CN115641721A - Multi-source traffic flow index fusion and road condition calculation method based on fusion index - Google Patents
Multi-source traffic flow index fusion and road condition calculation method based on fusion index Download PDFInfo
- Publication number
- CN115641721A CN115641721A CN202211554669.6A CN202211554669A CN115641721A CN 115641721 A CN115641721 A CN 115641721A CN 202211554669 A CN202211554669 A CN 202211554669A CN 115641721 A CN115641721 A CN 115641721A
- Authority
- CN
- China
- Prior art keywords
- traffic flow
- mileage
- interval
- road condition
- speed
- 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
Images
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
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Abstract
The invention relates to a multi-source traffic flow index fusion and a road condition calculation method based on the fusion index, wherein a discretization road network is established based on mileage piles; acquiring a floating car traffic flow index and a section detection traffic flow index of a road network closed area, wherein a mileage pile is used as an entrance or an exit in the closed area; the traffic flow indicator comprises a traffic flow speed; discretizing spatial continuous traffic flow indexes from different sources by taking the mileage stake interval as a unit; and fusing different source traffic flow indexes of each mileage pile interval. After different source traffic flow indexes are fused, the fused traffic flow speed is converted into a mileage stake interval road condition, and a discrete road network is combined to obtain a spatially continuous high-speed road condition. The method provided by the invention fully utilizes the multi-source road condition data, and realizes the whole road network road condition data fusion on any time slice based on the designed fusion algorithm, thereby outputting more accurate and more comprehensive road condition data.
Description
Technical Field
The invention belongs to the field of intelligent traffic informatization, and relates to a multi-source traffic flow index fusion and a road condition calculation method based on the fusion index.
Background
With the continuous improvement of the quantity of motor vehicles in China, the traffic jam condition of the highway is more serious, and road condition data becomes a common concern of a road manager and a large number of traffic participants. The road condition data is divided into quantitative data and qualitative data, wherein the former refers to specific traffic operation condition indexes (hereinafter referred to as traffic flow indexes) such as traffic volume, vehicle speed and the like, the latter refers to traffic operation condition descriptions such as slow traffic, congestion and severe congestion, and the latter is generally converted from the former and is easier to understand, so that the following road conditions are all designated road conditions.
The current road condition calculation mainly depends on two types of data of a floating car and section detection, the former realizes speed calculation by collecting GPS data such as a mobile phone and vehicle-mounted equipment, the latter obtains traffic flow indexes such as speed and traffic volume at the section through modes such as screen detection, image recognition, radar induction and geomagnetic induction, and the further obtains the road condition at the section through conversion. However, there are several problems and difficulties in current road condition calculation and effective application:
(1) The road condition of the floating car is based on a small sample and is not enough to represent the complete road condition
The current floating car data mainly comprise: 1) user mobile phone GPS data collected by a map service provider (map provider), 2) two-passenger one-dangerous vehicle GPS data, 3) special vehicle GPS data and the like. The GPS data of the mobile phone collected by the current map provider is the main data. However, each graph businessman can only acquire the GPS data of each user for calculating the road condition, and thus cannot describe the running condition of the complete road network, and the problem that two passengers, one dangerous vehicle, special vehicles and the like cannot express the complete road condition also exists.
(2) The space distribution of the detection points of the cross section is sparse, and the complete road condition cannot be described
The section detection needs to depend on specific facilities such as a camera, a radar, a geomagnetic coil and the like, and because the facilities are expensive and high in maintenance cost, the section detection only needs to be arranged at key points or road sections of a road network at present, the coverage of the detection data space range is insufficient, and the complete road condition cannot be described.
(3) The road condition descriptions of all sources are inconsistent
The reasons for inconsistent road condition descriptions are two reasons: 1) The traffic flow indexes calculated from all sources are inconsistent because of difference of the data and the calculation principle; 2) The manner of converting traffic flow indexes into road conditions is inconsistent. The problem of inconsistent road condition description prevents road managers and a large number of traffic participants from accurately acquiring the road running condition.
For the above problems, in the past, a single traffic data is usually selected in the service application. If in the traffic survey service, the method selects section detection data so as to obtain the running condition of a key point or a key road section of a road; in the active management and control service for road operation, the floating vehicle road condition from a single source is selected, so that the road condition data with fine granularity is obtained for precise management and control. However, the problem of insufficient spatial coverage and accuracy is caused by adopting the road condition data from a single source, and the accuracy and the service quality of the upper layer service are further affected.
Disclosure of Invention
The first objective of the present invention is to provide a method for fusing multi-source traffic flow indicators for multi-source incomplete multi-source traffic data.
In order to achieve the above purpose of the invention, the invention adopts the following scheme:
a multi-source traffic flow index fusion method comprises the following steps:
acquiring a floating car traffic flow index and a section detection traffic flow index of a road network closed area, wherein a mileage pile is used as an entrance or an exit in the closed area; the traffic flow indicator comprises a traffic flow speed;
discretizing spatial continuous traffic flow indexes from different sources by taking the mileage stake interval as a unit;
fusing different source traffic flow indexes of each mileage stake interval, comprising:
if the mileage pile interval is contained in the closed interval and is contained in the floating car route or is intersected with the floating car route, performing weight distribution on the floating car, and taking the weighted value of the traffic flow speed of the floating car as the traffic flow speed of the mileage pile interval;
if the mileage pile interval is only contained in the floating car route or is intersected with the floating car route, taking the average value of the traffic flow speed of the floating car as the traffic flow speed of the mileage pile interval;
if the mileage pile interval is only contained in the closed area, taking the traffic flow speed of the closed area as the traffic flow speed of the mileage pile interval;
and if the situation does not exist, judging that the traffic flow speed of the mileage stake interval is infinite.
In a preferred embodiment, the method further comprises encrypting the mileage peg by supplementing the virtual mileage peg. In traffic, the congestion starting point or ending point is not necessarily near the mile pile, and if the congestion starting point is 100.75 km from G2503, a 50-meter error is generated by using the nearest mile pile G2503K 100+700 or G2503K 100+800 instead. Therefore, in order to obtain a road condition with higher precision, the virtual mileage pile is supplemented and encrypted on the basis of the current inherent mileage pile, so that a discretization road network with higher precision is obtained.
In a preferred embodiment, a spatial linear interpolation method is adopted to supplement the virtual mileage pile, and the mileage pile is encrypted.
As a preferred embodiment, the discretization of the spatially continuous traffic flow indicators from different sources is as follows:
for a floating car data source, converting a floating car route into a coordinate system consistent with the pile number of the mileage pile, and for the mileage pile interval intersected with or contained in the floating car route, taking the corresponding traffic flow index as the traffic flow index of the associated floating car;
and for the data source of the closed area, the traffic flow index corresponding to the mileage pile interval is associated to be the traffic flow index of the closed area containing the mileage pile interval.
In a preferred embodiment, the traffic flow index further comprises traffic flow density, and the floating cars are weighted and assigned according to the traffic flow density of the closed area and the traffic flow speed of the floating cars.
As a preferred embodiment, the weight assignment principle is:
under the condition that the section traffic flow speed is greater than or equal to the average speed value of the floating cars, the weight is a monotone increasing function of the speed of the floating cars;
under the condition that the section traffic flow speed is smaller than the average value of the speeds of the floating vehicles, the weight is a monotone decreasing function of the speeds of the floating vehicles;
when the traffic flow index comprises the traffic flow density, combining the traffic flow density constraint weight, and setting the difference value of the maximum weight and the minimum weight as a monotonous decreasing function of the traffic flow density.
The multi-source traffic flow index fusion method provided by the invention fully utilizes the traffic space characteristics of the highway, establishes a discretization road network based on the mile posts, fully utilizes the traffic flow index data of multiple sources, performs fusion through variable weighted average to obtain a uniform and higher-accuracy traffic flow index, and utilizes the cross section detection traffic flow data and floating car data to complement each other so as to measure the space operation condition of the whole road network.
The second objective of the present invention is to provide a method for calculating a high-speed road condition based on a fusion index, which includes: after the traffic flow indexes from different sources are fused by the method, the fused traffic flow speed is converted into the road condition between the mileage stake intervals, and the discrete road networks are combined to obtain the spatially continuous high-speed road condition.
As a preferred embodiment, said merged discrete road network comprises: and combining the mileage pile sections with continuous space and the same road condition by taking the closed section as an upper limit.
In a preferred embodiment, the method further comprises performing spatial smoothing after combining the discrete road networks.
As a preferred embodiment, the spatial smoothing correction includes:
for the two spatially continuous mileage pile merging intervals, if the two spatially continuous mileage pile merging intervals are spatially continuous and the length ratio of the two mileage pile merging intervals meets a preset threshold, merging the two mileage pile merging intervals;
the mileage stake merge section refers to a merged mileage stake section.
According to the high-speed road condition calculation method, the multi-source road condition data are fully utilized, and the whole road network road condition data fusion on any time slice is realized based on the designed fusion algorithm, so that more accurate and more comprehensive road condition data are output.
The invention has the following beneficial effects:
1) In the field of traffic control, the generated fused road condition data can provide a manager with more accurate road network running conditions covering a wider area, and help the manager to improve the level of traffic operation active control, historical road condition study and judgment, personnel and control facility configuration and other services;
2) In the field of travel service, road condition data are fused more accurately and comprehensively, so that traffic participants can be helped to make travel plans, switch form routes, avoid congestion, traffic accidents and the like more reasonably;
3) In the field of data management, the invention systematically integrates and optimizes data from multiple sources, thereby improving the data management level in the aspects of data management, data release and storage, data life cycle management, data quality management and the like.
Drawings
Fig. 1 is an IDEF diagram for calculating highway conditions based on multi-source traffic flow index fusion.
Detailed Description
Example 1
This embodiment specifically illustrates a method for fusing traffic flow indicators based on multiple sources.
The scheme adopts batch processing, receives multi-source whole road network operation condition index data sliced at a certain time by calculation each time, and outputs the data as fused road condition data.
As shown in fig. 1, the technical solution of multi-source traffic flow index fusion includes the following steps:
A1. discrete road network preparation
The goal of this step is: 1) And encrypting the mileage piles, and cutting the route by using the encrypted mileage piles to obtain a discretized road network, so that the traffic flow index data of each source can be conveniently spatially aligned and fused in the follow-up process. 2) And obtaining the topological structure among the encrypted mileage piles, so that subsequent discrete road network merging and space continuity correction are facilitated.
The mileage peg is an elongated object vertically inserted into the roadside, and has a serial number, i.e., a mileage peg number, for identifying a spatial position on a route, i.e., a position of 100.7 km from a starting point, such as G2503K 100+700, which indicates a G2503 route. The highway mileage piles are characterized in that the interval is 100 meters, the density is high, the highway mileage piles are distributed on two sides of a road, and the number of the mileage piles on two sides of the road at the same position is consistent.
In the present invention, a topology structure between mileage piles is used, which requires unique topology node numbers, so that uplink and downlink mileage piles at the same position are defined as 1 direction and 0 direction respectively to distinguish, for example, at G2503K 100+700, the uplink mileage pile number is G2503K 100+700 | 1, and the downlink is G2503K 100+700 | 0.
The precondition of the step is the mileage stake interval before encryption. In a highway scene, a mileage stake interval refers to a route between two adjacent mileage stakes, and is LineString, and the mileage stake interval is specifically defined as follows:
Based on the above definitions, the following processes of performing spatial linear encryption on the mileage pile and generating an encrypted mileage pile interval are as follows.
A certain number of virtual mileage piles are required to be inserted into the system so as to ensureObtaining the encrypted milepost interval ofRice, wherein. For any one mileage stake intervalLet it start fromEnd point isGenerating the encrypted mileage piles and the mileage pile intervals:
S3: use ofSection of willBreaking and constructing mileage pile interval setConstructing a correlation function;
S4: computingAs a new set of mileposts,As a new set of milepost intervalsWill map toAndmerged as a new mapping。
Wherein, the step S1 of taking the equal division point of the LineString and the step S4 of breaking the LineString have a general method, which is not described here. Traverse all mileage pile intervalsPerforming the above steps A1S 1 to S4 to obtainThen it is the set of encrypted mile posts,the interval of the mileage piles after encryption is as followsAnd (4) rice.
A2. Section traffic flow index compartmentalization
And (3) traffic flow indexes of section detection classes only represent traffic conditions near the sections. However, in the high-speed traffic practice, the road network is widely distributed, and the cross-section detection cost is high, so that only one cross-section detection point is generally arranged in a closed area (the starting point and the ending point are toll stations or hubs, and no other exit exists in the middle).
Considering that the vehicle entrance and exit are unique in the closed area, for stable flow, namely no queuing phenomenon, the vehicle flow entering the closed area is equal to the leaving vehicle flow, the traffic volume detected by the section can represent the traffic volume of any point in the area, for unstable flow, namely queuing phenomenon, the traffic volume of the section detection point is the average value of the traffic volumes in the area, therefore, the invention adopts the section detection traffic flow index to approximately replace the closed area traffic flow index. The method has rough space granularity and is not sensitive enough to the perception of the congested road condition, so the method needs to be fused with the floating car data in the steps A4 and A5.
The precondition of the step is the relation between the closed area and the section detection point, and the coordinate system of the closed area is consistent with the mileage stake area, so that the subsequent treatment is convenient, and the starting point or the end point of the closed area is required to be the mileage stake. It should be noted that one section detection point only belongs to one closed area, and one closed area includes one or more detection points, which are specifically defined as follows:
the traffic flow indexes required by the invention are as follows: slicing in enclosed space for a certain timeDensity of traffic flow onAnd traffic flow speed. The section detection data directly include the driving speed of each vehicle, so that the section detection data is applied to a closed areaThe speed of the traffic flow is
Wherein the content of the first and second substances,
to representPoint of passage in time periodThe number of vehicles (a) in the vehicle,representation collectionThe number of elements (c).
Density of traffic flowCan not be directly obtained from section detection data, and the calculation mode is
Wherein, the first and the second end of the pipe are connected with each other,
wherein, the first and the second end of the pipe are connected with each other,
according to the formula (1) and the formula (2), all the closed areas can be calculatedThe traffic flow speed and the traffic flow density of (1) are as follows:
A3. Space continuous traffic flow index discretization
Discretizing the continuous space traffic flow indexes, including the continuous space traffic flow indexes based on the floating cars and the traffic flow indexes in the closed area obtained in A2. Because the interval traffic flow index obtained in the step A2 is an estimated value (calculated by adopting a section traffic flow index), the action of the interval traffic flow index is different from that of data directly obtained based on floating cars, specifically seen in the step A4, and therefore the interval traffic flow index is distinguished and processed in the step A.
A3.1 Floating car-based space continuous traffic flow index discretization
Is provided withRecording all traffic flow index data obtained based on floating cars on a certain time slice as a set(fc is floating car), for any piece of dataThe route is recorded asRecording the speed of the traffic flow asThen, thenThe discretization process of (1) is as follows.
S1: will be provided withConverting into a coordinate system consistent with the pile number system;
Traverse allIf the above steps A3.1S 1 to S3 are executed, all the steps are executedConverted to a record of the milepost dimensions, of the form:
Relates to a floating car traffic flow speed set between mileage stake intervalsAnd the traffic flow speed of the floating car in any mile stake interval is recorded as;
Is a mapping that associates milepost intervals with their corresponding floating car traffic flow speeds.
Note that due to the existence ofThe data source of the floating car, wherein one mileage stake interval may correspond to a plurality of speeds.
A3.2 Discretizing A2 closed area traffic flow index
Recording all the traffic flow index data in the closed area obtained in A2 on a certain time slice as a setFor any piece of data(Is estimation, i.e., an estimate), the route of which isThe speed of the traffic flow isThe density of the traffic flow isThen, thenIs discretized by a process such asAnd (5) the following.
S2: for all mileage stake intervalsRecords the corresponding traffic flow speed asCorresponding to a traffic flow density of。
Traverse allIf the above steps A3.2S 1 to S2 are executed, all the steps are executedConverted to a record of milepost dimensions, of the form:
Is a map that correlates milepost intervals with their corresponding cut plane estimated traffic flow velocities;
is a mapping that associates milepost intervals with their corresponding profile estimated traffic flow densities.
A4. Discrete road network traffic flow index fusion
Based on the step A3, the objective of this step is to merge traffic flow indexes of multiple sources in each mileage pile interval, and the specific process is as follows.
Wherein:
under the condition of acquiring the traffic flow density index, the weight distribution is carried out by supplementing the following formula:
wherein:
wherein:,,representThe medium maximum value is the maximum value of the average,to representThe medium minimum value.
Example 2
This embodiment specifically illustrates a method for calculating a high-speed road condition based on the fusion index obtained in embodiment 1.
A5. Discrete road network road condition calculation
This step is based on the result obtained in step A4Further converting the traffic flow index of the milepost sections into the road condition of the milepost sections according to the recommended road traffic congestion degree evaluation method (GA/T115-2020) of technical supervision committee of the ministry of public Security, the conversion standard of the traffic flow speed and the road condition is as follows,
whereinThe condition is the road condition, i.e. condition, i represents severe congestion, ii represents moderate congestion, iii represents mild congestion, and iv represents unblocked. Combined formula (3) and formula (4) for all mileage stake intervalsAnd (3) carrying out road condition conversion to obtain the qualitative road condition of each mileage pile interval, wherein the form is as follows:
A6. Discrete road network merging and spatial smoothing correction
The road condition calculation of each mileage pile section is completed by the step A5, however, the current space granularity is fine, and the section length isRice (see step A1), luoThe net is relatively broken, which is not convenient for subsequent analysis and display. Therefore, the objective of this step is to merge the mileage pile sections with continuous space and the same road conditions, and perform the spatial smoothing correction at the same time, for example, the first section on a certain roadToThe road condition between each mileage pile section is I (serious congestion), the secondThe road condition between each mileage pile is IV (smooth), and the second isToThe road condition in the section of the mileage stake is I (serious congestion), and the length of each section is equal to the granularity of the section of the current distance stakeShorter, so that the section is smoothly corrected to the road condition I, i.e., the sectionTo is thatThe serious congestion route which is combined into the road condition I is reasonable.
In addition, the upper limit of the discrete road network merging in the step is a closed area (see step A2), namely, the mileage stake areas in different closed areas are not merged even if the road conditions are consistent and the spaces are continuous. The reasons for this are the following three points: 1) In a highway scene, the closed area is long, and the problem of over-crushing of a road network can be avoided by taking the closed area as an upper limit; 2) On the management side of the highway, toll stations and hubs are important nodes in a road network, and the road network is divided by the toll stations and the hubs no matter the toll service, the traffic control service, the traffic big data analysis and the like are carried out; 3) In the public trip field, road conversion can be performed at toll stations and junctions, so that the road condition data taking the closed area as the upper limit can meet the public demand for judging the road condition.
The specific process of the step is as follows:
for any closed spaceExtracting quiltIncluding mileage stake intervalAs a setThen in the closed areaThe inner mileage pile interval merging process is as follows:
s1: initialization orderingTuple of elementsThe combined road condition data storage device is used for storing the combined road condition data;
S6: if present, andthen add from the rightTo orderTuple of elementsAnd are combined withEnd point of (1)In substitution S5Re-executing the steps S5 to S6;
S8: if present, andthen add from the leftTo orderTupleAnd are combined withStarting point of (2)In substitution S7Re-executing the steps S7 to S8;
s9: if not, thenMileage stake intervals with continuous space and same road conditions are all added to the orderTuple of elementsIn (1). Sequentially extractingAll the mileage pile intervals are combined into a routeGet itThe starting point of the mileage peg interval in the first element is marked asAnd taking the end point of the mileage pile interval in the last element and recording the end point as the end pointCalculatingNumber of elements (2)Recording the road condition asAdding ordered five-membered groupsTo aggregate;
For all closed areasIf the above-mentioned S1 to S11 are executed, the traffic information corresponding to each closed area can be obtainedWherein each route with the same road condition and continuous space in the closed area is savedNumber of covered milepost intervalsStarting point ofEnd point ofRoad conditions. All the closed area road condition information is merged, and then the traffic information is obtainedObtaining the road condition information with continuous space and the same road condition in the full high-speed range, and recording as a setWhereinIs shown asAnd road condition information corresponding to each closed area.
Then, the merged road condition data is further corrected spatially and smoothly, and it should be noted that the upper limit is still set to be the closed area.
For any enclosed spaceCorresponding to the road condition ofThen, the spatial smoothing correction process of the closed region is as follows:
S2: if it isGet the firstAn ordered five-membered groupOtherwise, the loop is terminated, andis a closed spaceSpatially smoothing the corrected result;
1) If it isThen, it is determinedCan be coveredSmooth correction, useSubstitutionAnd returning to execute the step S1 again;
WhereinIn order to set the threshold value in advance,representing a routeAndspatial merging of (2);
1) If it isThen, it is judgedCan be coveredSmooth correction usingSubstitutionAnd returning to execute the step S1 again;
3) If it isThen, without spatial smoothing correction, use+1 substitutionReturning to the step S2 to continue execution;
For each closed areaPerforming the above S1 to S7, correspondingly obtainedIs thatThe final road condition data set is the road condition information after the spatial smoothing correctionThe road condition information of the full-high speed road network after the discrete road network combination and the spatial smoothing is described, wherein each element is information of a route, a road condition grade, a starting point and an end point.
Claims (10)
1. A multi-source traffic flow index fusion method is characterized by comprising the following steps:
establishing a discretization road network based on the mileage pile;
acquiring a floating car traffic flow index and a section detection traffic flow index of a road network closed area, wherein the closed area takes a mileage pile as an entrance or an exit; the traffic flow indicator comprises a traffic flow speed;
discretizing spatial continuous traffic flow indexes from different sources by taking the mileage stake interval as a unit;
fusing different source traffic flow indexes of each mileage stake interval, comprising:
if the mileage pile interval is contained in the closed interval and is contained in the floating car route or is intersected with the floating car route, performing weight distribution on the floating car, and taking the weighted value of the traffic flow speed of the floating car as the traffic flow speed of the mileage pile interval;
if the mileage pile interval is only contained in the floating car route or is intersected with the floating car route, taking the average value of the traffic flow speed of the floating car as the traffic flow speed of the mileage pile interval;
if the mileage pile interval is only contained in the closed area, taking the traffic flow speed of the closed area as the traffic flow speed of the mileage pile interval;
and if the situation does not exist, judging that the traffic flow speed of the mileage stake interval is infinite.
2. The method of claim 1, further comprising, supplementing the virtual milepost encrypts the milepost.
3. The method of claim 2, wherein the virtual milepost is supplemented by a spatial linear interpolation method to encrypt the milepost.
4. The method according to claim 1, wherein the spatially continuous traffic flow indicators from different sources are discretized by:
for a floating car data source, converting a floating car route into a coordinate system consistent with the pile number of the mileage pile, and for the mileage pile interval intersected with or contained in the floating car route, taking the corresponding traffic flow index as the traffic flow index of the associated floating car;
for the data source of the closed area, the traffic flow index corresponding to the mileage stake interval is related to the traffic flow index of the closed area containing the mileage stake interval.
5. The method of claim 1, wherein the traffic flow indicators further include traffic flow density, and wherein floating cars are weighted using traffic flow density in the enclosed area and traffic flow speed of floating cars.
6. The method according to claim 1 or 5, wherein the weight assignment rule is:
under the condition that the section traffic flow speed is greater than or equal to the average speed value of the floating cars, the weight is a monotone increasing function of the speed of the floating cars;
under the condition that the section traffic flow speed is smaller than the average value of the speeds of the floating vehicles, the weight is a monotone decreasing function of the speeds of the floating vehicles;
when the traffic flow index comprises the traffic flow density, combining the traffic flow density constraint weight, and setting the difference value of the maximum weight and the minimum weight as a monotonous decreasing function of the traffic flow density.
7. A high-speed road condition calculation method based on fusion indexes is characterized by comprising the following steps: after the traffic flow indexes from different sources are fused by the method of any one of claims 1 to 6, the fused traffic flow speed is converted into a road condition of a mileage stake interval, and a discrete road network is combined to obtain a spatially continuous highway condition.
8. The method of claim 7, wherein said merging discrete road networks comprises: and combining the mileage pile sections with continuous space and the same road condition by taking the closed section as an upper limit.
9. The method of claim 7 or 8, further comprising performing spatial smoothing after merging the discrete road networks.
10. The method of claim 9, wherein the spatially smooth modification comprises:
for two mileage pile merging intervals with continuous space, if the two mileage pile merging intervals have continuous space and the length ratio of the two mileage pile merging intervals meets a preset threshold value, merging the two mileage pile merging intervals;
the mileage stake merge section refers to a merged mileage stake section.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211554669.6A CN115641721B (en) | 2022-12-06 | 2022-12-06 | Multi-source traffic flow index fusion and road condition calculation method based on fusion index |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211554669.6A CN115641721B (en) | 2022-12-06 | 2022-12-06 | Multi-source traffic flow index fusion and road condition calculation method based on fusion index |
Publications (2)
Publication Number | Publication Date |
---|---|
CN115641721A true CN115641721A (en) | 2023-01-24 |
CN115641721B CN115641721B (en) | 2023-04-07 |
Family
ID=84948415
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202211554669.6A Active CN115641721B (en) | 2022-12-06 | 2022-12-06 | Multi-source traffic flow index fusion and road condition calculation method based on fusion index |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115641721B (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 |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104658252A (en) * | 2015-02-10 | 2015-05-27 | 交通运输部科学研究院 | Method for evaluating traffic operational conditions of highway based on multisource data fusion |
CN105489004A (en) * | 2015-11-25 | 2016-04-13 | 杭州电子科技大学 | Gateway and floating vehicle data fusion method for road real-time speed calculation |
CN109308805A (en) * | 2018-08-20 | 2019-02-05 | 广东交通职业技术学院 | A kind of road network MFD estimating and measuring method based on self-adaptive weighted average data fusion |
CN109686090A (en) * | 2019-01-17 | 2019-04-26 | 中南大学 | A kind of virtual traffic method of calculating flux based on multisource data fusion |
CN111724589A (en) * | 2020-06-03 | 2020-09-29 | 重庆大学 | Multi-source data-based highway section flow estimation method |
