CN110176139A - A kind of congestion in road identification method for visualizing based on DBSCAN+ - Google Patents
A kind of congestion in road identification method for visualizing based on DBSCAN+ Download PDFInfo
- Publication number
- CN110176139A CN110176139A CN201910128612.1A CN201910128612A CN110176139A CN 110176139 A CN110176139 A CN 110176139A CN 201910128612 A CN201910128612 A CN 201910128612A CN 110176139 A CN110176139 A CN 110176139A
- Authority
- CN
- China
- Prior art keywords
- data
- cluster
- point
- congestion
- indicate
- 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
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
-
- 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
- G08G1/0108—Measuring and analyzing of parameters relative to traffic conditions based on the source of data
- G08G1/0112—Measuring and analyzing of parameters relative to traffic conditions based on the source of data from the vehicle, e.g. floating car data [FCD]
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Analytical Chemistry (AREA)
- Chemical & Material Sciences (AREA)
- Theoretical Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Probability & Statistics with Applications (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a kind of, and the congestion in road based on DBSCAN+ identifies method for visualizing, uploads data to Floating Car OBD car-mounted terminals a large amount of in city first and is pre-processed and cleaned；Low running speed GPS track point data in unit time period is extracted according to its instantaneous velocity；DBSCAN+ algorithm parameter is set, initial classes cluster block in low running speed region is obtained by parallel clustering to the data point of extraction；By calculating separately surface distance between each data point in class cluster block, farthest two o'clock and matching line segment are found out；Matching line segment is subjected to map match correction according to benefit relationship is opened up between section each in practical road network；Eventually by calculating separately in all kinds of cluster blocks operating range in different vehicle unit interval, and COMPREHENSIVE CALCULATING average travel judges all kinds of cluster block congestion levels, and indicates to be distinguish visualization in different colors.The present invention is adapted to large-scale city taxi OBD terminal GPS track data, convenient for identifying that urban road congestion, effect of visualization are good by taxi operating condition in real time.
Description
Technical field
The present invention relates to traffic big data fields, more particularly to one kind to be based on DBSCAN+ (Density-Based
Spatial Clustering of Applications with Noise Plus, the application added with noise based on density
Space clustering) congestion in road identify method for visualizing.
Background technique
With getting worse for Urban Traffic Jam Based, effective congestion in road identifying system is established, and is accurately identified
Traffic congestion section becomes current research direction in city out.
In existing traffic congestion detection technique, not by the characteristic value of processing mode and selection to traffic data
Together, traffic jam detection method can be divided into following a few classes: (1) being based on Vehicle Speed: directly being visited some with vehicle GPS
It directly uses after the vehicle speed data processing measured, or is calculated by the time of vehicle and mileage.Xu L etc.
Car speed is extracted using floating car data, congestion in road is judged to different stage, it is comprehensive for congestion level and section position
Analysis is closed, and identifies the congestion event in low speed section by time-space relationship.(2) it is based on traffic density: from the GPS data of vehicle
Or its location information is extracted in traffic monitoring video recording, divide after integrating location information according to Density Clustering, and to congestion class cluster is comprehensive
Analysis.Sole-Ribalta etc. considers section and crossing vehicle fleet size, proposes and a kind of surrounds and watches congestion model based on complex network
To detect traffic congestion hot spot region.(3) be based on time of vehicle operation: the vehicle delay time at stop is more than passing through under no jam situation
Required time is defined as traffic congestion, and treated, and travel time data can be used for indicating traffic congestion situation, in conjunction with more
Section, which carries out comprehensive analysis, can reflect the region congestion.Xu Y etc. uses vehicle in the different running times in two kinds of section, i.e.,
Average running time and certain amount vehicle are averaged running time to portray traffic congestion degree in certain time, and detect congestion
Period.(4) be based on vehicle driving trace: when vehicle is when occurring traffic congestion, many drivers can select to gather around around current
Stifled section, therefore when analyzing track of vehicle, especially as the abnormal section of this detour, traffic abnormity section can be excavated
Spatial and temporal distributions.Chen C etc. proposes the off path detection method detection traffic based on isolated point in real time and gathers around in short term
Stifled event.(5) be based on vehicle flow: the real-time change by monitoring the vehicle flow in each section can detecte certain tract section
Congestion.Kuang W etc. is come using the magnitude of traffic flow between different sections of highway using Wavelet transformation, principal component analysis method
The generation of traffic abnormal incident is detected, and these anomalous events are often exactly to cause the emergency event of congestion, thus can will work as
Preceding section is defined as congested link.
These common traffic jam detection methods are the thinking for carrying out extracted valid data to transport data processing, Hen Duoshi
It waits since traffic congestion detects no accurate result as judgment criteria, the research in this field is essentially all to belong to no prison
Educational inspector practises, and data can not be divided into training set and test set comes to experiment show, while the judge mode of result is also very much,
In this way for traffic congestion just ununified definition.
Summary of the invention
Goal of the invention: the present invention provides a kind of congestion in road identification method for visualizing based on DBSCAN+, is adapted to big
Scale city Floating Car OBD terminal GPS track data, convenient for identifying urban road congestion by Floating Car operating condition in real time,
Effect of visualization is good.
Technical solution: a kind of congestion in road identification method for visualizing based on DBSCAN+ of the present invention, including it is following
Step:
(1) data are uploaded to a large amount of Floating Car OBD car-mounted terminals and carries out cleaning pretreatment；
(2) low running speed GPS track point data in unit time period is extracted according to its instantaneous velocity；
(3) data point of extraction is loaded into queue, by the sweep radius, the most tuftlet point that set DBSCAN+ clustering algorithm
Several and piecemeal queue number carries out parallel clustering, label low running speed region class cluster block relevant data points cluster number label；
(4) it to calculation of longitude & latitude surface distance is passed through between each data point in class cluster block each in cluster result respectively, looks for
Farthest two o'clock and matching line segment out；
(5) matching line segment is subjected to map match correction according to benefit relationship is opened up between section each in practical road network information, makes it
Matching meets real road；
(6) by calculating separately in all kinds of cluster blocks operating range in different vehicle unit interval, and COMPREHENSIVE CALCULATING is average
Operating range judges all kinds of cluster block congestion levels, and is subject to visualized distinguishing.
Step (2) the GPS track point data is set by following formula:
N=p ∈ M | Vp< 10kph, tcurrent-Min(tp) < T (min)
Wherein, N indicates to meet all GPS track point sets walked or drive slowly in the unit time, and M indicates all GPS tracing points, p
Indicate the data point for meeting condition, VpIndicate instantaneous velocity, tcurrentIndicate current time, tpIndicate the time of track data point p
Stamp, Min (tp) indicating the earliest time stamp for meeting the track data point p of condition, the unit time is T minutes；In GPS data track
The middle GPS data track point sequence N for extracting instantaneous velocity in current T minutes and being less than 10kph (V)；Retain the GPS for meeting above formula
Data track point.
Setting DBSCAN+ algorithm parameter and the method for marking cluster number in step (3) are as follows: set sweep radius Eps as
100m；Minimum is 12 comprising points MinPts；Piecemeal queue number QueueNum is 10000；By all kinds of clusters after parallel clustering
Block successively adds up and sets cluster number, and demarcates the class cluster attribute cluster number of each track data point in class cluster block.
The step (4) is realized by following formula:
Wherein, L indicate t minutes before data point between current data point at a distance from, lat1Indicate the latitude of first data point
Degree, lat2Indicate the latitude of second data point, lng1Indicate the longitude of first tracing point, lng2Indicate second tracing point
Longitude, R indicate earth radius；Wherein least square is used for the line segment approximating method to each data point in same class cluster block
Method:
Wherein, error is prediction and actual path error amount, hθIt (x) is anticipation function, hθ(x(i)) it is predicted value, y is real
Border tracing point, m are sample number, and n is characterized number.
The step (6) the following steps are included:
(63) it to each vehicle driving distance counts respectively in t minutes in all kinds of cluster blocks, and is calculated using K-Means++
Method is to each operating range COMPREHENSIVE CALCULATING average moving distance in class cluster block；
(64) judgment criteria is set with average travel, judges all kinds of cluster block congestion levels, and be subject to visualized distinguishing:
Wherein, a, b, c are self-defining value.
The utility model has the advantages that compared with prior art, beneficial effects of the present invention: 1, compare the prior art, overcomes because adopting
With single, the with a low credibility problem of traffic density analytic approach, speed criterion, running time criterion isotype；2, Ke Yizhi
Effective integrated use urban taxi distribution and travelling characteristic are seen, effectively studies and judges and shows the practical congestion of each road network in city
Situation, and then the running scheduling for passenger's trip and public transportation provides science decision；3, algorithm introduces parallel meter
It calculates, compared to traditional density algorithm, is adapted to that large-scale data, cluster speed are fast, the real-time for congestion in road identification mentions
For ensureing.
Detailed description of the invention
Fig. 1 is the method overview flow chart of the embodiment of the present invention；
Fig. 2 is jogging area's class cluster identification figure in the embodiment of the present invention；
Fig. 3 is jogging area's class cluster starting point identification figure in the embodiment of the present invention；
Fig. 4 is jam road curve initial fitting figure in the embodiment of the present invention.
Specific embodiment
The present invention is described in further detail below in conjunction with the accompanying drawings.
As shown in Figure 1, congestion in road identification and method for visualizing based on DBSCAN+, comprising the following steps:
(1) one is uploaded within the vehicle-mounted OBD of hackney vehicle (On-Board Diagnostics, onboard diagnostic system) terminal 20 seconds
Secondary data, data include: the information such as longitude, latitude, timestamp, identification of the vehicle, passenger carrying status, are uploading urban taxi rail
In mark data set, the stop of cleaning roadside, operation suspension but still the corpse track data uploaded judge that vehicle is in its 5 minutes
It is no to be subjected to displacement.It selects to reject the GPS track point for meeting following formula from queue to be clustered when 5 minutes intrinsic displacement distances are less than 10m
All tracks of associated vehicle:
In formula, L indicate 5 minutes before data point between current data point at a distance from, lat1Indicate the latitude of first data point
Degree, lat2Indicate the latitude of second data point, lng1Indicate the longitude of first tracing point, lng2Indicate second tracing point
Longitude, R indicate earth radius.
(2) low running speed GPS track point data in unit time period is extracted: sets the unit time as 2 minutes；In GPS number
The GPS data track point sequence N for being less than 10kph according to instantaneous velocity in current 2 minutes is extracted in track, selection retain under satisfaction
The GPS data tracing point of formula:
N=p ∈ M | Vp< 10kph, tcurrent-Min(tp) < 2min
In formula, N indicates to meet all GPS track point sets walked or drive slowly in the unit time, and M indicates all GPS tracing points, p
Indicate the data point for meeting condition, VpIndicate instantaneous velocity.
(3) it sets DBSCAN+ algorithm parameter and marks cluster number: setting sweep radius Eps as 100m, minimum includes points
MinPts is 12, and piecemeal queue number QueueNum is 10000.It is with 10000 data by the track data point sequence N of extraction
One group is divided, and every group is traversed, and when the quantity nearby put is more than or equal to MinPts, then nearby point is formed current point with it
One cluster, and starting point is marked as having accessed (visited).Then recurrence handles in the cluster in the same way and owns
It is not labeled as having accessed the point of (visited), to be extended to cluster, finds maximal density connected regions.Cluster is tied
Fruit re-writes in the point sequence N of GPS data track to cluster again, until track point sequence N in data point number be less than etc.
In QueueNum, to carry out last time cluster.All kinds of cluster blocks after cluster are successively added up setting cluster number, and demarcate class cluster block
In each track data point class cluster attribute cluster number.GPS data point is equipped with cluster number attribute, and it is each that the cluster number, which is class cluster number,
Class cluster uniquely identifies, for distinguishing each class cluster.The result meaning of cluster is to find the big region of jogging density, experiment knot
Fruit is as shown in Figure 2.Many experiments show when MinPts is set as 8, will lead to count in result cluster it is more.And work as MinPts
When being set as 16 or higher, it will lead to and count very few in result cluster, therefore set MinPts value as 12.
4, the longitude and latitude data of adjacent two o'clock in list are obtained and are made marks (labeled point will be no longer participate in calculating), it will
Its longitude and latitude is respectively converted into radian, subtracts each other the difference for obtaining corresponding longitude and latitude, then calculate earth's surface between them away from
From.
Because ground spherical surface is a curved surface, calculate two geographical locations apart from when, cannot be with simple European
Distance calculates, and needs to consider actual distance of curved surface, therefore according to the longitude of GPS data point, latitude, determine two data points
The distance between, experiment effect is as shown in Figure 3.Then it by the way that data point is compared two-by-two in same cluster, finds out among them
Simultaneously matching line segment, experiment effect are as shown in Figure 4 for farthest two o'clock.Wherein determine the method for the surface distance between each data point are as follows:
Wherein, L indicate 5 minutes before data point between current data point at a distance from, lat1Indicate the latitude of first data point
Degree, lat2Indicate the latitude of second data point, lng1Indicate the longitude of first tracing point, lng2Indicate second tracing point
Longitude, R indicate earth radius；
Wherein least square method is used for the line segment approximating method to each data point in same class cluster block.
Wherein, error is prediction and actual path error amount, hθIt (x) is anticipation function, hθ(x(i)) it is predicted value, y is real
Border tracing point, m are sample number, and n is characterized number.
5, matching line segment is subjected to map match correction, its matching is made to meet real road: fitting in obtaining step (4)
Line segment information is set 20m as radius and does buffer zone analysis, be fitted with point centered on the GPS positioning point that is fitted on center line
Central point in current buffer is searched on center line to replace the gps data information after finding to the shortest road of vertical range
It is changed to road information, finally each GPS positioning point is matched on correct road.
6, comprehensive operating range in all kinds of cluster blocks is calculated, judges all kinds of cluster block congestion levels, and be subject to area in different colors
Divide visualization: each vehicle driving distance is counted respectively in 2 minutes in all kinds of cluster blocks, then uses K-Means++ algorithm pair
Each operating range COMPREHENSIVE CALCULATING average moving distance in class cluster block distinguishes congestion level and uses following discrimination standard:
Map match rectifies a deviation successful road information to map in uploading step 5.It sets average speed and is less than or equal to 10m/
Min is heavy congestion, is shown using purple line segment form；Average speed is less than or equal to 25m/min but is greater than 10m/min be congestion, adopts
Shown with red line segment form；Average speed is less than or equal to 50m/min but is greater than 25m/min be jogging, is shown using yellow line segment form.
Experiments have shown that a kind of congestion in road based on DBSCAN+ disclosed by the embodiments of the present invention identifies method for visualizing and is
System, is adapted to large-scale city taxi OBD terminal GPS track data, convenient for identifying in real time by taxi operating condition
Urban road congestion situation simultaneously distinguishes congestion level, and effect of visualization is good.
Claims (5)
1. a kind of congestion in road based on DBSCAN+ identifies method for visualizing, which comprises the following steps:
(1) data are uploaded to a large amount of Floating Car OBD car-mounted terminals and carries out cleaning pretreatment；
(2) low running speed GPS track point data in unit time period is extracted according to its instantaneous velocity；
(3) data point of extraction is loaded into queue, by set the sweep radius of DBSCAN+ clustering algorithm, most tuftlet points and
Piecemeal queue number carries out parallel clustering, label low running speed region class cluster block relevant data points cluster number label；
(4) it to calculation of longitude & latitude surface distance is passed through between each data point in class cluster block each in cluster result respectively, finds out most
Remote two o'clock and matching line segment；
(5) matching line segment is subjected to map match correction according to benefit relationship is opened up between section each in practical road network information, makes its matching
Meet real road；
(6) by calculating separately in all kinds of cluster blocks operating range in different vehicle unit interval, and COMPREHENSIVE CALCULATING averagely travels
All kinds of cluster block congestion levels of Distance Judgment, and it is subject to visualized distinguishing.
2. a kind of congestion in road based on DBSCAN+ according to claim 1 identifies method for visualizing, which is characterized in that
Step (2) the GPS track point data is set by following formula:
N=p ∈ M | Vp< 10kph, tcurrent-Min(tp) < T (min)
Wherein, N indicates to meet all GPS track point sets walked or drive slowly in the unit time, and M indicates that all GPS track points, p indicate
Meet the data point of condition, VpIndicate instantaneous velocity, tcurrentIndicate current time, tpIndicate the timestamp of track data point p,
Min(tp) indicating the earliest time stamp for meeting the track data point p of condition, the unit time is T minutes；In GPS data track
Extract the GPS data track point sequence N that instantaneous velocity in T minutes current is less than 10kph (V)；Retain the GPS data for meeting above formula
Tracing point.
3. a kind of congestion in road based on DBSCAN+ according to claim 1 identifies method for visualizing, which is characterized in that
Setting DBSCAN+ algorithm parameter and the method for marking cluster number in step (3) are as follows: set sweep radius Eps as 100m, minimum includes
The MinPts that counts is 12, and piecemeal queue number QueueNum is 10000, and all kinds of cluster blocks after parallel clustering are successively added up and are set
Cluster number, and demarcate the class cluster attribute cluster number of each track data point in class cluster block.
4. a kind of congestion in road based on DBSCAN+ according to claim 1 identifies method for visualizing, which is characterized in that
The step (4) is realized by following formula:
Wherein, L indicate t minutes before data point between current data point at a distance from, lat1Indicate the latitude of first data point,
lat2Indicate the latitude of second data point, lng1Indicate the longitude of first tracing point, lng2Indicate the warp of second tracing point
Degree, R indicate earth radius；Wherein least square method is used for the line segment approximating method to each data point in same class cluster block:
Wherein, error is prediction and actual path error amount, hθIt (x) is anticipation function, hθ(x(i)) it is predicted value, y is practical rail
Mark point, m are sample number, and n is characterized number.
5. a kind of congestion in road based on DBSCAN+ according to claim 1 identifies method for visualizing, which is characterized in that
The step (6) the following steps are included:
(61) to each vehicle driving distance counts respectively in t minutes in all kinds of cluster blocks, and using K-Means++ algorithm to class
Each operating range COMPREHENSIVE CALCULATING average moving distance in cluster block；
(62) judgment criteria is set with average travel, judges all kinds of cluster block congestion levels, and be subject to visualized distinguishing:
Wherein, a, b, c are self-defining value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910128612.1A CN110176139B (en) | 2019-02-21 | 2019-02-21 | DBSCAN + -based road congestion identification visualization method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910128612.1A CN110176139B (en) | 2019-02-21 | 2019-02-21 | DBSCAN + -based road congestion identification visualization method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110176139A true CN110176139A (en) | 2019-08-27 |
| CN110176139B CN110176139B (en) | 2021-01-05 |
Family
ID=67689122
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910128612.1A Active CN110176139B (en) | 2019-02-21 | 2019-02-21 | DBSCAN + -based road congestion identification visualization method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110176139B (en) |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110750573A (en) * | 2019-08-28 | 2020-02-04 | 广东工业大学 | Traffic jam evolution rule identification method based on gridding and space-time clustering |
| CN110827540A (en) * | 2019-11-04 | 2020-02-21 | 黄传明 | Motor vehicle movement mode recognition method and system based on multi-mode data fusion |
| CN111640304A (en) * | 2020-06-04 | 2020-09-08 | 扬州大学 | Automatic quantitative extraction method for traffic jam propagation characteristics of continuous flow traffic facility |
| CN111739283A (en) * | 2019-10-30 | 2020-10-02 | 腾讯科技（深圳）有限公司 | Road condition calculation method, device, equipment and medium based on clustering |
| CN112101433A (en) * | 2020-09-04 | 2020-12-18 | 东南大学 | Automatic lane-dividing vehicle counting method based on YOLO V4 and DeepsORT |
| CN112816959A (en) * | 2021-01-14 | 2021-05-18 | 森思泰克河北科技有限公司 | Clustering method, device, equipment and storage medium for vehicles |
| CN113836358A (en) * | 2021-09-14 | 2021-12-24 | 北京百度网讯科技有限公司 | Data processing method and device, electronic equipment and storage medium |
| CN113933012A (en) * | 2021-10-14 | 2022-01-14 | 西安现代控制技术研究所 | Propeller rotating speed measuring method based on K-means clustering |
| CN114037963A (en) * | 2021-11-26 | 2022-02-11 | 中关村科学城城市大脑股份有限公司 | Road sign state monitoring method and device, storage medium and equipment |
| WO2022032781A1 (en) * | 2020-08-12 | 2022-02-17 | 深圳技术大学 | Traffic flow feature extraction method and system |
| CN114764977A (en) * | 2022-04-06 | 2022-07-19 | 成都亿盟恒信科技有限公司 | Road congestion calculation method and system based on driving data |
| CN114852135A (en) * | 2022-07-08 | 2022-08-05 | 八维通科技有限公司 | Similar rail transit driving prediction method based on big data |
| CN114973732A (en) * | 2022-04-20 | 2022-08-30 | 安徽皖通科技股份有限公司 | Voice guidance system and method based on intelligent road network monitoring |
| CN117037465A (en) * | 2023-05-24 | 2023-11-10 | 东北师范大学 | Traffic jam propagation mode sensing and visual analysis method |
| CN118262571A (en) * | 2024-05-29 | 2024-06-28 | 以声动人(上海)教育科技有限公司 | Auxiliary automatic driving method |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105261217A (en) * | 2015-10-03 | 2016-01-20 | 上海大学 | Method for detecting urban traffic congestion state by using density-based clustering algorithm |
| CN105628033A (en) * | 2016-02-26 | 2016-06-01 | 广西鑫朗通信技术有限公司 | Map matching method based on road connection relationship |
| CN105872959A (en) * | 2016-05-12 | 2016-08-17 | 西安电子科技大学 | Automatic sensing method for urban road condition based on mobile adaptive clustering |
| CN108269401A (en) * | 2018-01-30 | 2018-07-10 | 银江股份有限公司 | A kind of overpass traffic congestion Forecasting Methodology based on data-driven |
| CN108960498A (en) * | 2018-06-27 | 2018-12-07 | 沈阳理工大学 | A kind of traffic congestion prediction technique based on temporal sequence association rule |
| US20190026546A1 (en) * | 2017-05-02 | 2019-01-24 | King Fahd University Of Petroleum And Minerals | Automated sign language recognition method |
-
2019
- 2019-02-21 CN CN201910128612.1A patent/CN110176139B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105261217A (en) * | 2015-10-03 | 2016-01-20 | 上海大学 | Method for detecting urban traffic congestion state by using density-based clustering algorithm |
| CN105628033A (en) * | 2016-02-26 | 2016-06-01 | 广西鑫朗通信技术有限公司 | Map matching method based on road connection relationship |
| CN105872959A (en) * | 2016-05-12 | 2016-08-17 | 西安电子科技大学 | Automatic sensing method for urban road condition based on mobile adaptive clustering |
| US20190026546A1 (en) * | 2017-05-02 | 2019-01-24 | King Fahd University Of Petroleum And Minerals | Automated sign language recognition method |
| CN108269401A (en) * | 2018-01-30 | 2018-07-10 | 银江股份有限公司 | A kind of overpass traffic congestion Forecasting Methodology based on data-driven |
| CN108960498A (en) * | 2018-06-27 | 2018-12-07 | 沈阳理工大学 | A kind of traffic congestion prediction technique based on temporal sequence association rule |
Non-Patent Citations (6)
| Title |
|---|
| CHEN M等: "PCNN:deep convolutional networks", 《IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS》 * |
| 刘瑶杰: "基于实时路况的交通拥堵时空聚类分析 ——以北京市二环以内为例", 《中国优秀硕士学位论文全文数据库》 * |
| 刘畅: "交通拥堵区域的发现与预测技术研究", 《中国优秀硕士学位论文全文数据库（电子期刊）》 * |
| 刘畅等: "基于DBSCAN算法的城市交通拥堵区域发现", 《智能计算机与应用》 * |
| 秦大同等: "基于K-均值聚类算法的行驶工况构建方法", 《吉林大学学报》 * |
| 金都: "基于Spark平台的空间数据挖掘DBSCAN聚类算法并行化研究", 《中国优秀硕士学位论文全文数据库（电子期刊）》 * |
Cited By (25)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110750573A (en) * | 2019-08-28 | 2020-02-04 | 广东工业大学 | Traffic jam evolution rule identification method based on gridding and space-time clustering |
| CN110750573B (en) * | 2019-08-28 | 2023-05-02 | 广东工业大学 | Traffic jam evolution rule identification method based on gridding and space-time clustering |
| CN111739283B (en) * | 2019-10-30 | 2022-05-20 | 腾讯科技（深圳）有限公司 | Road condition calculation method, device, equipment and medium based on clustering |
| CN111739283A (en) * | 2019-10-30 | 2020-10-02 | 腾讯科技（深圳）有限公司 | Road condition calculation method, device, equipment and medium based on clustering |
| CN110827540B (en) * | 2019-11-04 | 2021-03-12 | 黄传明 | Motor vehicle movement mode recognition method and system based on multi-mode data fusion |
| CN110827540A (en) * | 2019-11-04 | 2020-02-21 | 黄传明 | Motor vehicle movement mode recognition method and system based on multi-mode data fusion |
| CN111640304A (en) * | 2020-06-04 | 2020-09-08 | 扬州大学 | Automatic quantitative extraction method for traffic jam propagation characteristics of continuous flow traffic facility |
| CN111640304B (en) * | 2020-06-04 | 2021-01-08 | 扬州大学 | Automatic quantitative extraction method for traffic jam propagation characteristics of continuous flow traffic facility |
| WO2022032781A1 (en) * | 2020-08-12 | 2022-02-17 | 深圳技术大学 | Traffic flow feature extraction method and system |
| CN112101433A (en) * | 2020-09-04 | 2020-12-18 | 东南大学 | Automatic lane-dividing vehicle counting method based on YOLO V4 and DeepsORT |
| CN112101433B (en) * | 2020-09-04 | 2024-04-30 | 东南大学 | Automatic lane-dividing vehicle counting method based on YOLO V4 and DeepSORT |
| CN112816959A (en) * | 2021-01-14 | 2021-05-18 | 森思泰克河北科技有限公司 | Clustering method, device, equipment and storage medium for vehicles |
| CN113836358A (en) * | 2021-09-14 | 2021-12-24 | 北京百度网讯科技有限公司 | Data processing method and device, electronic equipment and storage medium |
| CN113933012B (en) * | 2021-10-14 | 2024-01-30 | 西安现代控制技术研究所 | Propeller rotating speed measuring method based on K-means clustering |
| CN113933012A (en) * | 2021-10-14 | 2022-01-14 | 西安现代控制技术研究所 | Propeller rotating speed measuring method based on K-means clustering |
| CN114037963B (en) * | 2021-11-26 | 2022-08-16 | 中关村科学城城市大脑股份有限公司 | Road sign state monitoring method and device, storage medium and equipment |
| CN114037963A (en) * | 2021-11-26 | 2022-02-11 | 中关村科学城城市大脑股份有限公司 | Road sign state monitoring method and device, storage medium and equipment |
| CN114764977A (en) * | 2022-04-06 | 2022-07-19 | 成都亿盟恒信科技有限公司 | Road congestion calculation method and system based on driving data |
| CN114973732A (en) * | 2022-04-20 | 2022-08-30 | 安徽皖通科技股份有限公司 | Voice guidance system and method based on intelligent road network monitoring |
| CN114973732B (en) * | 2022-04-20 | 2023-09-08 | 安徽皖通科技股份有限公司 | Speech guiding system and method based on intelligent road network monitoring |
| CN114852135A (en) * | 2022-07-08 | 2022-08-05 | 八维通科技有限公司 | Similar rail transit driving prediction method based on big data |
| CN114852135B (en) * | 2022-07-08 | 2022-10-04 | 八维通科技有限公司 | Similar rail transit driving prediction method based on big data |
| CN117037465B (en) * | 2023-05-24 | 2024-07-09 | 东北师范大学 | Traffic jam propagation mode sensing and visual analysis method |
| CN117037465A (en) * | 2023-05-24 | 2023-11-10 | 东北师范大学 | Traffic jam propagation mode sensing and visual analysis method |
| CN118262571A (en) * | 2024-05-29 | 2024-06-28 | 以声动人(上海)教育科技有限公司 | Auxiliary automatic driving method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110176139B (en) | 2021-01-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110176139A (en) | A kind of congestion in road identification method for visualizing based on DBSCAN+ | |
| CN109410586B (en) | Traffic state detection method based on multi-metadata fusion | |
| WO2018122801A1 (en) | Method for detecting traffic anomaly of urban road | |
| CN111091720B (en) | Congestion road section identification method and device based on signaling data and floating car data | |
| CN103839409B (en) | Based on the traffic flow modes method of discrimination of multibreak facial vision sensing cluster analysis | |
| CN109544932A (en) | A kind of city road network flow estimation method based on GPS data from taxi Yu bayonet data fusion | |
| CN107103775B (en) | Road quality detection method based on crowd-sourcing calculation | |
| CN111210612B (en) | Method for extracting bus route track based on bus GPS data and station information | |
| CN110164132B (en) | Method and system for detecting road traffic abnormity | |
| CN108062857B (en) | Prediction technique for cab-getter's trip purpose | |
| CN110807919A (en) | Urban road network traffic operation situation evaluation method based on vehicle passing data | |
| CN111768619A (en) | Express way vehicle OD point determining method based on checkpoint data | |
| CN106355884A (en) | Expressway vehicle guiding system and expressway vehicle guiding method based on vehicle classification | |
| Kianfar et al. | Placement of roadside equipment in connected vehicle environment for travel time estimation | |
| CN107590999A (en) | A kind of traffic state judging method based on bayonet socket data | |
| CN115691120A (en) | Congestion identification method and system based on highway running water data | |
| CN104750963A (en) | Intersection delay time estimation method and device | |
| CN105513362A (en) | Method for evaluating and verifying running state of bus in area adjacent to bus stop | |
| CN111640304A (en) | Automatic quantitative extraction method for traffic jam propagation characteristics of continuous flow traffic facility | |
| CN109489679A (en) | A kind of arrival time calculation method in guidance path | |
| CN108629982A (en) | A kind of section vehicle number estimation method based on the hourage regularity of distribution | |
| CN114091581A (en) | Vehicle operation behavior type identification method based on sparse track | |
| CN110211380B (en) | Multisource traffic data fusion expressway congestion interval detection method | |
| Brunauer et al. | Deriving driver-centric travel information by mining delay patterns from single GPS trajectories | |
| CN107085074B (en) | A method of classification monitoring motor-vehicle tail-gas |
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 | ||
| EE01 | Entry into force of recordation of patent licensing contract | ||
| EE01 | Entry into force of recordation of patent licensing contract |
Application publication date: 20190827 Assignee: HUAIAN TIANZE STAR NETWORK INFORMATION INDUSTRY LTD. Assignor: HUAIYIN INSTITUTE OF TECHNOLOGY Contract record no.: X2021980012224 Denomination of invention: A visualization method of road congestion recognition based on DBSCAN + Granted publication date: 20210105 License type: Common License Record date: 20211111 |