CN112396865A - Real-time bus arrival prediction method based on line track - Google Patents
Real-time bus arrival prediction method based on line track Download PDFInfo
- Publication number
- CN112396865A CN112396865A CN202011297791.0A CN202011297791A CN112396865A CN 112396865 A CN112396865 A CN 112396865A CN 202011297791 A CN202011297791 A CN 202011297791A CN 112396865 A CN112396865 A CN 112396865A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- time
- route
- distance
- real
- 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.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/123—Traffic control systems for road vehicles indicating the position of vehicles, e.g. scheduled vehicles; Managing passenger vehicles circulating according to a fixed timetable, e.g. buses, trains, trams
- G08G1/133—Traffic control systems for road vehicles indicating the position of vehicles, e.g. scheduled vehicles; Managing passenger vehicles circulating according to a fixed timetable, e.g. buses, trains, trams within the vehicle ; Indicators inside the vehicles or at stops
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0125—Traffic data processing
- G08G1/0129—Traffic data processing for creating historical data or processing based on historical data
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention provides a real-time bus arrival prediction method based on a line track, and aims to calculate the prediction time of a bus from a current stop by combining conditions such as line network data, Gps real-time data, historical driving speed and the like, solve the problem that an electronic stop board only displays distance stop numbers and does not display distance time, and improve the use satisfaction of the public. The method mainly comprises N steps, firstly, generating a track sequence set according to public traffic network data; then calculating the running average speed of the vehicle in different time periods of different lines according to the classification and summarization of the historical running Gps of the vehicle; loading real-time Gps vehicle-mounted terminal data, obtaining all vehicles under a route by taking the route as a classification condition, and calculating the arrival time and the distance station number of the stations before and after the distance of the vehicle according to the conditions of a road network track set of the current route, the real-time Gps projection position of the vehicle, the projection positions of all stations of the route, the predicted running speed of the route and the like. The method is suitable for measuring and calculating the arrival time of the bus.
Description
Technical Field
The invention relates to the technical field of bus information data processing, in particular to a real-time bus arrival prediction method based on a line track.
Background
Some large-city traffic managers in China have recognized the importance of urban public traffic intelligent scheduling systems, and begin to develop such systems step by step. Because the running time between stops is obtained by the ratio of the distance to the running speed of the vehicle, the arrival time of the next bus displayed on the electronic stop board is inaccurate, and the pace of the intelligent bus system in China is hindered.
The real-time bus arrival prediction is an important component of the intelligent travel service, and a reliable prediction result can help passengers to reasonably plan a travel scheme and reduce waiting time. The invention provides a real-time bus arrival prediction method based on a line track, aiming at the problems of multiple required data types, complex models, single application scene, high algorithm complexity and the like of a common real-time bus arrival algorithm, and providing prediction results of time, the number of remaining stations and the remaining distance for passengers.
Disclosure of Invention
The invention aims to solve the defects that the conventional electronic stop board cannot display the time of a next bus and only displays the distance between the next bus and the stop.
The distance and time of N nearest front and back stations in the running process of the vehicle are calculated by integrating the information of bus GPS real-time data, line network tracks, running speed per hour of the vehicle interval and the like. When a plurality of vehicles run on the same road network, the vehicles are filtered in unit time, and only the nearest stop reporting vehicle and the corresponding stop time and other information are sent.
The technical scheme for realizing the invention comprises the following steps:
s1: and generating a track set based on GPS data according to the public traffic network.
S2: and the terminal collector collects the GPS data in real time.
S3: and calculating the projection point of the vehicle on the route track according to the GPS data and the wire network data collected by the vehicle terminal collector, and taking the projection point as the current position of the vehicle.
S4: and calculating the track data of the line platform and the line network to obtain the distance between each station and the starting station.
S5: and calculating the N nearest stations and distance mileage of the current vehicle according to the distance difference.
S6: and obtaining the average speed of different lines in different time periods every day after summarizing and analyzing the past historical vehicle-mounted GPS data.
S7: calculating the distance between two coordinate points and the predicted waiting time according to the distance between the vehicle and different stations and the average speed
As a preferred scheme of the invention, a track set is generated according to the bus network data, and a coordinate set consisting of N GPS longitude and latitude coordinate points can be constructed by collecting the GPS data of the route through which the bus network passes. Connecting all the adjacent two points in the coordinate set to obtain a continuous directional route set consisting of N-1 vectors.
According to the invention, the projection point of the vehicle on the line track is calculated according to the real-time GPS data and the track sequence data sent back by the vehicle. The current position of the vehicle is estimated by calculating the minimum distance and the driving direction respectively according to the current GPS position of the vehicle and each line segment in the route set.
According to the invention, the average speed per hour of the vehicles owned by different routes at different time intervals (24-hour intervals per day) of each week is obtained in a classified and aggregated mode according to the historical GPS data of the vehicles, and the average speed per hour is used as a condition for calculating the time from the station. In the process of summarizing the average speed per hour, filtering is needed to remove abnormal data, dirty data and other data which can generate large errors in calculation, wherein the data comprises the following data: and (4) data cleaning, track matching, arrival time interpolation and road section travel time.
Compared with the prior art, the invention has the following beneficial effects: the method provides a real-time bus arrival prediction algorithm based on a historical average method, which is different from the traditional historical average method and uses stations to break a line into physical intervals in sequence. The traffic running conditions of the same road section have periodic characteristics, and historical data has a very important reference value for predicting the real-time arrival of the bus. The historical travel time calculation takes a physical interval as a basic unit, is distinguished according to working days and non-working days, and obtains travel time distribution required by the physical interval in each time period by time granularity of one hour, and the travel time distribution is used as the basis of real-time bus arrival prediction. The electronic bus stop board effectively overcomes the defects that the conventional electronic bus stop board cannot display the time of leaving bus, only displays the number of the leaving bus and the bus stop number or the arrival time of the leaving bus from the station is inaccurate, and the like.
Drawings
The present invention will be described in further detail with reference to the accompanying drawings;
fig. 1 is a schematic flow chart of a method for predicting bus arrival in real time based on a route track according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a station sequentially breaking a line into physical sections in the method of the present invention;
FIG. 3 is a schematic view of the present invention determining the direction of travel of a vehicle based on position and heading angle;
FIG. 4 is a schematic diagram of the present invention for determining a vehicle traveling direction according to track point position and direction angle information and matching the vehicle traveling direction to a nearest point on a bus route;
detailed description of the invention
In order to make the implementation objects, technical solutions and advantages of the present invention clearer, the technical solutions in the implementations of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and all other embodiments obtained by a person of ordinary skill in the art without any creative work based on the implementations of the present invention belong to the protection scope of the present invention.
Fig. 1 is a schematic flow chart of a real-time bus arrival prediction method based on a route track according to the present invention, and as shown in fig. 1, the real-time bus arrival prediction method based on the route track includes:
s1: and generating a track set based on GPS data according to the public traffic network.
S2: and the terminal collector collects the GPS data in real time.
S3: and calculating the projection point of the vehicle on the route track according to the GPS data and the wire network data collected by the vehicle terminal collector, and taking the projection point as the current position of the vehicle.
S4: and calculating the track data of the line platform and the line network to obtain the distance between each station and the starting station.
S5: and calculating the N nearest stations and distance mileage of the current vehicle according to the distance difference.
S6: and obtaining the average speed of different lines in different time periods every day after summarizing and analyzing the past historical vehicle-mounted GPS data.
S7: and calculating the distance between the two coordinate points and the predicted waiting time according to the distance between the vehicle and different stations and the average speed.
Specifically, the track set mentioned in step S1 may be a coordinate set composed of N GPS longitude and latitude coordinate points, which is constructed by collecting GPS data of a route through which the public transportation network passes. Connecting all the adjacent two points in the coordinate set to obtain a continuous directional route set consisting of N-1 vectors. Further, the scheme is different from the traditional historical averaging method, but as shown in fig. 2, the route is broken into physical sections in sequence by the stations, so that the distance between the vehicle and the stations can be calculated subsequently, and the arrival time can be calculated.
Specifically, the projected points mentioned in step S3: the minimum distance between the current GPS position of the vehicle and each line segment in the route set needs to be calculated separately, so as to obtain a route segment with the minimum distance smaller than a certain range (i.e. close). These route segments are the route segments where the vehicle may be located. And removing routes different from the driving direction of the vehicle from the route sections, selecting the shortest route section from the remaining routes as the route section where the vehicle is currently located, and if the projection point of the shortest distance on the route section is on the route section, taking the projection point as the current position of the vehicle. And if the projection point is before the starting point or after the end point, taking the starting point or the end point as the current position of the vehicle. Correspondingly, the real-time data sent back by the vehicle is GPS data, and considering that the invention aims to solve the distance prejudgment of urban buses, the real-time data is regarded as plane coordinates in a small range, and the error can be ignored.
Further, in step S3, to predict the arrival time of the bus in real time, the route position of the bus is determined, most of the non-loop buses include uplink and downlink directions, and the bus GPS track information only includes the longitude and latitude, the time, the vehicle direction angle, and the like of the position of the bus, and does not include the running direction. At this time, the vehicle running direction needs to be judged by the position and the direction angle. As shown in fig. 3, the line l has two directions of up and down, the direction angle of the track point P is α, the included angle with the up direction is smaller, and the distance | PP ' | from the point P to the nearest point P ' in the up direction of the line is less than 30 meters, so that the point P is matched to the point P ' in the up direction of the line.
Specifically, in step S6, the average speed per hour of the vehicle owned by the route having different time intervals (24-hour intervals per day) every week is obtained in a classified manner from the vehicle history GPS data as a condition for calculating the distance to the station. In the process of summarizing the average speed per hour, filtering is needed to remove abnormal data, dirty data and the like which cause large errors in calculation.
Further, the prediction model established for most methods needs a plurality of data supports, the method only needs to prepare the bus route, the stop data and the historical track data, and the processing process of the historical track comprises the following steps:
1) data cleaning: cleaning position abnormity, repeated and invalid records in the historical track data, and completing partial records with information loss according to other records;
2) track matching: judging the running direction of the vehicle according to the position and the direction angle information of the track point, and matching the running direction with the nearest point of the bus route (as shown in figure 4);
3) interpolation of arrival time: and searching the adjacent track points of the station, and interpolating historical arrival time. In order to simplify the estimation process, the vehicle between adjacent track points is assumed to run at a constant speed, so that the arrival time of the station is obtained according to distance interpolation. As shown in FIG. 4, A and B are two adjacent track points (from point A to point B), and the recording time is tAAnd tBAnd if the station x passes through the middle, the time of reaching x is as follows:
tx=tA+(tB-tA)*dAx/dAB
4) road section travel time: calculating travel time in a physical interval, and calculating the average travel time of each time period by taking 1 hour as granularity according to working days and non-working days, and recording the average travel time asWherein, A and B respectively represent the starting point and the end point of the interval, and the corner mark i represents the ith time period.
Specifically, in step S7, the distance between two coordinate points and the expected waiting time are calculated based on the distance between the vehicle and the different stations and the average speed. As shown in fig. 3, through the previous steps, it can be deduced that the vehicle is located in a certain physical interval (i, i +1), so that the remaining time of the vehicle to reach the subsequent station i, i +1, i +2, …, i + n can be predicted and calculated by using the following formula:
tP′,i+1=ti,i+1*dP′,i+1/di,i+1
Tn=tP′,i+1+ti,i+1+…+tn-1,n
wherein, tP′,i+1The time, T, required for the vehicle to arrive at the next station (i +1 station) when the vehicle is at the current position PnThe time required for the vehicle to arrive at the station n of the subsequent station when the vehicle is at the current position P'.
Claims (5)
1. A real-time bus arrival prediction method based on a line track is characterized in that:
s1: and generating a track set based on Gps data according to the public transportation network.
S2: and calculating the projection point of the vehicle on the line track according to the real-time GPS data and the line network data collected by the terminal collector, and taking the projection point as the current position of the vehicle.
S3: and calculating the projection points of the line platform and the line network track data to obtain the distance between each station and the starting station.
S4: and calculating the N nearest stations and distance mileage of the current vehicle according to the distance difference.
S5: and obtaining the average speed of different lines in different time periods every day after summarizing and analyzing the past historical vehicle-mounted Gps data.
S6: and calculating the distance between the two coordinate points and the predicted waiting time according to the distance between the vehicle and different stations and the average speed.
2. The real-time bus arrival prediction method based on the line track as claimed in claim 1, characterized in that: the generating of a track set according to the public traffic network data specifically comprises: a coordinate set consisting of N GPS longitude and latitude coordinate points can be constructed by collecting GPS data of a route through which a bus network passes. Connecting all the adjacent two points in the coordinate set to obtain a continuous directional route set consisting of N-1 vectors.
3. The real-time bus arrival prediction method based on the line track as claimed in claim 1, characterized in that: and calculating the distance from the projection point to the starting station along the route in the track set. The method specifically comprises the following steps: and calculating the distance from the projection point to the starting point step by step in the reverse direction by using a plane two-point distance formula.
4. The real-time bus arrival prediction method based on the line track as claimed in claim 1, characterized in that: and calculating the average running speed per hour of the actual operating vehicle in different time periods (dividing the day into 24 intervals) of different operating lines in stages according to the historical Gps data.
5. The real-time bus arrival prediction method based on the line track as claimed in claim 1, characterized in that: and calculating the projection point of the vehicle on the line track according to the real-time GPS data and the track sequence data sent back by the vehicle, and taking the projection point as the current position of the vehicle. The method specifically comprises the following steps: the minimum distance between the current GPS position of the vehicle and each line segment in the route set needs to be calculated separately, so as to obtain a route segment with the minimum distance smaller than a certain range (i.e. close). These route segments are the route segments where the vehicle may be located. And removing routes different from the driving direction of the vehicle from the route sections, selecting the shortest route section from the remaining routes as the route section where the vehicle is currently located, and if the projection point of the shortest distance on the route section is on the route section, taking the projection point as the current position of the vehicle. And if the projection point is before the starting point or after the end point, taking the starting point or the end point as the current position of the vehicle.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011297791.0A CN112396865A (en) | 2020-11-18 | 2020-11-18 | Real-time bus arrival prediction method based on line track |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011297791.0A CN112396865A (en) | 2020-11-18 | 2020-11-18 | Real-time bus arrival prediction method based on line track |
Publications (1)
Publication Number | Publication Date |
---|---|
CN112396865A true CN112396865A (en) | 2021-02-23 |
Family
ID=74607639
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011297791.0A Pending CN112396865A (en) | 2020-11-18 | 2020-11-18 | Real-time bus arrival prediction method based on line track |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112396865A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115100897A (en) * | 2022-05-23 | 2022-09-23 | 惠州华阳通用电子有限公司 | Vehicle position determining method and device |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2004118848A (en) * | 2002-09-24 | 2004-04-15 | Kt Corp | Guiding method for required arrival time up to bus stop for passenger in bus using short range wireless communication network |
CN103295414A (en) * | 2013-05-31 | 2013-09-11 | 北京建筑工程学院 | Bus arrival time forecasting method based on mass historical GPS (global position system) trajectory data |
CN103310651A (en) * | 2013-05-24 | 2013-09-18 | 北京市交通信息中心 | Bus arrival prediction method based on real-time traffic status information |
CN104064024A (en) * | 2014-06-23 | 2014-09-24 | 银江股份有限公司 | Public transport vehicle arrival time prediction method based on history data |
CN106710218A (en) * | 2017-03-09 | 2017-05-24 | 北京公共交通控股(集团)有限公司 | Method for predicting arrival time of bus |
CN108154698A (en) * | 2018-01-05 | 2018-06-12 | 上海元卓信息科技有限公司 | A kind of public transport based on GPS track big data is to precise time computational methods leaving from station |
CN109544908A (en) * | 2018-10-24 | 2019-03-29 | 佛山市慧城信息科技有限公司 | A kind of method, electronic equipment and the storage medium of real-time prediction public transport arrival time |
CN111007544A (en) * | 2019-12-18 | 2020-04-14 | 南京智慧交通信息有限公司 | Method for measuring and calculating distance between front bus and rear bus based on line track |
-
2020
- 2020-11-18 CN CN202011297791.0A patent/CN112396865A/en active Pending
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2004118848A (en) * | 2002-09-24 | 2004-04-15 | Kt Corp | Guiding method for required arrival time up to bus stop for passenger in bus using short range wireless communication network |
CN103310651A (en) * | 2013-05-24 | 2013-09-18 | 北京市交通信息中心 | Bus arrival prediction method based on real-time traffic status information |
CN103295414A (en) * | 2013-05-31 | 2013-09-11 | 北京建筑工程学院 | Bus arrival time forecasting method based on mass historical GPS (global position system) trajectory data |
CN104064024A (en) * | 2014-06-23 | 2014-09-24 | 银江股份有限公司 | Public transport vehicle arrival time prediction method based on history data |
CN106710218A (en) * | 2017-03-09 | 2017-05-24 | 北京公共交通控股(集团)有限公司 | Method for predicting arrival time of bus |
CN108154698A (en) * | 2018-01-05 | 2018-06-12 | 上海元卓信息科技有限公司 | A kind of public transport based on GPS track big data is to precise time computational methods leaving from station |
CN109544908A (en) * | 2018-10-24 | 2019-03-29 | 佛山市慧城信息科技有限公司 | A kind of method, electronic equipment and the storage medium of real-time prediction public transport arrival time |
CN111007544A (en) * | 2019-12-18 | 2020-04-14 | 南京智慧交通信息有限公司 | Method for measuring and calculating distance between front bus and rear bus based on line track |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115100897A (en) * | 2022-05-23 | 2022-09-23 | 惠州华阳通用电子有限公司 | Vehicle position determining method and device |
CN115100897B (en) * | 2022-05-23 | 2023-11-17 | 惠州华阳通用电子有限公司 | Vehicle position determining method and device |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP5374067B2 (en) | Traffic condition simulation apparatus and program | |
US7953544B2 (en) | Method and structure for vehicular traffic prediction with link interactions | |
CN104778274B (en) | A wide range of city road network hourage method of estimation based on sparse GPS data from taxi | |
CN108345666B (en) | Vehicle abnormal track detection method based on time-space isolated points | |
CN110491158B (en) | Bus arrival time prediction method and system based on multi-metadata fusion | |
US20100063715A1 (en) | Method and structure for vehicular traffic prediction with link interactions and missing real-time data | |
CN110398254B (en) | Method and system for relieving traffic congestion | |
Brockfeld et al. | Benefits and limits of recent floating car data technology–an evaluation study | |
CN110118567A (en) | Trip mode recommended method and device | |
US20220215749A1 (en) | Method for predicting at least one profile of the speed of a vehicle on a road network | |
CN105096590B (en) | Traffic information creating method and traffic information generating device | |
CN110375762B (en) | Method and device for assisting in planning navigation path | |
CN103903468A (en) | Time early-warning method for traffic jam and device thereof | |
CN113129588B (en) | Method and device for determining bus running line and electronic equipment | |
CN106228830A (en) | A kind of bus arrival time real-time estimate system and method | |
CN111915893A (en) | Road bottleneck point identification method and device, electronic equipment and storage medium | |
CN109754606B (en) | Method for predicting road congestion condition based on taxi positioning | |
CN112396865A (en) | Real-time bus arrival prediction method based on line track | |
CN114118766A (en) | Passenger flow OD algorithm based on bus passenger travel multiple matching | |
CN112562334A (en) | Method, device and medium for calculating real-time speed of curved road section based on floating car data | |
CN114078322B (en) | Bus running state evaluation method, device, equipment and storage medium | |
CN111007544A (en) | Method for measuring and calculating distance between front bus and rear bus based on line track | |
CN112529338A (en) | Method for calculating degree of forward road | |
CN110599768A (en) | Highway traffic flow estimation method based on telecommunication big data | |
CN115440037A (en) | Traffic flow data acquisition method and device, electronic equipment and storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210223 |
|
RJ01 | Rejection of invention patent application after publication |