CN114267173B - Multisource data fusion method, device and equipment for space-time characteristics of expressway - Google Patents
Multisource data fusion method, device and equipment for space-time characteristics of expressway Download PDFInfo
- Publication number
- CN114267173B CN114267173B CN202111518366.4A CN202111518366A CN114267173B CN 114267173 B CN114267173 B CN 114267173B CN 202111518366 A CN202111518366 A CN 202111518366A CN 114267173 B CN114267173 B CN 114267173B
- Authority
- CN
- China
- Prior art keywords
- data
- traffic
- highway
- vehicle
- sub
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Traffic Control Systems (AREA)
Abstract
The invention discloses a multisource data fusion method, device and equipment for highway space-time characteristics, which are used for acquiring highway panoramic traffic data; matching the SCATS ground induction coil data and the portal system data with a highway network, and carrying out double-layer road network division on the highway network to obtain traffic area division data and traffic area association data; according to portal system data and high-speed entrance and exit record data, vehicle passing track data based on a space sequence model is obtained; according to meteorological data along the expressway, meteorological change data based on a temporal grid model are obtained; and according to the traffic area association data, fusing the traffic state data and the traffic influence factor data of each sub-traffic area to obtain the space-time characteristics of the expressway. The invention can merge various heterogeneous sensor data, reserve the special time and space characteristics of traffic data, and construct holographic traffic data into trip business service oriented to safety and efficiency.
Description
Technical Field
The invention belongs to the field of data fusion and feature extraction, and particularly relates to a multisource data fusion method, device and equipment for space-time features of a highway.
Background
Road network is a complex system, and the running state of vehicles on the road is limited by various factors such as weather, road conditions, vehicle states and the like, and shows a certain relevance in time-space scale. Time sequence, a group of data of study objects is arranged in sequence along with time, and a certain relation exists between the traffic volume of the previous time period and the traffic volume of the previous time period, so that a group of regular traffic volume data sequences are arranged. Spatial sequential, derived from the inherent structure of highway network systems. The highway road network system is formed by connecting all road sections, and the traffic volume of one road section in the road network has certain correlation with the traffic volume distribution of the upstream road section and the downstream road section. When the road runs smoothly, the whole traffic flow presents a uniform forward running state, and when the road section encounters a bottleneck, a gathered wave opposite to the running direction of the traffic flow is generated, the traffic flow density is increased, and the vehicle speed is reduced; when congestion dissipates, an evanescent wave with the same running direction as the traffic flow is generated, the traffic flow density is reduced, and the vehicle speed is increased.
With the rapid development of information technology and the arrival of large data age, the intelligent informationized road traffic field can generate massive multi-source heterogeneous data which contains abundant time-space sequence information, the massive multi-source heterogeneous data is required to be analyzed and deduced for effective management and utilization, and the time characteristics and the space attributes reflected by various sensor data at the bottom layer are mined through means of data fusion, knowledge pickup and the like, so that the time sequence and the space sequence of the multidimensional traffic data are obtained, and the data analysis requirements of different time-space spans are met.
Data fusion can be divided into: data level fusion, feature level fusion, and decision level fusion. Data level fusion is performed on the most original sensor data, directly collected data is stored, the data is closest to the real world, and the defects are large data volume and difficult storage and transmission. The feature level fusion utilizes the feature information extracted from the sensor data to carry out comprehensive utilization and processing, and has the advantages of feature extraction and data compression, and reduces the data transmission amount, and has the disadvantage that the extracted features do not have a uniform mode. The decision-level fusion is higher-level fusion which is carried out on the basis of basic judgment and decision making on the data of each sensor after analysis processing, has higher fault tolerance, has a series of processes of preprocessing, feature extraction, target identification, decision judgment and the like before fusion, has combined multi-source data to generate basic conclusions, and provides more reliable data for subsequent analysis application.
The Chinese patent document 2019.09.06 discloses a method for detecting the congestion zone of a highway by fusing multi-source traffic data, wherein the patent publication number is CN110211380A and the application number is CN201910479607.5. The patent performs data preprocessing on three traffic data, namely identification data of a highway path identification system, charging station flow data of a networking charging system and GPS track data of two-passenger one-critical-point vehicles, and performs multi-level road network division on a highway road network; matching the first-level road network, the second-level road network and the third-level road network by utilizing the preprocessed three types of traffic source data and the divided road networks; and calculating the traffic state of each basic road section of the multi-level expressway by using three layers of matched data and using a layer congestion interval detection frame. The state evaluation of traffic jam is obtained through fuzzy evaluation, so that the actual running state of a road is difficult to finely describe, in addition, the GPS data of the expressway is easy to be interfered by signals, the charging system data only has two ends of a driving journey, and the like, so that the traffic state perception in the middle of the expressway is difficult.
Chinese patent document 2020.12.25 discloses a 5G-based intelligent traffic big data management method, system, apparatus and medium, the patent publication number CN112133099a, application number CN202011042631.1. Provided are a 5G-based intelligent traffic big data management method, system, equipment and medium. The invention acquires road image information and road video information in real time through a 5G sensor and processes the road image information and the road video information to obtain traffic accident occurrence position information and traffic flow information; and (5) evaluating to obtain the severity level of the traffic accident and the traffic flow unblocked index. The patent mainly aims at fusing image and video data, mainly considers monitoring of unstructured data, but does not consider other structured and semi-structured data sources such as road foundations, vehicles, climates and the like.
In addition, the above patents focus on the data fusion and feature extraction of two different sources, and the patent methods for three or more types of data from different sources are fewer, and the research of multi-source heterogeneous data fusion considering the three or more types is not yet available. Research on considering both traffic data time sequence properties and spatial sequence properties in traffic data fusion has not yet emerged. In the process of promoting intelligent expressway construction, how to more reasonably utilize a data fusion technology, fuse various multi-source heterogeneous sensor data, reserve the special time and space characteristics of traffic data, and construct holographic traffic data into travel business service oriented to safety and efficiency is the primary problem to be solved by the invention.
Disclosure of Invention
Aiming at the problems existing in the prior art, the invention provides a multisource data fusion method, a multisource data fusion device and multisource data fusion equipment for the space-time characteristics of highways, which aim to fuse various multisource heterogeneous sensor data, reserve the special time and space characteristics of traffic data and construct holographic traffic data as trip business service for safety and efficiency.
In order to solve the technical problems, the invention is realized by the following technical scheme:
a multisource data fusion method of highway space-time characteristics comprises the following steps:
acquiring highway panoramic traffic data, wherein the highway panoramic traffic data comprises SCATS ground induction coil data, portal system data, highway entrance and exit record data, highway along-line meteorological data, highway traffic event data and vehicle basic information data;
matching the SCATS ground induction coil data and the portal system data with a highway network, and carrying out double-layer road network division on the highway network to obtain traffic area division data and traffic area association data;
obtaining vehicle passing track data based on a space sequence model according to the portal system data and the high-speed access record data; according to the meteorological data along the expressway, meteorological change data based on a temporal grid model are obtained; according to the basic information data of the vehicle, obtaining the vehicle information data based on the ground state correction model;
Fitting and matching the vehicle passing track data, the weather change data, the vehicle information data and the highway panoramic traffic data to each sub-traffic area in the traffic area division data;
obtaining traffic state data of each sub-traffic area according to the SCATS ground induction coil data, the portal system data and the vehicle traffic track data matched with each sub-traffic area; obtaining traffic influence factor data of each sub-traffic area according to the weather change data, the expressway traffic event data and the vehicle basic information data matched with each sub-traffic area;
and according to the traffic area association data, fusing traffic state data and traffic influence factor data of each sub-traffic area to obtain the expressway space-time characteristics.
Further, after the highway panoramic traffic data is obtained, preprocessing is further included on the obtained highway panoramic traffic data.
Further, the matching the SCATS ground induction coil data and the gantry system data with the highway network, and performing double-level road network division on the highway network to obtain traffic area division data and traffic area association data, specifically includes:
Extracting highway network data, and performing topology inspection on the highway network to form perfect highway network data;
marking the position information of the SCATS ground induction coil and the position information of the portal system on perfect highway network data to obtain a first layer large-scale region division based on the portal system and a second layer small-scale region division based on the SCATS ground induction coil, namely obtaining traffic region division data;
based on the double-level road network division, a double-level road network mapping relation is established according to the total or partial inclusion between the first layer large-scale area and the second layer small-scale area and the high-speed access node influence factors, and traffic area association data is obtained.
Further, according to the portal system data and the high-speed entrance/exit record data, vehicle passing track data based on a space sequence model is obtained, specifically:
acquiring vehicle passing track data based on a space sequence model by adopting a set operation and relation operation method according to the portal system data and the high-speed entrance and exit record data;
according to the meteorological data along the expressway, meteorological change data based on a temporal grid model is obtained, specifically:
Acquiring weather variation data based on a temporal grid model by adopting a set operation and relation operation method according to the weather data along the expressway;
the vehicle information data based on the ground state correction model is obtained according to the vehicle basic information data, and specifically comprises the following steps:
and acquiring the vehicle information data based on the ground state correction model by adopting a set operation and relation operation method according to the vehicle basic information data.
Further, the fitting and matching the vehicle passing track data, the weather change data, the vehicle information data and the highway panoramic traffic data to each sub-traffic area in the traffic area division data specifically includes:
extracting the vehicle passing track data, the meteorological change data, the vehicle information data and the position information and the time-space sequence relation information in the highway panoramic traffic data;
and comparing the position information in the traffic area division data with the time-space sequence relation information respectively with the extracted vehicle passing track data, the meteorological change data, the vehicle information data and the position information in the highway panoramic traffic data, and completing fitting and matching.
Further, the step of obtaining traffic state data of each sub-traffic area according to the SCATS ground induction coil data, the portal system data and the vehicle traffic track data matched to each sub-traffic area specifically includes:
according to the recorded data of the SCATS ground induction coils in the corresponding sub-traffic areas, traffic saturation data and time occupancy data of each SCATS ground induction coil in each period are obtained through calculation;
according to the instantaneous speed in the portal system data and the time corresponding to the instantaneous speed, calculating to obtain the average speed of the vehicle on each road section and the average speed of all vehicles passing through each portal system;
and calculating to obtain the number of the running vehicles corresponding to each period in the sub-traffic area according to the vehicle passing track data.
Further, the obtaining traffic influence factor data of each sub-traffic area according to the weather change data, the highway traffic event data and the vehicle basic information data matched to each sub-traffic area specifically includes:
according to the weather change data in the corresponding sub-traffic areas, obtaining the traffic influence level of weather factors;
obtaining corresponding vehicle information data according to the number of vehicles running in the corresponding sub-traffic area and the basic vehicle information data, and calculating to obtain the traffic influence level of the vehicle factors according to the corresponding vehicle information data;
And obtaining traffic event factor traffic influence level according to the expressway traffic event in the corresponding sub-traffic area.
Further, according to the traffic area association data, the traffic state data and the traffic influence factor data of each sub-traffic area are fused to obtain the temporal-spatial characteristics of the expressway, which specifically comprises:
and combining, summarizing and deducting traffic state data and traffic influence factor data of each associated sub-traffic area to obtain the space-time characteristics of the expressway.
A multi-source data fusion device for highway spatiotemporal features, comprising:
the system comprises a data acquisition module, a data processing module and a data processing module, wherein the data acquisition module is used for acquiring highway panoramic traffic data, and the highway panoramic traffic data comprises SCATS ground induction coil data, portal system data, highway entrance and exit record data, highway along-line meteorological data, highway traffic event data and vehicle basic information data;
the first processing module is used for matching the SCATS ground induction coil data and the portal system data with the highway network, and carrying out double-level road network division on the highway network to obtain traffic area division data and traffic area association data;
The second processing module is used for obtaining vehicle passing track data based on a space sequence model according to the portal system data and the high-speed access record data; according to the meteorological data along the expressway, meteorological change data based on a temporal grid model are obtained; according to the basic information data of the vehicle, obtaining the vehicle information data based on the ground state correction model;
the fitting and matching module is used for fitting and matching the vehicle passing track data, the weather change data, the vehicle information data and the highway panoramic traffic data to each sub-traffic area in the traffic area division data;
the third processing module is used for obtaining traffic state data of each sub-traffic area according to the SCATS ground induction coil data, the portal system data and the vehicle traffic track data matched with each sub-traffic area; obtaining traffic influence factor data of each sub-traffic area according to the weather change data, the expressway traffic event data and the vehicle basic information data matched with each sub-traffic area;
and the fourth processing module is used for fusing traffic state data and traffic influence factor data of each sub-traffic area according to the traffic area associated data to obtain the space-time characteristics of the expressway.
An apparatus comprising a memory, a processor and a computer program stored in the memory and executable on the processor, the processor implementing the steps of a multi-source data fusion method of highway spatiotemporal features when the computer program is executed.
Compared with the prior art, the invention has at least the following beneficial effects:
1. the method can be used for carrying out double-layer road network division on the highway road network, efficiently acquiring traffic area division data and traffic area association data, establishing reliable association relation division basis for various different source data contained in highway panoramic traffic data, and providing support for subsequent space-time characteristic analysis and data fusion.
2. The method can extract the space-time characteristics of the highway panoramic traffic data, process the highway panoramic traffic data by adopting different space-time data models aiming at the characteristics and the expression forms of different types of data from different sources, obtain the time sequence and the space sequence structural information of the highway panoramic traffic data, and realize high-efficiency data analysis while retaining the space-time characteristics of the data.
3. Six types of data contained in the highway panoramic traffic data can be matched in a fitting mode, the data are matched to corresponding sub-traffic areas based on the road network topology structure, multi-source data with different sources, different scales, different precision and detail are effectively matched, and data fusion efficiency is improved.
4. The SCATS ground induction coil data, the portal system data and the vehicle passing track data can be subjected to data fusion, so that the problem that a single data source has a large blank blind area section or uncertain factors are more due to data ambiguity is solved, traffic passing state data of each sub-traffic area is obtained, the data reliability is improved, and the space-time characteristics of the expressway are described from the aspect of efficiency.
5. The traffic area traffic influence factors can be analyzed, meteorological change data, expressway traffic event data and vehicle basic information data are comprehensively considered, and the expressway space-time characteristics are described from the safety perspective.
6. The invention can perform data fusion on multi-source heterogeneous highway panoramic traffic data, and represents the efficiency and the safety condition of the highway in the running time and the space range from multiple angles, thereby providing perfect traffic state data analysis and prediction decision support capability.
In order to make the above objects, features and advantages of the present invention more comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the description of the embodiments will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic diagram of a method for multi-source data fusion of highway spatio-temporal features according to the present invention;
FIG. 2 is a schematic diagram of a highway double-level road network division.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
As shown in fig. 1, as a specific embodiment of the present invention, a method for merging multisource data of highway space-time features specifically includes the following steps:
step 1, acquiring highway panoramic traffic data, preferably, preprocessing the acquired highway panoramic traffic data after acquiring the highway panoramic traffic data; the highway panoramic traffic data comprises SCATS ground induction coil data, portal system data, highway entrance and exit record data, highway along-line meteorological data, highway traffic event data and vehicle basic information data.
Specifically, the SCATS ground-sensing coil data includes: data acquisition time, acquisition period, coil number, coil position and pass record.
Specifically, the gantry system data includes: the portal system basic data and the portal system record data, wherein the portal system basic data comprises equipment numbers, equipment positions, equipment orientations, equipment monitoring lanes and equipment types; the portal system record data comprises record numbers, record types, record time, record directions, traffic directions, license plate numbers, license plate colors, vehicle types, passing lanes, equipment numbers and instantaneous speeds.
Specifically, the high-speed doorway record data includes: license plate number, entry entrance, entry time, exit, exit time, vehicle type, load condition, direction of travel.
Specifically, the highway along-line weather data includes: recording number, recording time stamp, recording date, recording time period, recording place number, recording place coordinates, weather category, air temperature, air speed, time period rainfall, and visibility.
Specifically, the highway traffic event data includes: record number, event type, event start time, expected end time, event location.
Specifically, the vehicle basic information data includes: vehicle number, license plate color, vehicle type, vehicle color, accident recording, and load carrying capacity.
Specifically, preprocessing the obtained highway panoramic traffic data includes:
step 1.1, cleaning the data of the obtained highway panoramic traffic data, removing junk data through data denoising, eliminating abnormal values, and filling missing data through data filling;
and 1.2, converting unified dimension and data format through data standardization, and eliminating data structure difference to obtain high-quality standardized highway panoramic traffic data.
Step 2, matching SCATS ground induction coil data and portal system data with a highway network, and carrying out double-layer road network division on the highway network to obtain traffic area division data and traffic area association data, wherein the steps are as follows:
step 2.1, extracting highway network data, and performing topology inspection on the highway network, wherein the content of the topology inspection comprises the condition that the highway network data cannot be overlapped, suspended points cannot be arranged and intersection cannot be carried out, so that perfect highway network data is finally formed;
step 2.2, marking the position information of the SCATS ground induction coil and the position information of the portal system on perfect highway road network data to obtain a first layer large-scale region division based on the portal system and a second layer small-scale region division based on the SCATS ground induction coil, and obtaining traffic region division data;
And 2.3, based on the double-level road network division, establishing a double-level road network mapping relation according to the total or partial inclusion between the first layer large-scale area and the second layer small-scale area and the high-speed entrance node influence factors to obtain traffic area association data.
Step 3, acquiring vehicle passing track data based on a space sequence model according to portal system data and high-speed entrance and exit record data by adopting a set operation and relation operation method; according to meteorological data along the expressway, meteorological change data based on a temporal grid model are obtained; and obtaining the vehicle information data based on the ground state correction model according to the vehicle basic information data.
Specifically, the set operation includes:
and (Union): for example, if the portal system has the same N groups of attributes for two records R and S of the same vehicle, the operation of combining the two records is a parallel operation, and is recorded as R U S;
difference (Difference): for example, when two pieces of vehicle basic information data R and S before and after a change at a certain time have the same N sets of attributes, the operation of subtracting the old value R from the new value S to obtain the vehicle basic information variation value is a difference operation, which is expressed as: R-S;
cross (Intersection Referential integrity): for example, when a certain road section is simultaneously in the monitoring range of two adjacent automatic weather stations, two groups of expressway along-line weather data R and S recorded by the two automatic weather stations have the same N groups of attributes, the intersection of the two groups of data R and S obtains that the operation of the expressway along-line weather data of the road section is a traffic operation, and the traffic operation is recorded as: R.andS.
Specifically, the relational operation includes:
selection (Selection): means selecting a data item satisfying a given condition from one or more sets of data, for example, selecting data recorded by a certain ground induction coil from all SCATS ground induction coil data;
projection (Projection): extracting a part of attribute columns in one or more groups of data to form new data, for example, extracting visibility data from meteorological data along a group of expressways and performing correlation analysis on the visibility data and the recording time data;
connection (Join): the portal system data and the high-speed access record data are subjected to line connection operation to obtain vehicle passing track data.
Specifically, according to portal system data and high-speed entrance and exit record data, a method of collective operation and relational operation is adopted to obtain vehicle passing track data based on a space sequence model, and the method comprises the following steps:
and reading the high-speed entrance record data one by one, taking license plate numbers, entrance information, exit information, entrance time and exit time as limiting conditions, further searching portal system data to obtain complete tracks of a certain vehicle from entering a high speed to exiting a road in a road section specified by the limiting conditions and a period of time specified by the limiting conditions, and obtaining vehicle passing track data based on a space sequence model.
According to meteorological data along the expressway, adopting a set operation and relation operation method to obtain meteorological change data based on a temporal grid model, wherein the method comprises the following steps of:
the method comprises the steps of reading meteorological data along the expressway one by one, classifying information in a regional meteorological information database according to the limitation conditions by taking recording time and recording places as limitation and distinguishing conditions, integrating corresponding data of each group, and integrating all data records of each monitoring point every day into highly ordered meteorological data along the expressway to obtain meteorological change data based on a temporal grid model.
According to the basic information data of the vehicle, acquiring the information data of the vehicle based on the ground state correction model by adopting a set operation and relation operation method, wherein the method comprises the following steps:
and reading the vehicle basic information data one by one, and then adding a change value corresponding to the vehicle information change data in the vehicle basic information data at a corresponding vehicle basic information data attribute position according to change type modification, so as to complete the vehicle basic information data modification aiming at one piece of vehicle information change data and obtain the vehicle information data based on the ground state correction model.
And 4, fitting and matching the vehicle passing track data, the meteorological change data, the vehicle information data and the highway panoramic traffic data to each sub-traffic area in the traffic area division data, wherein the method comprises the following specific steps of:
Step 4.1, extracting vehicle passing track data, meteorological change data, vehicle information data and position information and time-space sequence relation information in highway panoramic traffic data;
step 4.2, comparing the position information in the traffic area division data with the time-space sequence relation information respectively with the extracted vehicle passing track data, the meteorological change data, the vehicle information data and the position information in the highway panoramic traffic data to finish fitting matching;
step 5, according to the SCATS ground induction coil data, the portal system data and the vehicle passing track data matched with each sub-traffic area, traffic state data of each sub-traffic area is obtained; and obtaining traffic influence factor data of each sub-traffic area according to the weather change data, the expressway traffic event data and the vehicle basic information data matched with each sub-traffic area.
Specifically, traffic state data of each sub-traffic area is obtained according to SCATS ground induction coil data, portal system data and vehicle traffic track data matched to each sub-traffic area, and the method specifically comprises the following steps:
according to the recorded data of the SCATS ground induction coils in the corresponding sub-traffic areas, traffic saturation data and time occupancy data of each SCATS ground induction coil in each period are obtained through operation, wherein:
Record set N in ground induction coil data according to SCATS x ＝{n 1 ,n 2 ,n 3 … }, where N x Data set representing the x-th coil record, n y Representing a single record of the passage of a vehicle through the coil, including the time t of passage of the vehicle y By time limitation on N x Screening the contained elements to obtain the maximum design traffic capacity C of the road section corresponding to the coil passing through the coil within a certain time, and obtaining the maximum design traffic capacity C according to a road traffic saturation calculation formulaRespectively calculating to obtain traffic saturation data of each coil in each period;
similarly, the vehicle elapsed time T recorded by a certain coil within the period T is extracted y And the number N of vehicles according to the time occupancy formulaRespectively calculating to obtain the time occupancy data of each coil in each period;
according to the instantaneous speed in the portal system data and the time corresponding to the instantaneous speed, calculating to obtain the average speed of the vehicle on each road section and the average speed of all vehicles passing through each portal system, wherein:
recording V based on instantaneous speed in gantry system data xy Record time T xy (records of vehicle y at the x-th portal, respectively) portal position data P x The average speed of the vehicle on a certain road section can be obtained And average speed of all vehicles through a portal +.>
And calculating to obtain the number of the running vehicles corresponding to each period in the sub-traffic area according to the vehicle passing track data.
Specifically, according to weather change data, highway traffic event data and vehicle basic information data matched with each sub-traffic area, traffic influence factor data of each sub-traffic area is obtained, and the method specifically comprises the following steps:
according to the weather change data in the corresponding sub-traffic areas, obtaining the traffic influence level of weather factors;
obtaining corresponding vehicle information data according to the number of vehicles running in the corresponding sub-traffic area and the basic vehicle information data, and calculating to obtain the traffic influence level of the vehicle factors according to the corresponding vehicle information data;
and obtaining traffic event factor traffic influence level according to the expressway traffic event in the corresponding sub-traffic area.
And 6, according to the traffic area association data, fusing traffic state data and traffic influence factor data of each sub-traffic area to obtain the time-space characteristics of the expressway, wherein the time-space characteristics are as follows:
establishing a factor set U= [ V, T, P, D of a highway traffic state evaluation object 1 ,D 2 ]Wherein V is the average passing speed of the vehicle, T is the average passing time of the vehicle, and P is the unit time of the road section Number of vehicles passing through D 1 For the relevant influence index of the characteristic factors of the vehicle, D 2 The method is characterized in that the method is an environmental characteristic factor related influence index;
establishing a two-dimensional expressway traffic state judgment result set: a= [ F, L]Wherein F= [ F 1 ,f 2 ,f 3 ,f 4 ,f 5 ]Is a traffic state; l= [ L ] 1 ,l 2 ,l 3 ,l 4 ]Is a risk level. According to the traffic flow state division standard of each grade of service level of the highways in China, the traffic state and the risk level of the highways are respectively divided into five types, f 1 、f 2 、f 3 、f 4 、f 5 The five traffic states of smoothness, congestion, crowding and congestion are respectively corresponding; l (L) 1 、l 2 、l 3 、l 4 Respectively corresponding to four early warning levels of no risk, low risk, medium risk and high risk;
and combining, summarizing and deducting the traffic state data and the traffic influence factor data of each associated sub-traffic area, converting the traffic state data and the traffic influence factor data into characteristic indexes by adopting a normalization algorithm, and bringing the characteristic indexes into a highway traffic state judging object factor set and a two-dimensional highway traffic state judging result set to obtain highway space-time characteristic data.
A multi-source data fusion device for highway spatiotemporal features, comprising:
the data acquisition module is used for acquiring highway panoramic traffic data, wherein the highway panoramic traffic data comprises SCATS ground induction coil data, portal system data, highway entrance and exit record data, highway along-line meteorological data, highway traffic event data and vehicle basic information data;
The first processing module is used for matching the SCATS ground induction coil data and the portal system data with the highway network, and carrying out double-level road network division on the highway network to obtain traffic area division data and traffic area association data;
the second processing module is used for obtaining vehicle passing track data based on the space sequence model according to portal system data and high-speed access record data; according to meteorological data along the expressway, meteorological change data based on a temporal grid model are obtained; according to the basic information data of the vehicle, obtaining the vehicle information data based on the ground state correction model;
the fitting and matching module is used for fitting and matching the vehicle passing track data, the meteorological change data, the vehicle information data and the highway panoramic traffic data to each sub-traffic area in the traffic area division data;
the third processing module is used for obtaining traffic state data of each sub-traffic area according to the SCATS ground induction coil data, the portal system data and the vehicle traffic track data matched with each sub-traffic area; obtaining traffic influence factor data of each sub-traffic area according to weather change data, expressway traffic event data and vehicle basic information data matched with each sub-traffic area;
And the fourth processing module is used for fusing traffic state data and traffic influence factor data of each sub-traffic area according to the traffic area association data to obtain the space-time characteristics of the expressway.
In one embodiment, the invention provides a computer device comprising a processor and a memory for storing a computer program comprising program instructions, the processor for executing the program instructions stored by the computer storage medium. The processor may be a central processing unit (Central Processing Unit, CPU), but may also be other general purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), off-the-shelf Programmable gate arrays (FPGAs) or other Programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc., which are the computational core and control core of the terminal adapted to implement one or more instructions, in particular adapted to load and execute one or more instructions to implement a corresponding method flow or a corresponding function; the processor provided by the embodiment of the invention can be used for the operation of a multisource data fusion method of the space-time characteristics of the expressway.
