWER institutes
The chronological order of position and appearance in corresponding physical space, and ID data matrixes are divided into it is two-way, and to each list
Subsequent processing is carried out to data；
Step 9：Within the period of moment T- Δ t to moment T, unidirectional valid data total amount is V, V=D { ID }, and is led to
Cross the detection that following methods carry out practical macroscopical section flow：
In formula, F () is the fitting function of effective ID data, and x is extension set sum in subnet, and i is extension set number in subnet；
Setting feedback Rule of judgmentS is algorithm training sample, and setting feedback iteration number is C, and iteration is arranged
End condition isWhenData fitting is completed when eligible, exports section data on flows.
Further, the S of algorithm training sample described in step 9 is the data that coil checker or radar detector obtain,
And as effective reference unit.
Advantageous effect：The present invention provides one kind being based on the unique ID of portable mobile terminal, gathered data timestamp and detection
The macro-traffic infomation detection algorithm of device location information realizes data mining and analysis to mobile terminal gathered data, is
Magnitude of traffic flow detector and detecting system based on WIFI signal provide the excavation of the depth based on the type data and the magnitude of traffic flow
Detection algorithm is realized, has been filled up application blank of the type data in terms of Vehicle Detection, has been promoted the development in wisdom traffic field.
Description of the drawings
Fig. 1 is the deployment principle schematic of the traffic flow detection system of the present invention based on WIFI signal；
Fig. 2 is the logic flow schematic diagram of macroscopical wagon flow flow detection algorithm of the present invention；
Fig. 3 is the sorting technique schematic diagram of valid data in macroscopical wagon flow flow detection algorithm of the present invention；
Fig. 4 is the optimization process schematic diagram of original valid data in macroscopical wagon flow flow detection algorithm of the present invention；
The road of vehicle flow detecting system disposes schematic diagram in Fig. 5 embodiment of the present invention；
Fig. 6 is detector initial data of the present invention, optimizes the contrast curve of data and training sample data；
Fig. 7 is the enlarged drawing of ellipse encircled portion in Fig. 6；
Ratio compares figures of the Fig. 8 between No. 21 experimental groups, No. 31 experimental groups and training sample data.
Specific implementation mode
Below in conjunction with the accompanying drawings and with specific embodiment, the present invention is furture elucidated.It should be understood that these embodiments are only used for
It the bright present invention rather than limits the scope of the invention, after having read the present invention, those skilled in the art are to of the invention
The modification of various equivalent forms falls within the application range as defined in the appended claims.
As shown in Figure 1, for traffic flow detection system and detection sub-network network deployment schematic diagram based on WIFI signal.This hair
It is bright to provide a kind of traffic information detection algorithm for data collected by the system.
As shown in Fig. 2, the traffic flow detection system operation principle the present invention is based on WIFI signal is as follows：
Detection device system deployment mode：In figure, Tower (j) indicates j-th of sub-network host computer in disposed road network,
Tower (i, j) indicates i-th of extension set in j-th of subnet.Each sub-network includes a host and several extension sets, extension set
Quantity can suitably increase and decrease according to road network condition, sub-network maximum coverage range 2Km, single extension set detection range maximum radius
250m, user can adjust single extension set detection range according to practical road conditions condition, between extension set distance d settings only need to be more than twice
Extension set detection range, equally can according to practical road conditions condition carry out flexible modulation.Sub-network deployment density can be according to practical friendship
Logical environmental management demand is disposed.
Detection device data acquisition flow：Single detection device, that is, extension set is acquired by wireless passive perceptual model by moving
Dynamic terminal device at random around environment send broadcast data packet, and screen wherein carry equipment id information data packet into
Row retrieval.It is uploaded to host after stamping extension set label, the data being collected into are carried out unified storage and stamp time tag by host,
And be uploaded in data server and stored, it waits to be analyzed.