CN112419712A (en) * | 2020-11-04 | 2021-02-26 | 同盾控股有限公司 | Road section vehicle speed detection method and system |
US20220222556A1 (en) * | 2020-04-30 | 2022-07-14 | Shandong Jiaotong University | Road traffic jam early warning method and system |
CN114999162A (en) * | 2022-08-02 | 2022-09-02 | 北京交研智慧科技有限公司 | Road traffic flow obtaining method and device |
-
2022
- 2022-12-06 CN CN202211554669.6A patent/CN115641721B/en active Active
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104658252A (en) * | 2015-02-10 | 2015-05-27 | 交通运输部科学研究院 | Method for evaluating traffic operational conditions of highway based on multisource data fusion |
CN105489004A (en) * | 2015-11-25 | 2016-04-13 | 杭州电子科技大学 | Gateway and floating vehicle data fusion method for road real-time speed calculation |
CN109308805A (en) * | 2018-08-20 | 2019-02-05 | 广东交通职业技术学院 | A kind of road network MFD estimating and measuring method based on self-adaptive weighted average data fusion |
CN109686090A (en) * | 2019-01-17 | 2019-04-26 | 中南大学 | A kind of virtual traffic method of calculating flux based on multisource data fusion |
US20220222556A1 (en) * | 2020-04-30 | 2022-07-14 | Shandong Jiaotong University | Road traffic jam early warning method and system |
CN111724589A (en) * | 2020-06-03 | 2020-09-29 | 重庆大学 | Multi-source data-based highway section flow estimation method |
CN112419712A (en) * | 2020-11-04 | 2021-02-26 | 同盾控股有限公司 | Road section vehicle speed detection method and system |
CN114999162A (en) * | 2022-08-02 | 2022-09-02 | 北京交研智慧科技有限公司 | Road traffic flow obtaining method and device |
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 |
Also Published As
Publication number | Publication date |
---|---|
CN115641721B (en) | 2023-04-07 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US9564048B2 (en) | Origin destination estimation based on vehicle trajectory data | |
US8392109B2 (en) | Methodology and system for routing optimization in GPS-based Navigation, combining dynamic traffic data | |
CN109544932A (en) | A kind of city road network flow estimation method based on GPS data from taxi Yu bayonet data fusion | |
CN106197458A (en) | A kind of cellphone subscriber's trip mode recognition methods based on mobile phone signaling data and navigation route data | |
US8260532B2 (en) | Traffic probe in-vehicle map-based process to reduce data communications and improve accuracy | |
EP3092462B1 (en) | Methods and systems for detecting a closure of a navigable element | |
CN102622880A (en) | Traffic information data recovery method and device | |
Kianfar et al. | Placement of roadside equipment in connected vehicle environment for travel time estimation | |
EP3671689A1 (en) | Method and apparatus for dynamic speed aggregation of probe data for high-occupancy vehicle lanes | |
Wang et al. | Exploring operating speeds on urban arterials using floating car data: Case study in Shanghai | |
KR101913134B1 (en) | Apparatus for generating lane by lane traffic velocity information in intelligent trasportation system | |
EP3671126A1 (en) | Method, apparatus, and system for providing road closure graph inconsistency resolution | |
CN115641721B (en) | Multi-source traffic flow index fusion and road condition calculation method based on fusion index | |
Oskarbski et al. | Estimating the average speed of public transport vehicles based on traffic control system data | |
CN106469503B (en) | A kind of method and apparatus for predicting traffic events coverage | |
Bogenberger et al. | Quality management methods for real-time traffic information | |
CN110175218A (en) | Generate method, apparatus, equipment and the computer storage medium of navigation casting content | |
CN110211380B (en) | Multisource traffic data fusion expressway congestion interval detection method | |
CN106651061A (en) | Real-time fusion method based on DSRC data and point detector data | |
Gong et al. | Estimating link travel time with sparse GPS data on highway corridors | |
JP6214827B1 (en) | Fuel consumption estimation system, fuel consumption estimation method, and fuel consumption estimation program | |
Han et al. | Spatiotemporal congestion recognition index to evaluate performance under oversaturated conditions | |
Zhu et al. | An evaluation of travel time on urban road network | |
CN111640303A (en) | City commuting path identification method and equipment | |
Xu et al. | Identifying and Tracking Network-Wide Traffic Congestion Based on Mapping-to-Cells Vehicle Trajectory 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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |