CN109644360A - A method of differentiating that pedestrian flows to using WI-FI probe - Google Patents

A method of differentiating that pedestrian flows to using WI-FI probe Download PDF

Info

Publication number
CN109644360A
CN109644360A CN201780033651.2A CN201780033651A CN109644360A CN 109644360 A CN109644360 A CN 109644360A CN 201780033651 A CN201780033651 A CN 201780033651A CN 109644360 A CN109644360 A CN 109644360A
Authority
CN
China
Prior art keywords
data
pedestrian
detection
probe
flow
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
Application number
CN201780033651.2A
Other languages
Chinese (zh)
Other versions
CN109644360B (en
Inventor
杜豫川
岳劲松
仇越
暨育雄
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Tongji University
Original Assignee
Tongji University
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Tongji University filed Critical Tongji University
Publication of CN109644360A publication Critical patent/CN109644360A/en
Application granted granted Critical
Publication of CN109644360B publication Critical patent/CN109644360B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S5/00—Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations
    • G01S5/02—Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations using radio waves
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S5/00—Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations
    • G01S5/02—Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations using radio waves
    • G01S5/0278—Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations using radio waves involving statistical or probabilistic considerations
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06M—COUNTING MECHANISMS; COUNTING OF OBJECTS NOT OTHERWISE PROVIDED FOR
    • G06M11/00—Counting of objects distributed at random, e.g. on a surface
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/50—Context or environment of the image
    • G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
    • G06V20/53—Recognition of crowd images, e.g. recognition of crowd congestion
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/20—Movements or behaviour, e.g. gesture recognition
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W24/00—Supervisory, monitoring or testing arrangements
    • H04W24/08—Testing, supervising or monitoring using real traffic
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
    • H04W4/02—Services making use of location information
    • H04W4/023—Services making use of location information using mutual or relative location information between multiple location based services [LBS] targets or of distance thresholds
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W84/00—Network topologies
    • H04W84/02—Hierarchically pre-organised networks, e.g. paging networks, cellular networks, WLAN [Wireless Local Area Network] or WLL [Wireless Local Loop]
    • H04W84/10—Small scale networks; Flat hierarchical networks
    • H04W84/12—WLAN [Wireless Local Area Networks]
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
    • Y02D30/00—Reducing energy consumption in communication networks
    • Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Theoretical Computer Science (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Multimedia (AREA)
  • Probability & Statistics with Applications (AREA)
  • Health & Medical Sciences (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • General Health & Medical Sciences (AREA)
  • Psychiatry (AREA)
  • Social Psychology (AREA)
  • Human Computer Interaction (AREA)
  • Traffic Control Systems (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

A method of differentiating that pedestrian flows to using WI-FI probe, including data acquisition, data screening, data processing, Modifying model, differentiation pedestrian's flow direction.In conjunction with the space layout of different WI-FI probes, the initial data detected analyzed based on the data of received signal strength indication and detection time, can differentiate directional information of each MAC Address data on road, so that it is determined that corresponding pedestrian flows to.

Description

A method of differentiating that pedestrian flows to using WI-FI probe
A method of differentiating that pedestrian flows to using WI-FI probe
Technical field
The invention belongs to the acquisition of WI-FI data and pedestrian's flow detection technique fields, and in particular to a method of differentiate that pedestrian flows to using WI-FI probe.WI-FI probe obtains the initial data including received signal strength and detection time by the MAC Address data of capture mobile device；In conjunction with the space layout of different WI-FI probes, the initial data detected analyzed based on the data of received signal strength indication and detection time, directional information of each MAC Address data on road can be differentiated, so that it is determined that corresponding pedestrian flows to.Background technique
On the main pedestrian road in the places such as megastore, transport hub, travel resort; it often will appear large passenger flow phenomenon, especially in phase commuter rush hour, a large amount of pedestrians pour in main roads; it will cause some potential safety problems, influence the efficiency of operation in these places.Therefore, it is of great significance to the real-time detection of road pedestrian flow, science estimates practical flow of the people according to testing result, reliable flow of the people data can be provided for corresponding Security Personnel, to guarantee the normal operation in market, transport hub and travel resort using reasonable means in due course.It is also more and more diversified about the detection means of flow of the people at present, following a few classes can be substantially divided into according to the classification of detection technique:
(1) manual counts: manual research is passenger flow counting method the most traditional, and method is simple and stackable artificial judgment standard.But since it is higher to investigation personnel requirement, counting error is big, the quality of data is not high, data to arrange work is heavy after investigation, data system is bad and can not provide real time data, can not meet the growth of transport need at present, and in the place of flow of the people comparatively dense, real-time difficulty is larger, inefficiency
(2) gate formula passenger flow counting: gate is a kind of channel barrier device (channel management equipment), for managing the stream of people and specification pedestrian discrepancy, is mainly used in subway gate system, charge ticket check gate system.Its most basic most crucial function is to realize primary by a people, can be used for various charge, at the access road of gate inhibition's occasion.Cost is relatively low for which, and quantity accuracy is good, but in the case where service group has a large amount of luggage parcel more, and which is lower by efficiency, in case of emergency causes to hinder to the evacuation of pedestrian, and be unfavorable for taking action The trip of inconvenient personage.And it is only a certain section which, which detects stream of people's data, and stream of people's distribution can be grasped by needing to arrange multiple sections, and occupied area is larger.
(3) pedal passenger flow counting: pressure plare passenger flow statistics instrument is mounted on the ground of Examination region, and pressure sensor information is triggered when pedestrian passes through and is able to be automatically recorded.The quasi-instrument can be roughly divided into two types, and one kind is that counting and walking direction are carried out according to " human body steps on lift step data pattern ", and another kind of judged according to " passenger rides profile ".It this method reduce the influence run to passenger flow and installs simply, but it is low to detect accuracy, and jams on system unit and be easily damaged, it is maintainable poor.
(4) infrared type passenger flow counting: infrared type passenger flow counting can be divided into passive infrared formula passenger flow counting and active infrared formula passenger flow counting.Passive infrared formula passenger flow counting is using the heat release infrared probe of signal can avoid the interference of other objects, being only capable of detection human body and issued.When someone passes through, infrared sensor can detect certain variation as caused by human body infrared spectrum, while trigger a pulse signal, then judge number according to pulse signal number.Active infrared formula is then to emit customization wavelength infrared ray by emitting head to cover certain area, and the light identification passengers quantity of the passenger's reflection detected by sensor.Active infrared formula passenger flow counting overcomes the shortcomings that being influenced in passive infrared formula passenger flow counting by environment, light, but since it determines number using by carrying out simple judgement to pulse number, the case where thus causing the accuracy of statistics low, passing through simultaneously to more people is even more can not Accurate Determining.Also, the direction of passenger flow can not be differentiated merely with infrared mode, and detection device higher cost, be unsuitable for using on a large scale.
(5) video passenger flow counts: video passenger flow counting can be divided into monocular video passenger flow counting and binocular video passenger flow counting.Video passenger flow technology obtains video image by installing camera in critical passage, is counted using image procossing such as image segmentation, the capture passenger flow countings such as artificial neural network, stereo-picture analysis.But this method is started late, and technology is not yet mature.And implementation cost, maintenance cost are all higher, are difficult to solve the stream of people's individual segmentation problem when crowded thus accuracy is lower.
(6) WI-FI probe detection of passenger flow: WI-FI probe detection of passenger flow is the MAC Address by disposing WI-FI network in detection zone to obtain the mobile device for opening WI-FI function, to realize passenger flow counting.Passenger flow statistical method based on WI-FI is easy to operate, and equipment cost is reasonable, is influenced by non line of sight factor small, and flexibility is high, can obtain a large amount of statistical data simultaneously, has great advantages in stream of people's statistics under intensive duty traffic.And the data content obtained to probe is analysed in depth, the characteristics such as available stream of people's residence time, streamline flow direction.And this detection method supports cloud platform, data application to can be extended to marketing layer in subsequent operation.It is widely used at present in places such as large scale business area, tourist attractions, recreation grounds. WI-FI probe technique: WI-FI probe can detect the address MAC for the mobile device for opening WI-FI function, its principle includes: that WI-FI is based on IEEE802. l la/b/g/n agreement, in standard agreement, two kinds of operating modes of wireless access point and client are defined, also specify a variety of wireless data frame types such as Beacon, Ack, Data and Probe in agreement.What is interacted when client is connected to wireless access point is exactly data frame and acknowledgement frame, wireless access point periodically sends Beacon when client is not connected in wireless access point simultaneously, and client also can constantly send Probe frame and be detected to neighbouring wireless access point.And WI-FI probe is namely based on various wireless data frames to arrest the wireless access point of neighbouring client-side information, it can intercept and capture the MAC layer information for the mobile client that WI-FI is opened in a certain range, mainly include MAC Address, signal receiving strength value, timestamp etc..
But, all there are the generally existing following problems of the passenger flow detection method based on WI-FI for needing the disadvantages of manpower is more, equipment is expensive and occupied area is larger, and more popular at present in manual counts, gate counting method, pedal counting method, infrared type counting method and video count method etc.:
(1) unique mac address of mobile device by probe in detecting to premise be that the WI-FI of mobile device needs to be opening state.And the ratio of mobile device opening WI-FI is lower and unknown in crowd under actual scene.So the volume of the flow of passengers that WI-FI is detected under normal circumstances differs greatly with the practical volume of the flow of passengers, the effect is unsatisfactory from detection limit.
(2) there are multipath phenomenons and reflex during being captured by probe for the wireless exploration signal that mobile device is launched, and the multipath phenomenon of wireless signal and reflex can make signal intensity attenuation, cause probe in detecting to received signal strength indication (RSSI) have different degrees of decaying, when situation is serious even can't detect.So the verification and measurement ratio for also resulting in WI-FI is lower.
(3) due to the lower essential characteristic of verification and measurement ratio, cause directly to count the volume of the flow of passengers using testing result.So needing to establish suitable prediction model between detection limit and actual amount, to improve by the precision of detected value prediction actual value, while it should also meet the high accuracy of prediction model in the case of pedestrian's flow constantly fluctuates.
(4) rough location information under the number information and current state of pedestrian can only be counted, can not differentiate that pedestrian's flows to information.
And the research in terms of WI-FI passenger flow statistics at present is than relatively limited, it is concentrated mainly on the accurate positionin problem that indoor pedestrian is sought based on the accurate research to received signal strength indication (RSSI), and the description including characteristic parameters such as intensity of passenger flow, passenger flow tracks under existing interior WI-FI system.For how to effectively improve How the verification and measurement ratio of WI-FI passenger flow statistics lays WI-FI probe to reach preferably detection effect and how to flow to information etc. by the data processing differentiation pedestrian of science and still lack research.Term is explained
To keep description of the invention more accurate clear, description below now is made to the various terms that will appear in the present invention:
WI-FI probe: a kind of to arrest the wireless access point for moving about facility information based on various wireless data frames, it can intercept and capture the MACXMedia Access Control for the mobile client that WI-FI is opened in a certain range) layer information mainly includes MAC Address, signal receiving strength value, timestamp etc.；
Detection zone: effective area of detection that WI-FI probe has, usually using probe as the center of circle, the 50-100 meters of spheric regions for radius；
Detect the period: used unit detection time length when detecting using WI-FI probe to road pedestrian.Pedestrian's mobile device: the portable electronic equipment, such as smart phone, laptop computer, IPAD etc. with WI-FI function of pedestrian；
MAC Address: i.e. the address Media Access Control, free translation are media access control, are the physical address, hardware address, the position for defining the network equipment of each mobile device.Show as a string of 12 characters being uniquely made of numeral and letter；
MAC Address initial data: by WI-FI probe in detecting to all MAC Address data strips；
Invalid MAC Address data: in MAC Address initial data, the MAC Address data strip that is not belonging within the scope of road to be studied；
Active mac addresses data: in MAC Address initial data, belong to the MAC Address data strip within the scope of road to be studied；
Detect flow of the people data: with active mac addresses data；
Corrected parameter ex: it is used to characterize probe to the parameter of the verification and measurement ratio of mobile device by what multiplicating experiment obtained；Corrected parameter β: the parameter for carrying the number of mobile device for characterizing road pedestrian obtained by questionnaire survey；Summary of the invention
The object of the present invention is to provide a kind of methods that pedestrian's flow direction is differentiated using WI-FI probe.Specific inspection Survey means are to be detected using WI-FI probe to the mobile device in effective detection zone, in the case where equipment WI-FI function is opened, the MAC Address that probe can detect the unique identification of the equipment by capturing wireless signal, to carry out the statistics of flow of the people.The initial data detected analyzed based on the data of received signal strength indication and detection time, can differentiate directional information of each MAC Address data on road, so that it is determined that corresponding pedestrian flows to.
When using WI-FI probe in detecting flow of the people, present invention mainly solves following four problems:
(1) when being detected using multiple probes to road pedestrian flow, there are multipath phenomenons and reflex in communication process for the wireless signal that mobile device is launched, there is different degrees of decaying to will lead to the signal that probe captures and receive intensity (RSSI), or even can not be detected.So, under the basis of influence of the present invention in the space layout for probing into multiple probes to the testing result of wireless signal, a variety of preferably probe layout schemes are provided, to reduce the influence of multipath phenomenon and reflex to testing result in the communication process of wireless signal to large extent.
(2) valid analysing range of WI-FI probe is facility center management, and certain length is the spheric region of radius.
So when detection zone is greater than road width, the mobile device except road (including in the building of two sides) can also be detected that there are these invalid datas so as to cause in testing result.So the present invention needs the data screening standard for setting science to reject these invalid datas, to guarantee the reliability of testing result.
(3) when pedestrian's changes in flow rate, the multipath of wireless signal and the degree of reflection are different, cause to the substandard verification and measurement ratio of data screening also significant change can occur with the variation of flow of the people.The present invention provides the computation model by detection limit prediction actual amount being suitable under the continuous situation of change of flow of the people, to improve precision of prediction.
(4) on the basis of obtaining effective pedestrian's data on flows, pass through the multi-analysis to testing result, differentiation is distinguished to pedestrian's flow of both direction on Ordinary Rd, and counts pedestrian's flow in all directions, to provide more detailed pedestrian information.In order to solve the above problem, the technical solution adopted by the present invention includes:
(1) using multiple WI-FI probe in detecting pedestrian's flows when, under identical detection environment, while the space layout scheme of a variety of probes is laid, scheme difference essentially consists in position of the probe on road vertical and horizontal space. (2) when collecting raw sensor data, the union of each probe in detecting result should be taken, counts the mobile device MAC Address number detected within certain section of period.
(3) effectively to reject invalid interference data, need to design the standard that preliminary experiment determines data screening.Preliminary experiment carries out on pedestrian road to be measured, it is identical when guaranteeing the laying form of multiple probes with detection flow of the people, in probe valid analysing range, use multiple smart machines of known MAC Address, and arbitrarily after displacement a period of time, the received signal strength indication of the MAC Address data arrived to probe in detecting is for statistical analysis, received signal strength minimum value in detection range needed for determining, as data screening standard, for excluding required detection range with pedestrian's mobile device MAC Address data in exterior domain.
(4) simultaneously, the invalid data in the building of both sides of the road should also be rejected.This kind of invalid data has the characteristics that the residence time is long in detection zone, the duration that the data are consecutively detected is compared with pedestrian under normal circumstances by the duration in the effective detection zone of probe so the principle rejected can be, should be rejected if being more than to pass through duration.
(5) since pedestrian's flow constantly changes, verification and measurement ratio also changes therewith.The present invention directly inquires into the relationship between pedestrian detection value and actual value when determining stream of people's prediction model, firstly the need of while using probe in detecting flow of the people, artificial counting goes out the size of practical flow of the people, and pass through contrived experiment and data processing, it provides the practical flow of the people of a variety of determinations and detects the functional relation between flow of the people, and thus functional relation is according to detected value reckoning actual value, to improve detection accuracy.
(6) in view of probe to the WI-FI probe in its detection zone and not all detects, it and there are the portable mobile device of a certain proportion of pedestrian is more than one, the present invention provides the modification method of functional relation between detection flow of the people and practical flow of the people by introducing corrected parameter α and β.
(7) in addition, the present invention is while detecting pedestrian's total flow, moreover it is possible to be flowed to by data processing to pedestrian's traffic differentiation.It distinguishes the detection time that flow to need to the MAC Address data after screening and received signal strength indication is compared analysis.When studying the laying form of multiprobe, the present invention detects Route for pedestrians using three probes, and provides four kinds of different layout schemes.The variation of lateral distance and fore-and-aft distance of the main distinction between probe, specific laying form is as follows, and schematic diagram is as shown in Fig. 1.
1) three probes are laid in pedestrian road two sides, and two of them are equal to pedestrian road width in pedestrian road the same side, spacing, another is in the pedestrian road other side； 2) three probes are laid on pedestrian road middle line, and spacing is equal to the half of pedestrian road width；
3) three probes are laid in on pedestrian road longitudinally perpendicular straight line, and spacing is equal to the half of pedestrian road width；
4) three probes are laid in respectively on pedestrian road two sides and middle line, and are the half of pedestrian road width along the spacing on pedestrian road vertical and horizontal.When determining the standard for rejecting invalid interference data, the present invention provides the data screening method based on received signal strength indication: under the premise of given detection place, a kind of preliminary experiment is provided, probe into received signal strength indication (RSSI) and mobile device to distance between probe corresponding relationship, to according to the spatial dimension size of the area to be tested in actual test place, determine the minimum value of corresponding signal receiving strength, as data screening line, from the interference data filtered out in initial data except area to be tested.Since the MAC Address in the building of both sides of the road can also be arrived by WI-FI probe in detecting, in view of these interference data have the characteristics that be constantly in detection zone, so the present invention provides the data screening method based on detection duration: carrying out the analysis of time series to each MAC Address detected, determine its time span being detected, using general pedestrian by the duration in area to be tested as the standard of data screening, it will test and detect the MAC Address data rejecting that duration is greater than the standard in result.Described data screening method based on received signal strength indication and need to be simultaneously using handling raw sensor data based on the data screening method of detection duration, but in no particular order, both it can first use the data screening method based on received signal strength indication to reuse the data screening method based on detection duration, the data screening method based on detection duration can also first be used to reuse the data screening method based on received signal strength indication.When determining functional relation between practical flow of the people and detection flow of the people, the present invention is between detection flow of the people data and actual persons data on flows using one of following three kinds of function models:
1) average detected rate model: using the detection flow of the people in each detection period with the ratio of corresponding practical flow of the people as verification and measurement ratio, average detected rate after finding out the verification and measurement ratio weighting of each detection period, for describing relationship between detection flow of the people and practical flow of the people；
2) it is segmented verification and measurement ratio model: using the detection flow of the people data in each detection period as index, will test Flow of the people data are divided into multiple sections, find out the verification and measurement ratio in each section, to establish the detection flow of the people in each section and the relationship between verification and measurement ratio；
3) relationship detected between flow of the people and practical flow of the people in each detection period cubic spline interpolation model: is fitted using cubic spline functions.
In the cubic spline functions S (x) that wherein present invention provides, having natural boundary conditions is 0, i.e.,
S"(x0) = 0
(present invention of xJ=0 is modified detection flow of the people-actual persons flow function relationship of foundation using corrected parameter α S "; corrected parameter e is by the way that single mobile device, repeatedly the experimental result Jing Guo certain WI-FI detection zone is obtained repeatedly; the WI-FI function of mobile device is opened in experiment, and records the information such as the MAC Address of mobile device, the number passed through repeatedly.
The present invention is modified using detection flow of the people-actual persons flow function relationship of the corrected parameter β to foundation, corrected parameter β is by carrying out questionnaire survey acquisition to the pedestrian on road to be measured, the portable mobile device number of pedestrian on the to the effect that investigation pedestrian road to be measured of questionnaire, the object of investigation is randomly selected.When using WI-FI probe in detecting flow of the people, the detection period of use needs depending on pedestrian's feature on actually detected pedestrian road the present invention, can take 10min, 30min or lh, acquire the unit time length with statistics as data.When three probe layout schemes are as shown in Fig. 4, i.e. three probes are laid in respectively on pedestrian road two sides and middle line, and when being the half of pedestrian road width along the spacing on pedestrian road vertical and horizontal, the present invention provide differentiate pedestrian flow direction the specific steps are such as attached drawings 5:
1) longitudinal respectively by three probes labeled as A, B and C along road;
2) union that the union of A and B the MAC Address data detected is denoted as the MAC Address data that X, B and C are detected is denoted as Y;
3) to the MAC Address data that each is detected, find its time being detected for the first time in X and Y, be denoted as respectively T, Τ2;If Τ < Τ2, then it is assumed that it flows to as by Α to the direction C；If 1 > fourth2, then it is assumed that it flows to as by C to A;
If 4) T=T2, then compare with Τ, ^ moment corresponding signal receiving strength value, be denoted as ^ respectively ^^ And S/2If " 55 > RSSI2, then think flow direction for by A to C;If " 55 < RSSI2, then it is assumed that it flows to as by C to A, RSSIi=RSSI2, then can not judge to flow to.
Brief Description Of Drawings Fig. 1 is the space layout scheme schematic diagram based on three probes.In the two-way street Ren Hang, the concrete form of four kinds of probe layout schemes.
Fig. 2 is data screening preliminary experiment schematic diagram.Reject the preliminary experiment middle probe layout scheme of invalid data.
Fig. 3 is data screening experiment analysis results schematic diagram.In data screening standard based on received signal strength indication, to the analysis method of detection data.
Fig. 4 is the probe layout scheme schematic diagram for distinguishing flow direction.When judging that pedestrian flows to, the layout scheme of three probes.Fig. 5 is the data handling procedure distinguished when flowing to detection flow of the people.
The specific embodiment present invention detects pedestrian's flow using three probes using the most common two-way pedestrian street as research object.And four kinds of probe layout schemes are provided, as shown in Fig. 1:
Three probes are laid in both sides of the road in scheme one, two of them the same side another in the other side, and spacing is equal to road width；
Three probes are respectively positioned on center line of road in scheme two, and spacing is equal to the half of road width；Three probes are laid in on road longitudinally perpendicular straight line in scheme three, and spacing is also equal to the half of road width；
Three probes are laid on both sides of the road and middle line respectively in scheme four, and are the half of road width along the spacing on road vertical and horizontal.Experiment test is carried out to four kinds of layout schemes in Fig. 1 respectively, in data processing, the method for taking the testing result of lower three probes of every kind of scheme to take union carrys out statistic mixed-state pedestrian's flow, then makees with practical pedestrian's flow Ratio finds out verification and measurement ratio(The present invention is by analysis experimental result discovery, and when pedestrian's flow is smaller, the verification and measurement ratio of each scheme is not much different；With the increase of pedestrian's flow, the verification and measurement ratio of various schemes can all decrease；Pedestrian detection rate highest when pedestrian's flow is larger, under probe layout mode shown in scheme four.This is because when pedestrian's flow is larger, multipath of the wireless signal that mobile device is launched in communication process, emission phenomena are more apparent, cause signal intensity attenuation serious, and in scheme four, probe is laid between in the road and two sides can effective decentralized signal receiving point, the data from road inner side and outer side are more fully received, i.e., reduces signal caused by multipath and reflex to a certain extent and decays；On the other hand, three probes have a certain distance on road longitudinal direction in scheme four, can effectively increase the effective detection zone of entirety of probe, to increase detection time, mobile device is effectively reduced in pedestrian by the probability but issued without signal in detection zone, that is, increases verification and measurement ratio.
So four kinds of probe distribution methods that the present invention provides, wherein scheme four be expert at flow of the people it is higher when verification and measurement ratio highest, detection effect is best.The present invention designs preliminary experiment and determines the data screening standard based on received signal strength indication, the particular content of preliminary experiment are as follows: the laying form of three probes is as shown in Fig. 2, using probe as the center of circle, using the half of road width as in the region of radius, use the movement of multiple mobile device simulation pedestrians for opening WI-FI function, after detection after a period of time, the testing result of each probe is counted.The present invention analyzes such as attached drawing 3 received signal strength indication data obtained in preliminary experiment, shows that received signal strength indication Normal Distribution, the present invention take 90% confidence interval to determine final data screening line.The present invention is when determining the data screening standard based on detection duration, specific steps are as follows:
1) length of the effective detection zone of three probes composition on trend of road is calculated；
2) the general speed of travel of pedestrian takes 1. 5m/s, and available pedestrian under normal circumstances passes through time span t needed for effective detection zone1 ;
3) the detection duration for the MAC Address data that statistics each detects, is denoted as t2 ;
If 4) t2> then reject the MAC Address data. What the present invention provided establishes the relationship between cubic spline functions fitting pedestrian's flow actual value and detected value.The specific method is as follows:
The present invention will obtain n group data in an experiment, count the mobile device MAC Address number detected in each group of data respectively and be denoted as χ.,Χι, ·'·χη, correspond to section [χ., χ ^] on each node, while artificial counting go out the corresponding practical flow of the people of each node be y., …；Determine that the corresponding relationship at each node is fOJ=yn.Can then construct according to the following steps cubic spline functions s (x).Remember hj=xj-xl, S " (Xj)=Mj then has
S!'(x =^M._i +^M. (1)
5,(χ) = ^^- ,-.ι + d- Μ + + (2)
J J 6hj J 1 6hj J 1 L
jMj—i + 2Mj + YjMj+1=dj, j=1,2..., n-(5) is wherein in formula (5):
(6) hi+h
Unified with nature boundary condition S " (x.)=M.=0 and S " (xJ=Μ=0, (5) formula can be write as matrix form:
According to formula α)-(9), cubic spline functions can be calculated as following form:cf 、 ) s2(x), x £ [ ι, ,]
S(x) = 2 1 2」
Sn ( ) X £ [^— 1' ^l] The present invention is modified using detection flow of the people-actual persons flow function relationship of the corrected parameter α to foundation, corrected parameter e is by the way that single mobile device, repeatedly the experimental result Jing Guo certain WI-FI detection zone is obtained repeatedly, the WI-FI function of mobile device is opened in experiment, and the information such as the MAC Address of mobile device, the number passed through repeatedly are recorded, and be handled as follows to experimental result:
If the mobile device passes through n times in the detection zone of probe, and by the MAC Address n times in probe in detecting result there are the mobile device, detect n times, then think that WI-FI probe is α to the verification and measurement ratio of the mobile device for opening WI-FI function, and c=then need in final cubic spline functions model
Upper corrected parameter α is removed before S (x), i.e., revised cubic spline functions are S (x) '=S (x)/c.The present invention is modified using detection flow of the people-actual persons flow function relationship of the corrected parameter β to foundation, corrected parameter is by carrying out questionnaire survey acquisition to the pedestrian on road to be measured, the portable mobile device number of pedestrian, specific modification method on the to the effect that investigation pedestrian road to be measured of questionnaire are as follows:
If questionnaire result shows that the ratio for carrying two mobile devices in pedestrian is a, then+a of corrected parameter β=1, it then needs to be multiplied by corrected parameter β before final cubic spline functions model S (x), i.e., revised cubic spline functions are S (x) '=S (x) ■ β.When three probes using scheme four lay when, when as shown in Fig. 4, the present invention provide differentiate pedestrian flow direction the specific steps are such as attached drawings 5:
1) longitudinally three probes are labeled as from left to right respectively along road, Β and C;
2) union that the union of Α and Β the MAC Address data detected is denoted as the MAC Address data that X, B and C are detected is denoted as Y;
3) to the MAC Address data that each is detected, find its time being detected for the first time in X and Y, be denoted as respectively T, Τ2;If Τ < Τ2, then it is assumed that it flows to as by Α to the direction C；If 1 > fourth2, then it is assumed that it flows to as by C to A;
If 4) T=T2, then compare with Τ, ^ moment corresponding signal receiving strength value, be denoted as ^ respectively ^^ standing grain mouth S/2If RSS > RSSI2, then think flow direction for by Α to C;If " 55 < RSSI2, then think that flow direction is served as reasons (extremely.Wherein- 1) when A and B or B and C detection flow of the people data take union, for the data of same MAC Address, its data being detected for the first time need to only be retained.
2) if some MAC Address data detected only occurs in X or Y, need to find out its all secondary data occurred in X or Y, determines its flow direction by comparing the received signal strength indication and detection time of every data.
If 3) time that some MAC Address data detected first appears in X and Y is identical, i.e., 1=T2When, received signal strength indication is also identical, i.e., = «S/2, then can not judge the flow direction of the MAC Address data.

Claims (1)

  1. Claims
    1. a kind of method for being differentiated pedestrian's flow direction using WI-FI probe, is included the following steps:
    1) data acquire: on street crossing road, laying the MAC Address initial data that one group of WI-FI probe obtains each detection period one skilled in the art mobile device of its detection zone；Artificial acquisition actual persons data on flows simultaneously；One group of WI-FI probe is used as using one of following four kinds of probe layout schemes and drafts probe layout scheme；
    La) three probes are laid in pedestrian road two sides, and two of them are equal to pedestrian road width in pedestrian road the same side, spacing, another is in the pedestrian road other side；
    Lb) three probes are laid on pedestrian road middle line, and spacing is equal to two/lc of pedestrian road width) three probes are laid in on pedestrian road longitudinally perpendicular straight line, and spacing is equal to the half of pedestrian road width；
    Id) three probes are laid in respectively on pedestrian road two sides and middle line, and are the half of pedestrian road width along the spacing on pedestrian road vertical and horizontal；
    2) data screening: screening the MAC Address initial data, rejects invalid MAC Address data, obtains pedestrian's mobile device active mac addresses data, as detection flow of the people data；The screening includes the data screening based on received signal strength indication and the data screening based on detection duration；
    3) data processing: to pedestrian's mobile device active mac addresses data, the function model between the detection flow of the people data and the actual persons data on flows is established；
    4) Modifying model: on the pedestrian road, corrected parameter α and β is obtained by the way that test and questionnaire survey is repeated several times respectively, the function model is modified；It is the verification and measurement ratio for probing into WI- FI probe to the mobile device for having opened WI-FI function in its detection zone that test, which is repeated several times,；Questionnaire survey is the portable mobile device number of pedestrian on investigation pedestrian road to be measured, and the object of investigation is randomly selected；
    5) differentiate pedestrian's flow direction: to the detection flow of the people data, analysis being compared by detection time to data and signal reception time intensity value, judges the flow direction of pedestrian.
    2. the method for pedestrian's flow direction is differentiated using WI-FI probe as described in claim 1, which is characterized in that step 2) data screening is using one of following two method:
    The data screening based on received signal strength indication first 2a) is done to the MAC Address initial data, then the result of screening is done into the data screening based on detection duration；The data screening based on received signal strength indication method particularly includes: by designing preliminary experiment, find effective corresponding to pedestrian's mobile device The minimum value of the received signal strength indication of MAC Address data rejects the MAC Address data that received signal strength indication in the MAC Address initial data is less than the standard as the standard of data screening；The data screening based on detection duration method particularly includes: will detect MAC Address data of the duration greater than the standard in the data screening result based on received signal strength indication as the standard of data screening by the duration in area to be tested using pedestrian and reject；
    The data screening based on detection duration first 2b) is done to the address the MAC initial data, then the result of screening is done into the data screening based on received signal strength indication；The data screening based on detection duration method particularly includes: will detect MAC Address data of the duration greater than the standard in the MAC Address initial data as the standard of data screening by the duration in area to be tested using pedestrian and reject；The data screening based on received signal strength indication method particularly includes: on the basis of based on the data screening result of detection duration, by designing preliminary experiment, find the minimum value of the received signal strength indication corresponding to the effective MAC address date of pedestrian's mobile device, as the standard of data screening, the MAC Address data that received signal strength indication is less than the standard in the data screening result based on detection duration are rejected.
    3. the method for pedestrian's flow direction is differentiated using WI-FI probe as described in claim 1, it is characterised in that: function model described in step 3) is following thrin:
    3a) average detected rate model: using the detection flow of the people in each detection period with the ratio of corresponding practical flow of the people as verification and measurement ratio, average detected rate after finding out the verification and measurement ratio weighting of each detection period, for describing relationship between detection flow of the people and practical flow of the people；
    3b) it is segmented verification and measurement ratio model: using the detection flow of the people data in each detection period as index, it will test flow of the people data and be divided into multiple sections, the verification and measurement ratio in each section is found out, to establish the detection flow of the people in each section and the relationship between verification and measurement ratio；
    3c) cubic spline interpolation model: the relationship detected between flow of the people and practical flow of the people in each detection period is fitted using cubic spline functions, and the value of natural boundary conditions is 0.
    4. the method for pedestrian's flow direction is differentiated using WI-FI probe as described in claim 1, it is characterised in that: the detection period needs depending on pedestrian's feature on actually detected pedestrian road, can take 1 Omin, 30min or lh.
    5. the method for differentiating pedestrian's flow direction using WI-FI probe as described in one of Claims 1-4, it is characterised in that: use layout scheme Id) differentiate the specific steps that pedestrian flows to are as follows:
    Ldl) longitudinal respectively by three probes labeled as A, B and C along road;
    Ld2 the union of A and B the MAC Address data detected) is denoted as the MAC that X, B and C are detected The union of address date is denoted as Y;
    Id3) to the MAC Address data that each is detected, find its time being detected for the first time in X and Y, be denoted as respectively T, T2；If 1 < Τ2, then it is assumed that it flows to as by Α to the direction C；If 1 > Τ2, then think flow direction for by C to A;
    Ld4) if TV z T^, then compare with T, Τ2Moment corresponding signal receiving strength value, is denoted as " 5 and S/ respectively2If " 55 > RSSI2, then think flow direction for by Α to C;If RSS < RSSI2, then think flow direction for by C to A；If=RSSI2, then can not judge to flow to.
    6. the method for pedestrian's flow direction is differentiated using WI-FI probe as claimed in claim 5, it is characterized by: in the specific steps for differentiating pedestrian's flow direction, when A and B or B and C detection flow of the people data are taken union, for the data of same MAC Address, it need to only retain its data being detected for the first time.
    7. the method for pedestrian's flow direction is differentiated using WI-FI probe as claimed in claim 5, it is characterized by: in the specific steps for differentiating pedestrian's flow direction, if some MAC Address data detected only occurs in union X or Y, it then needs to find out all detection datas of the MAC Address in X or Y, determines its flow direction by comparing the received signal strength indication and detection time of every detection data of the MAC Address.
    8. the method for pedestrian's flow direction is differentiated using WI-FI probe as claimed in claim 2, it is characterized by: the preliminary experiment of the data screening based on received signal strength indication, specific practice are as follows: on street crossing road, using drafting probe layout scheme, mobile device using multiple known MAC Address is being activity in the region of radius by the half of the center of circle, pedestrian road width of probe, and counts the testing result of each probe.
    9. the method for pedestrian's flow direction is differentiated using WI-FI probe as claimed in claim 2, it is characterized by: in the data screening based on received signal strength indication, the received signal strength indication Normal Distribution of the data detected, 90% confidence interval is taken, standard of the obtained received signal strength indication as data screening.
    10. the method for pedestrian's flow direction is differentiated using WI-FI probe as claimed in claim 2, it is characterised in that: in the data screening based on detection duration, the walking speed of pedestrian takes 1.5m/s.
CN201780033651.2A 2016-12-30 2017-12-30 Method for distinguishing pedestrian flow direction by using WI-FI probe Active CN109644360B (en)

Applications Claiming Priority (3)

Application Number Priority Date Filing Date Title
IBPCT/IB2016/058108 2016-12-30
PCT/IB2016/058108 WO2018122588A1 (en) 2016-12-30 2016-12-30 Method for detecting pedestrian traffic by using wi-fi probe
PCT/IB2017/058546 WO2018122816A1 (en) 2016-12-30 2017-12-30 Method for using wi-fi probes to determine pedestrian flow direction

Publications (2)

Publication Number Publication Date
CN109644360A true CN109644360A (en) 2019-04-16
CN109644360B CN109644360B (en) 2021-12-17

Family

ID=59713469

Family Applications (4)

Application Number Title Priority Date Filing Date
CN201680086285.2A Active CN109716358B (en) 2016-12-30 2016-12-30 Method for detecting pedestrian flow by using WI-FI probe
CN201780033657.XA Active CN109479206B (en) 2016-12-30 2017-12-30 Method for detecting pedestrian flow on road by using WI-FI probe
CN201780033651.2A Active CN109644360B (en) 2016-12-30 2017-12-30 Method for distinguishing pedestrian flow direction by using WI-FI probe
CN201780033645.7A Active CN109644320B (en) 2016-12-30 2017-12-30 Method for detecting pedestrian flow in public place by using WI-FI probe

Family Applications Before (2)

Application Number Title Priority Date Filing Date
CN201680086285.2A Active CN109716358B (en) 2016-12-30 2016-12-30 Method for detecting pedestrian flow by using WI-FI probe
CN201780033657.XA Active CN109479206B (en) 2016-12-30 2017-12-30 Method for detecting pedestrian flow on road by using WI-FI probe

Family Applications After (1)

Application Number Title Priority Date Filing Date
CN201780033645.7A Active CN109644320B (en) 2016-12-30 2017-12-30 Method for detecting pedestrian flow in public place by using WI-FI probe

Country Status (3)

Country Link
CN (4) CN109716358B (en)
GB (4) GB201711411D0 (en)
WO (4) WO2018122588A1 (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111476611A (en) * 2020-04-17 2020-07-31 支付宝(杭州)信息技术有限公司 Sensor-based data processing method and device
CN112502781A (en) * 2020-11-24 2021-03-16 海洋王照明科技股份有限公司 Mine personnel monitoring method and device, server and storage medium
CN115131964A (en) * 2022-06-23 2022-09-30 重庆交通大学 Tunnel traffic flow sensing system

Families Citing this family (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107124476B (en) * 2017-07-04 2020-04-10 百度在线网络技术（北京）有限公司 Information pushing method and device
CN109362041B (en) * 2018-12-18 2021-06-04 成都方未科技有限公司 Population space-time distribution analysis method based on big data
CN110113778A (en) * 2019-04-30 2019-08-09 清华大学 Extend scale calculation method and system in Expressway Service based on data-driven
CN112235430B (en) * 2019-06-28 2023-12-05 北京奇虎科技有限公司 Method and device for obstructing collection of effective information and electronic equipment
CN110493816B (en) * 2019-08-21 2022-10-21 上海工程技术大学 Real-time prediction method for rail transit subway station passenger flow volume
CN110598154B (en) * 2019-09-16 2023-04-07 新疆银狐数据科技有限公司 Tourism comprehensive statistics big data system based on fusion multi-channel data
CN110879975B (en) * 2019-11-06 2022-06-17 杭州宇泛智能科技有限公司 Personnel flow detection method and device and electronic equipment
CN113068215B (en) * 2021-03-12 2022-01-11 华扬联众数字技术(深圳)有限公司 Weight and filtering-based multi-WiFi probe MAC address dynamic line algorithm
CN116887339B (en) * 2023-09-07 2023-11-28 深圳中科爱讯科技有限公司 Real-time passenger flow statistics system and method based on WiFi probe

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2007051701A1 (en) * 2005-11-03 2007-05-10 International Business Machines Corporation Tracking a location of a wireless device user in a private network environment
CN103473840A (en) * 2013-09-23 2013-12-25 沈阳天目科技有限公司 Passenger flow counting system and method having personnel distinguishing function based on wireless network
CN105049422A (en) * 2015-06-25 2015-11-11 上海迪爱斯通信设备有限公司 WIFI detection and identification equipment and system and WIFI detection and identification method
CN105869388A (en) * 2016-05-31 2016-08-17 苏州朗捷通智能科技有限公司 Bus passenger flow data collection and origin-destination point analysis method and system

Family Cites Families (23)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7899039B2 (en) * 2008-02-15 2011-03-01 Cisco Technology, Inc. System and method for providing location and access network information support in a network environment
CN201340272Y (en) * 2008-09-02 2009-11-04 上海领美实业有限公司 Intelligent pedestrian flow management and service system for public places
CN101668244A (en) * 2008-09-02 2010-03-10 上海领美实业有限公司 System and method for intelligent management and service of people streams in public places
US8489112B2 (en) * 2009-07-29 2013-07-16 Shopkick, Inc. Method and system for location-triggered rewards
CN102104771B (en) * 2010-12-14 2012-12-12 浙江工业大学 Multi-channel people stream rate monitoring system based on wireless monitoring
KR101046421B1 (en) * 2011-02-09 2011-07-04 (주)멀린 Method and system of taking position information
CN102625331A (en) * 2011-06-14 2012-08-01 北京小米科技有限责任公司 Monitor method of data flow of mobile terminal and apparatus
CN202773078U (en) * 2011-07-30 2013-03-06 孙佰松 People stream positioning and monitoring system based on wireless communication
CN202528324U (en) * 2012-03-07 2012-11-14 南安市正冠机械有限公司 Columnar stone processing device
CN102737336A (en) * 2012-04-12 2012-10-17 林华龙 Method and management system for knowing passenger flow volume and behavior thereof based on mobile device
US9078162B2 (en) * 2013-03-15 2015-07-07 DGS Global Systems, Inc. Systems, methods, and devices for electronic spectrum management
KR20150006110A (en) * 2013-07-08 2015-01-16 용현중 System and method of checking attendance
CN104361658B (en) * 2014-09-30 2017-05-31 北京锐安科技有限公司 The detection method and device of a kind of region Nei Ge places people information
CN104540168B (en) * 2014-12-30 2018-05-11 杭州华为数字技术有限公司 A kind of method, apparatus and system for measuring crowded degree
CN105163277A (en) * 2015-08-10 2015-12-16 上海网罗电子科技有限公司 Position information-based big data task management system and method
CN105187240A (en) * 2015-08-19 2015-12-23 广东中兴新支点技术有限公司 Pedestrian volume detection method and device thereof,
CN105160321A (en) * 2015-09-05 2015-12-16 深圳市飞思未来云媒体科技有限公司 Vision-and-wireless-positioning-based mobile terminal identity verification method
CN205283824U (en) * 2015-11-24 2016-06-01 如东信息技术服务(上海)有限公司 Airport stream of people early warning system based on wifi
CN106022643A (en) * 2016-06-06 2016-10-12 北京智旅科技有限公司 Scenic spot tourist data analysis system
CN106211067A (en) * 2016-06-30 2016-12-07 北京奇虎科技有限公司 A kind of people's flow monitoring method and device based on terminal
CN106251578B (en) * 2016-08-19 2019-05-07 深圳奇迹智慧网络有限公司 Stream of people's early warning analysis method and system based on probe
CN106210144A (en) * 2016-08-22 2016-12-07 北京易游华成科技有限公司 People flow rate statistical method and apparatus
CN107360590A (en) * 2017-06-29 2017-11-17 上海工程技术大学 Track station part congestion points passenger flow condition judgement method

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2007051701A1 (en) * 2005-11-03 2007-05-10 International Business Machines Corporation Tracking a location of a wireless device user in a private network environment
CN103473840A (en) * 2013-09-23 2013-12-25 沈阳天目科技有限公司 Passenger flow counting system and method having personnel distinguishing function based on wireless network
CN105049422A (en) * 2015-06-25 2015-11-11 上海迪爱斯通信设备有限公司 WIFI detection and identification equipment and system and WIFI detection and identification method
CN105869388A (en) * 2016-05-31 2016-08-17 苏州朗捷通智能科技有限公司 Bus passenger flow data collection and origin-destination point analysis method and system

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111476611A (en) * 2020-04-17 2020-07-31 支付宝(杭州)信息技术有限公司 Sensor-based data processing method and device
CN111476611B (en) * 2020-04-17 2022-05-17 支付宝(杭州)信息技术有限公司 Sensor-based data processing method and device
CN112502781A (en) * 2020-11-24 2021-03-16 海洋王照明科技股份有限公司 Mine personnel monitoring method and device, server and storage medium
CN112502781B (en) * 2020-11-24 2022-10-25 海洋王照明科技股份有限公司 Mine personnel monitoring method, device, server and storage medium
CN115131964A (en) * 2022-06-23 2022-09-30 重庆交通大学 Tunnel traffic flow sensing system
CN115131964B (en) * 2022-06-23 2024-02-20 重庆交通大学 Tunnel traffic flow sensing system

Also Published As

Publication number Publication date
CN109716358A (en) 2019-05-03
CN109479206B (en) 2021-12-17
CN109644360B (en) 2021-12-17
GB2569752B (en) 2020-05-20
GB201909414D0 (en) 2019-08-14
GB201711411D0 (en) 2017-08-30
WO2018122588A1 (en) 2018-07-05
WO2018122815A1 (en) 2018-07-05
CN109479206A (en) 2019-03-15
CN109644320A (en) 2019-04-16
WO2018122816A1 (en) 2018-07-05
GB201909415D0 (en) 2019-08-14
WO2018122817A1 (en) 2018-07-05
CN109716358B (en) 2023-06-06
GB201905910D0 (en) 2019-06-12
CN109644320B (en) 2020-12-11
GB2569752A (en) 2019-06-26

Similar Documents

Publication Publication Date Title
CN109644360A (en) A method of differentiating that pedestrian flows to using WI-FI probe
CN105512720B (en) A kind of public transit vehicle passenger flow statistics method and system
CN103456172B (en) A kind of traffic parameter measuring method based on video
CN106297288B (en) A kind of acquisition of bus passenger passenger flow data and analysis method
CN103473840B (en) Based on wireless network, there is passenger flow counting system and the method that personnel distinguish function
CN104809879B (en) Expressway road traffic state estimation method based on dynamic Bayesian network
CN109285376A (en) A kind of bus passenger flow statistical analysis system based on deep learning
CN110127475B (en) Elevator taking personnel classification and elevator taking rule analysis method and system thereof
CN103985182B (en) A kind of bus passenger flow automatic counting method and automatic counter system
CN108460497A (en) A kind of departure hall queueing message reminding method
CN109255955A (en) A kind of expressway traffic accident monitoring method and system based on ground- and air-based collaborative perception
CN105513362B (en) A kind of bus platform adjacent area bus running state evaluation verification method
US11798414B2 (en) Vehicle flow monitoring system
CN109598947A (en) A kind of vehicle identification method and system
CN107590999A (en) A kind of traffic state judging method based on bayonet socket data
CN104217591B (en) Dynamic road condition detection method and system
CN103942865B (en) Subway fare evasion prevention system and its design method based on sonac
CN107844856A (en) Bus passenger flow Forecasting Methodology based on vehicle GPS and website WiFi
CN104794896B (en) Overpass congestion spacial hot spots extraction method based on lift height-limiting frame
van den Heuvel et al. Using Bluetooth and WiFi to unravel real-world slow mode activity travel behaviour
CN112001232A (en) Airport passenger flow travel chain accurate sensing device with individual characteristics
CN110263993A (en) A kind of real-time predicting method for handing over passenger&#39;s travel time for city rail
CN117877273B (en) Intelligent high-speed traffic state judging method and system based on air-ground information fusion
CN109459758A (en) A kind of airfield runway traffie distribution test macro and test method
CN111988735B (en) Airport passenger flow travel chain accurate sensing method containing individual characteristics

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