In one embodiment, a method of multi-source data fusion of highway spatiotemporal features may be stored in a computer readable storage medium if implemented in the form of software functional units and sold or used as a stand alone product. Based on such understanding, the present invention may implement all or part of the flow of the method of the above embodiment, or may be implemented by a computer program to instruct related hardware, where the computer program may be stored in a computer readable storage medium, and when the computer program is executed by a processor, the computer program may implement the steps of each of the method embodiments described above. Wherein the computer program comprises computer program code which may be in source code form, object code form, executable file or some intermediate form etc. Computer-readable storage media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data.
The computer storage media may be any available media or data storage device that can be accessed by a computer, including, but not limited to, magnetic storage (e.g., floppy disks, hard disks, magnetic tape, magneto-optical disks (MOs), etc.), optical storage (e.g., CD, DVD, BD, HVD, etc.), and semiconductor storage (e.g., ROM, EPROM, EEPROM, non-volatile memory (NANDFLASH), solid State Disk (SSD)), etc.
It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
Finally, it should be noted that: the above examples are only specific embodiments of the present invention, and are not intended to limit the scope of the present invention, but it should be understood by those skilled in the art that the present invention is not limited thereto, and that the present invention is described in detail with reference to the foregoing examples: any person skilled in the art may modify or easily conceive of the technical solution described in the foregoing embodiments, or perform equivalent substitution of some of the technical features, while remaining within the technical scope of the present disclosure; such modifications, changes or substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention, and are intended to be included in the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (10)
1. A method for multi-source data fusion of highway space-time features, comprising:
acquiring highway panoramic traffic data, wherein the highway panoramic traffic data comprises SCATS ground induction coil data, portal system data, highway entrance and exit record data, highway along-line meteorological data, highway traffic event data and vehicle basic information data;
matching the SCATS ground induction coil data and the portal system data with a highway network, and carrying out double-layer road network division on the highway network to obtain traffic area division data and traffic area association data;
obtaining vehicle passing track data based on a space sequence model according to the portal system data and the high-speed access record data; according to the meteorological data along the expressway, meteorological change data based on a temporal grid model are obtained; according to the basic information data of the vehicle, obtaining the vehicle information data based on the ground state correction model;
fitting and matching the vehicle passing track data, the weather change data, the vehicle information data and the highway panoramic traffic data to each sub-traffic area in the traffic area division data;
Obtaining traffic state data of each sub-traffic area according to the SCATS ground induction coil data, the portal system data and the vehicle traffic track data matched with each sub-traffic area; obtaining traffic influence factor data of each sub-traffic area according to the weather change data, the expressway traffic event data and the vehicle basic information data matched with each sub-traffic area;
and according to the traffic area association data, fusing traffic state data and traffic influence factor data of each sub-traffic area to obtain the expressway space-time characteristics.
2. The method for multi-source data fusion of highway spatiotemporal features according to claim 1, further comprising preprocessing the obtained highway panoramic traffic data after obtaining the highway panoramic traffic data.
3. The method for merging the multisource data of the space-time characteristics of the expressway according to claim 1, wherein the steps of matching the SCATS ground induction coil data and the gantry system data with the expressway network, and carrying out double-level road network division on the expressway network to obtain traffic area division data and traffic area association data comprise the following steps:
Extracting highway network data, and performing topology inspection on the highway network to form perfect highway network data;
marking the position information of the SCATS ground induction coil and the position information of the portal system on perfect highway network data to obtain a first layer large-scale region division based on the portal system and a second layer small-scale region division based on the SCATS ground induction coil, namely obtaining traffic region division data;
based on the double-level road network division, a double-level road network mapping relation is established according to the total or partial inclusion between the first layer large-scale area and the second layer small-scale area and the high-speed access node influence factors, and traffic area association data is obtained.
4. The method for merging the multisource data of the space-time characteristics of the expressway according to claim 1, wherein the method is characterized in that the method for merging the multisource data of the space-sequence model based vehicle passing track data is obtained according to the portal system data and the high-speed access record data, and specifically comprises the following steps:
acquiring vehicle passing track data based on a space sequence model by adopting a set operation and relation operation method according to the portal system data and the high-speed entrance and exit record data;
According to the meteorological data along the expressway, meteorological change data based on a temporal grid model is obtained, specifically:
acquiring weather variation data based on a temporal grid model by adopting a set operation and relation operation method according to the weather data along the expressway;
the vehicle information data based on the ground state correction model is obtained according to the vehicle basic information data, and specifically comprises the following steps:
and acquiring the vehicle information data based on the ground state correction model by adopting a set operation and relation operation method according to the vehicle basic information data.
5. The method for multi-source data fusion of highway spatiotemporal features according to claim 1, wherein said fitting said vehicle traffic trajectory data, weather variation data, vehicle information data and highway panoramic traffic data to each sub-traffic zone in said traffic zone division data comprises:
extracting the vehicle passing track data, the meteorological change data, the vehicle information data and the position information and the time-space sequence relation information in the highway panoramic traffic data;
and comparing the position information in the traffic area division data with the time-space sequence relation information respectively with the extracted vehicle passing track data, the meteorological change data, the vehicle information data and the position information in the highway panoramic traffic data, and completing fitting and matching.
6. The method for merging the multisource data of the space-time characteristics of the expressway according to claim 1, wherein the step of obtaining traffic state data of each sub-traffic area according to the SCATS ground induction coil data, the portal system data and the vehicle traffic track data matched with each sub-traffic area specifically comprises the following steps:
according to the recorded data of the SCATS ground induction coils in the corresponding sub-traffic areas, traffic saturation data and time occupancy data of each SCATS ground induction coil in each period are obtained through calculation;
according to the instantaneous speed in the portal system data and the time corresponding to the instantaneous speed, calculating to obtain the average speed of the vehicle on each road section and the average speed of all vehicles passing through each portal system;
and calculating to obtain the number of the running vehicles corresponding to each period in the sub-traffic area according to the vehicle passing track data.
7. The method for merging the multi-source data of the space-time characteristics of the expressway according to claim 6, wherein the obtaining the traffic impact factor data of each sub-traffic area according to the weather-change data, the expressway traffic event data and the vehicle basic information data matched with each sub-traffic area specifically comprises:
According to the weather change data in the corresponding sub-traffic areas, obtaining the traffic influence level of weather factors;
obtaining corresponding vehicle information data according to the number of vehicles running in the corresponding sub-traffic area and the basic vehicle information data, and calculating to obtain the traffic influence level of the vehicle factors according to the corresponding vehicle information data;
and obtaining traffic event factor traffic influence level according to the expressway traffic event in the corresponding sub-traffic area.
8. The method for merging the multi-source data of the temporal-spatial characteristics of the expressway according to claim 1, wherein the merging the traffic state data and the traffic influence factor data of each sub-traffic area according to the traffic area association data to obtain the temporal-spatial characteristics of the expressway specifically comprises the following steps:
and combining, summarizing and deducting traffic state data and traffic influence factor data of each associated sub-traffic area to obtain the space-time characteristics of the expressway.
9. A multi-source data fusion device for highway spatiotemporal features, comprising:
the system comprises a data acquisition module, a data processing module and a data processing module, wherein the data acquisition module is used for acquiring highway panoramic traffic data, and the highway panoramic traffic data comprises SCATS ground induction coil data, portal system data, highway entrance and exit record data, highway along-line meteorological data, highway traffic event data and vehicle basic information data;
The first processing module is used for matching the SCATS ground induction coil data and the portal system data with the highway network, and carrying out double-level road network division on the highway network to obtain traffic area division data and traffic area association data;
the second processing module is used for obtaining vehicle passing track data based on a space sequence model according to the portal system data and the high-speed access record data; according to the meteorological data along the expressway, meteorological change data based on a temporal grid model are obtained; according to the basic information data of the vehicle, obtaining the vehicle information data based on the ground state correction model;
the fitting and matching module is used for fitting and matching the vehicle passing track data, the weather change data, the vehicle information data and the highway panoramic traffic data to each sub-traffic area in the traffic area division data;
the third processing module is used for obtaining traffic state data of each sub-traffic area according to the SCATS ground induction coil data, the portal system data and the vehicle traffic track data matched with each sub-traffic area; obtaining traffic influence factor data of each sub-traffic area according to the weather change data, the expressway traffic event data and the vehicle basic information data matched with each sub-traffic area;
And the fourth processing module is used for fusing traffic state data and traffic influence factor data of each sub-traffic area according to the traffic area associated data to obtain the space-time characteristics of the expressway.
10. An apparatus comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the computer program, performs the steps of a method of multi-source data fusion of highway spatiotemporal features of any of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111518366.4A CN114267173B (en) | 2021-12-13 | 2021-12-13 | Multisource data fusion method, device and equipment for space-time characteristics of expressway |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111518366.4A CN114267173B (en) | 2021-12-13 | 2021-12-13 | Multisource data fusion method, device and equipment for space-time characteristics of expressway |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114267173A CN114267173A (en) | 2022-04-01 |
| CN114267173B true CN114267173B (en) | 2023-08-18 |
Family
ID=80827023
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111518366.4A Active CN114267173B (en) | 2021-12-13 | 2021-12-13 | Multisource data fusion method, device and equipment for space-time characteristics of expressway |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114267173B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114783194B (en) * | 2022-04-02 | 2024-07-19 | 贵州汇联通电子商务服务有限公司 | Method and system for obtaining section flow based on high-speed portal frame |
| CN115186781B (en) * | 2022-09-14 | 2022-11-22 | 南京感动科技有限公司 | Real-time fusion method for multi-source roadside traffic observation data |
| CN117912253A (en) * | 2024-01-31 | 2024-04-19 | 广州云玥科技有限公司 | Urban traffic database information acquisition method and system |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102231231A (en) * | 2011-06-16 | 2011-11-02 | 同济大学 | Area road network traffic safety situation early warning system and method thereof |
| CN102779410A (en) * | 2012-07-19 | 2012-11-14 | 杭州师范大学 | Parallel implementation method of multi-source heterogeneous traffic data fusion |
| CN106781457A (en) * | 2016-11-29 | 2017-05-31 | 东南大学 | A kind of freeway traffic flow parameter correction method based on multi-source fusion data |
| CN110211380A (en) * | 2019-06-04 | 2019-09-06 | 武汉大学 | A kind of highway congestion section detection method of multi-source traffic data fusion |
| AU2020100946A4 (en) * | 2019-10-18 | 2020-07-16 | Chang'an University | Multi-source traffic information sensing roadside device for smart highway |
| CN111582130A (en) * | 2020-04-30 | 2020-08-25 | 长安大学 | Traffic behavior perception fusion system and method based on multi-source heterogeneous information |
| CN111583675A (en) * | 2020-05-14 | 2020-08-25 | 吴钢 | Regional road network traffic signal lamp coordination control system and method |
| CN111862655A (en) * | 2020-05-27 | 2020-10-30 | 南京美慧软件有限公司 | Intelligent expressway network traffic facility system and control method |
| CN112512020A (en) * | 2020-11-20 | 2021-03-16 | 北京中交国通智能交通系统技术有限公司 | Multi-source data fusion-based traffic state weak signal perception studying and judging method |
| CN113269960A (en) * | 2021-05-17 | 2021-08-17 | 郑州航空工业管理学院 | Method for analyzing accident risk of highway tunnel group traffic |
| CN113538898A (en) * | 2021-06-04 | 2021-10-22 | 南京美慧软件有限公司 | Multisource data-based highway congestion management and control system |
| CN113781767A (en) * | 2021-08-05 | 2021-12-10 | 浙江省机电设计研究院有限公司 | Traffic data fusion method and system based on multi-source perception |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113554869B (en) * | 2021-07-01 | 2022-04-05 | 华东师范大学 | Road closure detection method based on multi-feature fusion |
| CN113724504B (en) * | 2021-08-06 | 2023-04-07 | 之江实验室 | Urban area traffic prediction system and method oriented to vehicle track big data |
-
2021
- 2021-12-13 CN CN202111518366.4A patent/CN114267173B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102231231A (en) * | 2011-06-16 | 2011-11-02 | 同济大学 | Area road network traffic safety situation early warning system and method thereof |
| CN102779410A (en) * | 2012-07-19 | 2012-11-14 | 杭州师范大学 | Parallel implementation method of multi-source heterogeneous traffic data fusion |
| CN106781457A (en) * | 2016-11-29 | 2017-05-31 | 东南大学 | A kind of freeway traffic flow parameter correction method based on multi-source fusion data |
| CN110211380A (en) * | 2019-06-04 | 2019-09-06 | 武汉大学 | A kind of highway congestion section detection method of multi-source traffic data fusion |
| AU2020100946A4 (en) * | 2019-10-18 | 2020-07-16 | Chang'an University | Multi-source traffic information sensing roadside device for smart highway |
| CN111582130A (en) * | 2020-04-30 | 2020-08-25 | 长安大学 | Traffic behavior perception fusion system and method based on multi-source heterogeneous information |
| CN111583675A (en) * | 2020-05-14 | 2020-08-25 | 吴钢 | Regional road network traffic signal lamp coordination control system and method |
| CN111862655A (en) * | 2020-05-27 | 2020-10-30 | 南京美慧软件有限公司 | Intelligent expressway network traffic facility system and control method |
| CN112512020A (en) * | 2020-11-20 | 2021-03-16 | 北京中交国通智能交通系统技术有限公司 | Multi-source data fusion-based traffic state weak signal perception studying and judging method |
| CN113269960A (en) * | 2021-05-17 | 2021-08-17 | 郑州航空工业管理学院 | Method for analyzing accident risk of highway tunnel group traffic |
| CN113538898A (en) * | 2021-06-04 | 2021-10-22 | 南京美慧软件有限公司 | Multisource data-based highway congestion management and control system |
| CN113781767A (en) * | 2021-08-05 | 2021-12-10 | 浙江省机电设计研究院有限公司 | Traffic data fusion method and system based on multi-source perception |
Non-Patent Citations (1)
| Title |
|---|
| 考虑特定OD分布形态的路网容量双层规划模型;张晓婷;吴兵;;交通运输工程与信息学报(第04期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114267173A (en) | 2022-04-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114267173B (en) | Multisource data fusion method, device and equipment for space-time characteristics of expressway | |
| CN103971523B (en) | A kind of mountain road traffic safety dynamic early-warning system | |
| CN103839409B (en) | Based on the traffic flow modes method of discrimination of multibreak facial vision sensing cluster analysis | |
| Fang et al. | FTPG: A fine-grained traffic prediction method with graph attention network using big trace data | |
| CN106856049B (en) | Key intersection demand aggregation analysis method based on bayonet number plate identification data | |
| CN113963539B (en) | Highway traffic accident identification method, module and system | |
| Ansariyar et al. | Statistical analysis of vehicle-vehicle conflicts with a LIDAR sensor in a signalized intersection. | |
| Aziz et al. | Identifying and characterizing truck stops from GPS data | |
| Meng et al. | Expressway crash prediction based on traffic big data | |
| CN113868492A (en) | Visual OD (origin-destination) analysis method based on electric police and checkpoint data and application | |
| Zong et al. | Bus-Car Mode Identification: Traffic Condition–Based Random-Forests Method | |
| US20220319323A1 (en) | Method for identifying road risk based on networked vehicle-mounted adas | |
| CN117273964B (en) | Intelligent vehicle insurance policy generation system and method for self-adaptive driving data | |
| Pandey et al. | Assessment of Level of Service on urban roads: a revisit to past studies. | |
| CN112185120A (en) | Commuting private car identification method based on electronic license plate data | |
| Huang | SVM‐Based Real‐Time Identification Model of Dangerous Traffic Stream State | |
| CN116259173A (en) | D-S evidence theory-based multi-detection mode traffic event fusion method | |
| Zhang et al. | Modeling lane-change risk in urban expressway off-ramp area based on naturalistic driving data | |
| Ge et al. | Research on characteristics and trends of traffic flow based on mixed velocity method and background difference method | |
| Anik et al. | Prediction of Crash Injury Severity in Florida's Interstate-95 | |
| Patil et al. | Infrastructure Camera Video Data Processing of Traffic at Roundabouts | |
| CN117315943B (en) | Monitoring analysis and early warning method and system for overrun transportation violations | |
| CN118629216B (en) | Road target identification method and system based on radar fusion | |
| CN118587072B (en) | Road emergency event processing method and system | |
| Le | Real-time perception of urban road congestion based on internet of vehicles technology. |
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 |