WO2011079689A1 - Procédé et appareil d'extraction de valeurs caractéristiques de données de conditions de circulation routière - Google Patents

Procédé et appareil d'extraction de valeurs caractéristiques de données de conditions de circulation routière Download PDF

Info

Publication number
WO2011079689A1
WO2011079689A1 PCT/CN2010/079512 CN2010079512W WO2011079689A1 WO 2011079689 A1 WO2011079689 A1 WO 2011079689A1 CN 2010079512 W CN2010079512 W CN 2010079512W WO 2011079689 A1 WO2011079689 A1 WO 2011079689A1
Authority
WO
WIPO (PCT)
Prior art keywords
road
value
class
clustering
condition data
Prior art date
Application number
PCT/CN2010/079512
Other languages
English (en)
Chinese (zh)
Inventor
李建军
贾学力
梅生
申小次
Original Assignee
北京世纪高通科技有限公司
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 北京世纪高通科技有限公司 filed Critical 北京世纪高通科技有限公司
Publication of WO2011079689A1 publication Critical patent/WO2011079689A1/fr

Links

Classifications

    • 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

Definitions

  • the present invention relates to the field of application of intelligent transportation systems, and in particular, to a method and apparatus for extracting feature values of road condition data.
  • the Advanced Traffic Information System is based on a well-established information network and is equipped with sensors and transmission equipment on the road, on the bus, on the transfer station, on the parking lot, and in the weather center. All kinds of traffic information are comprehensively processed to provide comprehensive and accurate road traffic congestion information to the society in real time.
  • the inventor found that the data source of the ATIS is acquired in real time, and the ATIS can only feedback the real-time road condition information, and cannot predict the road condition to warn the pedestrian, which causes some traffic congestion points to be evacuated, so How to make ATIS predict the road conditions is an urgent problem to be solved.
  • Embodiments of the present invention provide a method and apparatus for extracting feature values of road condition data to solve the problem that road conditions are not predicted by ATIS to alert the pedestrians, causing some traffic congestion points to be evacuated.
  • a method for extracting feature values of road condition data comprising:
  • a road condition data feature value extracting device comprising:
  • An obtaining unit configured to obtain historical road condition data of at least three months
  • a sorting unit which identifies the road speed according to an inherent characteristic of the road speed in the historical road condition data acquired by the acquiring unit;
  • a clustering unit configured to perform a clustering operation on the road speed of the same identifier obtained by the finishing unit
  • An extracting unit configured to extract a road vehicle speed average value of the class that meets the condition after the clustering unit clustering operation, where the number of road speeds included in the qualified class is greater than or equal to a preset number of road speeds;
  • an output unit configured to output the road vehicle speed average value extracted by the extracting unit as the road condition data feature value.
  • the method and device for extracting the feature data of the road condition data provided by the embodiment of the present invention, by clustering the road speed, and outputting the mean value of the road speed of the eligible class as the feature value of the road condition data, according to the characteristic value of the road condition data, the ATIS can The change law of the traffic congestion situation in a certain area is obtained, thereby realizing the prediction of the road condition, and solving the problem that the current situation is that the ATIS cannot realize the road condition prediction to warn the pedestrians, and some traffic congestion points are not timely.
  • FIG. 1 is a flowchart of a method for extracting feature values of road condition data according to an embodiment of the present invention
  • FIG. 2 is a flowchart of a method for extracting feature values of road condition data according to another embodiment of the present invention
  • FIG. 3 is a flowchart of the invention shown in FIG. The flowchart of step 202 in the method for extracting road condition data feature values provided by the example;
  • step 203 is a flow chart 1 of step 203 in the flowchart of the method for extracting feature data of road condition data provided by the embodiment of the invention shown in FIG. 2;
  • FIG. 5 is a flowchart of step 2032 in the flowchart of the method for extracting feature data of the road condition data provided by the embodiment of the invention shown in FIG. 4;
  • FIG. 6 is a flow chart 2 of step 203 in the flowchart of the method for extracting feature data of the road condition data provided by the embodiment of the invention shown in FIG. 2;
  • FIG. 7 is a flowchart of a method for extracting feature data of road condition data provided by the embodiment of the invention shown in FIG. The flowchart of step 204;
  • FIG. 8 is a schematic structural diagram of an apparatus for extracting feature values of road condition data according to an embodiment of the present invention
  • FIG. 9 is a schematic structural diagram 1 of a clustering unit in an apparatus for extracting feature data of road condition data provided by the embodiment of the invention shown in FIG. 8;
  • FIG. 10 is a schematic structural diagram 2 of a clustering unit in an apparatus for extracting feature data of road condition data provided by an embodiment of the invention shown in FIG. 8;
  • FIG. 11 is a schematic structural diagram of an extracting unit in an apparatus for extracting feature data of road condition data provided by the embodiment of the invention shown in FIG. 5.
  • the embodiment of the present invention provides a method and apparatus for extracting the feature data of the road condition data.
  • a method for extracting feature data of road condition data includes: Step 101: Obtain historical road condition data of at least three months;
  • Step 102 Mark the road speed according to an inherent feature of the road speed in the historical road condition data
  • the intrinsic feature is a road name, a day of the week, and a time window corresponding to the road speed.
  • Step 103 Perform clustering operation on the road speed of the same identifier
  • the road speed of the same sign refers to the same road, the same week characteristic day, and the road speed under the same time window.
  • Step 104 Extract a road vehicle speed average value of a class that meets the condition after the clustering operation, and output the road vehicle speed average value as a road condition data feature value, where the number of road speeds included in the qualified class is greater than or equal to a preset value. The number of road speeds.
  • the method for extracting the feature data of the road condition data provided by the embodiment of the present invention, by clustering the road speed, and outputting the average road speed of the eligible class as the feature value of the road condition data, according to the feature value of the road condition data, the ATIS can obtain a certain a change in the traffic congestion situation in an area, thereby The realization of the prediction of the road condition solves the problem in the prior art that the ATIS cannot realize the road condition prediction to warn the pedestrians, and some traffic congestion points are not evacuated.
  • a method for extracting feature values of road condition data includes:
  • Step 201 Obtain historical road condition data of at least three months
  • Step 202 Identify the road speed according to an inherent feature of the road speed in the historical road condition data
  • the intrinsic features include a day of the week feature, a road name, and a time window.
  • the value of the week feature day includes Monday, Tuesday, Wednesday, Thursday, Friday, Saturday, and Sunday.
  • the value of the road includes the main roads of the city, and each road is distinguished by the road name, such as the collection of all road units of the Beijing main line, the West Second Ring Road, and the College Road.
  • the time window is obtained by dividing the 00: 00-23: 59 every other preset time, such as a time window set obtained by dividing each 5 minutes, 08: 00, 08: 05, 08: 10, 08: 15 and so on.
  • the step 202 includes the following steps:
  • Step 2021 Traverse the road set in the historical road condition data, and read the historical road condition data of the latest at least three months according to the week feature date;
  • step 2022 the road speed of the same road and the same week characteristic day in the historical road condition data is saved in a data file, and the data file is in the form of a road name; the data file may be in a form of a table, such as: The road speed of the College Road on Monday to December 2009 can be expressed in Table 1.
  • AH is expressed as the road speed value.
  • Step 2023 Store the data file under the same week feature date in a folder, and the folder is named after the week feature day.
  • Step 203 Perform clustering operation on the road speed of the same identifier
  • the step 203 includes:
  • Step 2031 Sort the road speeds of the same road, the same week characteristic day, and the different dates under the same time window according to the collated historical road condition data, and generate a vehicle speed data set;
  • Step 2032 Cluster the vehicle speed data set into a K class according to a preset K value.
  • the step 2042 includes:
  • Step 301 The vehicle speed data set is divided into K categories according to a preset K value, and the absolute value of the sample quantity difference between each class is at most 1; according to experience, the K value is generally taken as 6.
  • Step 302 Record the original boundary points between each class, and calculate the average road speed value of each class as the original center point of each class;
  • Step 303 Perform clustering according to the original center point and the original boundary point to form a final center point and a final boundary point, where the final center point is an average value of road speeds of each type, and the average speed of the road and the belonging class
  • the absolute value of the difference between the first road speeds is equal to the absolute value of the difference between the road speed average and the last road speed of the class;
  • Step 304 calculating a square error according to the final center point and the final boundary point.
  • E yy ⁇ x _
  • the square error can be obtained by the formula " m" .
  • M TM represents the lower label of the last element of the mth class
  • ⁇ represents the lower label of the first element of the mth class.
  • ⁇ indicates the final center point of the mth class.
  • the method further includes: Step 2033, re-assigning the preset K value to generate a new K value, and replacing the new K value.
  • the preset K value is clustered, and the square error is calculated until the square error calculated from the new K value is 50% of the square error calculated from the preset K value.
  • re-assigning the preset K value can be implemented by adding 1 to the K value.
  • Step 204 Extract a road vehicle speed average value of the class that meets the condition after the clustering operation, and output the road vehicle speed average value as the road condition data feature value, where the number of road speeds included in the qualified class is greater than or equal to a preset value. The number of road speeds.
  • the step 204 includes:
  • Step 2041 traversing the clustering result of each road under different week feature days and different time windows; Step 2042, when the number of samples included in a certain class of the clustering result is greater than or equal to the sample of the clustering calculation When 1/8 of the number is used, the average road speed of the class is extracted as the eigenvalue output.
  • the method for extracting the feature data of the road condition data provided by the embodiment of the present invention, by clustering the road speed, and outputting the average road speed of the eligible class as the feature value of the road condition data, according to the feature value of the road condition data, the ATIS can obtain a certain The change rule of the traffic congestion situation in a region, so as to realize the prediction of the road condition, solves the problem that the current situation is that the ATIS cannot realize the road condition prediction to warn the pedestrians, and some traffic congestion points are not evacuated.
  • the road condition data feature value extracting apparatus provided by the embodiment of the present invention, as shown in FIG. 8, includes: an obtaining unit 401, configured to acquire historical road condition data of at least three months in the past; The description of step 201 is not repeated here.
  • a sorting unit 402 according to the road speed in the historical road condition data acquired by the acquiring unit For details, refer to step 202 shown in FIG. 2, which is not described here.
  • the clustering unit 403 is configured to perform a clustering operation on the road speed of the same identifier obtained by the finishing unit. For the specific implementation method, refer to step 203 shown in FIG. 2, and details are not described herein again.
  • the clustering unit as shown in FIG. 9, includes:
  • a sorting generation sub-unit 4031 configured to sort road speeds of the same road, the same week feature day, and different dates under the same time window according to the historical road condition data organized by the sorting unit, and generate a vehicle speed data set;
  • step 2031 shown in FIG. 4 and the sequent data set clustering is not described here.
  • step 2032 shown in FIG. Narration For the specific implementation method, refer to step 2032 shown in FIG. Narration.
  • the clustering unit further includes:
  • the assignment sub-unit 4033 is configured to re-assign the preset K value to generate a new K value, replace the new K value with a preset K value, perform clustering, and calculate a square error until the The square error calculated by the new K value is 50% of the square error calculated from the preset K value.
  • the extracting unit 404 is configured to extract a road vehicle speed average value of the class that meets the condition after the clustering unit clustering operation, and the number of road speeds included in the qualified class is greater than or equal to a preset number of road speeds; For the specific implementation, refer to step 204 shown in Figure 2, and details are not described herein.
  • the extracting unit includes:
  • the traversing sub-unit 4041 is used to traverse the clustering result of each road in different week feature days and different time windows. For the specific implementation method, refer to step 2041 shown in FIG. 7 , and details are not described herein.
  • Extracting subunit 4042 when the traversal subunit traverses the clustering result included in a certain class
  • the number of samples is greater than or equal to 1/8 of the number of samples calculated by the cluster
  • the average road speed of the class is extracted.
  • the output unit 405 is configured to output the road vehicle speed average value extracted by the extraction unit as the road condition data feature value. For the specific implementation, refer to step 204 shown in Figure 2, and details are not described here.
  • the device for extracting the feature data of the road condition data provided by the embodiment of the present invention outputs the road vehicle speed average value as the road condition data feature value by clustering the road vehicle speed, and according to the road condition data feature value, the ATIS can obtain a certain The change rule of the traffic congestion situation in a region, so as to realize the prediction of the road condition, solves the problem that the current situation is that the ATIS cannot realize the road condition prediction to warn the pedestrians, and some traffic congestion points are not evacuated.
  • the method and device for predicting road conditions provided by the embodiments of the present invention are applicable to the field of intelligent transportation, such as ATIS.

Landscapes

  • Chemical & Material Sciences (AREA)
  • Analytical Chemistry (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Traffic Control Systems (AREA)

Abstract

L'invention porte sur un procédé et sur un appareil destinés à extraire des valeurs caractéristiques de données de conditions de circulation routière. Le procédé comprend : l'obtention de données historiques de circulation routière sur au moins les trois mois précédents (101), le marquage de la vitesse de croisière selon la caractéristique inhérente de la vitesse de croisière contenue dans les données historiques de conditions de circulation routière (102), la réalisation d'une opération de regroupement sur les vitesses de croisière avec le même marquage (103), l'extraction de la valeur moyenne des vitesses de croisière dans le groupe satisfaisant aux exigences après l'opération de regroupement, et la délivrance de la valeur moyenne en tant que valeur caractéristique des données de conditions de circulation routière, le nombre de vitesses de croisière dans le groupe satisfaisant les exigences étant supérieur ou égal à un nombre préétabli des vitesses de véhicule routiers (104). Le procédé permet d'éviter le problème selon lequel le système perfectionné d'informations de conditions de circulation (ATIS) ne peut pas prévoir les conditions de circulation, afin d'alerter un voyageur si les points d'embouteillage de la circulation ne sont pas dégagés immédiatement.
PCT/CN2010/079512 2009-12-29 2010-12-07 Procédé et appareil d'extraction de valeurs caractéristiques de données de conditions de circulation routière WO2011079689A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN200910244110.1 2009-12-29
CN 200910244110 CN101763729B (zh) 2009-12-29 2009-12-29 路况数据特征值提取的方法和装置

Publications (1)

Publication Number Publication Date
WO2011079689A1 true WO2011079689A1 (fr) 2011-07-07

Family

ID=42494880

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2010/079512 WO2011079689A1 (fr) 2009-12-29 2010-12-07 Procédé et appareil d'extraction de valeurs caractéristiques de données de conditions de circulation routière

Country Status (2)

Country Link
CN (1) CN101763729B (fr)
WO (1) WO2011079689A1 (fr)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106407206A (zh) * 2015-07-29 2017-02-15 高德软件有限公司 一种道路聚合方法及装置

Families Citing this family (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101763729B (zh) * 2009-12-29 2012-12-12 北京世纪高通科技有限公司 路况数据特征值提取的方法和装置
CN102622370B (zh) * 2011-01-30 2017-02-22 高德软件有限公司 一种获取路线描述的方法及装置、电子地图服务器
CN102509445B (zh) * 2011-10-19 2013-12-04 北京世纪高通科技有限公司 路况预测因素的筛选方法及装置
CN102542801B (zh) * 2011-12-23 2014-10-08 北京易华录信息技术股份有限公司 一种融合多种交通数据的交通状况预测系统及方法
EP2953110B1 (fr) * 2013-02-01 2021-11-10 Hitachi Astemo, Ltd. Dispositif de contrôle de déplacement et système de contrôle de déplacement
CN104217591B (zh) * 2014-08-29 2017-03-15 哈尔滨工业大学深圳研究生院 动态路况检测方法及系统
CN106935052B (zh) * 2015-12-30 2020-12-18 沈阳美行科技有限公司 一种基于行驶数据的变速提示方法及装置
CN106504534B (zh) * 2016-11-28 2019-06-14 北京世纪高通科技有限公司 一种预测道路路况的方法、装置及用户设备
CN110197583B (zh) * 2018-05-03 2021-10-22 腾讯科技（深圳）有限公司 一种道路路况的识别方法、装置及存储介质
CN110246331B (zh) * 2019-05-30 2021-02-26 武汉智云集思技术有限公司 基于指标数据的路况分析方法、设备及可读存储介质

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2002365072A (ja) * 2001-04-13 2002-12-18 Hewlett Packard Co <Hp> マッピング情報をユーザに提供する方法
CN1611918A (zh) * 2003-10-28 2005-05-04 日本先锋公司 交通状况报知设备及其系统、方法、程序和记录介质
EP1783718A1 (fr) * 2005-11-04 2007-05-09 HONDA MOTOR CO., Ltd. Procédé de radiodiffusion de données pour des informations de trafic
CN101488284A (zh) * 2008-01-16 2009-07-22 闵万里 道路交通状况即时预测的智能管理系统
US20090271100A1 (en) * 2005-12-08 2009-10-29 Electronics And Telecommunications Research Institute Apparatus and Method for Providing Traffic Jam Information, and Apparatus for Receiving Traffic Jam Information for Automobile
CN101763729A (zh) * 2009-12-29 2010-06-30 北京世纪高通科技有限公司 路况数据特征值提取的方法和装置

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2002365072A (ja) * 2001-04-13 2002-12-18 Hewlett Packard Co <Hp> マッピング情報をユーザに提供する方法
CN1611918A (zh) * 2003-10-28 2005-05-04 日本先锋公司 交通状况报知设备及其系统、方法、程序和记录介质
EP1783718A1 (fr) * 2005-11-04 2007-05-09 HONDA MOTOR CO., Ltd. Procédé de radiodiffusion de données pour des informations de trafic
US20090271100A1 (en) * 2005-12-08 2009-10-29 Electronics And Telecommunications Research Institute Apparatus and Method for Providing Traffic Jam Information, and Apparatus for Receiving Traffic Jam Information for Automobile
CN101488284A (zh) * 2008-01-16 2009-07-22 闵万里 道路交通状况即时预测的智能管理系统
CN101763729A (zh) * 2009-12-29 2010-06-30 北京世纪高通科技有限公司 路况数据特征值提取的方法和装置

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106407206A (zh) * 2015-07-29 2017-02-15 高德软件有限公司 一种道路聚合方法及装置

Also Published As

Publication number Publication date
CN101763729A (zh) 2010-06-30
CN101763729B (zh) 2012-12-12

Similar Documents

Publication Publication Date Title
WO2011079689A1 (fr) Procédé et appareil d&#39;extraction de valeurs caractéristiques de données de conditions de circulation routière
CN111966729B (zh) 一种车辆轨迹数据处理方法、装置、设备及存储介质
CN109493620B (zh) 一种交通路况分析系统、方法以及装置
WO2011060727A1 (fr) Procédé de prédiction des conditions de trafic routier et dispositif associé
US20210375128A1 (en) System and method for detection and quantification of irregular traffic congestion
US9286801B2 (en) Leveraging information for use in a traffic prediction scenario
Kazagli et al. Estimation of arterial travel time from automatic number plate recognition data
Liu et al. Exploiting heterogeneous human mobility patterns for intelligent bus routing
EP4035435A1 (fr) Système et procédé de traitement de données d&#39;événement de véhicule pour une analyse de trajet
WO2012024976A1 (fr) Procédé de traitement d&#39;informations de circulation et dispositif associé
EP2831545B1 (fr) Procédés de traitement de données numériques géo-référencées et produit
CN111199247B (zh) 一种公交运行仿真方法
Chepuri et al. Travel time reliability analysis on selected bus route of mysore using GPS data
CN106570182B (zh) 公交车辆下车站点识别方法与系统
CN108051011B (zh) 基于出租车经验数据的可靠导航路径设置方法
EP4123618A1 (fr) Système et procédé de traitement de données d&#39;événement de véhicule pour une analyse de trajet
Evans et al. A random forest incident detection algorithm that incorporates contexts
Heckmann et al. Stage Prediction of Traffic Lights Using Machine Learning
CN116431923B (zh) 一种针对城市道路的交通出行预测方法、设备及介质
CN111506777A (zh) 数据处理方法、装置、电子设备和存储介质
CN108986466B (zh) 一种基于WiFi探针的交通OD信息采集系统及处理方法
Ashwini et al. Variability Analysis of Public Transit Bus Travel Time Using GPS Logs: A Case Study
US20150348407A1 (en) Recommendation Engine Based on a Representation of the Local Environment Augmented by Citizen Sensor Reports
CN106887138B (zh) 一种堵车蔓延态势侦测方法与系统
US20220156660A1 (en) System and method for automatic identification of events for transport and event management

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: 10840478

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 10840478

Country of ref document: EP

Kind code of ref document: A1