As in Figure 2-4, section flow detection algorithm basic procedure of the present invention is as follows：
Step 1：Acquiring complete period, (partial data of T- Δs t), partial data are expressed as
Wherein DijIndicate No. i-th extension set data of j-th of subnet；
Step 2：Data are sliced, and extraction and analysis section S and the period (partial data of T- Δs t)
Step 3：Physical spatial location maps, itself and practical section S are carried out space by corresponding disposed sub-network
Match, each sub-network host carries the corresponding number information of corresponding road section and extension set deployment scenario list；
Step 4：Gathered data is ranked up according to its ID number, and establishes data matrix { Tower (i, s), t }；
Step 5：The ID data lists of foundation are classified by the number appeared in different Tower, it will be only one
The ID occurred in a Tower, which is individually extracted, to be analyzed, and the ID data occurred in more than two Tower are classified as one kind；
Step 6：It analyzes, situation is divided into following for only occurring in the ID in a Tower in period Δ t
Two kinds：1, within the Δ t periods, repeat the ID in the Tower, and this kind of situation largely occurs, there is a great deal of ID
This occurs, then it represents that congestion occurs in the section, which is valid data；If 2, not finding this in the Δ t periods
ID repeats in the Tower, then traverses subnet before and after the S of the section, search whether identical ID number occur, if do not gone out
Existing, this data is handled as noise data, if occurring in other subnets, stamps mark, and be included into valid data
List；
Step 7：Step 4,5,6 are repeated, until data processing finishes；
Step 8：The valid data of processing gained in step 5 and 6 are subjected to merger, and according to Tower in physical space
Position and appearance time t sequencing, be two-way (track have directionality) by ID data separations, and to each list
It is handled to data；
Step 9：In T- Δs t to T time section, unilateral direction valid data total amount is V=D { ID }, using following methods
Practical macroscopical section flow is assessed, as shown in Figure 4：
By that can be obtained in figure, ID_X indicates that effective ID data, F () indicate that approximate fits function, bias reference system S indicate
Imitate reference unit, such as coil checker data, radar detector data.Cumulative ID data, and pass through approximate fits letter
Number F (), is fitted, and feedback Rule of judgment isCan according to accuracy of detection need to the ratio domain value range into
Row is adjusted, when S/V resulting values are in domain value range, such asIt indicates to complete data fitting operations, be formed effective
Section data on flows.
As shown in figure 5, to be tested using the sections this method G42, two groups of experimental groups are deployed in figure is respectively
No. 21 and No. 31, and it is distributed in two-way road both sides.For 31 experimental groups with every 5 minutes for chronomere, to its Shanghai extremely
Beijing direction and Beijing to Shanghai angle detecting quantity, the 1 kilometer of average rate and detection irrelevance progress with coil checker
Compare control.
As shown in Figures 6 and 7, it is excellent by above-mentioned algorithm that the present invention is based on the initial data of the detecting system of WIFI signal acquisition
Change the data on flows after output and keeps highly consistent with training sample data；As it can be observed in the picture that No. 21 experimental groups and No. 31 experimental groups
Ratio keep highly consistent, ratio range is essentially 1, and ratio curve fluctuation is smaller, illustrates that detector of the present invention (mainly divides
Machine) deployed position on road influences little, and both sides can be deployed in, can also be deployed among intermediate isolation flower bed,
Have the characteristics that deployment is flexible；No. 21 experimental groups and No. 31 the experimental groups ratio with training sample data respectively, it is also basic to keep
It is consistent.
Claims (2)
1. a kind of macroscopical wagon flow flow detection algorithm based on WIFI signal disposes detection device system along traffic route, described
Detection device system includes multiple sub-networks, and each sub-network includes a host and several extension sets, and the extension set passes through nothing
The passive perceptual model of line, acquisition is by mobile terminal device based on the Wifi agreements broadcast data that environment is sent around at random
Packet, and screen the wherein data packet with mobile terminal device id information and retrieved, it is uploaded to host after stamping extension set label,
The data being collected into are carried out unified storage and stamp time tag by host, and are uploaded in data server and are stored, and are passed through
Data analysis carries out assessment detection to macroscopical wagon flow flow；
The analysis of the data includes the following steps：
Step 1：The data D of complete period is acquired by extension set,Wherein, DijIndicate j-th of subnet
No. i-th extension set data；N indicates that the number of subnet, M indicate the extension set number in j-th of subnet；
Step 2：Data are sliced and are extracted with section to be analyzed and complete period (the data D of T- Δs t)s',D in formulaisFor the collected data of extension set that number is i under s subnets；
Step 3：Spatial match is carried out with corresponding practical section S to the sub-network of deployment, obtains sub-network host and corresponding road section
Number information and the sub-network extension set deployment scenario list；
Step 4：The data of each extension set acquisition are ranked up according to mobile terminal device ID number, establish data matrix { Tower
(i,s),t}；
Step 5：The ID data lists of foundation are classified by the number for appearing in different data matrix：For in period Δ
In t, what mobile terminal ID only occurred in the single extension set of sub-network, after individually extracting progress to the corresponding data of mobile terminal ID
Continuous efficiency analysis；For in period Δ t, mobile terminal ID occurs in sub-network two or more extension set, the movement
The corresponding data of Termination ID are directly as valid data；
Step 6：For in period Δ t, mobile terminal ID is only in the single extension set appearance of sub-network, to mobile terminal ID
Corresponding data, which are individually extracted, carries out follow-up efficiency analysis：1, within the Δ t times, mobile terminal ID is in single extension set
Repeating in data matrix TOWER, and case above occur in multiple mobile terminal ID, mark corresponding road section is congestion,
And such ID data is denoted as valid data；2, within the Δ t times, do not find mobile terminal ID in single extension set data square
Repeat in battle array TOWER, then traverses whether the sub-network before and after sub-network corresponding road section S identical ID number occurs, if
Do not occur, then using the ID data as noise data processing, if occurred in other sub-networks, identifies and arranged into valid data
Table；
Step 7：Step 4~6 are repeated until data processing finishes；
Step 8：Merger will be carried out by the valid data of step 5 and 6 processing gained, and according to corresponding to data matrix TOWER
The chronological order of position and appearance in physical space, and ID data matrixes are divided into it is two-way, and to each unidirectional number
According to progress subsequent processing；
Step 9：In T- Δs t to T time section, unidirectional valid data total amount is V, V=D { ID }, and is carried out by the following method
The detection of practical macroscopic view section flow：
In formula, F () is the fitting function of effective ID data, and x is extension set sum in subnet, and i is extension set number in subnet；
Setting feedback Rule of judgmentS is algorithm training sample, and setting feedback iteration number is C, and iteration ends are arranged
Condition isWhenData fitting is completed when eligible, exports section data on flows.
2. macroscopical wagon flow flow detection algorithm based on WIFI signal according to claim 1, it is characterised in that：In step 9
The algorithm training sample S is the data that coil checker or radar detector obtain, and as effective reference unit.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710736719.5A CN107564283B (en) | 2017-08-24 | 2017-08-24 | A kind of macroscopical wagon flow flow detection algorithm based on WIFI signal |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710736719.5A CN107564283B (en) | 2017-08-24 | 2017-08-24 | A kind of macroscopical wagon flow flow detection algorithm based on WIFI signal |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107564283A CN107564283A (en) | 2018-01-09 |
| CN107564283B true CN107564283B (en) | 2018-10-26 |
Family
ID=60975816
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710736719.5A Active CN107564283B (en) | 2017-08-24 | 2017-08-24 | A kind of macroscopical wagon flow flow detection algorithm based on WIFI signal |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107564283B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108682151B (en) * | 2018-05-30 | 2020-11-17 | 广东矩阵流大数据科技有限公司 | Mobile traffic flow statistical device and method based on wireless signal scanning technology |
| CN109525981B (en) * | 2018-11-22 | 2021-11-02 | 南京茶非氪信息科技有限公司 | Real-time flow detection method for macroscopic region |
| CN109670631B (en) * | 2018-11-22 | 2021-09-17 | 南京极行信息科技有限公司 | Real-time flow prediction method for macroscopic region |
| CN109362034B (en) * | 2018-11-22 | 2020-12-04 | 南京茶非氪信息科技有限公司 | Macroscopic region connecting channel heat degree prediction method |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101950481A (en) * | 2010-08-27 | 2011-01-19 | 杭州妙影微电子有限公司 | Method for obtaining road traffic flow cloud picture in real-time manner |
| CN102734510A (en) * | 2011-04-12 | 2012-10-17 | 白翼誌 | Safe flow guide device |
| CN106920388A (en) * | 2015-12-24 | 2017-07-04 | 北京奇虎科技有限公司 | A kind of highway monitoring system and control method |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106251646B (en) * | 2016-08-16 | 2018-09-07 | 寿光明 | Traffic flow detection system based on WIFI signal and detection method |
| CN106485918B (en) * | 2016-09-29 | 2019-04-05 | 蔡诚昊 | A kind of traffic congestion evacuation effect evaluation method based on WIFI |
-
2017
- 2017-08-24 CN CN201710736719.5A patent/CN107564283B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101950481A (en) * | 2010-08-27 | 2011-01-19 | 杭州妙影微电子有限公司 | Method for obtaining road traffic flow cloud picture in real-time manner |
| CN102734510A (en) * | 2011-04-12 | 2012-10-17 | 白翼誌 | Safe flow guide device |
| CN106920388A (en) * | 2015-12-24 | 2017-07-04 | 北京奇虎科技有限公司 | A kind of highway monitoring system and control method |
Non-Patent Citations (1)
| Title |
|---|
| 基于Wi-Fi Direct的道路交通状态信息采集方法;李珺;《公路》;20151231(第12期);第164-169页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107564283A (en) | 2018-01-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107564283B (en) | A kind of macroscopical wagon flow flow detection algorithm based on WIFI signal | |
| CN107564281B (en) | A kind of macroscopical wagon flow volume forecasting algorithm based on WIFI signal | |
| CN102737510B (en) | Real-time traffic condition acquisition method based on mobile intelligent terminal | |
| CN108109423B (en) | Underground parking lot intelligent navigation method and system based on WiFi indoor positioning | |
| CN106251646B (en) | Traffic flow detection system based on WIFI signal and detection method | |
| CN108320501A (en) | Public bus network recognition methods based on user mobile phone signaling | |
| CN102083204A (en) | Positioning and tracking system method of active nodes in linear environment | |
| CN104217593B (en) | A kind of method for obtaining road condition information in real time towards mobile phone travelling speed | |
| CN105785411A (en) | Abnormal locus detection method based on area division | |
| CN107507419A (en) | A kind of magnitude of traffic flow detector based on WIFI signal | |
| CN202134048U (en) | Scenic area visitor distribution statistical system | |
| CN106023643A (en) | Internet of things-based novel vehicle detection device | |
| CN102062866A (en) | Method and device for calculating travelling speed between two geographic positions | |
| CN103152697A (en) | Method for realizing automatic floor positioning by using intelligent mobile phone Wi-Fi (Wireless Fidelity) function | |
| CN111583651A (en) | Road tunnel traffic situation sensing system and method based on radar | |
| CN109615851A (en) | A kind of sensing node choosing method in intelligent perception system based on key road segment | |
| CN106453523A (en) | Intelligent weather identification system and method | |
| CN108449439A (en) | Number of people in car statistical system based on WiFi technology | |
| CN107564284B (en) | A kind of traffic based on WIFI signal detection is passed unimpeded grade forecast system | |
| CN103870631A (en) | Construction method for intelligent power transmission network layout model based on 3S technology | |
| CN107689153B (en) | A kind of traffic cross-sectional flow prediction algorithm based on WIFI signal | |
| CN107529664B (en) | A kind of traffic based on WIFI signal is passed unimpeded grade detection system | |
| CN107564282B (en) | A kind of traffic cross-sectional flow detection method based on WIFI signal | |
| CN103095815B (en) | Positioning of mobile equipment method and apparatus | |
| CN202121780U (en) | Active node positioning tracking system under linear environment |
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 | ||
| CB02 | Change of applicant information |
Address after: 211135 2, B unit 300, Zhihui Road, Kirin science and Technology Innovation Park, Jiangning District, Nanjing, Jiangsu. Applicant after: Nanjing tea, non krypton Mdt InfoTech Ltd Address before: 210000 room 529, science and technology base, 12 Hengguang Road, Nanjing economic and Technological Development Zone, Nanjing, Jiangsu Applicant before: Nanjing tea, non krypton Mdt InfoTech Ltd |
|
| CB02 | Change of applicant information | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |