CN115880909A - Highway congestion identification method based on floating car data - Google Patents
Highway congestion identification method based on floating car data Download PDFInfo
- Publication number
- CN115880909A CN115880909A CN202211612353.8A CN202211612353A CN115880909A CN 115880909 A CN115880909 A CN 115880909A CN 202211612353 A CN202211612353 A CN 202211612353A CN 115880909 A CN115880909 A CN 115880909A
- Authority
- CN
- China
- Prior art keywords
- congestion
- floating car
- car data
- time interval
- highway
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 37
- 238000004458 analytical method Methods 0.000 claims description 16
- 238000005311 autocorrelation function Methods 0.000 claims description 11
- 238000007621 cluster analysis Methods 0.000 claims description 11
- 238000004590 computer program Methods 0.000 claims description 11
- 230000015654 memory Effects 0.000 claims description 5
- 230000002776 aggregation Effects 0.000 claims description 4
- 238000004220 aggregation Methods 0.000 claims description 4
- 238000004422 calculation algorithm Methods 0.000 claims description 4
- 230000008569 process Effects 0.000 abstract description 3
- 230000008859 change Effects 0.000 abstract description 2
- 230000001133 acceleration Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 1
- 230000000739 chaotic effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
Images
Landscapes
- Traffic Control Systems (AREA)
Abstract
The invention discloses a highway congestion identification method, equipment and a computer readable storage medium based on floating car data. According to the method, the speed change in the vehicle forming process can be accurately identified through floating vehicle speed clustering, so that the congestion smooth condition of a high-speed kilometer is judged, the accuracy of vehicle travel time prediction is improved, and efficient travel of citizens is assisted.
Description
Technical Field
The invention relates to the technical field of traffic, in particular to a highway congestion identification method based on floating car data.
Background
With the development of motorization of transportation modes and highways, the service demands of people on the highways are increased more and more. Meanwhile, people pay more and more attention to real-time dynamic traffic information distribution of highways, wherein travel time is one of the most valuable and most concerned contents in the highway traffic information. However, although it is easy to predict the travel time in a smooth traffic state on a road, when congestion occurs on a road in different situations, it becomes complicated and variable to predict the travel time of a vehicle. Therefore, the method is necessary to accurately identify the congestion condition of the expressway, can improve the accuracy of vehicle travel time prediction, and assists citizens to efficiently go out.
Disclosure of Invention
The invention aims to provide a highway congestion identification method and device based on floating car data and a computer readable storage medium, so as to accurately identify the congestion condition of the highway and assist citizens to efficiently travel.
In order to achieve the purpose, the invention adopts the following technical scheme:
the invention discloses a highway congestion identification method based on floating car data, which comprises the following steps of:
s1, floating car data of a certain time interval of a highway and a congestion state of the previous time interval are obtained;
s2, determining phase space reconstruction delay time by utilizing autocorrelation function
；
S3, determining an embedding dimension m of phase space reconstruction by using a false proximity method;
s4, according to the embedding dimension
And said delay time>
Performing phase space reconstruction on the continuous time speed sequence of the floating car in the time interval;
s5, performing cluster analysis on the floating car continuous time speed sequence after the phase space reconstruction;
and S6, accurately identifying the congestion state of the expressway in the previous time period according to the clustering analysis result and the congestion state in the previous time period.
Further, the floating car data includes vehicle position, speed, direction; the floating car data is a continuous data sequence.
Further, the autocorrelation function is:
wherein n is the total quantity of the floating car data in the time period; i is the serial number of the floating car data; t is the time interval.
Further, the autocorrelation function is dropped to
When, the resulting time->
Recording the reconstruction delay time of the phase space->
。
Further, the step S3 specifically includes: calculating the proportion of false nearest points from the minimum value of the embedding dimension; gradually increasing the embedding dimension until the proportion of false nearest points is less than 5% or the false nearest points no longer decrease with the increase of the embedding dimension; the embedding dimension at this time is denoted as the embedding dimension m of the phase space reconstruction.
Further, the cluster analysis algorithm is as follows: DBSCAN.
Further, the step S7 specifically includes:
if the clustering analysis result is a type 1 cluster, when the congestion state of the previous time interval is the smooth state, judging that the congestion state of the expressway at the time interval is the smooth state; otherwise, judging that the congestion state of the expressway in the time period is the end of congestion;
if the clustering analysis result is a 3-type cluster, judging that the congestion state of the expressway at the time interval is the beginning of congestion;
if the clustering analysis result is a 4-type cluster, judging that the congestion state of the expressway at the time interval is congestion aggregation;
and if the clustering analysis result is a 5-class cluster, judging that the congestion state of the expressway at the time interval is congestion dissipation.
The invention relates to a highway jam identification device based on floating car data, which comprises:
a memory for storing a computer program;
a processor for implementing the steps of a method for highway congestion identification based on floating car data according to any one of claims 1 to 7 when said computer program is executed.
A computer-readable storage medium according to the invention, on which a computer program is stored which, when being executed by a processor, carries out the steps of the method for floating car data-based highway congestion identification according to any one of claims 1 to 7.
The method has the advantages that floating car data of the expressway at a certain time interval are reconstructed through the phase space, the speed data of the floating cars are clustered and analyzed, and the congestion smoothness condition of the expressway at the current time interval is determined according to the clustering analysis result and the congestion state at the previous time interval. According to the method, speed change in the vehicle forming process can be accurately identified through floating vehicle speed clustering, so that the congestion smooth condition of a high-speed kilometer is judged, the accuracy of vehicle travel time prediction is improved, and citizens are helped to go out efficiently.
Drawings
FIG. 1 is a flow chart of the method of the present invention.
Fig. 2 to 5 are schematic diagrams of cluster analysis structures according to the embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be described clearly and completely below, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all 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.
As shown in fig. 1, the method for identifying highway congestion based on floating car data according to the present invention includes the following steps:
s1, floating car data of a certain time interval of a highway and a congestion state of the previous time interval are obtained; the floating car data includes vehicle position, speed, direction; it is a continuous data sequence, and the typical calculation window takes 20min.
S2, determining phase space reconstruction delay time by utilizing autocorrelation function
；
The autocorrelation function is:
wherein n is the total sequence length of the floating car data in the time period; i is the serial number of the floating car data; t is the time interval.
Aiming at a floating car with a speed time sequence length larger than 30 in floating car data, carrying out speed phase space reconstruction on all current continuous data of the floating car, and obtaining known floating car speed sequence data
And extracting linear correlation among the speed sequences, and making an image of which the autocorrelation function changes along with time intervals according to the autocorrelation function. When the autocorrelation function falls below +>
When, the resulting time QUOTE->
/>
As reconstruction delay time of phase spaceIs between->
。
S3, determining an embedding dimension m of phase space reconstruction by using a false proximity method;
the embedding dimension is denoted by the letter d, then
In the dimensional phase space, there is
And there are nearest neighbors
. Define its distance
。
Increasing embedding dimension
To/is>
When, is greater or less>
And/or>
Is a distance of
。
Order to
If->
(threshold value->
Can be on>
Value in between), then it is considered £ based>
Is->
False nearest neighbors of (c).
That is, starting from the minimum value of the embedding dimension d, the proportion of false nearest points is calculated; gradually increasing the embedding dimension d until the proportion of false nearest points is less than 5% or the false nearest points no longer decrease with the increase of the embedding dimension d; at this time, the chaotic attractor can be considered to be completely opened, and the embedding dimension d at this time is recorded as the embedding dimension m of the phase space reconstruction.
S4, according to the embedding dimension
And the delay time->
Performing phase space reconstruction on the continuous time speed sequence of the floating car in the time interval;
such as taking phase space reconstruction delay time
3, an embedding dimension m of the phase space reconstruction of 2, and a sequence of successive time speeds->
Phase space reconstruction is performed, and the reconstruction result is as follows.
S5, performing cluster analysis on the floating car continuous time speed sequence after the phase space reconstruction; the clustering analysis algorithm is as follows: DBSCAN.
DBSCAN (sensitivity-Based Spatial Clustering of Applications with Noise) is a relatively representative Density-Based Clustering algorithm. It defines clusters as the largest set of densely connected points, can divide areas with a sufficiently high density into clusters, and can find clusters of arbitrary shape in a spatial database of noise.
And S6, accurately identifying the congestion state of the expressway in the time interval according to the cluster analysis result and the congestion state in the previous time interval.
The method specifically comprises the following steps:
if the clustering analysis result is a cluster of 1 type, when the congestion state of the previous time interval is smooth, judging that the congestion state of the expressway in the time interval is smooth; otherwise, judging that the congestion state of the expressway in the time period is the end of congestion;
if the clustering analysis result is a 3-type cluster, judging that the congestion state of the expressway at the time interval is the beginning of congestion;
if the clustering analysis result is a 4-type cluster, judging that the congestion state of the expressway at the time interval is congestion aggregation;
and if the clustering analysis result is a 5-class cluster, judging that the congestion state of the expressway at the time interval is congestion dissipation.
As shown in FIGS. 2-5, the sample set is the phase space reconstruction result of a single vehicle, and the neighborhood distance threshold is set
Minimum number of clusters>
And clustering the results of the phase space reconstruction of different vehicles, and analyzing as follows:
as shown in fig. 2, the floating car speed data only gathers 1 type of clusters by using a DBSCAN cluster analysis method, and both the speeds of the phase space points are higher, which indicates that the car only has a high speed state in the driving process on the highway, and can judge that the highway section is in a smooth or jammed ending state at the moment; if the traffic state of the previous period is smooth, the high-speed road section is in a smooth state, otherwise, the high-speed road section is in a congestion ending state;
as shown in fig. 3, the speed data of the floating vehicle is clustered into 3 types of clusters by using a DBSCAN cluster analysis method, and the two speeds of the corresponding space points are respectively higher, the two speeds are higher first and lower second, and the two speeds are lower first and higher second, which respectively shows that the vehicle passes through 3 speed states of high speed, deceleration and acceleration, and the high-speed road section can be judged to be in a congestion starting state at the moment;
as shown in fig. 4, the floating car speed data is clustered into 4 types of clusters by using a DBSCAN cluster analysis method, and the clusters correspond to space points respectively, where two speeds are all large, two speeds are large first and then small, two speeds are small, and two speeds are small first and then large, and it indicates that the car passes through 4 speed states of high speed, deceleration, low speed and acceleration, and it can be determined that a high-speed road section is in a congestion aggregation state at the moment;
as shown in fig. 5, floating car data is clustered into 5 types of clusters by using a DBSCAN cluster analysis method, and the two speeds of the floating car data are respectively large, large before small, small before small, medium before medium, and large before small before large corresponding to the space point, which indicates that the floating car is in five speed states of high speed, deceleration, low speed, medium speed and acceleration, and the high-speed road section can be judged to be in a congestion dissipation state at the moment.
The invention provides highway congestion identification equipment based on floating car data, which can generate larger difference due to different configurations or performances and can comprise one or more processors and memories. A memory for storing a computer program; and the processor is used for realizing the steps of the highway congestion identification method based on the floating car data when executing the computer program.
The invention provides a computer readable storage medium, which stores a computer program, wherein the computer program is executed by a processor to realize the steps of the highway congestion identification method based on floating car data
The computer-readable storage medium may be a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and various other readable storage media capable of storing program codes.
Claims (9)
1. A highway congestion identification method based on floating car data is characterized by comprising the following steps: the method comprises the following steps:
s1, floating car data of a certain time interval of a highway and a congestion state of the previous time interval are obtained;
s2, determining phase space reconstruction delay time by utilizing autocorrelation function
；
S3, determining an embedding dimension m of phase space reconstruction by using a false proximity method;
s4, according to the embedding dimension
And the delay time->
Performing phase space reconstruction on the continuous time speed sequence of the floating vehicle in the time interval;
s5, carrying out cluster analysis on the floating car continuous time speed sequence after the phase space reconstruction;
and S6, accurately identifying the congestion state of the expressway in the time interval according to the cluster analysis result and the congestion state in the previous time interval.
2. The floating car data-based highway congestion identification method according to claim 1, wherein: the floating car data comprises vehicle position, speed, direction; the floating car data is a continuous data sequence.
3. The floating car data-based highway congestion identification method according to claim 1, wherein: the autocorrelation function is:
wherein n is the total quantity of the floating car data in the time period; i is the serial number of the floating car data; t is the time interval.
4. The floating car data-based highway congestion identification method according to claim 3, wherein: said autocorrelation function falling to
When, the resulting time->
Reconstruction delay time recorded as phase space>
。
5. The method for identifying highway congestion based on floating car data according to claim 1, characterized by comprising the following steps: s3, the step specifically comprises: calculating the proportion of false nearest points from the minimum value of the embedding dimension; gradually increasing the embedding dimension until the proportion of false nearest points is less than 5% or the false nearest points no longer decrease with the increase of the embedding dimension; the embedding dimension at this time is denoted as the embedding dimension m of the phase space reconstruction.
6. The floating car data-based highway congestion identification method according to claim 1, wherein: the clustering analysis algorithm is as follows: DBSCAN.
7. The method for identifying highway congestion based on floating car data according to claim 1, characterized by comprising the following steps: s7, the step specifically comprises:
if the clustering analysis result is a cluster of 1 type, when the congestion state of the previous time interval is smooth, judging that the congestion state of the expressway in the time interval is smooth; otherwise, judging that the congestion state of the expressway in the time period is the end of congestion;
if the clustering analysis result is a 3-type cluster, judging that the congestion state of the expressway at the time interval is the beginning of congestion;
if the clustering analysis result is a 4-type cluster, judging that the congestion state of the expressway at the time interval is congestion aggregation;
and if the clustering analysis result is a 5-class cluster, judging that the congestion state of the expressway at the time interval is congestion dissipation.
8. A tolling highway congestion identification device based on floating car data is characterized by comprising the following components:
a memory for storing a computer program;
a processor for implementing the steps of the method for floating car data based highway congestion identification according to any one of claims 1 to 7 when executing said computer program.
9. A computer-readable storage medium, characterized in that a computer program is stored on the computer-readable storage medium, which computer program, when being executed by a processor, carries out the steps of the method for floating car data based highway congestion identification according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211612353.8A CN115880909A (en) | 2022-12-15 | 2022-12-15 | Highway congestion identification method based on floating car data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211612353.8A CN115880909A (en) | 2022-12-15 | 2022-12-15 | Highway congestion identification method based on floating car data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115880909A true CN115880909A (en) | 2023-03-31 |
Family
ID=85767626
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211612353.8A Pending CN115880909A (en) | 2022-12-15 | 2022-12-15 | Highway congestion identification method based on floating car data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115880909A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117253364A (en) * | 2023-11-15 | 2023-12-19 | 南京感动科技有限公司 | Traffic jam event extraction and situation fusion method and system |
-
2022
- 2022-12-15 CN CN202211612353.8A patent/CN115880909A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117253364A (en) * | 2023-11-15 | 2023-12-19 | 南京感动科技有限公司 | Traffic jam event extraction and situation fusion method and system |
| CN117253364B (en) * | 2023-11-15 | 2024-01-26 | 南京感动科技有限公司 | Traffic jam event extraction and situation fusion method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9527384B2 (en) | Driving context generation system for generating driving behavior description information | |
| CN112700072B (en) | Traffic condition prediction method, electronic device, and storage medium | |
| WO2021203972A1 (en) | Risk prevention method, apparatus and device based on collision model, and storage medium | |
| CN113401143B (en) | Individualized self-adaptive trajectory prediction method based on driving style and intention | |
| Marczak et al. | Key variables of merging behaviour: empirical comparison between two sites and assessment of gap acceptance theory | |
| Li et al. | Characterizing Heterogeneity in Drivers’ Merging Maneuvers Using Two‐Step Cluster Analysis | |
| CN110738856A (en) | urban traffic jam fine recognition method based on mobile clustering | |
| CN113870564B (en) | Traffic jam classification method and system for closed road section, electronic device and storage medium | |
| CN111126438B (en) | Driving behavior recognition method and system | |
| CN115880909A (en) | Highway congestion identification method based on floating car data | |
| JP6511982B2 (en) | Driving operation discrimination device | |
| US20220343637A1 (en) | Traffic flow machine-learning modeling system and method applied to vehicles | |
| Oh et al. | In-depth understanding of lane changing interactions for in-vehicle driving assistance systems | |
| Xu et al. | Utilizing structural equation modeling and segmentation analysis in real-time crash risk assessment on freeways | |
| CN110766940A (en) | Method for evaluating running condition of road signalized intersection | |
| CN113297795A (en) | Method for constructing running condition of pure electric vehicle | |
| Taylor et al. | Road type classification through data mining | |
| CN111860383B (en) | Group abnormal behavior identification method, device, equipment and storage medium | |
| CN116704750B (en) | Traffic state identification method based on clustering algorithm, electronic equipment and medium | |
| Gomes et al. | A survey on traffic flow prediction and classification | |
| Van Hinsbergh et al. | Vehicle point of interest detection using in-car data | |
| CN110097074B (en) | Vehicle track compression method based on sequence similarity | |
| CN115257803A (en) | Functional scene extraction method suitable for high-speed automatic driving | |
| CN113393011B (en) | Method, device, computer equipment and medium for predicting speed limit information | |
| Zhang et al. | Modeling lane-change risk in urban expressway off-ramp area based on naturalistic driving data |
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 |