WO2018122815A1 - 一种使用wi-fi探针检测道路行人流量的方法 - Google Patents

一种使用wi-fi探针检测道路行人流量的方法 Download PDF

Info

Publication number
WO2018122815A1
WO2018122815A1 PCT/IB2017/058545 IB2017058545W WO2018122815A1 WO 2018122815 A1 WO2018122815 A1 WO 2018122815A1 IB 2017058545 W IB2017058545 W IB 2017058545W WO 2018122815 A1 WO2018122815 A1 WO 2018122815A1
Authority
WO
WIPO (PCT)
Prior art keywords
data
pedestrian
detection
road
probe
Prior art date
Application number
PCT/IB2017/058545
Other languages
English (en)
French (fr)
Inventor
杜豫川
岳劲松
暨育雄
Original Assignee
同济大学
许军
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 同济大学, 许军 filed Critical 同济大学
Priority to GBGB1909414.3A priority Critical patent/GB201909414D0/en
Priority to CN201780033657.XA priority patent/CN109479206B/zh
Publication of WO2018122815A1 publication Critical patent/WO2018122815A1/zh

Links

Classifications

    • GPHYSICS
    • G01MEASURING; TESTING
    • G01SRADIO 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
    • G01S5/00Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations
    • G01S5/02Position-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
    • GPHYSICS
    • G01MEASURING; TESTING
    • G01SRADIO 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
    • G01S5/00Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations
    • G01S5/02Position-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
    • G01S5/0278Position-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
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06MCOUNTING MECHANISMS; COUNTING OF OBJECTS NOT OTHERWISE PROVIDED FOR
    • G06M11/00Counting of objects distributed at random, e.g. on a surface
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00Scenes; Scene-specific elements
    • G06V20/50Context or environment of the image
    • G06V20/52Surveillance or monitoring of activities, e.g. for recognising suspicious objects
    • G06V20/53Recognition of crowd images, e.g. recognition of crowd congestion
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/20Movements or behaviour, e.g. gesture recognition
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04WWIRELESS COMMUNICATION NETWORKS
    • H04W24/00Supervisory, monitoring or testing arrangements
    • H04W24/08Testing, supervising or monitoring using real traffic
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04WWIRELESS COMMUNICATION NETWORKS
    • H04W4/00Services specially adapted for wireless communication networks; Facilities therefor
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04WWIRELESS COMMUNICATION NETWORKS
    • H04W4/00Services specially adapted for wireless communication networks; Facilities therefor
    • H04W4/02Services making use of location information
    • H04W4/023Services making use of location information using mutual or relative location information between multiple location based services [LBS] targets or of distance thresholds
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04WWIRELESS COMMUNICATION NETWORKS
    • H04W84/00Network topologies
    • H04W84/02Hierarchically pre-organised networks, e.g. paging networks, cellular networks, WLAN [Wireless Local Area Network] or WLL [Wireless Local Loop]
    • H04W84/10Small scale networks; Flat hierarchical networks
    • H04W84/12WLAN [Wireless Local Area Networks]
    • YGENERAL 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
    • Y02TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02DCLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
    • Y02D30/00Reducing energy consumption in communication networks
    • Y02D30/70Reducing energy consumption in communication networks in wireless communication networks

Definitions

  • the invention belongs to the technical field of WI-FI data acquisition and pedestrian flow detection, and particularly relates to a method for detecting pedestrian flow using a WI-FI probe.
  • the WI-FI probe obtains the raw data of the human traffic by capturing the MAC address data of the mobile device; by adjusting the spatial layout of the WI-FI probe device, the detection rate in the crowd can be effectively improved; the original data is processed by using the data screening standard. And provide a variety of methods to establish a functional relationship between the detection of human flow and actual human flow, thereby improving the accuracy of WI-FI detection. Background technique
  • Manual investigation is the most traditional method for counting passenger flow. The method is simple and can be superimposed on the standard of manual judgment. However, due to its high requirements for investigators, large counting errors, and low data quality, the data collection work after the investigation is heavy, the data system is not systematic and cannot provide real-time data, and currently it cannot meet the growth of traffic demand. Intensive places are difficult and inefficient in real time.
  • Gate-type passenger flow counting The gate is a channel blocking device (channel management equipment), which is used to manage the flow of people and regulate pedestrian access. It is mainly used in subway gate system and toll gate gate system. Its most basic and core function is to realize the entrance passage of only one person at a time, which can be used for various charging and access control occasions. This method is low in cost and accurate in quantity. However, when the service crowd has a large amount of baggage parcels, the method is less efficient, hinders the evacuation of pedestrians in an emergency, and is not conducive to the inconvenience of movement. People's travel. And the method of detecting human flow data is only a certain section, and it is necessary to arrange a plurality of sections to grasp the distribution of people flow, and the floor space is large.
  • Pedal-type passenger flow counting The pressure plate passenger flow statistic meter is installed on the ground of the inspection area, when pedestrians pass by The trigger pressure sensor information is automatically recorded.
  • This type of instrument can be roughly divided into two categories, one is based on the "human treading data model mode" for counting and direction judgment, and the other is based on "passenger pedal profile". The method reduces the influence on the passenger flow operation and is simple to install, but the detection accuracy is low, and the components of the pressing system are easily damaged, and the maintainability is poor.
  • Infrared passenger flow counting can be divided into passive infrared passenger flow counting and active infrared passenger flow counting.
  • Passive infrared passenger flow counting uses a pyroelectric infrared probe that can avoid interference from other objects and can only detect signals from the human body. When someone passes, the infrared sensor can detect a certain change caused by the infrared spectrum of the human body, trigger a pulse signal, and then judge the number of people according to the number of pulse signals.
  • the active infrared type transmits a custom wavelength infrared ray to cover a certain area through the transmitting head, and the number of passengers is recognized by the light reflected by the passenger detected by the sensor.
  • the active infrared passenger flow counter overcomes the shortcomings of the passive infrared passenger flow count affected by the environment and light. However, since it uses the simple judgment of the number of pulses to determine the number of people, the statistical accuracy is low, and for many people at the same time. The situation passed is even more difficult to measure. Moreover, the direction of the passenger flow cannot be discriminated by only the infrared method, and the cost of the detection device is high, and it is not suitable for a wide range of use.
  • Video passenger flow count can be divided into single-eye video passenger flow count and binocular video passenger flow count.
  • Video passenger flow technology captures video images by installing cameras in critical channels, and captures passenger flow counts using image processing counts such as image segmentation, artificial neural networks, and stereo image analysis.
  • image processing counts such as image segmentation, artificial neural networks, and stereo image analysis.
  • the method started late and the technology is not yet mature.
  • the implementation cost and maintenance cost are high, and it is difficult to solve the problem of individual flow segmentation when the flow of people is dense, so the accuracy is low.
  • WI-FI probe passenger flow detection is achieved by deploying the WI-FI network in the detection area to obtain the MAC address of the mobile device that enables WI-FI function, thereby realizing passenger flow counting.
  • the WI-FI-based passenger flow statistical method is simple in operation, reasonable in equipment cost, small in impact by non-line-of-sight factors, high in flexibility, and capable of acquiring a large amount of statistical data at the same time, and has great advantages in the flow statistics under dense passenger flow.
  • In-depth analysis of the data content acquired by the probe can obtain characteristic data such as the flow stop time and streamline flow direction. And this detection method supports the cloud platform in subsequent operations, and the data application can be extended to the marketing layer. It is currently widely used in large commercial areas, tourist attractions, playgrounds and other places.
  • WI-FI probe technology The WI-FI probe can detect the MAC address of the mobile device with WI-FI enabled.
  • the principle includes: WI-FI is based on IEEE802. l la/b/g/n protocol, In the standard protocol, two working modes of the wireless access point and the client are defined, and the protocol also specifies Beacon, Ack, and Data. And a variety of wireless data frame types such as Probe.
  • the client connects to the wireless access point, the data frame and the response frame are interacted, and the wireless access point periodically sends the Beacon.
  • the client When the client is not connected to the wireless access point, the client also continuously sends the Probe frame. Probing to a nearby wireless access point.
  • the WI-FI probe is a wireless access point that captures information about nearby clients based on various wireless data frames. It can intercept the MAC layer information of mobile clients opened by WI-FI within a certain range, including MAC address and signal. Receive intensity values, timestamps, etc.
  • the mobile device's unique MAC address is detected by the probe on the premise that the mobile device's WI-FI needs to be open.
  • the proportion of mobile devices that open WI-FI in the crowd is low and unknown. Therefore, under normal circumstances, the difference between the traffic volume detected by WI-FI and the actual passenger traffic is large, and the effect is not satisfactory from the detection amount.
  • WI-FI probe A wireless access point that captures information about nearby mobile devices based on various wireless data frames. It can intercept MACXMedia Access Control layer information of mobile clients opened by WI-FI within a certain range, including MAC address, signal reception strength value, time stamp, etc.
  • the effective detection area of the WI-FI probe is generally a spherical area with a probe centered on the radius of 50-100 meters.
  • Detection period The length of the unit detection time used to detect pedestrians on the road using the WI-FI probe.
  • Pedestrian mobile devices WI-FI-enabled electronic devices that are carried by pedestrians, such as smart phones, hand-held computers, IPADs, etc.;
  • the Media Access Control address which translates to media access control, is the physical address of each mobile device, the hardware address, and the location used to define the network device. Expressed as a unique series of 12 characters consisting of numbers and letters;
  • MAC address raw data All MAC address data strips detected by the WI-FI probe
  • Invalid MAC address data In the original MAC address data, it is not a MAC address data strip within the scope of the road to be studied;
  • Valid MAC address data In the original MAC address data, the MAC address data strip in the range of the road to be studied;
  • Correction parameter ex a parameter obtained by a plurality of repeated experiments for characterizing the detection rate of the probe to the mobile device; a modified parameter ⁇ : a parameter obtained by a questionnaire for characterizing the number of mobile devices carried by the pedestrian on the road;
  • the specific detection method is to use the WI-FI probe to detect the mobile device in the effective detection area.
  • the probe can detect the unique identifier of the device by capturing the wireless signal. The address, thus the statistics of the flow of people.
  • the wireless signal information captured by the probe includes a capture time, a received signal strength value, a MAC address, and the like.
  • the present invention mainly solves the following three problems: (1) When multiple pedestrians are used to detect pedestrian pedestrian traffic, the wireless signal transmitted by the mobile device has multipath phenomenon and reflection phenomenon during the propagation process, which may result in the signal received strength (RSSI) captured by the probe. Different degrees of attenuation can't even be detected. Therefore, the present invention provides a plurality of superior probe placement schemes based on the influence of the spatial layout of multiple probes on the detection results of wireless signals, thereby greatly reducing the propagation of wireless signals. The effect of path phenomena and reflections on the test results.
  • RSSI signal received strength
  • the effective detection range of the WI-FI probe is a spherical area with a certain length as a radius centered on the device.
  • the present invention needs to set a scientific data screening standard to eliminate these invalid data, thereby ensuring the reliability of the test results.
  • the present invention provides a calculation model suitable for predicting the actual amount of the detected amount in the case of a constantly changing human flow rate, thereby improving the prediction accuracy.
  • the technical solutions adopted by the present invention include:
  • the spatial layout scheme of multiple probes is deployed in the same detection environment. The difference is mainly in the position of the probe in the longitudinal and lateral space of the road.
  • invalid data in buildings on both sides of the road should also be eliminated.
  • This type of invalid data has The detection time is long in the detection area, so the principle of rejection may be that the duration of the continuous detection of the data is compared with the length of time in which the descendant passes the probe effective detection area, and if it exceeds the elapsed time, it should be eliminated.
  • the detection rate also changes.
  • the invention directly discusses the relationship between the pedestrian detection value and the actual value when determining the flow prediction model. Firstly, the probe is used to detect the human flow rate, and the actual human flow rate is manually counted, and the design experiment and data processing are performed. A variety of functions are established to determine the actual human flow rate and the detected human flow rate, and the function value is used to estimate the actual value based on the detected value, thereby improving the detection accuracy.
  • the present invention considers that the probe does not detect all of the WI-FI probes in its detection area, and there is a certain proportion of mobile devices that are carried by pedestrians more than one, the present invention is given by introducing correction parameters ⁇ and ⁇ . A method of correcting the functional relationship between human flow and actual human flow.
  • the present invention can detect the flow of pedestrians through data processing while detecting the total flow of pedestrians. Differentiating the flow direction requires comparison and analysis of the detected time of the filtered MAC address data and the received signal strength value.
  • the present invention uses three probes to detect the pedestrian road and gives four different layout schemes. The main difference is the change of the lateral distance and the longitudinal distance between the probe and the probe.
  • the specific layout is as follows, and the schematic diagram is as shown in Fig. 1.
  • All three probes are placed on the pedestrian midline, with a spacing equal to one-half the width of the pedestrian road;
  • All three probes are arranged on a straight line perpendicular to the longitudinal direction of the pedestrian road, and the spacing is equal to one-half of the width of the pedestrian road;
  • the present invention provides a data screening method based on received signal strength values: providing a pre-experiment to explore received signal strength values (RSSI) and mobile devices to a given detection site Correspondence between the distances between the probes, so that the actual test site is to be inspected The spatial extent of the measurement area is determined, and the minimum value of the corresponding signal reception intensity is determined. As the data screening line, the interference data outside the to-be-detected area is filtered out from the original data.
  • RSSI received signal strength values
  • the present invention provides a data screening method based on the detection duration:
  • the detected MAC address is analyzed by time series to determine the length of time it is detected.
  • the length of time in the area to be detected by the general pedestrian is used as the standard for data screening, and the detection time in the detection result is greater than the standard MAC address data. Eliminated.
  • the data screening method based on the received signal strength value and the data screening method based on the detection duration may be simultaneously used to process the original detection data, but in any order, the data filtering method based on the received signal strength value may be used first and then based on
  • the data screening method for detecting the duration may also first use a data screening method based on the detection duration and then use a data screening method based on the received signal strength value.
  • the present invention adopts one of the following three functional models between detecting the human flow data and the actual human flow data:
  • Average detection rate model The ratio of the detected person flow in each detection period to the corresponding actual person flow rate is taken as the detection rate, and the average detection rate weighted by the detection rate of each detection period is obtained, which is used to describe the detected flow rate and The relationship between actual human traffic;
  • Segmentation detection rate model The detected person flow data in each detection period is used as an indicator, and the detected person flow data is divided into a plurality of intervals, and the detection rate in each interval is obtained, thereby establishing the detection person in each interval. The relationship between traffic and detection rate;
  • Cubic spline interpolation model The cubic spline interpolation function is used to fit the relationship between the detected human flow and the actual human flow in each detection period.
  • cubic spline interpolation function S (x) given by the present invention has a natural boundary condition of 0, that is,
  • the present invention uses the correction parameter ⁇ to correct the established detected human flow-actual human flow function relationship, and the modified parameter e is obtained by experimentally evaluating a single mobile device repeatedly through a certain WI-FI detection region. In the experiment, the WI-FI function of the mobile device is turned on, and the MAC address of the mobile device, the number of repeated passes, and the like are recorded.
  • the invention uses the correction parameter ⁇ to correct the established relationship between the detected person flow rate and the actual person flow function, and the correction parameter ⁇ is obtained through questionnaire survey on the pedestrians on the road to be tested.
  • the main content of the questionnaire is to investigate the pedestrians on the road to be tested.
  • the number of mobile devices, the object of the survey is randomly selected.
  • the detection period used according to the actual detection of pedestrian characteristics on the pedestrian road may take 10 min, 30 min or lh as the unit time length of data collection and statistics.
  • the three probe deployment schemes are as shown in Fig. 4, that is, three probes are respectively arranged on both sides and the center line of the pedestrian road, and the distance between the longitudinal and lateral directions of the pedestrian road is two points of the pedestrian road width.
  • the present invention provides a specific step for discriminating pedestrian flow as shown in Fig. 5:
  • Figure 1 is a schematic diagram of a spatial layout scheme based on three probes. In the two-way pedestrian street, the specific form of the four probe layout schemes.
  • Figure 2 is a schematic diagram of data screening pre-experiment. Pre-experimental probe placement scheme that eliminates invalid data.
  • Figure 3 is a schematic diagram showing the results of data screening experiments. An analysis method for detection data in a data screening standard based on received signal strength values.
  • Figure 4 is a schematic diagram of a probe layout scheme for differentiating the flow direction.
  • FIG. 5 is a schematic diagram of a data processing process when the flow direction is detected for detecting human traffic.
  • the present invention takes the most common two-way pedestrian street as a research object and uses three probes to detect pedestrian traffic.
  • Four probe placement schemes are given, as shown in Figure 1:
  • three probes are arranged on both sides of the road, two of them are on the same side and the other is on the other side, and the spacing is equal to the width of the road;
  • the three probes are located on the middle line of the road, and the spacing is equal to one-half of the width of the road.
  • the three probes are arranged on a straight line perpendicular to the longitudinal direction of the road, and the spacing is also equal to the width of the road.
  • the three probes in scheme 4 are respectively arranged on the two sides of the road and on the center line, and the distance along the longitudinal and lateral directions of the road is one-half of the width of the road.
  • Experiments were carried out on the four layout schemes in Figure 1.
  • the detection results of the three probes under each scheme were taken to collect the flow of the pedestrians, and then the actual pedestrian flow was compared. Out detection rate.
  • the invention finds that when the pedestrian flow is small, the detection rate of each scheme is not much different; as the pedestrian flow increases, the detection rate of various schemes will decrease; when the pedestrian flow is large, the scheme The pedestrian detection rate shown in the four probe layout mode is the highest.
  • the probe is disposed in the middle and both sides of the road. It can effectively disperse the signal receiving point and receive more comprehensive data from the inner side and the outer side of the road, which reduces the signal attenuation caused by multipath and reflection phenomenon to some extent.
  • the three probes in scheme four have the longitudinal direction of the road. a certain distance, can Effectively increase the overall effective detection area of the probe, thereby increasing the detection time, effectively reducing the probability that the mobile device does not signal when the pedestrian passes through the detection area, that is, increases the detection rate.
  • the pre-experiment of the present invention determines the data screening standard based on the received signal strength value.
  • the specific content of the pre-experiment is as follows: The layout of the three probes is as shown in FIG. 2, and the probe is centered, and the width of the road is two-thirds. In a radiused area, multiple mobile devices that turn on the WI-FI function are used to simulate the movement of the pedestrian. After a period of detection, the detection results of the probes are counted.
  • the present invention analyzes the received signal strength value data obtained in the preliminary experiment as shown in Fig. 3, indicating that the received signal strength value obeys a normal distribution, and the present invention takes a 90% confidence interval to determine the final data screening line.
  • the specific steps are:
  • the general walking speed of pedestrians is 1.5m/s, which can obtain the length of time t 1 required for the general person to pass the effective detection area ;
  • the present invention establishes a cubic spline interpolation function to fit the relationship between the actual value of the pedestrian flow and the detected value.
  • the specific method is as follows:
  • the invention will obtain n sets of data in the experiment, and separately count the mobile devices detected in each set of data.
  • the cubic spline interpolation function S(x) can be constructed as follows.
  • the cubic spline interpolation function can be calculated as follows:
  • the invention uses the correction parameter ⁇ to correct the established relationship between the detected human flow rate and the actual human flow function, and the modified parameter e is obtained by repeatedly experimenting with a certain mobile device over a certain WI-FI detection area.
  • the FI function is turned on, and the MAC address of the mobile device, the number of repeated passes, and the like are recorded, and the experimental results are processed as follows:
  • the WI-FI probe pair opens the WI-
  • the invention uses the modified parameter ⁇ to correct the established relationship between the detected human flow rate and the actual human flow function, and the modified parameter is obtained through a questionnaire survey of the pedestrian on the road to be tested. The main content of the questionnaire is to investigate the pedestrians on the road to be tested.
  • the number of mobile devices, the specific correction method is:
  • T ⁇ T 2
  • compare the signal reception intensity values corresponding to ⁇ and ⁇ times, respectively, as ⁇ ? ⁇ ⁇ «S/ 2 if RSS > RSSI 2 , then the flow direction is from ⁇ to C; if "55 ⁇ RSSI 2 , then the flow direction is considered to be (to.

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

一种使用WI-FI探针检测道路行人流量的方法,采用WI-FI探针捕获移动设备的MAC地址数据,获得人流量原始数据;通过调整WI-FI探针设备的空间布局,可以有效提高人群中的检测率。

Description

一种使用 WI-FI探针检测道路行人流量的方法 技术领域
本发明属于 WI-FI 数据采集和行人流量检测技术领域, 具体涉及一种使用 WI-FI探针检测行人流量的方法。 WI-FI探针通过捕获移动设备的 MAC地址数据, 获得人流量原始数据; 通过调整 WI-FI探针设备的空间布局, 可以有效提高人群 中的检测率; 采用数据筛选标准对原始数据进行处理, 并提供多种方法建立检测 人流量与实际人流量之间的函数关系, 从而提高 WI-FI检测的精度。 背景技术
大型商场、 交通枢纽、 旅游度假区等场所经常出现大客流现象, 尤其在客流 高峰期, 大量行人涌入主要道路, 会造成一定的安全隐患, 影响这些场所内的运 营效率。 因此, 对道路行人流量的实施检测具有重要意义, 根据检测结果科学估 测实际人流量, 可以为相应的安保人员提供可靠的人流量数据, 从而适时采用合 理的手段保证商场、交通枢纽及旅游度假区内的正常运作。 目前关于人流量的检 测手段也越来越多样化, 根据检测技术的类别大致可以分为以下几类:
( 1 ) 人工调查法: 人工调查是最为传统的客流计数方法, 方法简单且可叠加人 工判断标准。 但由于其对调查人员要求较高, 计数误差大, 数据质量不高, 调查 后资料整理工作繁重,数据系统性不佳且无法提供实时数据, 目前也不能满足交 通需求的增长, 在人流量较密集的场所实时难度较大, 效率低下,
( 2) 闸机式客流计数: 闸机是一种通道阻挡装置(通道管理设备), 用于管理人 流并规范行人出入, 主要应用于地铁闸机系统、 收费检票闸机系统。 其最基本最 核心的功能是实现一次只通过一人, 可用于各种收费、 门禁场合的入口通道处。 该方式成本较低,且数量精确度佳, 但在服务人群多带有大量的行李包裹的情况 下, 该方式通过效率较低, 在紧急情况下对行人的疏散造成阻碍, 且不利于行动 不便人士的出行。 并且该方式检测人流数据仅为某一断面, 需要布置多个断面 才可掌握人流分布, 占地面积较大。
( 3) 踏板式客流计数: 压力板客流统计仪安装在检验区域的地面, 行人经过时 触发压力传感器信息得以被自动记录下来。该类仪器大致可以分为两类, 一类是 根据 "人体踏抬步数据模型模式"进行计数和方向判断, 另一类是根据 "乘客脚 踏轮廓 "进行判断。该方法降低了对客流运行的影响且安装简单, 但检测正确率 低, 且踩压系统部件容易损坏, 可维护性较差。
(4) 红外式客流计数: 红外式客流计数可分为被动红外式客流计数和主动红外 式客流计数。被动红外式客流计数采用的是可避免其他物体干扰的、仅能检测人 体所发出的信号的热释红外线探头。有人通过的时候, 红外传感器便可探测到由 人体红外光谱所产生的某种变化, 同时触发一个脉冲信号, 然后根据脉冲信号个 数来判断人数。 主动红外式则是通过发射头发射定制波长红外线覆盖一定区域, 并通过传感器检测到的乘客反射的光线识别乘客数量。主动红外式客流计数克服 了被动红外式客流计数中受环境、光线影响的缺点, 但由于它采用通过对脉冲个 数进行简单的判断来确定人数, 因而造成统计的准确度低, 对多人同时通过的情 况更是无法准确测定。 并且, 仅利用红外方式无法判别客流的方向, 且检测设备 成本较高, 不宜于大范围使用。
( 5 ) 视频客流计数: 视频客流计数可分为单目视频客流计数和双目视频客流计 数。视频客流技术通过在关键通道内安装摄像头获取视频图像,利用图像处理计 数如图像分割, 人工神经网络、立体图像分析等捕获客流计数。但该方法起步较 晚, 技术尚未成熟。且实施成本、 维护成本都较高, 人流密集时难以解决人流个 体分割问题因而精确度较低。
(6) WI-FI探针客流检测: WI-FI探针客流检测是通过在检测区域内部署 WI-FI 网络以获取开启 WI-FI功能的移动设备的 MAC地址, 从而实现客流计数。 基于 WI-FI的客流统计方法操作简单, 设备成本合理, 受非视距因素影响小, 灵活性 高, 能同时获取大量的统计数据, 在密集客流下的人流统计中具有较大的优势。 并且对探针获取的数据内容进行深入分析, 可以得到人流停留时间、流线流向等 特征数据。并且这种检测方法在后续操作支持云平台、数据应用可扩展至营销层。 目前在大型商业区、 旅游景点、 游乐场所等场所应用广泛。
WI-FI探针技术: WI-FI探针可以探测到开启了 WI-FI功能的移动设备的 MAC 地址, 其原理包括: WI-FI是基于 IEEE802. l la/b/g/n协议, 在标准协议中, 定 义了无线接入点和客户端两种工作模式, 协议中也规定了 Beacon、 Ack、 Data 和 Probe等多种无线数据帧类型。当客户端连接到无线接入点时进行交互的就是 数据帧和应答帧, 同时无线接入点周期性的发送 Beacon 当客户端没有连接到 无线接入点上,客户端也会不断发送 Probe帧到附近的无线接入点进行探测。而 WI-FI探针就是基于各种无线数据帧来抓获附近客户端信息的无线接入点, 它能 截获一定范围内 WI-FI打开了的移动客户端的 MAC层信息, 主要包括 MAC地址、 信号接收强度值、 时间戳等。
但是, 人工调查法、 闸机计数法、 踏板式计数法、 红外式计数法以及视频计 数法等都存在需要人力较多、设备昂贵且占地面积较大等缺点, 而目前较为流行 的基于 WI-FI的客流检测方法又普遍存在以下问题:
( 1 ) 移动设备的唯一 MAC地址被探针检测到的前提是移动设备的 WI-FI需要是 打开状态。 而实际场景下人群中移动设备打开 WI-FI的比例较低且未知。 所以一般情况下 WI-FI检测到的客流量与实际客流量差异较大,从检测量 上看效果并不理想。
( 2) 移动设备发射出的无线探测信号在被探针捕获到的过程中存在多径现象 与反射现象, 而无线信号的多径现象与反射现象会使信号强度衰减, 导致 探针检测到的接收信号强度值(RSSI )有不同程度的衰减, 情形严重时甚 至检测不到。 所以也会导致 WI-FI的检测率较低。
( 3) 由于检测率较低的基本特征,导致不能直接使用检测结果对客流量进行统 计。所以需要在检测量与实际量之间建立合适的预测模型, 从而提高由检 测值预测实际值的精度,同时也应满足行人流量不断波动情况下预测模型 的高准确性。
而目前关于 WI-FI客流统计方面的研究比较有限,主要集中在基于对接收信 号强度值 (RSSI ) 的精准研究探求室内行人的准确定位问题, 以及在现有室内 WI-FI系统下的包括客流密度、 客流轨迹等特征参数的描述。 对于如何有效提高 WI-FI客流统计的检测率、 如何布设 WI-FI探针以达到较优的检测效果以及如何 通过建模提高客流估算的精度等方面仍缺乏研究。 术语解释
为使本发明的描述更加准确清晰,现对本发明中会出现的各种术语作如下解 释:
WI-FI 探针: 一种基于各种无线数据帧来抓获附近移动设备信息的无线接入点, 它能截获一定范围内 WI-FI打开了的移动客户端的 MACXMedia Access Control ) 层信息, 主要包括 MAC地址、 信号接收强度值、 时间戳等;
检测区域: WI-FI 探针所具备的有效检测面积, 一般是以探针为圆心, 50-100 米为半径的球形区域;
检测时段: 使用 WI-FI探针对道路行人进行检测时所使用的单位检测时间长度。 行人移动设备: 行人随身携带的具有 WI-FI功能的电子设备, 例如智能手机、 手 提电脑、 IPAD等;
MAC地址: 即 Media Access Control地址, 意译为媒体访问控制, 是每个移动 设备的物理地址、 硬件地址、用来定义网络设备的位置。表现为一串唯一的由数 字和字母组成的 12位字符;
MAC地址原始数据: 由 WI-FI探针检测到的所有 MAC地址数据条;
无效 MAC地址数据: MAC地址原始数据中, 不属于待研究道路范围内的 MAC地址 数据条;
有效 MAC地址数据: MAC地址原始数据中, 属于待研究道路范围内的 MAC地址数 据条;
检测人流量数据: 同有效 MAC地址数据;
修正参数 ex: 由多次重复实验得到的用于表征探针对移动设备的检测率的参数; 修正参数 β : 由问卷调查得到的用于表征道路行人随身携带移动设备的个数的参 数; 发明内容
本发明的目的在于, 提供一种使用 WI-FI探针检测道路行人流量的方法。具 体检测手段是使用 WI-FI 探针对有效检测区域内的移动设备进行探测, 在设备 WI-FI功能打开的情况下, 探针就能通过捕获无线信号而检测到该设备的唯一标 识的 MAC地址,从而进行人流量的统计。探针捕获的无线信号信息包括捕获时间、 接收信号强度值、 MAC地址等。
使用 WI-FI探针检测人流量时, 本发明主要解决以下三个问题: ( 1 ) 使用多个探针对道路行人流量进行检测时,移动设备发射出的无线信号在 传播过程中存在多径现象和反射现象,从而会导致探针捕获到的信号接受 强度(RSSI )有不同程度的衰减, 甚至无法被检测到。 所以, 本发明在探 究多个探针的空间布局对无线信号的检测结果的影响的基础下,给出多种 较优的探针布设方案,从而较大限度地减少无线信号的传播过程中多径现 象和反射现象对检测结果的影响。
( 2) WI-FI探针的有效检测范围是以设备为中心,一定长度为半径的球形区域。
所以当检测区域大于道路宽度时, 道路之外(包括两侧建筑物内) 的移动 设备也会被检测到从而导致检测结果中存在这些无效数据。所以,本发明 需要设定科学的数据筛选标准来剔除这些无效数据,从而保证检测结果的 可靠性。
( 3) 当行人流量变化时, 无线信号的多径与反射的程度不同, 导致在所给的数 据筛选标准下的检测率也会随着人流量的变化而发生明显变化。本发明给 出一个适用于人流量不断变化情况下的由检测量预测实际量的计算模型, 从而提高预测精度。 为解决以上问题, 本发明采用的技术方案包括:
( 1 ) 使用多个 WI-FI探针检测行人流量时,在相同的检测环境下, 同时布设多 种探针的空间布局方案,方案区别主要在于探针在道路纵向和横向空间上 的位置。
( 2) 收集原始检测数据时, 应取各个探针检测结果的并集, 统计在某段时间段 内检测到的移动设备 MAC地址数目。
( 3) 为有效剔除无效干扰数据, 需要设计预实验确定数据筛选的标准。预实验 在待测行人道路上进行,保证多个探针的的布设形式与检测人流量时相同, 在探针有效检测范围内, 使用已知 MAC地址的多个智能设备, 并随意位移 一段时间后,对探针检测到的 MAC地址数据的接收信号强度值进行统计分 析, 确定所需检测范围内的接收信号强度最小值, 作为数据筛选标准, 用 来排除所需检测范围以外区域内的行人移动设备 MAC地址数据。
(4) 同时, 对于道路两侧建筑物内的无效数据也应剔除。这类无效数据具有在 检测区域内停留时间长的特点,所以剔除的原则可以是将该数据被连续检 测到的时长与一般情况下行人经过探针有效检测区域内的时长相比较,若 超过经过时长则应剔除。
( 5) 由于行人流量不断变动, 检测率也随之变化。本发明在确定人流预测模型 时直接探讨行人检测值与实际值之间的关系,首先需要在使用探针检测人 流量的同时,人工计数出实际人流量的大小,并通过设计实验和数据处理, 给出多种确定实际人流量与检测人流量之间的函数关系,并由此函数关系 根据检测值推算实际值, 从而提高检测精度。
(6) 考虑到探针对其检测区域内的 WI-FI探针并非全部检测到,且存在一定比 例的行人随身携带的移动设备超过一台, 本发明通过引入修正参数 α和 β, 给出检测人流量与实际人流量之间函数关系的修正方法。
( 7) 此外, 本发明在检测行人总流量的同时, 还能通过数据处理对行人流量区 分流向。区分流向需对经过筛选后的 MAC地址数据的检测时间和接收信号 强度值进行比较分析。 在研究多探针的布设形式时, 本发明使用三个探针对人行道路进行检测, 并 给出四种不同的布设方案。主要区别在与探针之间的横向距离和纵向距离的变化, 具体布设形式如下, 示意图如附图 1所示。
1 ) 三个探针布设在行人道路两侧, 其中两个在行人道路同一侧, 间距等于 行人道路宽度, 另一个在行人道路另一侧;
2)三个探针均布设在行人道路中线上,间距等于行人道路宽度的二分之一;
3) 三个探针均布设在与行人道路纵向相垂直的直线上, 间距等于行人道路 宽度的二分之一;
4) 三个探针分别布设在行人道路两侧和中线上, 且沿着行人道路纵向和横 向上的间距均为行人道路宽度的二分之一。 在确定剔除无效干扰数据的标准时,本发明给出基于接收信号强度值的数据 筛选方法: 在给定检测场所的前提下, 提供一种预实验, 探究接收信号强度值 (RSSI )与移动设备到探针之间距离的对应关系, 从而根据实际测试场所的待检 测区域的空间范围大小, 确定相应的信号接收强度的最小值, 作为数据筛选线, 从原始数据中过滤掉待检测区域之外的干扰数据。 由于道路两侧建筑物内的 MAC地址也会被 WI-FI探针检测到,考虑到这些干 扰数据具有一直处于检测区域内的特点,所以本发明给出基于检测时长的数据筛 选方法: 对每个检测到的 MAC地址进行时间序列的分析, 确定其被检测到的时间 长度, 以一般行人通过待检测区域内的时长作为数据筛选的标准, 将检测结果中 检测时长大于该标准的 MAC地址数据剔除。 所述的基于接收信号强度值的数据筛选方法和基于检测时长的数据筛选方 法需同时采用来处理原始检测数据, 但不分先后, 既可以先使用基于接收信号强 度值的数据筛选方法再使用基于检测时长的数据筛选方法,也可以先使用基于检 测时长的数据筛选方法再使用基于接收信号强度值的数据筛选方法。 在确定实际人流量与检测人流量之间函数关系时,本发明在检测人流量数据 与实际人流量数据之间采用如下三种函数模型之一:
1 ) 平均检测率模型: 将各个检测时段内的检测人流量与对应的实际人流量 的比值作为检测率, 求出各个检测时段的检测率加权后的平均检测率, 用来描述 检测人流量与实际人流量之间关系;
2) 分段检测率模型: 以各个检测时段内的检测人流量数据为指标, 将检测 人流量数据划分为多个区间, 求出每个区间内的检测率, 从而建立各个区间内的 检测人流量与检测率之间的关系;
3) 三次样条插值模型: 采用三次样条插值函数拟合各个检测时段内检测人 流量与实际人流量之间的关系。
其中本发明给出的三次样条插值函数 S (x)中, 有自然边界条件为 0, 即
S"(x0) = 0
S"(xJ = 0 本发明使用修正参数 α对建立的检测人流量 -实际人流量函数关系进行修正, 修正参数 e通过对单个移动设备多次反复经过某 WI-FI检测区域的实验结果获得, 实验中移动设备的 WI-FI功能打开, 并记录下移动设备的 MAC地址、反复经过的 次数等信息。
本发明使用修正参数 β对建立的检测人流量 -实际人流量函数关系进行修正, 修正参数 β通过对待测道路上的行人进行问卷调查获得, 问卷的主要内容是调查 待测行人道路上行人随身携带的移动设备数目, 调查的对象是随机选择的。 本发明在使用 WI-FI探针检测人流量时,采用的检测时段需要根据实际检测 行人道路上的行人特征而定, 可以取 10min、 30min或 lh, 作为数据采集与统计 的单位时间长度。 当三个探针布设方案如附图 4所示时,即三个探针分别布设在行人道路两侧 和中线上,且沿着行人道路纵向和横向上的间距均为行人道路宽度的二分之一时, 本发明给出判别行人流向的具体步骤为如附图 5 :
1) 沿道路纵向分别将三个探针标记为 A、 B和 C;
2) 将 A与 B检测到的 MAC地址数据的并集记为 X, B与 C检测到的 MAC地址 数据的并集记为 Y;
3) 对每一个检测到的 MAC地址数据, 找到其在 X与 Y中首次被检测到的时 间, 分别记为 T\、 Τ2 ; 若 Τ\ < Τ2, 则认为流向为由 Α至 C方向; 若 1\ >丁2, 则认为流向为由 C至 A;
4) 若 T\ = T2, 则比较与 Τ\、 时刻对应的信号接收强度值, 分别记为^?^^ 禾口«S/2, 若 RSSL^ > RSSI2 , 则认为流向为由 Α至 C; 若《55 < RSSI2 , 则认 为流向为由 C至 A, RSSIi = RSSI2 , 则无法判断流向。
附图简要说明 图 1为基于三探针的空间布局方案示意图。在双向人行街道中, 四种探针布设方 案的具体形式。
图 2为数据筛选预实验示意图。 剔除无效数据的预实验中探针布设方案。 图 3为数据筛选实验分析结果示意图。 基于接收信号强度值的数据筛选标准中, 对检测数据的分析方法。
图 4为区分流向的探针布设方案示意图。 判断行人流向时, 三探针的布设方案。 图 5为对检测人流量区分流向时的数据处理过程示意图。
具体实施方式 本发明以最常见的双向行人街道为研究对象,并使用三个探针对行人流量进 行检测。 并给出四种探针布设方案, 如附图 1所示:
方案一中三个探针布设在道路两侧, 其中两个在同一侧另一个在另一侧, 且 间距等于道路宽度;
方案二中三个探针均位于道路中线上, 且间距等于道路宽度的二分之一; 方案三中三个探针布设在与道路纵向相垂直的直线上,间距也等于道路宽度 的二分之一;
方案四中三个探针分别布设在道路两侧和中线上,且沿着道路纵向和横向上 的间距均为道路宽度的二分之一。 分别对图 1中的四种布设方案进行实验测试, 在数据处理时, 采取每种方案 下三个探针的检测结果取并集的方法来统计检测行人流量,再与实际行人流量作 比值求出检测率。 本发明通过分析实验结果发现, 当行人流量较小时, 各方案的检测率相差不 大;随着行人流量的增大,各种方案的检测率都会有所降低;当行人流量较大时, 方案四所示的探针布局方式下的行人检测率最高。这是由于行人流量较大时, 移 动设备发射出的无线信号在传播过程中的多径、发射现象较明显, 导致信号强度 衰减严重, 而方案四中, 在道路中间及两侧均布设探针能有效分散信号接收点, 更全面的接收来自道路内侧和外侧的数据,即一定程度上减少了多径与反射现象 造成的信号衰减; 另一方面, 方案四中三探针在道路纵向上有一定的距离, 可以 有效增大探针的整体有效检测区域, 从而增加检测时间, 有效降低移动设备在行 人通过检测区域内却没有信号发出的概率, 即增加了检测率。
所以本发明给出的四种探针布设方法,其中方案四在行人流量较高时的检测 率最高, 检测效果最好。 本发明设计预实验确定基于接收信号强度值的数据筛选标准,预实验的具体 内容为: 三探针的布设形式如附图 2所示, 在以探针为圆心, 以道路宽度的二分 之一为半径的区域内, 使用多个打开 WI-FI功能的移动设备模拟行人的运动,经 过一段时间的检测后, 统计各探针的检测结果。 本发明对预实验中得到的接收信号强度值数据进行分析如附图 3, 表明接收 信号强度值服从正态分布, 本发明取 90%的置信区间确定最终的数据筛选线。 本发明在确定基于检测时长的数据筛选标准时, 具体步骤为:
1) 计算三探针组成的有效检测区域在道路走向上的长度;
2) 行人一般行走速度取 1.5m/s, 可得到一般情况下行人通过有效检测区域 所需的时间长度 t1;
3) 统计每个检测到的 MAC地址数据的检测时长, 记为 t2;
4) 若 t2 > 则将该 MAC地址数据剔除。 本发明给出的建立三次样条插值函数拟合行人流量实际值与检测值之间的 关系。 具体方法如下:
本发明在实验中将得到 n组数据,分别统计出各组数据中检测到的移动设备
MAC地址数目记为 χ。、 Χι, ·'· χη, 对应于区间 [χ。, χ^]上各个节点, 同时人工计 数出各个节点对应的实际人流量为 y。、 …; 即确定各节点处的对应关系 为 fOJ =;^。 则可以按照以下步骤构造三次样条插值函数 S(x)。
记 hj = xj― x l, S"(x;) = Mj, 则有
5/'(χ) =¾-^ , 1 +^ , (1) 5,(x) = ^-^M^ + d- 3 M + + (2)
J J 6hj J 1 6hj J 1 L
Figure imgf000012_0001
μ]Μ]_1 + 2Mj + YjMj+1 = dj, j = 1,2...,n - (5) 其中式 (5) 中:
(6)
Π hj+hj+1 = 1~Yj = (7) hi+h
Figure imgf000012_0002
结合自然边界条件 S"(x。) = M。 = 0 和 S"(xJ = Μ„ = 0, (5) 式可写成矩阵 形式:
Figure imgf000012_0003
根据式 α) - (9), 三次样条插值函数可计算为如下形式:
i S (x), X G [ Q. I]
s2 ( )' Χ G [Χι,Χ2]
本发明使用修正参数 α对建立的检测人流量 -实际人流量函数关系进行修正, 修正参数 e通过对单个移动设备多次反复经过某 WI-FI检测区域的实验结果获得, 实验中移动设备的 WI-FI功能打开, 并记录下移动设备的 MAC地址、反复经过的 次数等信息, 并对实验结果作如下处理:
若该移动设备在探针的检测区域内经过 N次,并且由探针检测结果里存在该 移动设备的 MAC地址 n次, 即检测到了 n次, 则认为 WI-FI探针对打开了 WI-FI 功能的移动设备的检测率为 α, 且 c = 则需要在最终的三次样条插值函数模型
S(x)前除上修正参数 α, 即修正后的三次样条插值函数为 S(x)' = S(x)/a。 本发明使用修正参数 β对建立的检测人流量 -实际人流量函数关系进行修正, 修正参数通过对待测道路上的行人进行问卷调查获得,问卷的主要内容是调查待 测行人道路上行人随身携带的移动设备数目, 具体修正方法为:
若问卷结果显示行人中随身携带两台移动设备的比例为 a,则修正参数 β = 1 + a,则需要在最终的三次样条插值函数模型 S(x)前乘上修正参数 β,即修正后的 三次样条插值函数为 S(x)' = S(x)■ β。 当三个探针布设方案如附图 4所示时,本发明给出判别行人流向的具体步骤 为如附图 5:
1) 沿道路纵向分别将三个探针由左向右标记为 、 Β和 C;
2) 将 Α与 Β检测到的 MAC地址数据的并集记为 X, B与 C检测到的 MAC地址 数据的并集记为 Y;
3) 对每一个检测到的 MAC地址数据, 找到其在 X与 Y中首次被检测到的时 间, 分别记为 T\、 Τ2 ; 若 Τ\ < Τ2, 则认为流向为由 Α至 C方向; 若 1\ >丁2, 则认为流向为由 C至 A;
4) 若 T\ = T2, 则比较与 Τ\、 ^时刻对应的信号接收强度值, 分别记为^?^^ 禾口«S/2, 若 RSS > RSSI2 , 则认为流向为由 Α至 C; 若《55 < RSSI2 , 则认 为流向为由(至 。 其中-
1) 当 A与 B或 B与 C检测人流量数据取并集时,对于同一 MAC地址的数据, 只需保留其首次被检测到的数据。
2) 若某个检测到的 MAC地址数据只在 X或 Y中出现, 则需找出其在 X或 Y 中出现的所有次数据,通过比较每条数据的接收信号强度值和检测时间确定其流 向。
3)若某个检测到的 MAC地址数据在 X和 Y中首次出现的时间相同,即1\ = T2 时, 接收信号强度值也相同, 即 = «S/2, 则无法判断该 MAC地址数据的 流向。

Claims

权利要求书
1. 一种使用 WI-FI探针检测道路行人流量的方法, 包括如下步骤:
1 ) 数据采集: 在行人道路上,布设一组 WI-FI探针获取其检测区域各个检测时 段内行人移动设备的 MAC地址原始数据; 同时人工采集实际人流量数据; 所述的一组 WI-FI探针,采用如下四种探针布设方案之一作为拟定探针布设 方案;
la) 三个探针布设在行人道路两侧, 其中两个在行人道路同一侧, 间距等于行 人道路宽度, 另一个在行人道路另一侧;
lb)三个探针均布设在行人道路中线上, 间距等于行人道路宽度的二分之一; lc)三个探针均布设在与行人道路纵向相垂直的直线上, 间距等于行人道路宽 度的二分之一;
Id) 三个探针分别布设在行人道路两侧和中线上,且沿着行人道路纵向和横向 上的间距均为行人道路宽度的二分之一;
2) 数据筛选: 对所述的 MAC地址原始数据进行筛选, 剔除无效 MAC地址数 据, 获得行人移动设备有效 MAC地址数据, 作为检测人流量数据; 所述筛 选包括基于接收信号强度值的数据筛选和基于检测时长的数据筛选;
3) 数据处理: 对所述的行人移动设备有效 MAC地址数据, 建立所述检测人流 量数据与所述实际人流量数据之间的函数模型;
4) 模型修正:在所述的行人道路上,分别通过多次重复试验和问卷调查获得修 正参数 α和 β , 对所述的函数模型进行修正。
2. 如权利要求 1 所述的使用 WI-FI探针检测道路行人流量的方法, 其特征在于, 步骤 2) 数据筛选采用以下两种方法之一:
2a) 先对所述的 MAC地址原始数据做基于接收信号强度值的数据筛选, 再将 筛选的结果做基于检测时长的数据筛选; 所述的基于接收信号强度值的数据筛 选的具体方法为: 通过设计预实验, 找到对应于所述行人移动设备有效 MAC 地址数据的接收信号强度值的最小值, 作为数据筛选的标准, 将所述的 MAC 地址原始数据中接收信号强度值小于该标准的 MAC地址数据剔除; 所述的基 于检测时长的数据筛选的具体方法为: 以行人通过待检测区域内的时长作为数 据筛选的标准, 将基于接收信号强度值的数据筛选结果中检测时长大于该标准 的 MAC地址数据剔除;
2b) 先对所述的 MAC地址原始数据做基于检测时长的数据筛选, 再将筛选的 结果做基于接收信号强度值的数据筛选; 所述的基于检测时长的数据筛选的具 体方法为: 以行人通过待检测区域内的时长作为数据筛选的标准, 将所述的 MAC地址原始数据中检测时长大于该标准的 MAC地址数据剔除; 所述的基于 接收信号强度值的数据筛选的具体方法为: 在基于检测时长的数据筛选结果的 基础上, 通过设计预实验, 找到对应于所述行人移动设备有效 MAC地址数据 的接收信号强度值的最小值, 作为数据筛选的标准, 将所述的基于检测时长的 数据筛选结果中接收信号强度值小于该标准的 MAC地址数据剔除。
3. 如权利要求 1 所述的使用 WI-FI探针检测道路行人流量的方法, 其特征在于: 步骤 3) 中所述的函数模型为以下三者之一:
3a) 平均检测率模型: 将各个检测时段内的检测人流量与对应的实际人流量的 比值作为检测率, 求出各个检测时段的检测率加权后的平均检测率, 用来描述 检测人流量与实际人流量之间关系;
3b) 分段检测率模型: 以各个检测时段内的检测人流量数据为指标, 将检测人 流量数据划分为多个区间, 求出每个区间内的检测率, 从而建立各个区间内的 检测人流量与检测率之间的关系;
3c) 三次样条插值模型: 采用三次样条插值函数拟合各个检测时段内检测人流 量与实际人流量之间的关系。
4. 如权利要求 1所述的使用 WI-FI探针检测行人流量的方法, 其特征在于: 所述 的检测时段需要根据实际检测行人道路上的行人特征而定, 可以取 10min、 30min或 lh。
5. 如权利要求 1 所述的使用 WI-FI探针检测道路行人流量的方法, 其特征在于: 所述的模型修正中, 多次重复试验是探究 WI- FI 探针对其检测区域内已打开 WI-FI 功能的移动设备的检测率; 问卷调查是调查待测行人道路上行人随身携 带的移动设备数目, 调查的对象是随机选择的。
6. 如权利要求 2所述的使用 WI-FI探针检测道路行人流量的方法, 其特征在于: 所述的基于接收信号强度值的数据筛选的预实验,具体做法为:在行人道路上, 采用拟定探针布设方案,使用多个已知 MAC地址的移动设备在以探针为圆心、 行人道路宽度的一半为半径的区域内活动, 并统计各探针的检测结果。
7. 如权利要求 2所述的使用 WI-FI探针检测道路行人流量的方法, 其特征在于 所述的基于接收信号强度值的数据筛选中, 检测到的数据的接收信号强度值服 从正态分布, 取 90%置信区间, 得到的接收信号强度值作为数据筛选的标准。
8. 如权利要求 2所述的使用 WI-FI探针检测道路行人流量的方法, 其特征在于: 所述的基于检测时长的数据筛选中, 行人的步行速度取 1.5m/s。
9. 如权利要求 3所述的使用 WI-FI探针检测行人流量的方法, 其特征在于: 所述 的三次样条插值模型中, 自然边界条件的取值为 0。
PCT/IB2017/058545 2016-12-30 2017-12-30 一种使用wi-fi探针检测道路行人流量的方法 WO2018122815A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
GBGB1909414.3A GB201909414D0 (en) 2016-12-30 2017-12-30 Method for detecting traffic of pedestrians on road by using wi-fi probe
CN201780033657.XA CN109479206B (zh) 2016-12-30 2017-12-30 一种使用wi-fi探针检测道路行人流量的方法

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
IBPCT/IB2016/058108 2016-12-30
PCT/IB2016/058108 WO2018122588A1 (zh) 2016-12-30 2016-12-30 一种使用wi-fi探针检测行人流量的方法

Publications (1)

Publication Number Publication Date
WO2018122815A1 true WO2018122815A1 (zh) 2018-07-05

Family

ID=59713469

Family Applications (4)

Application Number Title Priority Date Filing Date
PCT/IB2016/058108 WO2018122588A1 (zh) 2016-12-30 2016-12-30 一种使用wi-fi探针检测行人流量的方法
PCT/IB2017/058546 WO2018122816A1 (zh) 2016-12-30 2017-12-30 一种使用wi-fi探针判别行人流向的方法
PCT/IB2017/058545 WO2018122815A1 (zh) 2016-12-30 2017-12-30 一种使用wi-fi探针检测道路行人流量的方法
PCT/IB2017/058547 WO2018122817A1 (zh) 2016-12-30 2017-12-30 一种使用wi-fi探针检测公共场所人流量的方法

Family Applications Before (2)

Application Number Title Priority Date Filing Date
PCT/IB2016/058108 WO2018122588A1 (zh) 2016-12-30 2016-12-30 一种使用wi-fi探针检测行人流量的方法
PCT/IB2017/058546 WO2018122816A1 (zh) 2016-12-30 2017-12-30 一种使用wi-fi探针判别行人流向的方法

Family Applications After (1)

Application Number Title Priority Date Filing Date
PCT/IB2017/058547 WO2018122817A1 (zh) 2016-12-30 2017-12-30 一种使用wi-fi探针检测公共场所人流量的方法

Country Status (3)

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

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110598154A (zh) * 2019-09-16 2019-12-20 新疆银狐数据科技有限公司 一种基于融合多渠道数据的旅游综合统计大数据平台

Families Citing this family (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107124476B (zh) * 2017-07-04 2020-04-10 百度在线网络技术(北京)有限公司 信息推送方法和装置
CN109362041B (zh) * 2018-12-18 2021-06-04 成都方未科技有限公司 一种基于大数据的人口时空分布分析方法
CN110113778A (zh) * 2019-04-30 2019-08-09 清华大学 基于数据驱动的高速公路服务区扩建规模测算方法及系统
CN112235430B (zh) * 2019-06-28 2023-12-05 北京奇虎科技有限公司 阻碍收集有效信息的方法和装置、电子设备
CN110493816B (zh) * 2019-08-21 2022-10-21 上海工程技术大学 一种用于轨交地铁车站客流量的实时预测方法
CN110879975B (zh) * 2019-11-06 2022-06-17 杭州宇泛智能科技有限公司 人员流量检测方法、装置及电子设备
CN111476611B (zh) * 2020-04-17 2022-05-17 支付宝(杭州)信息技术有限公司 基于传感器的数据处理方法以及装置
CN112502781B (zh) * 2020-11-24 2022-10-25 海洋王照明科技股份有限公司 一种矿井人员监控方法、装置、服务器及存储介质
CN113068215B (zh) * 2021-03-12 2022-01-11 华扬联众数字技术(深圳)有限公司 一种基于权重与过滤的多WiFi探针MAC地址的动线算法
CN115131964B (zh) * 2022-06-23 2024-02-20 重庆交通大学 隧道车流量感知系统
CN116887339B (zh) * 2023-09-07 2023-11-28 深圳中科爱讯科技有限公司 一种基于WiFi探针的实时客流统计系统及方法

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20110029359A1 (en) * 2009-07-29 2011-02-03 Cyriac Roeding Method and system for detecting presence using a wifi network probe detector
KR101046421B1 (ko) * 2011-02-09 2011-07-04 (주)멀린 위치정보 획득방법 및 시스템
KR20150006110A (ko) * 2013-07-08 2015-01-16 용현중 출퇴근 체크 앱 서비스 시스템 및 방법
CN105187240A (zh) * 2015-08-19 2015-12-23 广东中兴新支点技术有限公司 一种人流量检测方法及其装置
CN106210144A (zh) * 2016-08-22 2016-12-07 北京易游华成科技有限公司 人流量统计方法和设备
CN106251578A (zh) * 2016-08-19 2016-12-21 深圳奇迹智慧网络有限公司 基于探针的人流预警分析方法和系统

Family Cites Families (21)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8254395B2 (en) * 2005-11-03 2012-08-28 International Business Machines Corporation Computer-implemented method, system, and program product for tracking a location of a user of a wireless device in a private network environment
US8942112B2 (en) * 2008-02-15 2015-01-27 Cisco Technology, Inc. System and method for providing selective mobility invocation in a network environment
CN101668244A (zh) * 2008-09-02 2010-03-10 上海领美实业有限公司 公共场所人流智能管理与服务系统及其方法
CN201340272Y (zh) * 2008-09-02 2009-11-04 上海领美实业有限公司 公共场所人流智能管理与服务系统
CN102104771B (zh) * 2010-12-14 2012-12-12 浙江工业大学 基于无线监控的多路通道人流量监测系统
CN102625331A (zh) * 2011-06-14 2012-08-01 北京小米科技有限责任公司 一种移动终端数据流量的监控方法和装置
CN202773078U (zh) * 2011-07-30 2013-03-06 孙佰松 一种基于无线通信的人流定位和监控系统
CN202528324U (zh) * 2012-03-07 2012-11-14 南安市正冠机械有限公司 一种柱形石材加工装置
CN102737336A (zh) * 2012-04-12 2012-10-17 林华龙 基于移动装置来了解客流量及其行为的方法与管理系统
US9288683B2 (en) * 2013-03-15 2016-03-15 DGS Global Systems, Inc. Systems, methods, and devices for electronic spectrum management
CN103473840B (zh) * 2013-09-23 2016-03-16 沈阳天目科技有限公司 基于无线网络的具有人员区分功能的客流计数系统及方法
CN104361658B (zh) * 2014-09-30 2017-05-31 北京锐安科技有限公司 一种区域内各场所人口信息的检测方法和装置
CN104540168B (zh) * 2014-12-30 2018-05-11 杭州华为数字技术有限公司 一种测量人群拥挤度的方法、装置与系统
CN105049422B (zh) * 2015-06-25 2018-04-13 迪爱斯信息技术股份有限公司 一种wifi探测识别设备、系统以及wifi探测识别方法
CN105163277A (zh) * 2015-08-10 2015-12-16 上海网罗电子科技有限公司 一种基于位置信息的大数据任务的管理系统及方法
CN105160321A (zh) * 2015-09-05 2015-12-16 深圳市飞思未来云媒体科技有限公司 一种基于视觉与无线定位的移动终端身份确认方法
CN205283824U (zh) * 2015-11-24 2016-06-01 如东信息技术服务(上海)有限公司 一种基于wifi的机场人流预警系统
CN105869388B (zh) * 2016-05-31 2018-09-04 苏州朗捷通智能科技有限公司 一种公交客流数据采集及起讫点的分析方法及系统
CN106022643A (zh) * 2016-06-06 2016-10-12 北京智旅科技有限公司 景区游客数据分析系统
CN106211067A (zh) * 2016-06-30 2016-12-07 北京奇虎科技有限公司 一种基于终端的人流监控方法及装置
CN107360590A (zh) * 2017-06-29 2017-11-17 上海工程技术大学 轨道车站局部拥堵点客流状态判定方法

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20110029359A1 (en) * 2009-07-29 2011-02-03 Cyriac Roeding Method and system for detecting presence using a wifi network probe detector
KR101046421B1 (ko) * 2011-02-09 2011-07-04 (주)멀린 위치정보 획득방법 및 시스템
KR20150006110A (ko) * 2013-07-08 2015-01-16 용현중 출퇴근 체크 앱 서비스 시스템 및 방법
CN105187240A (zh) * 2015-08-19 2015-12-23 广东中兴新支点技术有限公司 一种人流量检测方法及其装置
CN106251578A (zh) * 2016-08-19 2016-12-21 深圳奇迹智慧网络有限公司 基于探针的人流预警分析方法和系统
CN106210144A (zh) * 2016-08-22 2016-12-07 北京易游华成科技有限公司 人流量统计方法和设备

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110598154A (zh) * 2019-09-16 2019-12-20 新疆银狐数据科技有限公司 一种基于融合多渠道数据的旅游综合统计大数据平台
CN110598154B (zh) * 2019-09-16 2023-04-07 新疆银狐数据科技有限公司 一种基于融合多渠道数据的旅游综合统计大数据系统

Also Published As

Publication number Publication date
CN109716358A (zh) 2019-05-03
GB201909414D0 (en) 2019-08-14
CN109479206A (zh) 2019-03-15
CN109644320B (zh) 2020-12-11
CN109644360B (zh) 2021-12-17
CN109644320A (zh) 2019-04-16
GB201711411D0 (en) 2017-08-30
GB2569752B (en) 2020-05-20
WO2018122817A1 (zh) 2018-07-05
CN109716358B (zh) 2023-06-06
GB2569752A (en) 2019-06-26
GB201905910D0 (en) 2019-06-12
WO2018122816A1 (zh) 2018-07-05
CN109479206B (zh) 2021-12-17
CN109644360A (zh) 2019-04-16
WO2018122588A1 (zh) 2018-07-05
GB201909415D0 (en) 2019-08-14

Similar Documents

Publication Publication Date Title
WO2018122815A1 (zh) 一种使用wi-fi探针检测道路行人流量的方法
CN106297288B (zh) 一种公交乘客客流数据采集与分析方法
CN109362038A (zh) 基于WiFi探针的客流量统计分析及服务的方法和系统
CN106792465A (zh) 一种基于众包指纹的室内指纹地图构建方法
JP2005522120A5 (zh)
CN105513362B (zh) 一种公交站台毗邻区公交车运行状态评价验证方法
Panichpapiboon et al. Exploiting wireless communication in vehicle density estimation
CN108810808A (zh) 一种基于手机信令数据的区域客流饱和度计算方法
CN108737968A (zh) 一种通过无线技术感知乘客异常行为的方法
CN106408944A (zh) 基于双通信数据的拥堵等级分析平台
CN101131796A (zh) 一种道路交通参数检测装置及检测方法
Kanjo et al. CrowdTracing: overcrowding clustering and detection system for social distancing
CN111866725B (zh) 一种基于wifi探针技术的人流检测方法
CN109410597B (zh) 一种园区出入口车流量检测方法、装置和系统
CN110232817A (zh) 一种基于WiFi嗅探数据的高速公路路况分析方法
Toutouh-el-Alamin et al. Enabling low cost smart road traffic sensing
Bánhalmi et al. Extracting information from Wi-fi traffic on public transport
Dong et al. Bus passenger flow and running status analyzation system based on MAC address
CN106781483A (zh) 智能交通管理系统
CN110263993A (zh) 一种用于城市轨交乘客走行时间的实时预测方法
CN117877273B (zh) 基于空地信息融合的智慧高速交通状态判别方法及系统
Zhu et al. A passenger flow monitoring method in Hongqiao hub area based on gridded Wi-Fi sniffing
CN110851970B (zh) 基于co2浓度的建筑物疏散通道内行人统计及管理方法
Ozaita Araico Detection of the crowdedness of a place sensing the devices in the area
CN109657700B (zh) 一种宏观区域连通道热度检测方法

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 17888235

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 22.10.2019)

122 Ep: pct application non-entry in european phase

Ref document number: 17888235

Country of ref document: EP

Kind code of ref document: A1