CN109712401B - Composite road network bottleneck point identification method based on floating car track data - Google Patents
Composite road network bottleneck point identification method based on floating car track data Download PDFInfo
- Publication number
- CN109712401B CN109712401B CN201910074831.6A CN201910074831A CN109712401B CN 109712401 B CN109712401 B CN 109712401B CN 201910074831 A CN201910074831 A CN 201910074831A CN 109712401 B CN109712401 B CN 109712401B
- Authority
- CN
- China
- Prior art keywords
- bottleneck
- track
- point
- executing
- points
- 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.)
- Active
Links
Images
Landscapes
- Traffic Control Systems (AREA)
Abstract
The invention relates to a composite road network bottleneck point identification method based on floating car track data, which comprises the following steps: step S1: carrying out data cleaning on the track data of the floating car; step S2: fusing track data and geographic information data of the cleaned floating car track data; step S3: carrying out information mining to obtain a bottleneck point; step S4: dividing the bottleneck point into a mobile bottleneck or a fixed bottleneck according to the position change of the bottleneck point, and dividing the bottleneck point into a frequent bottleneck or a sporadic bottleneck according to the time change of the bottleneck point; step S5: and outputting the cause of the bottleneck point. Compared with the prior art, the track data of the invention does not need to be additionally provided with a traffic detection sensor, and the acquisition cost is low.
Description
Technical Field
The invention relates to the field of traffic state analysis, in particular to a composite road network bottleneck point identification method based on floating car track data.
Background
A bottleneck point in a traffic network is a point in a road segment where there is a significant drop in vehicle throughput. The formation of bottlenecks will directly lead to the formation of traffic congestion and the spread of queued vehicles. The timely detection and dissipation of bottleneck points is one of the primary tasks of road traffic managers. Regarding the bottleneck, the position of the bottleneck, the formed queuing length and the duration of the bottleneck, the occurrence frequency and the occurrence rule are the most concerned contents for traffic managers.
The bottleneck is usually composed of two part parameters, one is the bottleneck starting point, especially when downstream cross-sectional traffic throughput is significantly increased and traffic exhibits free flow characteristics. And queuing caused by the bottleneck refers to a queue formed by vehicles with slow running speed and appearing from the bottleneck starting point to the upstream direction.
The bottleneck can be divided into a fixed bottleneck and a mobile bottleneck according to whether the starting point of the bottleneck moves in the duration time period. The bottleneck can be divided into a common bottleneck and a sporadic bottleneck according to the space-time regularity of the bottleneck. A common bottleneck point refers to a class of bottlenecks that occur repeatedly at the same or similar locations over different time periods (e.g., different days). The sporadic bottlenecks exhibit poor regularity.
There are a lot of methods and studies on bottleneck detection, and the most common method is to detect a section with a significantly reduced speed. But the source of the detection data on which it is based is essentially cross-sectional fixed detector data, such as a toroid. It is common practice to lay loop coils at intervals over a plurality of adjacent road segments and detect speed information. However, this method cannot be extended to the road network level for analysis, and the accuracy of this method is limited by the detector density. With the advent of trajectory data, more methods for performing bottleneck judgment based on such data have also emerged. The method has the advantages of low acquisition cost, no need of installing entity detection equipment on the road and wide coverage range. However, the problems of low track permeability, large and inconsistent sampling intervals, inconsistent GPS positioning accuracy and the like of the floating car bring certain difficulty to the direct application of data. And the existing bottleneck point feature calculation identification and description method based on the track data is not enough.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provide a composite road network bottleneck point identification method based on floating car track data.
The purpose of the invention can be realized by the following technical scheme:
a composite road network bottleneck point identification method based on floating car track data comprises the following steps:
step S1: carrying out data cleaning on the track data of the floating car;
step S2: fusing track data and geographic information data of the cleaned floating car track data;
step S3: carrying out information mining to obtain a bottleneck point;
step S4: dividing the bottleneck point into a mobile bottleneck or a fixed bottleneck according to the position change of the bottleneck point, and dividing the bottleneck point into a frequent bottleneck or a sporadic bottleneck according to the time change of the bottleneck point;
step S5: and outputting the cause of the bottleneck point.
The step S1 specifically includes:
step S11: judging whether the vehicle ID and the timestamp of the current track point in the floating vehicle track data are missing or abnormal, if so, executing step S12, otherwise, executing step S13;
step S12: discarding the current track point, reading the next track point and judging whether the track data is finished, if not, executing the step S11;
step S13: judging whether the instantaneous speed of the current track point is missing or abnormal, if so, executing the step S14, otherwise, executing the step S15;
step S14: attempting to use the instantaneous speed smooth restoration of the adjacent track points, and judging whether the instantaneous speed smooth restoration is successful, if so, executing the step S15, otherwise, executing the step S12;
step S15: judging whether the longitude and latitude of the current track point is missing or abnormal, if so, executing the step S16, otherwise, executing the step S17;
step S16: attempting to use the longitude and latitude of the adjacent track points for smooth restoration, and judging whether the restoration is successful, if so, executing the step S17, otherwise, executing the step S12;
step S17: and reading the next track point and judging whether the track data is finished, if not, executing the step S11.
The process of determining whether the step S14 is successful specifically includes: and judging whether the difference between the instantaneous speeds of the adjacent track points is smaller than a threshold speed.
The process of determining whether the step S16 is successful specifically includes:
calculating the distance between two track points based on the longitude and latitude of the adjacent track points;
and calculating to obtain a first speed according to the distance and the time difference between the two track points, and judging whether the difference value between the first speed and the instantaneous speed is smaller than a set proportion, if so, judging to be successful, otherwise, judging to be failed.
The step S2 specifically includes:
step S21: obtaining all track points in a target intersection group by defining a rectangular area;
step S22: assigning a track point intersection number, an intard number, a roadid number and a trip number, tripid;
step S23: giving a track point steering number moveid according to whether the track passes through the intersection or not and the advancing direction when the track passes through the intersection;
step S24: for a road section between two intersections, numbering the intersection according to the orthogonal intersection of the intersection track points to which the vehicle drives;
step S25: the distance of the vehicle from the stop line is acquired.
The step S22 specifically includes:
step S221: converting the road time format into seconds;
step S222: for roads between intersections, dividing the middle into two intersections in half, and assigning intersection numbers, namely, intersection, to each track point;
step S223: defining longitude and latitude areas for different road sections, and correspondingly assigning road number roadid values;
step S224: and giving a trip number trimid according to the trip sequence corresponding to each track point.
In step S25, for the track point covered by each trim of each vehicle, the method specifically includes:
if only 1 roadid value is contained, directly calculating the distance to the intersection;
if 3 roadid values are included, only one intersection is passed through, and the distance is directly calculated;
if the route contains more than 3 roadid values, representing that the route passes through a plurality of intersections, sequentially screening track points corresponding to a pair of intersection numbers, and respectively calculating the distance between the track points and a stop line.
The step S5 includes:
if the traffic is a moving bottleneck, outputting vehicles (possibly big trucks or slow-moving cars) with traffic retardation;
if the bottleneck is fixed, the traffic capacity of the existing traffic facilities outputting the bottleneck point of the bottleneck point cannot meet the current traffic demand.
Compared with the prior art, the invention has the following beneficial effects:
1) and the acquisition of the track data does not need to additionally install a traffic detection sensor, so that the acquisition cost is low.
2) And classifying the bottle neck points by combining the diverse topological structures of the composite road network and the traffic flow conditions. The established bottleneck characteristic judging and classifying method is relatively easier to execute.
Drawings
FIG. 1 is a schematic flow chart of the main steps of the method of the present invention;
FIG. 2 is a schematic view of spatiotemporal trajectories of trajectory data;
fig. 3 is a schematic diagram of a trajectory data fusion process.
Detailed Description
The invention is described in detail below with reference to the figures and specific embodiments. The present embodiment is implemented on the premise of the technical solution of the present invention, and a detailed implementation manner and a specific operation process are given, but the scope of the present invention is not limited to the following embodiments.
The method aims to overcome the defects of the existing bottleneck point identification analysis method, and a composite road network bottleneck point identification algorithm is constructed based on increasingly abundant traffic track big data, so that the accuracy of traffic state detection is improved, and the application range of bottleneck point identification is expanded. The method is beneficial to promoting the construction and the upgrade of the urban traffic control system, and accurately identifies the key problem of urban traffic jam, so as to achieve the aim of more pertinently relieving the urban traffic jam.
The method for identifying the bottleneck point of the composite road network is provided, and the parameter characteristics and the law of the bottleneck point are quantitatively evaluated from the time domain space angle based on the track data of the floating car, so that objective and effective basis is provided for the evaluation and optimization of network traffic supersaturation control.
A composite road network bottleneck point identification method based on floating car track data is disclosed, as shown in FIG. 1, and comprises the following steps:
step S1: the data cleaning is performed on the track data of the floating car, as shown in fig. 2, specifically including:
step S11: judging whether the vehicle ID and the timestamp of the current track point in the floating vehicle track data are missing or abnormal, if so, executing step S12, otherwise, executing step S13;
step S12: discarding the current track point, reading the next track point and judging whether the track data is finished, if not, executing the step S11;
step S13: judging whether the instantaneous speed of the current track point is missing or abnormal, if so, executing the step S14, otherwise, executing the step S15;
step S14: attempting to use the instantaneous speed smooth restoration of the adjacent track points, and judging whether the instantaneous speed smooth restoration is successful, if so, executing the step S15, otherwise, executing the step S12;
specifically, the process of determining whether the process is successful may specifically be: and judging whether the difference between the instantaneous speeds of the adjacent track points is smaller than a threshold speed.
Step S15: judging whether the longitude and latitude of the current track point is missing or abnormal, if so, executing the step S16, otherwise, executing the step S17;
step S16: attempting to use the longitude and latitude of the adjacent track points for smooth restoration, and judging whether the restoration is successful, if so, executing the step S17, otherwise, executing the step S12;
specifically, the process of determining whether the process is successful may include:
calculating the distance between two track points based on the longitude and latitude of the adjacent track points; and then calculating to obtain a first speed according to the distance and the time difference between the two track points, and judging whether the difference value between the first speed and the instantaneous speed is smaller than a set proportion, if so, determining that the speed is successful, otherwise, determining that the speed is failed.
Step S17: and reading the next track point and judging whether the track data is finished, if not, executing the step S11.
Step S2: the method for fusing the track data and the geographic information data of the cleaned floating car track data specifically comprises the following steps:
step S21: screening a target area: a large number of irrelevant track points are arranged in the folder, and all track points in a target intersection group are obtained by defining a rectangular area;
step S22: endowing track point intersection number inteid, road number roadid, trip number tripid, specifically including:
step S221: converting the road time format into seconds, for example, 17 o' clock 35 minutes 35 seconds into seconds;
step S222: for roads between intersections, dividing the middle into two intersections in half, and assigning intersection numbers, namely, intersection, to each track point;
step S223: dividing longitude and latitude areas for different road sections, correspondingly assigning road serial number roadid values, specifically, dividing longitude and latitude areas for different road sections, correspondingly assigning roadid values (cross port areas can be assigned at will), and deleting the roadid which is an empty data line, namely a track point which is not on the road section;
step S224: the trip number trip is assigned according to the trip sequence corresponding to each track point, specifically, for a vehicle, it may trip for many times in one day and not appear continuously in time, so different trips are divided. If the time interval between the upper track point and the lower track point is greater than 15 seconds (the sampling frequency of the track point with the type of 11 is 15 seconds/time, and the other is 1 second/time), the vehicle is judged to start another new trip, and the trip is numbered from 1, so that the setting of the subsequent steering parameters is laid.
Step S23: giving a track point steering number moveid according to whether the track passes through the intersection or not and the traveling direction when the track passes through the intersection, specifically, the following steps are carried out:
a) for a vehicle track passing through an intersection, setting: turning left to 1, straight to 2, and turning right to 3;
b) the vehicle trajectory that does not pass through the intersection is set to 4.
Step S24: for a road section between two intersections, the orthogonal intersection number inteid of the intersection track point to which the vehicle drives is corrected according to the intersection track point, namely, the road section between the two intersections needs to be corrected: assigning the intersection to be the number of the intersection when the vehicle drives to the intersection;
step S25: obtaining the distance between the vehicle and a stop line, wherein for track points covered by each trim of each vehicle, the method specifically comprises the following steps:
if only 1 roadid value is contained, directly calculating the distance to the intersection;
if 3 roadid values are included, only one intersection is passed through, and the distance is directly calculated;
if the route contains more than 3 roadid values, representing that the route passes through a plurality of intersections, sequentially screening track points corresponding to a pair of intersection numbers, and respectively calculating the distance between the track points and a stop line.
Next, a space-time diagram is drawn as shown in fig. 3, the distance between the virtual stop line and the real stop line is checked, and the existing distance data is corrected.
Step S3: carrying out information mining to obtain a bottleneck point;
step S4: dividing the bottleneck point into a mobile bottleneck or a fixed bottleneck according to the position change of the bottleneck point, and dividing the bottleneck point into a frequent bottleneck or a sporadic bottleneck according to the time change of the bottleneck point;
the bottleneck point analysis specifically comprises: analyzing the evolution rule and the influence range of the bottleneck point.
(1) Evolution law of bottleneck point
And dividing the road sections into a plurality of independent spaces at certain intervals, and performing state matching based on the corrected track data on the assumption that the traffic conditions of all the unit road sections are the same. And when the vehicle speed at the upstream is detected to be obviously lower than that of the section at the downstream, the bottleneck point is determined. And recording the change rules of the bottleneck points at different moments, and performing feature identification and evolution situation prediction by using a machine learning algorithm.
(2) Bottleneck point impact range
And observing the upstream traffic state of the identified bottleneck point based on the track data. Generally, state division is carried out according to a range of 1km and 5km (namely, the position of the starting point of the jam at the upstream of the bottleneck is searched), and the state division range is flexibly adjusted according to the range of the city. Since the positioning accuracy of the track does not reach the lane level, it needs to be determined by the direction angle attribute of the track.
The bottleneck types include:
1) a common bottleneck: repeatedly identifying that bottlenecks exist in a certain road section at similar moments or the moving trend of bottleneck points and the influence range of the bottleneck points are consistent on multiple days, and classifying the bottleneck points as frequent bottlenecks;
2) sporadic bottlenecks: the detected bottleneck point and the influence range thereof are not matched with the spatial rule and the time rule in the historical data;
3) moving and fixing the bottle neck: for a certain bottleneck, if the bottleneck point has not moved in the process of forming and dissipating, the bottleneck point is a fixed bottleneck, otherwise, the bottleneck point is a moving bottleneck.
Step S5: outputting bottleneck point causes comprising:
if the traffic is a moving bottleneck, outputting vehicles (possibly big trucks or slow-moving cars) with traffic retardation;
if the bottleneck is fixed, the traffic capacity of the existing traffic facilities outputting the bottleneck point of the bottleneck point cannot meet the current traffic demand.
Claims (1)
1. A composite road network bottleneck point identification method based on floating car track data is characterized by comprising the following steps:
step S1: the data cleaning is carried out on the track data of the floating car,
step S2: fusing track data and geographic information data of the cleaned floating car track data,
step S3: the information is mined to obtain a bottleneck point,
step S4: classifying the bottleneck points into mobile bottlenecks or fixed bottlenecks according to position changes of the bottleneck points, classifying the bottleneck points into frequent bottlenecks or sporadic bottlenecks according to time changes of the bottleneck points,
step S5: outputting a bottleneck point cause;
the step S1 specifically includes:
step S11: judging whether the vehicle ID and the timestamp of the current track point in the floating vehicle track data are missing or abnormal, if so, executing the step S12, otherwise, executing the step S13,
step S12: discarding the current trace point, reading the next trace point and determining whether the trace data is finished, if not, executing step S11,
step S13: judging whether the instantaneous speed of the current track point is missing or abnormal, if so, executing step S14, otherwise, executing step S15,
step S14: and (4) trying to use the instantaneous speed smooth restoration of the adjacent track points, and judging whether the instantaneous speed smooth restoration is successful, if so, executing the step S15, otherwise, executing the step S12,
step S15: judging whether the longitude and latitude of the current track point is missing or abnormal, if so, executing the step S16, otherwise, executing the step S17,
step S16: and (4) attempting to use the longitude and latitude of the adjacent track points for smooth restoration, and judging whether the restoration is successful, if so, executing the step S17, otherwise, executing the step S12,
step S17: reading the next track point and judging whether the track data is finished, if not, executing the step S11;
the process of determining whether the step S14 is successful specifically includes: judging whether the difference between the instantaneous speeds of the adjacent track points is smaller than a threshold speed or not;
the process of determining whether the step S16 is successful specifically includes:
calculating the distance between two track points based on the longitude and latitude of the adjacent track points,
calculating to obtain a first speed according to the distance and the time difference between the two track points, and judging whether the difference value between the first speed and the instantaneous speed is smaller than a set proportion, if so, determining that the speed is successful, otherwise, determining that the speed is failed;
the step S2 specifically includes:
step S21: all track points in the target intersection group are obtained by delimiting a rectangular area,
step S22: endowing track points with intersection numbers, road numbers, roadids and trip numbers, namely, three,
step S23: giving a track point turning number moveid according to whether the track passes through the intersection or not and the advancing direction when the track passes through the intersection,
step S24: for a road section between two intersections, according to the orthogonal intersection number inteid of the intersection track-repairing point to which the vehicle is driven,
step S25: obtaining the distance between the vehicle and a stop line;
the step S22 specifically includes:
step S221: the link time format is converted to seconds,
step S222: for roads between intersections, the middle part is divided into two intersections, each track point is endowed with an intersection number, intersection,
step S223: defining longitude and latitude areas for different road sections, correspondingly assigning road number roadid values,
step S224: giving a trip sequence number, which corresponds to each track point, according to the time stamp interval between each continuous track point;
the step S5 includes:
if the traffic is a moving bottleneck, outputting vehicles with traffic block,
if the bottleneck is fixed, the traffic capacity of the existing traffic facilities outputting the bottleneck point cannot meet the current traffic demand.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910074831.6A CN109712401B (en) | 2019-01-25 | 2019-01-25 | Composite road network bottleneck point identification method based on floating car track data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910074831.6A CN109712401B (en) | 2019-01-25 | 2019-01-25 | Composite road network bottleneck point identification method based on floating car track data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109712401A CN109712401A (en) | 2019-05-03 |
| CN109712401B true CN109712401B (en) | 2021-05-11 |
Family
ID=66262967
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910074831.6A Active CN109712401B (en) | 2019-01-25 | 2019-01-25 | Composite road network bottleneck point identification method based on floating car track data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109712401B (en) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110781266B (en) * | 2019-09-16 | 2020-06-09 | 北京航空航天大学 | Urban perception data processing method based on time-space causal relationship |
| CN111739319B (en) * | 2019-10-18 | 2022-06-24 | 腾讯科技（深圳）有限公司 | Information processing method and device |
| WO2021097759A1 (en) * | 2019-11-21 | 2021-05-27 | Beijing Didi Infinity Technology And Development Co., Ltd. | Systems and methods for traffic control based on vehicle trajectory data |
| CN111190891B (en) * | 2019-12-27 | 2023-07-25 | 武汉长江通信产业集团股份有限公司 | Multi-semantic track data segment storage method |
| CN113127466B (en) * | 2021-04-20 | 2023-04-11 | 同济大学 | Vehicle track data preprocessing method and computer storage medium |
| CN114153204B (en) * | 2021-11-09 | 2024-03-08 | 北京三快在线科技有限公司 | Repairing method and repairing device for driving track |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104112361A (en) * | 2014-04-25 | 2014-10-22 | 浙江大学 | Identification method of common bottleneck and accidental bottleneck in road network |
| US9424748B2 (en) * | 2014-09-09 | 2016-08-23 | Here Global B.V. | Reporting traffic conditions on road segments containing a bottleneck |
| CN106960571A (en) * | 2017-03-30 | 2017-07-18 | 百度在线网络技术（北京）有限公司 | Congestion in road bottleneck point determines method, device, server and storage medium |
| CN108877244A (en) * | 2018-06-21 | 2018-11-23 | 东南大学 | A kind of public transit vehicle intersection operation bottleneck method of discrimination based on dynamic data |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170222908A1 (en) * | 2016-01-29 | 2017-08-03 | Hewlett Packard Enterprise Development Lp | Determining candidates for root-cause of bottlenecks in a storage network |
| CN107798871B (en) * | 2017-10-27 | 2020-07-03 | 云南大学 | Traffic flow prediction method and system for highway toll station |
| CN108364127B (en) * | 2018-02-01 | 2021-07-27 | 北京市地铁运营有限公司 | Road network passenger flow cooperative control optimization system |
| CN109147330B (en) * | 2018-09-19 | 2020-12-08 | 青岛海信网络科技股份有限公司 | Congestion identification method and device |
-
2019
- 2019-01-25 CN CN201910074831.6A patent/CN109712401B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104112361A (en) * | 2014-04-25 | 2014-10-22 | 浙江大学 | Identification method of common bottleneck and accidental bottleneck in road network |
| US9424748B2 (en) * | 2014-09-09 | 2016-08-23 | Here Global B.V. | Reporting traffic conditions on road segments containing a bottleneck |
| CN106960571A (en) * | 2017-03-30 | 2017-07-18 | 百度在线网络技术（北京）有限公司 | Congestion in road bottleneck point determines method, device, server and storage medium |
| CN108877244A (en) * | 2018-06-21 | 2018-11-23 | 东南大学 | A kind of public transit vehicle intersection operation bottleneck method of discrimination based on dynamic data |
Non-Patent Citations (2)
| Title |
|---|
| 城市区域路网交通瓶颈识别与预测;邓瑞;《中国优秀硕士学位论文全文数据库（工程科技Ⅱ辑）》;20151015;全文 * |
| 基于浮动车数据的城市常发性交通拥堵时空分布特征研究;何巍楠;《中国优秀硕士学位论文全文数据库（工程科技Ⅱ辑）》;20121015;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109712401A (en) | 2019-05-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109712401B (en) | Composite road network bottleneck point identification method based on floating car track data | |
| CN107784835B (en) | Traffic state mode prediction system based on traffic data analysis and prediction method thereof | |
| Geroliminis et al. | Identification and analysis of queue spillovers in city street networks | |
| US8694242B2 (en) | Traveling information creating device, traveling information creating method and program | |
| CN109993969A (en) | A kind of road conditions determine information acquisition method, device and equipment | |
| CN103903465B (en) | A kind of congestion in road reason real-time release method and system | |
| CN110176139A (en) | A kind of congestion in road identification method for visualizing based on DBSCAN+ | |
| KR100820467B1 (en) | a traffic estimating system and the method considered road type | |
| Kerper et al. | Learning traffic light phase schedules from velocity profiles in the cloud | |
| JP2005259116A (en) | Method and system for calculating traffic information, and method and system for displaying the traffic information | |
| CN108848460B (en) | Man-vehicle association method based on RFID and GPS data | |
| CN105046985A (en) | Traffic control system for whole segments of main street based on big data | |
| JP3485774B2 (en) | Traffic flow simulation system | |
| KR101943198B1 (en) | Method for estimation of link travel time and signal delay | |
| Rehborn et al. | Data-driven traffic engineering: understanding of traffic and applications based on three-phase traffic theory | |
| Gurupackiam et al. | Empirical study of accepted gap and lane change duration within arterial traffic under recurrent and non-recurrent congestion | |
| Fitzpatrick et al. | Spatial and temporal analysis of driver gap acceptance behavior at modern roundabouts | |
| CN108021924A (en) | A kind of discarded target identification method and device | |
| JP4572944B2 (en) | Driving support device, driving support method, and driving support program | |
| CN110827561B (en) | Road condition information forecasting system and method based on vehicles | |
| CN117274303A (en) | Intelligent tracking method and system for vehicle track | |
| JP5381808B2 (en) | Traffic information processing apparatus and method for detecting traffic jam information using the same | |
| JP4957612B2 (en) | Travel pattern information acquisition device, travel pattern information acquisition method, and travel pattern information acquisition program | |
| CN104021675B (en) | A kind of system and method predicted needed for the future time instance of through street between whilst on tour | |
| Kessler et al. | Detection rate of congestion patterns comparing multiple traffic sensor technologies |
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 |