CN110634290B - Bicycle track data-based retrograde behavior identification method - Google Patents

Bicycle track data-based retrograde behavior identification method Download PDF

Info

Publication number
CN110634290B
CN110634290B CN201910865192.5A CN201910865192A CN110634290B CN 110634290 B CN110634290 B CN 110634290B CN 201910865192 A CN201910865192 A CN 201910865192A CN 110634290 B CN110634290 B CN 110634290B
Authority
CN
China
Prior art keywords
road
bicycle
track
reverse
behavior
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
Application number
CN201910865192.5A
Other languages
Chinese (zh)
Other versions
CN110634290A (en
Inventor
马晓磊
栾森
李萌
李欣
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.)
Beihang University
Original Assignee
Beihang 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 Beihang University filed Critical Beihang University
Priority to CN201910865192.5A priority Critical patent/CN110634290B/en
Publication of CN110634290A publication Critical patent/CN110634290A/en
Application granted granted Critical
Publication of CN110634290B publication Critical patent/CN110634290B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

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
    • G08G1/0125—Traffic data processing
    • 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
    • G08G1/056—Detecting movement of traffic to be counted or controlled with provision for distinguishing direction of travel

Abstract

The invention discloses a retrograde motion behavior identification method based on bicycle track data, which comprises the following steps: 1) acquiring and cleaning bicycle running track data, wherein the tracks needing to be cleaned have tracks with lower sampling rate and tracks with abnormal speed; 2) map matching: projecting each track to a corresponding road section to realize map matching; 3) on the one-way road, judging the bicycle in the reverse direction; 4) on a bidirectional road, judging the bicycle in the reverse direction; 5) and counting the frequency of the bicycle retrograde motion events on each road section within a period of time, dividing five grade levels by a frequency pane, and marking the road sections on the OSM map platform by different colors respectively to represent the retrograde motion severity. According to the invention, the converse behavior is judged by map matching and geometric methods without the help of a geographic information system platform for identifying the converse behavior, so that the accuracy of the converse detection is effectively improved.

Description

Bicycle track data-based retrograde behavior identification method
Technical Field
The invention belongs to the technical field of intelligent traffic information processing, and particularly relates to a retrograde motion behavior identification method based on bicycle track data.
Background
The bicycle is a popular, healthy and environment-friendly travel mode, and is particularly beneficial to the problem of the last kilometer. In particular, the advent of shared bicycles has stimulated the demand for riding to a great extent in recent years. However, a sharp increase in the amount of bicycle usage may also present more safety risks. Bicycles have various riding behaviors on common roads, although corresponding laws and regulations do not strictly regulate the riding behaviors, some dangerous riding behaviors such as retrograde motion and running red light are undoubtedly potential threats to traffic safety.
Among the many dangerous riding behaviors, retrograde motion has always been one that occurs with high frequency and is easily overlooked by the rider. The behavior of retrograde motion is specifically divided into two types: reverse driving on a one-way road and left driving on a two-way road. In order to improve riding safety, it is necessary to evaluate when and where retrograde motion is occurring. However, since the bicycles are not controlled by the traffic control department, the dangerous riding records and data exposure are lacked, and the states of riding behaviors in the road network cannot be evaluated.
The vast amount of available shared bicycle trajectory data is benefited so that we can analyze and evaluate the state of retrograde behavior in the road network from it. In recent years, research on reverse behavior recognition is mostly carried out by means of geographic information system platforms (such as ArcGIS). The basic idea of the method is to establish a buffer area with a certain width for a road, and compare the riding direction and the road direction of the track falling into the buffer area so as to judge whether the track is in the wrong direction. Although the method can evaluate the reverse running behavior on the road network on a large scale, the method ignores the random position offset of a potential positioning system, and the problem seriously influences the precision of the reverse running detection.
Therefore, how to provide a method for identifying retrograde motion behavior based on bicycle track data is an urgent problem to be solved by those skilled in the art.
Disclosure of Invention
In view of the above, the invention provides a retrograde motion behavior identification method based on bicycle track data, which is used for judging a retrograde motion behavior through a map matching and geometric method without identifying the retrograde motion behavior by means of a geographic information system platform, so that the precision of retrograde motion detection is effectively improved.
In order to achieve the purpose, the invention adopts the following technical scheme:
a retrograde behavior identification method based on bicycle track data comprises the following steps:
1) acquiring and cleaning bicycle running track data, wherein the tracks needing to be cleaned have tracks with lower sampling rate and tracks with abnormal speed;
2) map matching: projecting each track to a corresponding road section to realize map matching;
3) on the one-way road, judging the bicycle in the reverse direction;
4) on a bidirectional road, judging the bicycle in the reverse direction;
5) and counting the frequency of the bicycle retrograde motion events on each road section within a period of time, dividing five grade levels by a frequency pane, and marking the road sections on the OSM map platform by different colors respectively to represent the retrograde motion severity.
Preferably, the bicycle trajectory data is derived from a shared bicycle.
Preferably, the trace with the lower sampling rate is: when the GPS system is in failure or the mobile communication network is influenced by high-rise building factors, partial track data is lost.
Preferably, the trajectory of the velocity anomaly is: the running speed of the track is lower than 5km/h or higher than 20 km/h.
Preferably, each track is projected onto a corresponding road segment, and the method for implementing map matching includes the following steps:
(1) road network data is prepared, wherein the road network data is composed of road sections and nodes, and each road section comprises four elements: { road identification, road level, road direction, road azimuth }, and each node contains three elements: { road number, longitude, latitude };
(2) establishing indexes for the tracks according to the time sequence so as to improve the map matching efficiency;
(3) each track point is projected on a corresponding road segment and is accompanied by four elements: { road identification, road direction, projection deviation, projection driving distance };
(4) deleting the invalid matching result, wherein the invalid matching result is as follows: part of the track can appear in an area which is not covered by the road network, and when the part of the track is projected to an adjacent road section, the projection deviation can exceed a threshold value; also, part of the trajectory detours near the road, resulting in irregular variations in the projected travel distance.
Preferably, the threshold range of the projection deviation is 10-20 m.
Preferably, on a one-way road, the bicycle is judged in a retrograde motion manner intuitively through the difference between the riding direction and the road azimuth, and the formula is as follows:
Figure BDA0002201058160000031
wherein the content of the first and second substances,
Figure BDA0002201058160000032
showing the riding direction of the track points; ω represents the road azimuth; [ d1,d2]Is composed of
Figure BDA0002201058160000033
Confidence interval of total sample; 180 is
Figure BDA0002201058160000034
The expected value of (d); n is the number of tracing points, sigmadIs composed of
Figure BDA0002201058160000035
Allowable float value of the sample.
Preferably, σdIs composed of
Figure BDA0002201058160000036
The allowable floating value of the sample ranges from 30 to 45.
Preferably, on a bidirectional road, let PsAnd PeFor the nodes at both ends of the road, the vector a is equal to PsPe＝(ax,ay) Indicating a road bearing; let vector bi＝PsPi＝(bx,by) Representing points of track PiThe riding direction of (2); the retrograde motion is represented as a locus point PiWhen driving on the left side of the road, the following formula needs to be satisfied:
a×bi＝axby-aybx＞0 (2)
wherein, axAnd ayIs a track point PsAnd PeCalculating the longitude and latitude of the user to obtain a parameter of a two-dimensional vector; same bxAnd byIs a track point PsAnd PiCalculating the longitude and latitude of the user to obtain a parameter of a two-dimensional vector;
if the above formula is established, a single track point is on the left side of the road direction, and when more than half of points in one track fall on the left side of the road, the track is considered to be in a reverse direction.
Preferably, in step 5), the frequency of the bicycle reverse driving events on each road section in the week is counted in units of hours, five grade levels are divided by a proper frequency window, and the road sections are marked by five colors of green, blue, orange, yellow and red on the OSM map platform respectively to represent the reverse driving severity, so that the reverse driving state of the road network level can be observed.
The invention has the beneficial effects that:
firstly, carrying out data cleaning work on massive shared bicycle tracks; secondly, carrying out map matching on the riding track; and then, judging whether the behavior is the retrograde motion behavior by using the geometric knowledge, and finally realizing the state evaluation of the road network level by counting the retrograde motion behavior, thereby having higher precision and reliability. The method does not need to identify the reverse behavior by means of a geographic information system platform, judges the reverse behavior by means of map matching and a geometric method, evaluates the reverse behavior state of the road network layer by means of reverse behavior detection, and has strong innovative significance.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
FIG. 1 is a flow chart of the method of the present invention.
FIG. 2 is a flow chart of a retrograde detection method of the present invention.
FIG. 3 is a diagram illustrating a map matching result according to an embodiment of the present invention.
Fig. 4 is a schematic diagram illustrating a track retrograde determination result based on map matching in an embodiment of the present invention.
Fig. 5 is a spatial distribution diagram of a retrograde motion behavior state at a road network level according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1-2, the present invention provides a retrograde behavior identification method based on bicycle track data, comprising the following steps:
1) bicycle driving track data obtains and washs, and bicycle track data derives from sharing bicycle, and sharing bicycle track data derives from the cell-phone APP that corresponds, and the error data that mainly has two kinds of type need wash: a track with a low sampling rate and a track with an abnormal speed;
trace with lower sampling rate: when the GPS system is in failure or the mobile communication network is influenced by factors such as high-rise buildings, partial track data are lost.
Track of speed anomaly: the travel speed of the trajectory is lower than 5km/h or higher than 20km/h, which may be due to the fact that the rider does not close the lock after the ride is over, and the trajectory of his walking or transfer bus is still mistaken for the ride trajectory.
2) Map matching: projecting each track to a corresponding road section to realize map matching, wherein the method comprises the following steps:
(1) road network data is prepared, wherein the road network data is composed of road sections and nodes, and each road section comprises four elements: { road identification, road level, road direction, road azimuth }, and each node contains three elements: { road number, longitude, latitude };
(2) establishing indexes for the tracks according to the time sequence so as to improve the map matching efficiency;
(3) each track point is projected on a corresponding road segment and is accompanied by four elements: { road identification, road direction, projection deviation, projection driving distance }; wherein, the road direction is a category variable, 1 represents a one-way road, and 0 represents a two-way road; the projection deviation refers to the distance from the track point to the projection point; the projected driving distance is a travel distance of the projection point relative to the departure point.
(4) Deleting invalid matching results: part of the track can appear in an area (such as a residential district) which is not covered by the road network, and when the part of the track is projected onto an adjacent road section, the projection deviation is larger and exceeds a threshold value; also, part of the trajectory detours near the road, resulting in irregular variations in the projected travel distance. Both types of tracks are invalid and need to be deleted.
In order to further optimize the technical scheme, the threshold range of the projection deviation is 10-20 m.
In order to further optimize the above technical solution, road network data is obtained from an Open Street Map (OSM) platform.
2) And detecting the reverse behavior of the one-way path. On a one-way road, as shown in fig. 2a, the bicycle running backwards can be intuitively judged by the difference between the riding direction and the road azimuth, and the formula is as follows:
Figure BDA0002201058160000061
wherein the content of the first and second substances,
Figure BDA0002201058160000062
showing the riding direction of the track points; ω represents the road azimuth; d1And d2Confidence interval for total sample
Figure BDA0002201058160000063
Boundary of [ d ]1,d2]Is composed of
Figure BDA0002201058160000064
Confidence interval of total sample; 180 is
Figure BDA0002201058160000065
The expected value of (d); n is the number of tracing points, sigmadIs composed of
Figure BDA0002201058160000066
Allowable float value of the sample.
To further optimize the above solution, σdIs composed of
Figure BDA0002201058160000067
The allowable floating value of the sample ranges from 30 to 45.
4) And detecting the reverse behavior of the bidirectional road. On a bidirectional road, a retrograde motion of the bicycle appears to be a left-hand travel. Let P as shown in FIG. 2bsAnd PeFor the nodes at both ends of the road, the vector a is equal to PsPe＝(ax,ay) Indicating a road bearing; let vector bi＝PsPi＝(bx,by) Representing points of track PiThe riding direction of (2); the retrograde motion is represented as a locus point PiWhen driving on the left side of the road, the following formula needs to be satisfied:
a×bi＝axby-aybx＞0 (2)
wherein, axAnd ayIs a track point PsAnd PeCalculating the longitude and latitude of the user to obtain a parameter of a two-dimensional vector; same bxAnd byIs a track point PsAnd PiCalculating the longitude and latitude of the user to obtain a parameter of a two-dimensional vector;
if the above formula is established, the single track point is on the left side of the road direction, and in order to improve the identification accuracy of the retrograde motion judgment, when more than half of points in one track fall on the left side of the road, the track is considered as the retrograde motion.
5) And counting the frequency of the bicycle reverse driving events on each road section in one week by taking hours as a unit, dividing a proper frequency pane into five grade levels, and marking the road sections on an OSM map platform by using five colors of green, blue, orange, yellow and red to represent the reverse driving severity so as to observe the reverse driving state of the road network level.
Firstly, carrying out data cleaning work on massive shared bicycle tracks; secondly, carrying out map matching on the riding track; and then, judging whether the behavior is the retrograde motion behavior by using the geometric knowledge, and finally realizing the state evaluation of the road network level by counting the retrograde motion behavior, thereby having higher precision and reliability. The method does not need to identify the reverse behavior by means of a geographic information system platform, judges the reverse behavior by means of map matching and a geometric method, evaluates the reverse behavior state of the road network layer by means of reverse behavior detection, and has strong innovative significance.
Example (b):
a retrograde behavior identification method based on bicycle track data specifically comprises the following steps:
1) taking a Wu-Hou district in metropolis as an example, firstly, the track data and the corresponding road network data are obtained, and the data preprocessing work is completed.
2) Carrying out map matching on the single-vehicle track and the road network data, and adding four elements for each track point: road number, road direction, projection deviation, and projection driving distance. Fig. 3a shows a one-way road to which the track points P1, P2 and P3 are matched. The matching result is as follows: p1{101,1,0.7m,0 }; p2{101,1,0.5m,1.6m }; p3{101,1,0.6m,4.0m }. Fig. 3b shows a bidirectional road to which the track points P4, P5 and P6 are each adapted. The matching result is as follows: p4{203, 0, 0.9m, 0 }; p5{203, 0, 0.7m, 2.3m }; p6{203, 0, 0.7m, 4.1m }. In each track, the projection deviation of the three track points is smaller than the threshold value 20m, and the projection driving distance is gradually increased, which shows that the track is an effective driving track.
3) And judging the track points on the road 101 by using the formula (1). As shown in fig. 4a, when the road azimuth ω is 186, the difference between the driving direction of the track point and the road azimuth is shown as
Figure BDA0002201058160000081
Sample the sample to have an allowable float value of σdThe average value of the three is 22.67 and does not belong to [180-]Then the track appears as normal driving.
4) And (3) judging the track points on the road 203 by using a formula (2). As shown in fig. 4b, the vector a for road direction is PsPe(iii) when represented by (0.003737,0.000058), also can obtain b4＝(0.000418,0.000086)，b5＝(0.000768,-0.000050)，b6= (0.001128, 0.000109). Due to a x b4＞0，a×b5＜0，a×b6If the position is more than 0, P4, P5 and P6 are respectively positioned at the left side, the right side and the left side of the road, and the track is judged to be in the wrong direction.
5) Selecting all tracks of the early peak time period (8:00-9:00) in the range of one week, repeating the steps 1) to 4), and then counting the frequency of the reverse driving events on each road. Marking the road sections with the reverse running frequency lower than 50 as green; the road segment at (50,100) is marked blue; the road segment at (100,150) is marked orange; the road section at (150,200) is marked yellow; road segments above 200 are marked red; the spatial distribution of the final retrograde state is shown in fig. 5.
The embodiments in the present description are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. The device disclosed by the embodiment corresponds to the method disclosed by the embodiment, so that the description is simple, and the relevant points can be referred to the method part for description.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims (8)

1. A retrograde behavior identification method based on bicycle track data is characterized by comprising the following steps:
1) acquiring and cleaning bicycle running track data, wherein the tracks needing to be cleaned have tracks with lower sampling rate and tracks with abnormal speed;
2) map matching: projecting each track to a corresponding road section to realize map matching;
3) on the one-way road, judging the bicycle in the reverse direction;
on a one-way road, the bicycle is judged in a retrograde motion mode intuitively through the difference between the riding direction and the road azimuth angle, and the formula is as follows:
Figure FDA0002419656540000011
wherein the content of the first and second substances,
Figure FDA0002419656540000012
showing the riding direction of the track points; ω represents the road azimuth; [ d1,d2]Is composed of
Figure FDA0002419656540000013
Confidence interval of total sample; 180 is
Figure FDA0002419656540000014
The expected value of (d); n is the number of tracing points, sigmadIs composed of
Figure FDA0002419656540000015
An allowable float value of the sample;
4) on a bidirectional road, judging the bicycle in the reverse direction;
on a bidirectional road, let PsAnd PeFor the nodes at both ends of the road, the vector a is equal to PsPe＝(ax,ay) Indicating a road bearing; let vector bi＝PsPi＝(bx,by) Representing points of track PiThe riding direction of (2); the retrograde motion is represented as a locus point PiWhen driving on the left side of the road, the following formula needs to be satisfied:
a×bi＝axby-aybx＞0 (2)
wherein, axAnd ayFor nodes P at both ends of the roadsAnd PeCalculating the longitude and latitude of the user to obtain a parameter of a two-dimensional vector; same bxAnd byIs a track point PsAnd PiCalculating the longitude and latitude of the user to obtain a parameter of a two-dimensional vector;
if the formula is established, the single track point is on the left side of the road direction, and when more than half of points in one track fall on the left side of the road, the track is considered to be in a retrograde motion;
5) and counting the frequency of the bicycle retrograde motion events on each road section within a period of time, dividing five grade levels by a frequency pane, and marking the road sections on the OSM map platform by different colors respectively to represent the retrograde motion severity.
2. The method for reverse behavior recognition based on bicycle trajectory data according to claim 1, wherein the bicycle trajectory data is derived from a shared bicycle.
3. The method for reverse behavior recognition based on bicycle trajectory data as claimed in claim 1, wherein the trajectory with lower sampling rate is: when the GPS system is in failure or the mobile communication network is influenced by high-rise building factors, partial track data is lost.
4. The method for reverse behavior recognition based on bicycle trajectory data according to claim 1 or 3, wherein the trajectory of the speed abnormality is: the running speed of the track is lower than 5km/h or higher than 20 km/h.
5. The method for identifying retrograde behavior based on bicycle track data of claim 1, wherein each track is projected onto a corresponding road segment, and the method for realizing map matching comprises the following steps:
(1) road network data is prepared, wherein the road network data is composed of road sections and nodes, and each road section comprises four elements: { road identification, road level, road direction, road azimuth }, and each node contains three elements: { road number, longitude, latitude };
(2) establishing indexes for the tracks according to the time sequence so as to improve the map matching efficiency;
(3) each track point is projected on a corresponding road segment and is accompanied by four elements: { road identification, road direction, projection deviation, projection driving distance };
(4) deleting the invalid matching result, wherein the invalid matching result is as follows: part of the track can appear in an area which is not covered by the road network, and when the part of the track is projected to an adjacent road section, the projection deviation can exceed a threshold value; also, part of the trajectory detours near the road, resulting in irregular variations in the projected travel distance.
6. The method for identifying retrograde behavior based on bicycle trajectory data of claim 5, wherein the threshold range of projection deviation is 10-20 m.
7. The method for reverse behavior recognition based on bicycle trajectory data as claimed in claim 1, wherein σ isdIs composed of
Figure FDA0002419656540000031
The allowable floating value of the sample ranges from 30 to 45.
8. The method as claimed in claim 1, wherein in the step 5), the frequency of bicycle reverse driving events on each road segment in a week is counted in hours, and five grade levels are divided by an appropriate frequency window, and road segments are marked with five colors of green, blue, orange, yellow and red on the OSM map platform to indicate the severity of reverse driving, so as to observe the reverse driving state at the road network level.
CN201910865192.5A 2019-09-12 2019-09-12 Bicycle track data-based retrograde behavior identification method Active CN110634290B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910865192.5A CN110634290B (en) 2019-09-12 2019-09-12 Bicycle track data-based retrograde behavior identification method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910865192.5A CN110634290B (en) 2019-09-12 2019-09-12 Bicycle track data-based retrograde behavior identification method

Publications (2)

Publication Number Publication Date
CN110634290A CN110634290A (en) 2019-12-31
CN110634290B true CN110634290B (en) 2020-06-09

Family

ID=68971146

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910865192.5A Active CN110634290B (en) 2019-09-12 2019-09-12 Bicycle track data-based retrograde behavior identification method

Country Status (1)

Country Link
CN (1) CN110634290B (en)

Families Citing this family (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111611901B (en) * 2020-05-15 2023-10-03 北京百度网讯科技有限公司 Vehicle reverse running detection method, device, equipment and storage medium
CN112017447B (en) * 2020-08-20 2022-09-23 北京赛博星通科技有限公司 Method and system for judging vehicle converse violation based on GPS position information
CN113602264B (en) * 2021-08-17 2023-02-28 北京市商汤科技开发有限公司 Vehicle driving behavior detection method, device, equipment and storage medium
CN113865600B (en) * 2021-09-28 2023-01-06 北京三快在线科技有限公司 High-precision map construction method and device
CN114509062B (en) * 2021-12-31 2023-10-13 武汉中海庭数据技术有限公司 Retrograde trajectory filtering method and device based on large trajectory data

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103605362B (en) * 2013-09-11 2016-03-02 天津工业大学 Based on motor pattern study and the method for detecting abnormality of track of vehicle multiple features
CN104318766B (en) * 2014-10-22 2016-06-08 北京建筑大学 A kind of road network method of public transport GPS track data
CN107657813B (en) * 2017-09-21 2020-09-04 中交第二公路勘察设计研究院有限公司 Highway traffic law enforcement discrimination method based on driving track
CN109633727A (en) * 2018-12-29 2019-04-16 西南交通大学 A kind of retrograde Activity recognition method of the shared bicycle based on track drift angle
CN110136442A (en) * 2019-05-20 2019-08-16 东南大学 Pedestrian based on shared bicycle GPS track data occupies road Activity recognition method

Also Published As

Publication number Publication date
CN110634290A (en) 2019-12-31

Similar Documents

Publication Publication Date Title
CN110634290B (en) Bicycle track data-based retrograde behavior identification method
CN110176139B (en) DBSCAN + -based road congestion identification visualization method
CN112017447B (en) Method and system for judging vehicle converse violation based on GPS position information
CN101739824B (en) Data fusion technology-based traffic condition estimation method
CN104573116B (en) The traffic abnormity recognition methods excavated based on GPS data from taxi
CN110276973B (en) Automatic intersection traffic rule identification method
CN109686091B (en) Traffic flow filling algorithm based on multi-source data fusion
CN105976062A (en) Signal lamp duration data mining method, and travel service implementation method and device
CN113031033B (en) Track deviation correcting device and method based on GPS data
CN108170793A (en) Dwell point analysis method and its system based on vehicle semanteme track data
CN109359169B (en) Shared bicycle reverse behavior real-time identification method based on probability map model
CN109147323A (en) A kind of vehicle GPS data processing method for highway passenger and freight transportation indicator-specific statistics
CN107240264A (en) A kind of non-effective driving trace recognition methods of vehicle and urban road facility planing method
CN113870570A (en) ETC-based road network operation state method, system and storage medium
Saremi et al. Combining map-based inference and crowd-sensing for detecting traffic regulators
CN110969861B (en) Vehicle identification method, device, equipment and computer storage medium
CN102436742A (en) Method and device for evaluating traffic information service level of floating vehicle system
CN112511971A (en) Travel mode identification method based on mobile phone signaling data
CN108520044B (en) Least square method path prediction algorithm based on axiality thought
CN114663992B (en) Multisource data fusion expressway portal positioning method
CN115510953A (en) Method and equipment for identifying flow pattern of shared bicycle in connection area of subway station
CN113870559B (en) Traffic flow calculation method based on big data Internet of vehicles
CN115631082A (en) Multi-scene path restoration method based on expressway network topological structure
CN116229708A (en) Perception test method of road side perception system on traffic target based on V2I
CN115662124A (en) GPS track data road section flow matching method based on network coding

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