CN107564282A - A kind of traffic cross-sectional flow detection algorithm based on WIFI signal - Google Patents
A kind of traffic cross-sectional flow detection algorithm based on WIFI signal Download PDFInfo
- Publication number
- CN107564282A CN107564282A CN201710736700.0A CN201710736700A CN107564282A CN 107564282 A CN107564282 A CN 107564282A CN 201710736700 A CN201710736700 A CN 201710736700A CN 107564282 A CN107564282 A CN 107564282A
- Authority
- CN
- China
- Prior art keywords
- data
- sub
- extension
- mobile terminal
- 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.)
- Granted
Links
Landscapes
- Traffic Control Systems (AREA)
Abstract
The invention discloses a kind of traffic cross-sectional flow detection algorithm based on WIFI signal, including multiple sub-networks, each sub-network includes a main frame and several extension sets, the extension set passes through wireless passive perceptual model, gather the broadcast data bag sent at random to surrounding environment based on Wifi agreements from mobile terminal device, and screen the wherein packet with mobile terminal device id information and retrieved, main frame is uploaded to after stamping extension set label, the data being collected into are carried out unified storage and stamp time tag by main frame, and it is uploaded in data server and stores, and traffic cross-sectional flow is detected by data analysis.The present invention realizes the data mining and analysis to mobile terminal gathered data, has filled up application blank of the type data in terms of Vehicle Detection, has promoted the development in wisdom traffic field.
Description
Technical Field
The invention belongs to the mobile internet technology, and particularly relates to an improvement of a macroscopic traffic information monitoring algorithm.
Background
The traffic flow data is an important information source of a traffic operation scheduling command system, and can provide decision basis for command scheduling, traffic flow control and traffic guidance. The existing traffic flow detection technologies are various, and can be divided into a contact detection mode and a non-contact detection mode according to installation modes. Among the contact detection techniques are piezoelectric, pressure tube detection and toroidal coil detection. The main defects of the technology are that the rolling of the vehicle on the road causes the service life of the detector to be short, and when the detector is arranged, the traffic needs to be interrupted and the road surface needs to be damaged, so that the installation and the enclosure are difficult, and the use cost is high. The non-contact detection technology mainly comprises wave frequency detection and video detection. The wave frequency detection is divided into three types, namely microwave, ultrasonic wave, infrared and the like. The non-contact detector can be installed through a bracket, is convenient to maintain and long in service life, and has the main defects of being easily influenced by outdoor weather conditions, and the problems of low environmental adaptability, large data transmission quantity, low detection accuracy, high manufacturing cost and the like.
With the rapid development of the highway network in China, the application requirement of highway traffic flow detection is increased dramatically. In the expressway network, traffic flow information is also very important, and through the flow information, an expressway network management department can know the real-time vehicle quantity information of each road section in real time, so that intuitive expressway network vehicle load capacity is provided, and accurate data is provided for dispatching and overall planning of the expressway network.
However, there are some special situations in the highway network, such as inconvenient power supply on the highway, difficult information transmission, and failure to lay various detectors in advance in the construction process, and the like, which cannot achieve intensive monitoring and management, and further design and improvement of the existing detectors are needed.
Disclosure of Invention
Aiming at the problems in the prior art, the invention provides a traffic cross-section flow velocity detection algorithm based on a WIFI signal.
The invention realizes data mining and analysis of the data collected by the mobile terminal based on the unique ID of the portable mobile terminal, the timestamp of the collected data and the macroscopic traffic information detection algorithm of the position information of the detection equipment, and can be applied to the detection of traffic section flow velocity.
In order to solve the technical problems, the invention adopts the following technical scheme:
a traffic cross-section flow velocity detection algorithm based on WIFI signals deploys a detection device system along a traffic road, the detection device system comprises a plurality of sub-networks, each sub-network comprises a host and a plurality of extension sets, each extension set (single detection device) collects broadcast data packets sent to the surrounding environment randomly based on a Wifi protocol by mobile terminal devices through a wireless passive sensing mode, screens the data packets with ID information of the mobile terminal devices for retrieval, uploads the data packets to the host after the extension set labels are printed, the host stores collected data in a unified mode, prints time labels on the collected data, uploads the collected data to a data server for storage, and detects traffic cross-section flow velocity through data analysis.
Further, the analysis of the data comprises the steps of:
step 1: the data D for the complete time period are collected by the extension set,wherein D is ij Indicating the ith extension data of the jth subnet; n represents the number of the sub-networks, and M represents the number of the sub-networks in the jth sub-network;
and 2, step: slicing the data and extracting the data D of the section S to be analyzed and the complete time period (T-delta T) s '，In the formula D is The data collected by the extension set with the number i under the s sub-network;
and step 3: carrying out space matching on the deployed sub-network and the corresponding actual road section S to obtain the number information of the sub-network host and the corresponding road section and an extension deployment condition list of the sub-network;
and 4, step 4: sequencing the data collected by each extension according to the ID number of the mobile terminal equipment, and establishing a data matrix { Tower (i, s), t };
and 5: classifying the established ID data list according to the times of occurrence in different data matrixes: for the condition that the mobile terminal ID only appears in a single extension of the sub-network in the time period delta t, independently extracting data corresponding to the mobile terminal ID for subsequent validity analysis; for the situation that the mobile terminal ID appears in two or more extension sets of the sub-network within the time period delta t, the data corresponding to the mobile terminal ID is directly used as valid data;
and 6: for the situation that the mobile terminal ID only appears in a single extension of the sub-network in the time period delta t, the data corresponding to the mobile terminal ID is independently extracted for subsequent validity analysis: 1. when the mobile terminal ID repeatedly appears in the data matrix TOWER of a single extension within the time delta t and a plurality of mobile terminal IDs appear, marking the corresponding road section as a congestion condition, and recording the ID data as effective data; 2. when the mobile terminal ID is not found to repeatedly appear in a single extension data matrix TOWER within the time delta t, traversing whether sub-networks before and after a section S corresponding to the sub-network have the same ID number or not, if not, processing the ID data as noise data, and if the ID data appear in other sub-networks, marking the ID data into a valid data list;
and 7: repeating the steps 4-6 until the data processing is finished;
and 8: merging the effective data obtained by the processing in the steps 5 and 6, dividing the ID data matrix into two directions according to the position in the physical space corresponding to the data matrix TOWER and the appearance time sequence, and performing subsequent processing on each unidirectional data;
and step 9: in a time period from T-delta tT-delta T to T, the total amount of the one-way effective data is V, V = D { ID }, and the actual macroscopic cross section flow is detected by the following method:
(1) First, the weight Δ (x) of the velocity of each ID involved in the calculation is introduced and the average flow velocity v' (n-m) between extension numbers m and n is obtained by the following formula: (since the speed result of each road section is obtained from the valid ID detected by the road section, and there is an actual offset in the actual physical location L of each ID, the time information of the ID collected and time-stamped by the extension corresponds to the actual physical location of the ID when the extension is usedUsing the distance difference L between two points as the calculation reference n -L m (m&And (n) when the mileage is used as the mileage, the calculated speed obtains the deviation which needs to be corrected)
Where v' (n-m) is the average flow rate in the j-th subnetwork calculated by the subset numbered m to n (i.e. the average flow rate between the subset numbered m and n), L n The physical position of the extension with the number n in the jth subnet is obtained;the moment when the kth ID number is collected by the extension with the number of n in the subnet; Δ (k) is a weight value of the kth ID number in the effective data of the calculation data, and
(2) In the actual self-network learning process, the reference system such as a coil, a video, a microwave and other detectors can only represent the traffic flow, the flow velocity and the like passing through the cross section, and the two-dimensional data form belongs to. The algorithm of the embodiment adopts a three-dimensional distribution based on the detection equipment, and can measure the flow velocity between any two extensions in the sub-network within the coverage area of the algorithm. However, considering that the existing reference system cannot meet the flow rate calibration for any covered road section in the sub-network, and meanwhile, due to the principle limitation of the system (the physical position of the signal cannot be accurately positioned, and the signal can only be represented by a range) and certain error exists in the flow rate calculation, the method is to perform the calibration on any covered road section L m To L n L of a road section m' To L n' The sum of the road sections is corrected, and omega (n ', m') is introduced as any L m' To L n' A matrix of weight coefficients for the road segments,
wherein j is the subnet number, i is the total number of the extension sets in the subnet, n, m, n ', m' are all the number of the extension set in the subnet of j, and n>, m; ω (n ', m') represents L calculated from the extension number group numbered (n ', m') n' To L' m A weight coefficient matrix occupied by the set of results when averaging the velocity;
(3) Finally, the L under the subnet is calculated by the following formula m To L n Average flow velocity v (L) of road section n -L m )，
Further, in step 9, the distribution scheme of the weights Δ (x) and ω (n ', m') is obtained by self-feedback learning and multiple iterative approximation approximate fitting, and the specific steps are as follows:
firstly, setting initial values of delta (x) and omega (n ', m') respectively, and calculating an initial value Vo of the output cross-sectional flow velocity;
then, by setting the initial value v of the cross-sectional flow velocity 0 And performing self-feedback learning with the bias reference system S, performing approximate fitting by calculating a correction weight function value through multiple iterations to obtain an approximate fitting function F (·), setting the termination range of S/v according to the judgment basis of the self-feedback learning as S/v, and finishing the iterative fitting and outputting a distribution scheme of delta (x) and omega (n ', m') when the value of S/v accords with the termination range.
Further, in step 9, the bias reference system S is data obtained by a coil detector or a radar detector, and is used as an algorithm training sample or an effective reference unit.
Furthermore, the value range of the judgment basis of the self-feedback learning is more than or equal to 0.99 and less than or equal to 1.01.
Further, the distance between the adjacent extensions is d, the signal coverage radius of a single extension is r, and d > 2r.
Has the advantages that: the invention provides a macroscopic traffic information detection algorithm based on the unique ID of a portable mobile terminal, a collected data timestamp and position information of detection equipment, realizes data mining and analysis of the collected data of the mobile terminal, provides a traffic flow detector and a detection system based on WIFI signals with deep mining and traffic flow detection algorithm implementation based on the data, fills the application blank of the data in the aspect of traffic detection, and promotes the development of the field of intelligent traffic.
Drawings
Fig. 1 is a schematic diagram of a road deployment principle of the traffic cross-section flow velocity detection algorithm based on the WIFI signal.
Fig. 2 is a schematic flow chart of the traffic cross-section flow velocity detection algorithm based on the WIFI signal.
Fig. 3 is a schematic diagram of a noise reduction screening process of effective data in the traffic cross-section flow velocity detection algorithm based on the WIFI signal according to the present invention;
FIG. 4 is a schematic diagram of a process of approximating a real value by data approximate fitting in the traffic cross-section flow velocity detection algorithm based on the WIFI signal;
FIG. 5 is a schematic view of a system for detecting a section of Beijing Shanghai according to an embodiment of the present invention;
FIG. 6 is a graph comparing the cross-sectional flow rate measured in experiment set No. 31 with the flow rate measured by the coil detector for a unit of 5 minute data volume;
fig. 7 is a graph comparing the flow rates measured by the experiment set No. 21, the experiment set No. 31 and the coil detector.
Detailed Description
The invention will be further elucidated with reference to the following description of an embodiment in conjunction with the accompanying drawing. It is to be understood that these examples are for illustrative purposes only and are not intended to limit the scope of the present invention, which is to be given the full breadth of the appended claims and any and all equivalent modifications thereof which may occur to those skilled in the art upon reading the present specification.
As shown in fig. 1, the present invention includes a plurality of sub-networks, each sub-network and an actual road segment S are in a spatial matching mapping relationship, and a detection device deployed on each sub-network road segment S includes a plurality of extension sets and at least one host; the extension set is used as a basic sensor and is based on a 802.1b protocol (WIFI protocol) and used for monitoring and receiving a broadcast data packet sent by mobile equipment based on the WIFI signal protocol in the surrounding environment and transmitting the broadcast data packet to the data processing module, the data processing module deletes and reads the broadcast data packet to obtain an ID number of the mobile equipment and transmits data comprising the ID number and the extension set module number to the host; and the host computer is stored after being stamped with the timestamp and then uploads the timestamp to the remote server. The invention is based on the data packet containing ID number received by the extension sensor to carry out detection and calculation, and the traffic cross-section flow velocity of the corresponding road section is obtained. Specifically, the method comprises the following steps:
the detection equipment deployment mode of the invention is as follows: in fig. 1, tower (j) represents the j-th subnet host in the deployed road network, and Tower (i, j) represents the i-th extension in the j-th subnet. Each sub-network comprises a host and a plurality of extensions, the number of the extensions can be properly increased or decreased according to road network conditions, the maximum coverage range of the sub-network is 2Km, the maximum radius of the signal coverage range of a single extension is 250m, a user can adjust the prediction range of the single extension according to actual road conditions, the distance d between the extensions is set to be the extension prediction range which is only more than two times, and flexible adjustment can be performed according to the actual road conditions. The deployment density of the sub-networks can be deployed according to the management requirements of the actual traffic environment.
The data acquisition process of the detection equipment comprises the following steps: a single detection standby extension, namely a branch extension, randomly sends WIFI broadcast type data packets to the surrounding environment through a WiFi-based protocol acquisition by a mobile terminal device through a wireless passive sensing mode, namely a detector of a CC3 XXXXXX series chip of TI, and screens the data packets with device ID information for retrieval. And uploading the extension labels to a host computer, uniformly storing the collected data and stamping time labels by the host computer, uploading the data to a data server for storage, and waiting for analysis. The algorithm principle process of the invention is explained in detail as follows:
step 1: collecting complete data of complete time period (T-delta T) to finishThe whole data is represented asWherein D ij Indicating the ith extension data of the jth subnet;
and 2, step: slicing the data, and extracting the complete data of the analysis road section S and the time period (T-delta T)And step 3: mapping physical space positions, corresponding to the deployed sub-networks, and performing space matching on the sub-networks and the actual road sections S, wherein each sub-network host is provided with corresponding serial number information of the corresponding road sections and an extension deployment condition list;
and 4, step 4: sequencing the collected data according to the ID number of the collected data, and establishing a data matrix { Tower (i, s), t };
and 5: classifying the established ID data list according to the times of appearing in different Tower, independently extracting IDs appearing in only one Tower for analysis, and classifying the ID data appearing in more than two towers into one class;
and 6: the analysis of the IDs appearing in only one Tower classifies the cases into the following two: 1. during the time period of delta t, the ID repeatedly appears in the Tower, and the condition is occurred in a large amount, and the condition that a certain number of IDs appear indicates that the road section is in a congestion condition, and the ID is valid data; 2. if the ID is not found to be repeated in the Tower during the Δ t period, the data is culled, as shown in FIG. 3.
And step 7: repeating the step 4,5,6 to confirm that no missing data exists;
and 8: aiming at the situation of incomplete congestion, a data matrix { Tower (i, s), t } associated with the ID number is reestablished after the data are deleted;
and step 9: the data is further classified into a bidirectional data matrix according to the relation between time t and power in the data matrix { power (i, s), t }: d L And D R And calculating the data respectively;
step 10: since the speed result of each road section is detected by that road sectionObtaining valid IDs, wherein the actual physical position L of each ID has an actual offset, the time information of the ID collected by the extension and printed with the time stamp information corresponds to the actual physical position of the ID, and when the physical position of the extension is used as a calculation reference, the distance difference L between two points is used n -L m (m&And (n) when the mileage is used as the mileage, the calculated speed is deviated, and the deviation needs to be corrected. The weighting function Δ (x) is introduced as in fig. 4. In addition, in the actual self-network learning process, only the traffic flow, the flow velocity and the like passing through the cross section can be represented due to a reference system such as a coil, a video, a microwave and the like detector, and the method belongs to a two-dimensional data form. The algorithm of the embodiment adopts three-dimensional distribution based on the detection equipment, and can measure the flow rate between any two extensions in the sub-network within the coverage range of the algorithm. However, it is considered that the existing reference system cannot meet the flow rate calibration for any covered road section in the sub-network, and meanwhile, certain errors exist in flow rate calculation due to the principle limitation of the system (the physical position of a signal cannot be accurately positioned, and the signal can only be represented by a range). Therefore, it is necessary to pass through the arbitrary coverage L m To L n L of road section m' To L n' The sum of the road sections is corrected, and omega (n ', m') is introduced as any L m' To L n' A weight coefficient matrix for the road segment. The average flow velocity for the sub-network segments is finally calculated by the following formula,
where v' (n-m) is the average flow rate in the j subnet calculated by the subset numbered m to n (i.e. the average flow rate between the subset numbered m and n), L n The physical position of the extension with the number of n in the jth subnet is obtained; t is t n The moment when the kth ID number is collected by the extension with the number of n in the subnet; Δ (k) is a weight value occupied by the kth ID number in the effective data of the calculation data; i is the total number of the extension sets in the sub-network, n, m, n ', m' are all the number of the extension sets in the sub-network of the j number, and n>, m; ω (n ', m') represents the calculation of L from the set of extension numbers numbered (n ', m') n′ To L m′ A weight coefficient matrix occupied by the set of results when averaging the speed; ω (n ', m') is any L m' To L n' A weight coefficient matrix for the road segment.
Since the average flow velocity of the road section obtained from Δ (x) and ω (n ', m') will gradually generate an offset error with time as the data is updated, it is necessary to reset the value distribution scheme. Here, the weight coefficient matrices Δ (x) and ω (n ', m') may be subjected to multiple iterative approximate fitting according to neural network self-feedback learning, so as to obtain values of the weight coefficients Δ (x) and ω (n ', m') in the current time period, as shown in fig. 4:
and establishing a flow velocity calculation neural network, and generating a flow velocity matrix Vx of each ID according to the ID data matrix. As shown in FIG. 4, a weight function Δ (x) is introduced, the sum of the weight functions is 1, and the cross-sectional flow velocity is output after matrix summationThe method comprises the steps of setting an initial value of a weight function delta (x), correcting relevant parameters to perform approximate fitting through self-feedback learning in a bias reference system S (such as a coil detector, a radar detector and the like), and performing fitting through an approximate fitting function F (·), wherein when a feedback judgment condition is S/v and S/v is more than or equal to 0.99 and less than or equal to 1.01, data fitting is indicated to be completed, and a value assignment scheme of the delta (x) is determined. Similarly, self-feedback learning is performed on ω (n ', m') to obtain the closest value in the current time period.
As shown in FIG. 5, the following experiments are carried out on a certain section of G42 highway from Beijing to the Shanghai, and traffic flow detection systems of the invention are installed and deployed on two sides of the highway.
As shown in fig. 6, the flow rate of the road section obtained by detecting the data collected in the 31 experimental groups in the time unit of every 5 minutes and calculating by the algorithm of the present invention is compared with the real flow rate obtained by the coil detection. As shown in fig. 7, the ratio of the flow rate measured in experimental group No. 21 and experimental group No. 31 to the flow rate of the coil was analyzed to obtain a comparative graph. It can be seen from the graph that, in terms of average velocity, the deviation value between the calculated velocity of the detector and the detected velocity of the coil in 5 minutes is kept stable without any compensation. Through further mining of data and further optimization of experiments, the speed deviation can be effectively controlled, and the speed calculation precision is further improved.
Claims (5)
1. A WIFI signal-based traffic cross-section flow velocity detection algorithm is characterized in that a detection equipment system is deployed along a traffic road, the detection equipment system comprises a plurality of sub-networks, each sub-network comprises a host and a plurality of sub-networks, the sub-networks (single detection equipment) collect broadcast data packets sent to the surrounding environment by mobile terminal equipment based on a Wifi protocol through a wireless passive perception mode, screen the data packets with ID information of the mobile terminal equipment for retrieval, upload the data packets to the host after the tags of the sub-networks are printed, uniformly store the collected data and print time tags by the host, upload the data packets to a data server for storage, and detect the traffic cross-section flow velocity through data analysis.
2. The WIFI signal-based traffic cross section flow velocity detection algorithm of claim 1, wherein: the analysis of the data comprises the steps of:
step 1: the data D for the complete time period are collected by the extension set,wherein D is ij To representJ sub-net number i extension data; n represents the number of the sub-networks, and M represents the number of the sub-networks in the jth sub-network;
step 2: slicing the data and extracting data D 'of a road section S to be analyzed and a complete time period (T-delta T)' s ，In the formula D is The data collected by the extension set with the number i under the s sub-network;
and 3, step 3: carrying out space matching on the deployed sub-network and the corresponding actual road section S to obtain the number information of the sub-network host and the corresponding road section and an extension deployment condition list of the sub-network;
and 4, step 4: sequencing the data collected by each extension according to the ID number of the mobile terminal equipment, and establishing a data matrix { Tower (i, s), t };
and 5: classifying the established ID data list according to the times of occurrence in different data matrixes: for the condition that the mobile terminal ID only appears in a single extension of the sub-network in the time period delta t, independently extracting data corresponding to the mobile terminal ID for subsequent validity analysis; for the situation that the mobile terminal ID appears in two or more extension sets of the sub-network within the time period delta t, the data corresponding to the mobile terminal ID is directly used as valid data;
step 6: for the situation that the mobile terminal ID only appears in a single extension of the sub-network in the time period delta t, the data corresponding to the mobile terminal ID is independently extracted for subsequent validity analysis: 1. when the mobile terminal ID repeatedly appears in the data matrix TOWER of a single extension within the time delta t and a plurality of mobile terminal IDs appear, marking the corresponding road section as a congestion condition, and recording the ID data as effective data; 2. when the mobile terminal ID is not found to repeatedly appear in a single extension data matrix TOWER within the time delta t, traversing whether sub-networks before and after the sub-network corresponding to the road section S have the same ID number, if not, processing the ID data as noise data, and if the ID data appear in other sub-networks, marking the ID data into an effective data list;
and 7: repeating the steps 4-6 until the data processing is finished;
and 8: merging the effective data processed in the steps 5 and 6, distinguishing the ID data matrix into two directions according to the position in the physical space corresponding to the data matrix TOWER and the appearance time sequence, and performing subsequent processing on each unidirectional data;
and step 9: in a time period from T-delta T to T, the total amount of the one-way effective data is V, V = D { ID }, and the actual macroscopic cross-section flow is detected by the following method:
(1) First, the weight Δ (x) of the velocity of each ID involved in the calculation is introduced and the average flow velocity v' (n-m) between extension numbers m and n is obtained by the following formula:
where v' (n-m) is the average flow rate in the j subnet calculated by the subset numbered m to n (i.e. the average flow rate between the subset numbered m and n), L n The physical position of the extension with the number of n in the jth subnet is obtained;the moment when the kth ID number is collected by the extension with the number of n in the subnet; Δ (k) is a weight value occupied by the kth ID number in effective data of the calculation data, and
(2) By covering arbitrary L m To L n L of a road section m' To L n' The sum of the road sections is corrected, and omega (n ', m') is introduced as any L m' To L n' A weight coefficient matrix for the road segment, and:
in the formula, jIs the subnet number, i is the total number of the extension sets in the subnet, n, m, n ', m' are all the number of the extension set in the subnet of the j, and n>, m; ω (n ', m') represents L calculated from the extension number group numbered (n ', m') n' To L m′ A weight coefficient matrix occupied by the set of results when averaging the velocity;
(3) Finally, the L under the subnet is calculated by the following formula m To L n Average flow velocity v (L) of road section n -L m )，
3. The WIFI signal-based traffic cross-section flow velocity detection algorithm of claim 2, wherein: the distribution scheme of the weights Δ (x) and ω (n ', m') in step 9 is obtained by self-feedback learning and multiple iterative approximation approximate fitting, and the specific steps are as follows:
first, initial values of Δ (x) and ω (n ', m') are set, and an initial value v of the output cross-sectional flow velocity is calculated 0 ；
Then, by setting the initial value v of the cross-sectional flow velocity 0 Performing self-feedback learning with a bias reference system S, performing approximate fitting by repeatedly calculating and correcting a weight function value to obtain an approximate fitting function F (-) and performing self-feedback learning with the bias reference system S,
then, the ratio S/v of the output value S of the offset reference system and the cross-sectional flow velocity v is taken as a basis for judging the termination of the feedback learning, and the S/v range is set to be more than or equal to 0.99 and less than or equal to 1.01;
finally, when the value of S/v meets the termination range, the iterative fitting is complete and the assignment schemes for Δ (x) and ω (n ', m') are output.
4. The WIFI signal based traffic cross-section flow velocity detection algorithm according to claim 3, wherein: in step 9, the bias reference system S is data obtained by a coil detector or a radar detector, and is used as an algorithm training sample or an effective reference unit.
5. The WIFI signal-based traffic cross section flow velocity detection algorithm of claim 2, wherein: the distance between the adjacent extensions is d, the signal coverage radius of a single extension is r, and d is larger than 2r.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710736700.0A CN107564282B (en) | 2017-08-24 | 2017-08-24 | A kind of traffic cross-sectional flow detection method based on WIFI signal |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710736700.0A CN107564282B (en) | 2017-08-24 | 2017-08-24 | A kind of traffic cross-sectional flow detection method based on WIFI signal |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107564282A true CN107564282A (en) | 2018-01-09 |
| CN107564282B CN107564282B (en) | 2019-02-12 |
Family
ID=60976858
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710736700.0A Active CN107564282B (en) | 2017-08-24 | 2017-08-24 | A kind of traffic cross-sectional flow detection method based on WIFI signal |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107564282B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109362034A (en) * | 2018-11-22 | 2019-02-19 | 南京茶非氪信息科技有限公司 | A kind of macro-regions communication channel temperature prediction technique |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103794070A (en) * | 2014-02-24 | 2014-05-14 | 中国航天系统工程有限公司 | Dynamic induction information broadcasting method and system based on vehicle and road collaboration |
| CN204087491U (en) * | 2014-09-22 | 2015-01-07 | 深圳市金溢科技股份有限公司 | Information acquisition system, server, information issuing system and car-mounted terminal |
| US8937903B2 (en) * | 2011-06-14 | 2015-01-20 | At&T Intellectual Property I, L.P. | System and method for providing a content delivery network via a motor vehicle |
-
2017
- 2017-08-24 CN CN201710736700.0A patent/CN107564282B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8937903B2 (en) * | 2011-06-14 | 2015-01-20 | At&T Intellectual Property I, L.P. | System and method for providing a content delivery network via a motor vehicle |
| CN103794070A (en) * | 2014-02-24 | 2014-05-14 | 中国航天系统工程有限公司 | Dynamic induction information broadcasting method and system based on vehicle and road collaboration |
| CN204087491U (en) * | 2014-09-22 | 2015-01-07 | 深圳市金溢科技股份有限公司 | Information acquisition system, server, information issuing system and car-mounted terminal |
Non-Patent Citations (1)
| Title |
|---|
| 李珺: "基于Wi-Fi Direct的道路交通状态信息采集方法", 《公路》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109362034A (en) * | 2018-11-22 | 2019-02-19 | 南京茶非氪信息科技有限公司 | A kind of macro-regions communication channel temperature prediction technique |
| 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 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107564282B (en) | 2019-02-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR102116824B1 (en) | Positioning system based on deep learnin and construction method thereof | |
| CN100579307C (en) | Wireless node location method and device for featuring definition of search region to optimize location computation | |
| CN103476118B (en) | A kind of WLAN indoor location fingerprint positioning method for monitoring in real time | |
| CN106714102A (en) | Method of using intelligent mobile phone to assist indoor positioning | |
| CN102170697A (en) | Indoor positioning method and device | |
| CN102573049A (en) | Method and system for indoor positioning | |
| CN109598947B (en) | Vehicle identification method and system | |
| CN108109423A (en) | Underground parking intelligent navigation method and system based on WiFi indoor positionings | |
| CN107564281B (en) | A kind of macroscopical wagon flow volume forecasting algorithm based on WIFI signal | |
| CN103473706A (en) | Operating tunnel maintenance health monitoring management system based on BIM | |
| CN107564283B (en) | A kind of macroscopical wagon flow flow detection algorithm based on WIFI signal | |
| CN110022530B (en) | Wireless positioning method and system for underground space | |
| CN106453523A (en) | Intelligent weather identification system and method | |
| CN116684878A (en) | 5G information transmission data safety monitoring system | |
| CN107564282A (en) | A kind of traffic cross-sectional flow detection algorithm based on WIFI signal | |
| EP4081835B1 (en) | Methods, apparatuses, systems and computer program products for estimating road surface temperature | |
| Hung et al. | Model-driven traffic data acquisition in vehicular sensor networks | |
| CN114218978A (en) | Embedded lightweight millimeter wave radar target identification method | |
| CN107564284A (en) | A kind of traffic based on WIFI signal detection is passed unimpeded grade forecast system | |
| CN107529664A (en) | A kind of traffic based on WIFI signal is passed unimpeded grade detecting system | |
| CN107689153B (en) | A kind of traffic cross-sectional flow prediction algorithm based on WIFI signal | |
| KR20110130608A (en) | A slef-calibration motheod for vehicle detection system using dsrc road side equipment and on board unit | |
| CN103940421A (en) | Vertical locating method and device | |
| CN114782903A (en) | ESN-based highway river-crossing grand bridge group fog recognition and early warning method | |
| CN113449689A (en) | Communication tower remote monitoring method based on Internet of things platform |
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 | ||
| 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 |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |