CN109816982A - Attribute correction method of non-motorized vehicle lanes in virtual road network based on shared bicycle trajectory - Google Patents

Attribute correction method of non-motorized vehicle lanes in virtual road network based on shared bicycle trajectory Download PDF

Info

Publication number
CN109816982A
CN109816982A CN201910135932.XA CN201910135932A CN109816982A CN 109816982 A CN109816982 A CN 109816982A CN 201910135932 A CN201910135932 A CN 201910135932A CN 109816982 A CN109816982 A CN 109816982A
Authority
CN
China
Prior art keywords
shared bicycle
road
vehicle lane
points
point
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN201910135932.XA
Other languages
Chinese (zh)
Other versions
CN109816982B (en
Inventor
王炜
陈坦
李欣然
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Southeast University
Original Assignee
Southeast University
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Southeast University filed Critical Southeast University
Priority to CN201910135932.XA priority Critical patent/CN109816982B/en
Publication of CN109816982A publication Critical patent/CN109816982A/en
Application granted granted Critical
Publication of CN109816982B publication Critical patent/CN109816982B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Landscapes

  • Traffic Control Systems (AREA)

Abstract

The invention discloses a kind of virtual networks non-motorized lane attribute modification method based on shared bicycle track, field processing and multi-source data loading method including sharing bicycle track data, shared bicycle track histogram frequency distribution diagram acquisition methods, the coefficient of skewness and coefficient of kurtosis acquisition methods of shared bicycle track frequency distribution, non-motorized lane isolation method and width method of discrimination.This method can correct the error of non-motorized lane isolation method and width in virtual networks according to shared bicycle track data, to keep city virtual traffic system platform more accurate and intelligence, while reducing the workload of artificial correction, improve efficiency.

Description

Virtual networks non-motorized lane attribute modification method based on shared bicycle track
Technical field
The present invention relates to urban traffic managements and emulation field, more particularly to based on the virtual of shared bicycle track Road network non-motorized lane attribute modification method.
Background technique
City Slow transport system includes pedestrian system and non-motor vehicle system, is important composition portion in Metropolitan Integrative Traffic Point.Manpower Transportation system based on bicycle is built for advocating people-oriented and low-carbon environment-friendly urban transportation at this stage If it is of great significance to.With the further development of " internet+" and the shared economic innovation mode combined, share Bicycle becomes the important model of resident trip in city.On the one hand shared bicycle trip mode promotes resident and green is selected to go out On the other hand row has also added up the original traffic data of magnanimity, has provided more for the planning, construction and control of Traffic Systems Add data abundant.
With the fast development of information technology, planning, construction and the control of traffic system are increasingly by based on big data The city virtual traffic system platform of building.Multi-source data can be concentrated on a system by city virtual traffic system platform In, the comprehensive effective information for extracting Various types of data is simultaneously pocessed, complicated traffic behavior is reproduced on virtual platform, point Analysis person can carry out various operations according to different business, solve a problem promptly.However at present in city virtual traffic system platform Road network construction work in, the width of non-motorized lane generally take open source electronic map recommendation, error is larger, while portion The isolation method information of pavement branch sections is wrong.It now solves the problems, such as this method for mostly using manual identified, passes through traffic study early period It obtains the associated materials of government department or carries out field survey, workload is bigger.
Currently, the smart lock of partial sharing bicycle enterprise has supported " BEI-DOU position system+GPS by constantly optimizing Three mould satellite positioning scheme of (global positioning system)+GLONASS (GLONASS satellite navigation system) ", and apply DGPS (difference Global positioning system) location technology, the positioning accuracy of bicycle is promoted other to sub-meter grade.The isolation method of city non-motorized lane With the microcosmic movement of wide constraint bicyclist, thus the road of non-motorized lane can be judged by the track data of bicycle Road attribute.Magnanimity and accurately share bicycle track data be urban road data are matched by bicycle track point data, into And it corrects urban road non-motorized lane attribute and provides new approach.
Summary of the invention
In order to solve problem above, the present invention provides the virtual networks non-motorized lane attribute based on shared bicycle track and repairs Correction method, this method accurately share bicycle track data using magnanimity, are aided with the analysis of mathematical statistics, and judgement is specified non-maneuver The isolation method and width in lane provide efficient method for the basic road network amendment of city virtual traffic system platform.It should Method can correct the attribute of non-motorized lane in virtual networks according to shared bicycle track data, to make city virtual traffic Platform is more accurate and intelligent, while reducing the workload of artificial correction, improves efficiency, for this purpose, the present invention provides base Virtual networks non-motorized lane attribute modification method in shared bicycle track, comprising the following steps:
(1) field processing and the multi-source data loading method of bicycle track data are shared；
(2) bicycle track histogram frequency distribution diagram acquisition methods are shared；
(3) coefficient of skewness and coefficient of kurtosis acquisition methods of the frequency distribution of bicycle track are shared；
(4) non-motorized lane isolation method and width method of discrimination.
Further improvement of the present invention, original shared bicycle track data includes order id, user id, vehicle in step (1) Id, tracing point number time corresponding with tracing point, longitude, latitude.It sets with reference to the period as T1-T2, it will be with reference in the period Tracing point longitude and latitude data extract, obtain shared bicycle tracing point longitude and latitude data, will treated shared bicycle rail Mark data are loaded into platform；Original urban road network is loaded into city virtual traffic system platform, platform can show city City's road network and section attribute, the specified road to be studied, the upstream or downstream direction of Selecting research road, in platform, Urban road is frequently not a straight straight line, but has certain linear curve, in platform, the start and end of a road Point is the intersection of road in road network, and road passes through different topological points, and the section between topology point is straight line, so that road With specific linear, the topology point quantity that selected road passes through is denoted as m, then road, which can be denoted as, successively passes through from starting point The m+1 section that each topology point is reached home.
Further improvement of the present invention, the middle note section i length of step (2) is L, and the starting point of section i is denoted as coordinate original Point, direction of advance are denoted as Y-axis positive direction, and Y-axis positive direction rotates to the right 90 degree and is denoted as X-axis positive direction, by (0,0), (0, L), (50m, L), the shared bicycle tracing point in the rectangle frame that (50m, 0) is surrounded project in X-axis, obtain point set D, judge point set D Sample size size, when sample size N no more than minimum allow sample size N '=1000 when, may cause to judge due to accidental error Mistake, therefore the method for taking manual identified；When sample size, which is greater than minimum, allows sample size, it can continue to operate, be with 0.1m Siding-to-siding block length, statistics fall in the frequency of the point in each section of X-axis, give up group of the frequency less than 0.01, obtain the shared list of section i Wheel paths histogram frequency distribution diagram.
Further improvement of the present invention, the coefficient of skewness of the middle shared bicycle track probability distribution for calculating section i of step (3) S and coefficient of kurtosis k, the calculation method reference formula of two coefficients:
Wherein:
N: the sample size of shared bicycle track abscissa；
xj: the abscissa of j-th of shared bicycle track；
The mean value of shared bicycle track abscissa.
Further improvement of the present invention, middle setting coefficient of skewness threshold alpha=1 of step (4) and coefficient of kurtosis β=1, remember the degree of bias The absolute value of coefficient s is | s |, when | s | when being less than α, judge that the form of non-motorized lane is to be physically isolated；As | s | not less than α and When k is not less than β, judge the form of non-motorized lane for scribing line isolation；When | s | when not less than α and k is less than β, judge on the section It is non-maneuver when non-motorized lane and car lane are without isolation facility without the isolation facility between car lane and non-motorized lane The width in lane is defaulted as W=0；When the form of non-motorized lane is physical isolation, with average value in histogram frequency distribution diagram Centered on, the point of each statistics accumulation 47.5%, this 95% point corresponding cumulative length in X-axis is denoted as non-to the left and to the right The width of car lane；When the form of non-motorized lane is scribing line isolation, centered on average value in histogram frequency distribution diagram, The point of statistics accumulation 27.5% to the left, the point of statistics accumulation 47.5% to the right, by this 75% point, corresponding accumulation is grown in X-axis Degree is denoted as the width of non-motorized lane, and circulation carries out step (2)-(4) until i > m+1.
The present invention is based on the virtual networks non-motorized lane attribute modification methods of shared bicycle track, with prior art phase Than this method can accurately share bicycle track data based on magnanimity, be aided with the analysis of mathematical statistics, and judgement is specified non-maneuver The isolation method and width in lane provide efficient method for the basic road network amendment of city virtual traffic system platform.Phase Compared with the method for artificial observation, this method can reduce workload, improve efficiency, while efficiently use big data resource.
Detailed description of the invention
Fig. 1 is the overview flow chart of the method for the present invention；
Fig. 2 is the terminus and topological point of a certain example area road network structure and selected road；
Fig. 3 is the shared bicycle track histogram frequency distribution diagram in selected section.
Specific embodiment
Present invention is further described in detail with specific embodiment with reference to the accompanying drawing:
The present invention provides the virtual networks non-motorized lane attribute modification method based on shared bicycle track, this method application Mathematical Statistics Analysis shares bicycle track data, can determine whether the isolation method and width of specified non-motorized lane, is that city is virtual The basic road network amendment of traffic system platform provides efficient method.
This example carries out the Attribute Recognition of non-motorized lane for road shown in Fig. 2, comprising the following steps:
(1) field processing and the multi-source data loading method of bicycle track data are shared
Original shared bicycle track data includes order id, user id, and vehicle id, tracing point number and tracing point are corresponding Time, longitude, latitude, data format is as shown in table 1.It sets with reference to the period as 2018/01/01.00:00:00-2018/12/ 3123:59:59 extracts the tracing point longitude and latitude data in the reference period, and it is as shown in table 2 that data format is obtained after processing. By original urban road network, shared bicycle track data is loaded into city virtual traffic system platform with treated, specified to be intended to grind The road studied carefully is the main road Nanjing Shuan Long, and the down direction of Selecting research road, origin number 18, terminal number is 47.Road The topology point that road is passed through is followed successively by 146,147,148, and the section between topology point is straight line, so that road has specific line Shape.The topology point quantity of process is 3, and road can be denoted as successively from 4 sections that starting point is reached home by each topology point.It should The terminus of the road network structure in region and selected road and topology point are as shown in Figure 2.
The original shared bicycle track data example of table 1
Treated the shared bicycle tracing point data set example of table 2
(2) bicycle track histogram frequency distribution diagram acquisition methods are shared
For section 1, platform shows that 1 length of section is 124.7m, and the starting point in section 1 is denoted as coordinate origin, advances Direction is denoted as Y-axis positive direction, and Y-axis positive direction rotates to the right 90 degree and is denoted as X-axis positive direction.By (0,0), (0,124.7m), (50m, 124.7m), the shared bicycle tracing point in rectangle frame that (50m, 0) is surrounded is projected in X-axis, obtains point set D.Point set D is counted, Obtaining its sample size N size is 1938.This example sample size N is greater than minimum and allows sample size, can continue to operate.Using 0.1m as section Length, statistics fall in the frequency of the point in each section of X-axis, give up group of the frequency less than 0.01, obtain the shared bicycle rail in section 1 Mark histogram frequency distribution diagram, as shown in Figure 3.
(3) coefficient of skewness and coefficient of kurtosis acquisition methods of the frequency distribution of bicycle track are shared
Calculate the coefficient of skewness s and coefficient of kurtosis k of the shared bicycle track probability distribution in section 1.The calculating side of two coefficients Method reference formula:
Wherein:
N: the sample size of shared bicycle track abscissa
xi: the abscissa of i-th of shared bicycle track
The mean value of shared bicycle track abscissa
Into cross calculate section 1 shared bicycle track probability distribution coefficient of skewness s and coefficient of kurtosis k be respectively- 0.024 and -0.5706.
(4) non-motorized lane isolation method and width method of discrimination
Degree of bias s is -0.0221 in this example, and kurtosis k is -0.5706.S < α judges the non-motorized lane and motor vehicle in section 1 Road is physical isolation.When the form of non-motorized lane is physical isolation, centered on average value in histogram frequency distribution diagram, to This 95% point corresponding length in X-axis is denoted as the width of non-motorized lane by left and each statistics accumulation 47.5% to the right point Degree.According to histogram frequency distribution diagram as a result, judging non-motorized lane width for 2.5m.
Circulation carries out step (2)-(4) until i > 4.
The above described is only a preferred embodiment of the present invention, being not the limit for making any other form to the present invention System, and made any modification or equivalent variations according to the technical essence of the invention, still fall within present invention model claimed It encloses.

Claims (5)

1.基于共享单车轨迹的虚拟路网非机动车道属性修正方法，其特征在于，包括以下步骤：1. A method for correcting the attributes of a non-motorized vehicle lane in a virtual road network based on a shared bicycle trajectory, characterized in that it comprises the following steps: (1)共享单车轨迹数据的字段处理和多源数据加载方法；(1) Field processing and multi-source data loading method of shared bicycle trajectory data; (2)共享单车轨迹频率分布直方图获取方法；(2) The method for obtaining the histogram of the frequency distribution of shared bicycle trajectories; (3)共享单车轨迹频率分布的偏度系数和峰度系数获取方法；(3) The method for obtaining the skewness coefficient and kurtosis coefficient of the frequency distribution of shared bicycle trajectories; (4)非机动车道隔离方式和宽度判别方法。(4) Non-motor vehicle lane isolation method and width discrimination method. 2.根据权利要求1所述的基于共享单车轨迹的虚拟路网非机动车道属性修正方法，其特征在于：步骤(1)中原始共享单车轨迹数据包含订单id，用户id，车辆id、轨迹点编号、和轨迹点对应的时间、经度、纬度。设定参考时段为T1-T2，将参考时段内的轨迹点经纬度数据提取出来，得到共享单车轨迹点经纬度数据，将处理后的共享单车轨迹数据加载到平台中；将原始城市道路网络载入城市虚拟交通系统平台，平台可以显示城市道路网络和路段属性，指定欲研究的道路，选择研究道路的上行或下行方向，在平台中，城市道路往往不是一条笔直的直线，而是具有一定线形的曲线，在平台中，一条道路的起终点是路网中道路的交叉口，道路经过不同的拓扑点，拓扑点间的路段是直线，从而使得道路具有特定的线形，将选定的道路经过的拓扑点数量记为m，则道路可以记为依次从起点经过各拓扑点到达终点的m+1个路段。2. The method for correcting non-motor vehicle lane attributes of virtual road network based on shared bicycle track according to claim 1, characterized in that: in step (1), original shared bicycle track data comprises order id, user id, vehicle id, track point Number, time, longitude, and latitude corresponding to the track point. Set the reference period as T1-T2, extract the latitude and longitude data of the trajectory points in the reference period, obtain the longitude and latitude data of the shared bicycle trajectory points, and load the processed shared bicycle trajectory data into the platform; load the original urban road network into the city Virtual traffic system platform, the platform can display the urban road network and road segment attributes, specify the road to be studied, and select the upward or downward direction of the research road. In the platform, the urban road is often not a straight line, but a certain linear curve. , In the platform, the starting and ending point of a road is the intersection of the road in the road network, the road passes through different topological points, and the road segments between the topological points are straight lines, so that the road has a specific line shape, and the selected road passes through the topology. The number of points is denoted as m, then the road can be denoted as m+1 road segments from the starting point through each topological point to the end point in sequence. 3.根据权利要求1所述的基于共享单车轨迹的虚拟路网非机动车道属性修正方法，其特征在于：步骤(2)中记路段i长度为L，将路段i的起始点记为坐标原点，前进方向记为Y轴正方向，Y轴正方向向右旋转90度记为X轴正方向，将(0，0)，(0，L)，(50m，L)，(50m，0)围成的矩形框内的共享单车轨迹点向X轴上投影，得到点集D，判断点集D的样本量大小，当样本量N不大于最小容许样本量N’＝1000时，可能由于偶然误差造成判断错误，故采取人工识别的方法；当样本量大于最小容许样本量时，可以继续操作，以0.1m为区间长度，统计落在X轴各区间内的点的频率，舍弃频率小于0.01的组，得到路段i的共享单车轨迹频率分布直方图。3. the virtual road network non-motor vehicle lane attribute correction method based on shared bicycle track according to claim 1, it is characterized in that: in step (2), mark the length of section i as L, and mark the starting point of section i as the origin of coordinates , the forward direction is recorded as the positive direction of the Y axis, the positive direction of the Y axis is rotated 90 degrees to the right as the positive direction of the X axis, and (0, 0), (0, L), (50m, L), (50m, 0) The shared bicycle track points in the enclosed rectangular frame are projected on the X-axis to obtain the point set D, and the sample size of the point set D is judged. When the sample size N is not greater than the minimum allowable sample size N'=1000, it may be due to accidental Errors cause errors in judgment, so the method of manual identification is adopted; when the sample size is larger than the minimum allowable sample size, the operation can be continued. With 0.1m as the interval length, the frequency of points falling in each interval of the X-axis is counted, and the frequency of rejection is less than 0.01 The frequency distribution histogram of shared bicycle trajectories of road segment i is obtained. 4.根据权利要求1所述的基于共享单车轨迹的虚拟路网非机动车道属性修正方法，其特征在于：步骤(3)中计算路段i的共享单车轨迹概率分布的偏度系数s和峰度系数k，两系数的计算方法参考公式：4. The method for correcting non-motorized vehicle lane attributes of virtual road network based on shared bicycle trajectory according to claim 1, characterized in that: in step (3), the skewness coefficient s and kurtosis of the shared bicycle trajectory probability distribution of road segment i are calculated The coefficient k, the calculation method of the two coefficients refers to the formula: 其中：in: n：共享单车轨迹横坐标的样本容量；n: The sample capacity of the abscissa of the shared bicycle trajectory; xj：第j个共享单车轨迹的横坐标；x j : the abscissa of the jth shared bicycle track; 共享单车轨迹横坐标的均值。 The mean value of the abscissa of the shared bicycle trajectory. 5.根据权利要求1所述的基于共享单车轨迹的虚拟路网非机动车道属性修正方法，其特征在于：步骤(4)中设定偏度系数阈值α＝1和峰度系数β＝1，记偏度系数s的绝对值为|s|，当|s|小于α时，判断非机动车道的形态为物理隔离；当|s|不小于α且k不小于β时，判断非机动车道的形态为划线隔离；当|s|不小于α且k小于β时，判断该路段上无机动车道与非机动车道间的隔离设施，当非机动车道与机动车道无隔离设施时，非机动车道的宽度默认为W＝0；当非机动车道的形态为物理隔离时，以频率分布直方图中平均值为中心，向左和向右各统计累积47.5％的点，将这95％的点在X轴上对应的累积长度记为非机动车道的宽度；当非机动车道的形态为划线隔离时，以频率分布直方图中平均值为中心，向左统计累积27.5％的点，向右统计累积47.5％的点，将这75％的点在X轴上对应的累积长度记为非机动车道的宽度，循环进行步骤(2)-(4)直到i>m+1。5. The method for correcting non-motor vehicle lane attributes of virtual road network based on shared bicycle trajectory according to claim 1, characterized in that: in step (4), set skewness coefficient threshold α=1 and kurtosis coefficient β=1, The absolute value of the skewness coefficient s is |s|. When |s| is less than α, the shape of the non-motorized lane is judged to be physical isolation; when |s| is not less than α and k is not less than β, it is judged that the non-motorized lane is not The form is line isolation; when |s| is not less than α and k is less than β, it is judged that there is no isolation facility between the motor vehicle lane and the non-motor vehicle lane on the road section. When there is no isolation facility between the non-motor vehicle lane and the motor vehicle lane, the non-motor vehicle lane The width of the default is W=0; when the shape of the non-motorized lane is physical isolation, take the average value of the frequency distribution histogram as the center, accumulate 47.5% of the points to the left and right, and put these 95% points in the The corresponding cumulative length on the X-axis is recorded as the width of the non-motorized vehicle lane; when the non-motorized vehicle lane is separated by a dashed line, the average value in the frequency distribution histogram is taken as the center, and the accumulated 27.5% points are counted to the left and counted to the right. Accumulate 47.5% of the points, record the accumulated length of these 75% points on the X-axis as the width of the non-motorized vehicle lane, and repeat steps (2)-(4) until i>m+1.
CN201910135932.XA 2019-02-25 2019-02-25 Virtual road network non-motor lane attribute correction method based on shared bicycle track Active CN109816982B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910135932.XA CN109816982B (en) 2019-02-25 2019-02-25 Virtual road network non-motor lane attribute correction method based on shared bicycle track

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910135932.XA CN109816982B (en) 2019-02-25 2019-02-25 Virtual road network non-motor lane attribute correction method based on shared bicycle track

Publications (2)

Publication Number Publication Date
CN109816982A true CN109816982A (en) 2019-05-28
CN109816982B CN109816982B (en) 2021-05-11

Family

ID=66607317

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910135932.XA Active CN109816982B (en) 2019-02-25 2019-02-25 Virtual road network non-motor lane attribute correction method based on shared bicycle track

Country Status (1)

Country Link
CN (1) CN109816982B (en)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110473402A (en) * 2019-08-20 2019-11-19 河北德冠隆电子科技有限公司 A kind of accident detection early warning system based on target abnormal behaviour trajectory analysis
CN111288999A (en) * 2020-02-19 2020-06-16 深圳大学 A mobile terminal-based pedestrian road network attribute detection method, device and equipment
CN111537990A (en) * 2020-04-27 2020-08-14 西安象德信息技术有限公司 Lane calibration method and device and electronic equipment
CN112163166A (en) * 2020-10-27 2021-01-01 腾讯科技（深圳）有限公司 Method and device for detecting road attribute, computer readable medium and electronic equipment

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN203440771U (en) * 2013-08-05 2014-02-19 无锡市政设计研究院有限公司 Moving vehicle induction guard bar
CN104331422A (en) * 2014-10-14 2015-02-04 广州市香港科大霍英东研究院 Road section type presumption method
CN104361649A (en) * 2014-10-14 2015-02-18 江苏科技大学 Automobile data recorder capable of prompting other vehicles and control method thereof
CN104361648A (en) * 2014-10-10 2015-02-18 江苏科技大学 Event data recorder provided with signal lamps for reminding other vehicles and control method of event data recorder
CN104700617A (en) * 2015-04-02 2015-06-10 武汉大学 High-precision lane information extracting method based on low-precision GPS track data
CN105138779A (en) * 2015-08-31 2015-12-09 武汉大学 Vehicle-mounted GPS space-time trajectory big data optimization method and system
CN106289036A (en) * 2016-08-03 2017-01-04 福建工程学院 A kind of road width measuring method analyzed based on floating car data
CN108871363A (en) * 2018-06-15 2018-11-23 杭州后博科技有限公司 It is a kind of to be ridden the non-motorized lane road conditions judgment method and system of data based on history

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN203440771U (en) * 2013-08-05 2014-02-19 无锡市政设计研究院有限公司 Moving vehicle induction guard bar
CN104361648A (en) * 2014-10-10 2015-02-18 江苏科技大学 Event data recorder provided with signal lamps for reminding other vehicles and control method of event data recorder
CN104331422A (en) * 2014-10-14 2015-02-04 广州市香港科大霍英东研究院 Road section type presumption method
CN104361649A (en) * 2014-10-14 2015-02-18 江苏科技大学 Automobile data recorder capable of prompting other vehicles and control method thereof
CN104700617A (en) * 2015-04-02 2015-06-10 武汉大学 High-precision lane information extracting method based on low-precision GPS track data
CN105138779A (en) * 2015-08-31 2015-12-09 武汉大学 Vehicle-mounted GPS space-time trajectory big data optimization method and system
CN106289036A (en) * 2016-08-03 2017-01-04 福建工程学院 A kind of road width measuring method analyzed based on floating car data
CN108871363A (en) * 2018-06-15 2018-11-23 杭州后博科技有限公司 It is a kind of to be ridden the non-motorized lane road conditions judgment method and system of data based on history

Cited By (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110473402A (en) * 2019-08-20 2019-11-19 河北德冠隆电子科技有限公司 A kind of accident detection early warning system based on target abnormal behaviour trajectory analysis
CN110473402B (en) * 2019-08-20 2021-04-27 河北德冠隆电子科技有限公司 Abnormal event detection and early warning system based on target abnormal behavior trajectory analysis
CN111288999A (en) * 2020-02-19 2020-06-16 深圳大学 A mobile terminal-based pedestrian road network attribute detection method, device and equipment
CN111288999B (en) * 2020-02-19 2021-08-31 深圳大学 A mobile terminal-based pedestrian road network attribute detection method, device and equipment
CN111537990A (en) * 2020-04-27 2020-08-14 西安象德信息技术有限公司 Lane calibration method and device and electronic equipment
CN111537990B (en) * 2020-04-27 2022-02-22 西安象德信息技术有限公司 Lane calibration method and device and electronic equipment
CN112163166A (en) * 2020-10-27 2021-01-01 腾讯科技（深圳）有限公司 Method and device for detecting road attribute, computer readable medium and electronic equipment
CN112163166B (en) * 2020-10-27 2022-10-14 腾讯科技（深圳）有限公司 Method and device for detecting road attribute, computer readable medium and electronic equipment

Also Published As

Publication number Publication date
CN109816982B (en) 2021-05-11

Similar Documents

Publication Publication Date Title
CN110599570B (en) Map generation method and system based on crowdsourcing data open scene
CN109816982A (en) Attribute correction method of non-motorized vehicle lanes in virtual road network based on shared bicycle trajectory
CN108802776B (en) Bus GPS (global positioning system) deviation rectifying method based on abnormal point elimination and track compression algorithm
JP5064870B2 (en) Digital road map generation method and map generation system
CN102521973B (en) A kind of mobile phone switches the road matching method of location
CN113989451B (en) High-precision map construction method, device and electronic equipment
CN108763558B (en) A crowdsourced map road quality improvement method based on map matching
CN102968900B (en) Method for processing RFID (Radio Frequency Identification) traffic data
CN112344947B (en) Map matching method, map matching device, electronic equipment and computer readable storage medium
CN101986102B (en) Method for matching electronic map in urban geographic information system
CN106323301A (en) Road information obtaining method and device
CN109993064B (en) Method for extracting connection path between road network nodes in picture
CN104422451A (en) Road recognition method and road recognition apparatus
CN110990661B (en) A Method of Extracting Entrances and Exits of Regions of Interest Based on Road Network Constraints and Density Clustering
CN109101743A (en) A kind of construction method of high-precision road net model
CN116105717A (en) Lane-level high-precision map construction method and system
CN112833891A (en) Road data and lane-level map data fusion method based on satellite film recognition
CN104034337B (en) Map matching method and device for geographic position point of floating vehicle
CN115344655A (en) Method and device for finding change of feature element, and storage medium
CN113506459A (en) Crowdsourcing map acquisition method for underground parking lot
CN116226309A (en) Map data processing method, device, electronic device and storage medium
CN105844031A (en) Mobile phone positioning data based urban traffic corridor identification method
CN108447262A (en) One kind being constructed the technology and method of &#34; digital road &#34; by wheelpath
CN114116927A (en) Roundabout road identification method and device, electronic equipment and storage medium
CN117789066A (en) Unmanned aerial vehicle multi-view image steel rail line automatic extraction method based on deep learning

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant