CN108010316A - A kind of road traffic multisource data fusion processing method based on road net model - Google Patents
A kind of road traffic multisource data fusion processing method based on road net model Download PDFInfo
- Publication number
- CN108010316A CN108010316A CN201711133277.1A CN201711133277A CN108010316A CN 108010316 A CN108010316 A CN 108010316A CN 201711133277 A CN201711133277 A CN 201711133277A CN 108010316 A CN108010316 A CN 108010316A
- Authority
- CN
- China
- Prior art keywords
- mrow
- road
- munderover
- data
- node
- 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.)
- Withdrawn
Links
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0125—Traffic data processing
Landscapes
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Traffic Control Systems (AREA)
Abstract
A kind of road traffic multisource data fusion processing method based on road net model of the present invention, it is characterised in that comprise the following steps:Road guide figure layer is read, is classified to node-link object, and merges basic road according to classification;Statistics class Vehicle Detection equipment and bicycle class Vehicle Detection equipment are associated with basic road and node-link object;Similar gathered data is merged by identical form and time granularity;The quality of data for counting class Vehicle Detection equipment is handled, and OD distribution is carried out to the data of bicycle class Vehicle Detection equipment;Road section traffic volume parameter is obtained benefit of the invention is that by establishing unified road object division, the unified association of data acquisition object, data quality control processing specification, realizes the fusion treatment of different traffic information system multi-source datas.
Description
Technical field
The present invention relates to a kind of road traffic multisource data fusion processing method based on road net model, belong to intelligent transportation
Applied technical field.
Background technology
City traffic network carry country and urban construction with operating task, and resident's routine work life it is basic
Facility.Increasingly draw the problems such as the traffic congestion of generally existing, traffic safety, traffic pollution and traffic energy consumption in big city
Play the attention of society.Tighten traffic management, relieve traffic congestion just particularly significant for this, and key is that to road traffic parameter
Overall Acquisition, differentiates road traffic operating status and finds road traffic congestion and the origin cause of formation.
Traditional traffic parameter acquisition methods rely on manual research, not only time-consuming and laborious input number that is huge, but also obtaining
Very limited according to species, space-time unique, data accuracy is also difficult to ensure.With the development of intelligent transportation, traffic number is realized
It is Overall Acquisition road grid traffic parameter according to extensive, automation collection, grasps road grid traffic operation situation and provide favourable bar
Part.But each intelligent transportation data model of a urban area is often independently built, and lacks unified data of information system
Specification and processing method, cause each traffic guidance with management information, system acquisition telecommunication flow information to be difficult to merge, and then are formed
The difficult situation that data much can not but efficiently use.
At present multisource data fusion there are the problem of be concentrated mainly on the following aspects:
1) the unified road traffic object criteria for classifying, the often self-defined friendship of oneself of different intelligent transportation systems are lacked
The logical object criteria for classifying, and lack topological link relation between traffic object;
2) each traffic collecting device is associated with customized road traffic object, causes different traffic collecting devices cannot
Direct interconnection;
3) data format disunity, similar traffic collecting device data class, time granularity disunity;
4) there are substantial amounts of fault data, direct application may cause the conclusion of mistake for data;
5) traffic flow model is lacked, Various types of data cannot make full use of, and fusion is unified.
The content of the invention
It is an object of the present invention to provide a kind of multi-source data fusion method suitable for traffic administration.
In order to achieve the above object, the technical scheme is that to provide a kind of road traffic based on road net model more
Source data method for amalgamation processing, it is characterised in that comprise the following steps:
The first step, read road guide figure layer, classifies to node-link object, and closes basic road according to classification
And;
Second step, traffic collecting device include statistics class Vehicle Detection equipment and bicycle class Vehicle Detection equipment, will count
Class Vehicle Detection equipment and bicycle class Vehicle Detection equipment are associated with basic road and node-link object;
3rd step, the data characteristics according to traffic collecting device, identical form and time are pressed by similar gathered data
Granularity merges;
4th step, handle the quality of data for counting class Vehicle Detection equipment, and to bicycle class Vehicle Detection equipment
Data carry out OD distribution, wherein:
Processing is carried out to the quality of data for counting class Vehicle Detection equipment to comprise the following steps:
Step a1, according to the gathered data feature of statistics class Vehicle Detection equipment, set and be used to know abnormal data
Other decision rule;
Step a2, the decision rule set to mass historical data according to step a1 differentiate by day, filters out normal
Data, based on normal data and spatial neighborhood relations, demarcate adjacent lane traffic parameter correlation;
Step a3, the decision rule based on step a1 settings carries out quality discrimination to real time data, for being determined as exception
Data, the correlation of valid data based on the adjacent lane obtained in real time and step a2 calibration repaired;
Data progress OD distribution to bicycle class Vehicle Detection equipment comprises the following steps:
Step b1, car record is crossed based on vehicle, trip track is ranked up by vehicle, elapsed time, it is special with reference to trip
Sign sets out between-line spacing, and identification bicycle trip tracing point and OD, statistics obtain region OD;
Step b2, based on region OD origin and destination, with basic road, node-link object and rule search OD the beginning and the end are turned to
Point shortest path section set;
Step b3, gathered with shortest path section, regional OD is separately dispensed into path and corresponds to basic road;
Step b4, each OD flows in basic road are counted, obtain link flow;
5th step, the statistics class detection device data modification result differentiated based on the quality of data and bicycle class OD distribution knots
Fruit merges to obtain road section traffic volume parameter, specifically includes:
Step 5.1, the statistics class detection device data modification result calculating link flow and row differentiated based on the quality of data
Journey speed;
Step 5.2, fusion link flow and travel speed.
Preferably, the first step includes:
Step 1.1, read road guide figure layer, reads node figure layer and basic road figure layer, reads node and basic road
Section incidence relation, obtains the category of roads of basic road associated by node, classifies to node type, is divided into road intercommunication friendship
Prong, cell entrance, ring road division flow point, track change point, wherein road intercommunication intersection and ring road division flow point are road
Section interrupts a little, cell entrance and track change point position subsections mergence point;
Step 1.2, according to basic road upstream and downstream combination of nodes type, classify to basic road, be divided into:Starting
Section, i.e., starting point node is that point is interrupted in section, terminal section is subsections mergence point;Interlude, i.e. starting point node for subsections mergence point,
Peripheral node is subsections mergence point;Termination section, i.e. starting point node are subsections mergence point, peripheral node is that section is interrupted a little;Section,
I.e. starting point node interrupts a little for section, and peripheral node interrupts a little for section;
Step 1.3, obtain the basic road that type is the initial segment, and downstream straight trip base is searched according to basic road downstream node
This section, if tract is terminates section, poll-final, the basic segment that Fusion query arrives, if tract is interlude, weighs
Duplicate step;
Step 1.4, based on basic road and node relationships, generation basic road to the feasible steering of downstream road section theory
System, with reference to actual intersection rule, is marked the actual connectivity for turning to relation.
Preferably, the second step includes:
Step 2.1, read information system segmentation figure layer, based on basic road and segmentation geometric position, to basic road and
Segmentation correspondence is identified, and establishes basic road and segmentation correspondence, and segmentation ID and attribute are copied to basic road;
Step 2.2, based on traffic collecting device, facility, traffic events, road construction with segmentation incidence relation, establish road
Section and equipment, facility, traffic events and the incidence relation of road construction.
Preferably, in the 4th step, adjacent lane traffic parameter correlation includes adjacent windings relevance parameter, should
The extracting method of adjacent windings relevance parameter includes:
Correlation of the target coil between coil within the scope of the same travel direction interval 2km of road is calculated, as mesh
The data modification source of loop data repairing is marked, note target coil traffic parameter is X (i, t, d), and adjacent windings traffic parameter is Y
(i, t, d), in formula, i represents coil numbering, and t represents process cycle, and d represents the date, and correlation uses parameter a, b, R2Represent,
Slope, intercept and the related coefficient of linear equations are represented respectively, then are had:
In formula, m represents the number of days for having data in statistical interval.
Preferably, in the 4th step, when being repaired, adjacent lane method for repairing and mending comprises the following steps:
If it is invalid or missing data that x (i, t, d) is corresponding,It is that the history identical with d days date types is same
Phase traffic parameter average, in formula, k represents date type,It is j-th of coil linear estimate, RjIt is j-th of coil
Related coefficient,It is the average of multiple adjacent windings linear estimates, λ (i, t, d) is weighting weight, utilizes following public affairs
Formula repairs the corresponding data of x (i, t, d):
In formula, R (i, t, d) represents the related coefficient after fusion.
Benefit of the invention is that divided by establishing unified road object, the unification of data acquisition object associates, data
Quality control treatments specification, realizes the fusion treatment of different traffic information system multi-source datas.
Brief description of the drawings
Fig. 1 is overall process flow;
Fig. 2 is navigation figure layer process flow;
Fig. 3 associates section flow for Vehicle Detection equipment;
Fig. 4 is traffic gathered data standardized format flow;
Fig. 5 repairs flow for the quality of data;
Fig. 6 is quality of data entirety discriminant parameter;
Fig. 7 extracts for relevance parameter;
Fig. 8 is flow repair efficiency;
Fig. 9 is extracted for OD and allocation flow;
Figure 10 is data fusion flow.
Embodiment
To make the present invention more aobvious understandable, elaborate below in conjunction with the accompanying drawings to the embodiment of the present invention:The present embodiment exists
Implemented under technical solution of the present invention, give the implementation process and implementation result of the present invention.Protection scope of the present invention is not
It is limited to following embodiments.
The present invention provides a kind of road traffic multisource data fusion processing method based on road net model, including following step
Suddenly:
The first step, read road guide figure layer, classifies to node-link object, and closes basic road according to classification
And including:
Step 1.1, read road guide figure layer, reads node figure layer and basic road figure layer, reads node and basic road
Section incidence relation, obtains the category of roads of basic road associated by node, classifies to node type, is divided into road intercommunication friendship
Prong, cell entrance, ring road division flow point, track change point, wherein road intercommunication intersection and ring road division flow point are road
Section interrupts a little, cell entrance and track change point position subsections mergence point;
Step 1.2, according to basic road upstream and downstream combination of nodes type, classify to basic road, be divided into:Starting
Section, i.e., starting point node is that point is interrupted in section, terminal section is subsections mergence point;Interlude, i.e. starting point node for subsections mergence point,
Peripheral node is subsections mergence point;Termination section, i.e. starting point node are subsections mergence point, peripheral node is that section is interrupted a little;Section,
I.e. starting point node interrupts a little for section, and peripheral node interrupts a little for section;
Step 1.3, obtain the basic road that type is the initial segment, and downstream straight trip base is searched according to basic road downstream node
This section, if tract is terminates section, poll-final, the basic segment that Fusion query arrives, if tract is interlude, weighs
Duplicate step;
Step 1.4, based on basic road and node relationships, generation basic road to the feasible steering of downstream road section theory
System, with reference to actual intersection rule, is marked the actual connectivity for turning to relation.
Second step, traffic collecting device include statistics class Vehicle Detection equipment and bicycle class Vehicle Detection equipment, will count
Class Vehicle Detection equipment and bicycle class Vehicle Detection equipment are associated with basic road and node-link object, including:
Step 2.1, read information system segmentation figure layer, based on basic road and segmentation geometric position, to basic road and
Segmentation correspondence is identified, and establishes basic road and segmentation correspondence, and segmentation ID and attribute are copied to basic road;
Step 2.2, based on traffic collecting device, facility, traffic events, road construction with segmentation incidence relation, establish road
Section and equipment, facility, traffic events and the incidence relation of road construction.
3rd step, the data characteristics according to traffic collecting device, identical form and time are pressed by similar gathered data
Granularity merges.The step is conducive to the unification of gathered data form and provides basis for fusion treatment, specifically includes various
The unification of vehicle fixed class collecting device data format and the unification of time granularity, data format containing device numbering, timestamp,
Total flow, speed, occupation rate, each vehicle flow etc..
4th step, handle the quality of data for counting class Vehicle Detection equipment, and to bicycle class Vehicle Detection equipment
Data carry out OD distribution, wherein:
To count class Vehicle Detection equipment the quality of data carry out processing include the quality of data differentiate, relevant parameter demarcate and
Repairing, comprises the following steps:
Step a1, according to the gathered data feature of statistics class Vehicle Detection equipment, set and be used to know abnormal data
Other decision rule.
1) twin coil entirety decision rule
2) unicoil entirety decision rule
3) twin coil wall scroll discriminating data rule
4) single latitude circle wall scroll discriminating data rule
5) adjacent lane decision rule
Step a2, the decision rule set to mass historical data according to step a1 differentiate by day, filters out normal
Data, based on normal data and spatial neighborhood relations, demarcate adjacent lane traffic parameter correlation.
Adjacent lane traffic parameter correlation includes adjacent windings relevance parameter, which carries
Method is taken to include:
Correlation of the target coil between coil within the scope of the same travel direction interval 2km of road is calculated, as mesh
The data modification source of loop data repairing is marked, note target coil traffic parameter is X (i, t, d), and adjacent windings traffic parameter is Y
(i, t, d), in formula, i represents coil numbering, and t represents process cycle, and d represents the date, and correlation uses parameter a, b, R2Represent,
Slope, intercept and the related coefficient of linear equations are represented respectively, then are had:
In formula, m represents the number of days for having data in statistical interval.
Step a3, the decision rule based on step a1 settings carries out quality discrimination to real time data, for being determined as exception
Data, the correlation of valid data based on the adjacent lane obtained in real time and step a2 calibration repaired.
When being repaired, adjacent lane method for repairing and mending comprises the following steps:
If it is invalid or missing data that x (i, t, d) is corresponding,It is that the history identical with d days date types is same
Phase traffic parameter average, in formula, k represents date type,It is j-th of coil linear estimate, RjIt is j-th of coil
Related coefficient,It is the average of multiple adjacent windings linear estimates, λ (i, t, d) is weighting weight, utilizes following public affairs
Formula repairs the corresponding data of x (i, t, d):
In formula, R (i, t, d) represents the related coefficient after fusion.
Data progress OD distribution to bicycle class Vehicle Detection equipment comprises the following steps:
Step b1, car record is crossed based on vehicle, trip track is ranked up by vehicle, elapsed time, it is special with reference to trip
Sign sets out between-line spacing, and identification bicycle trip tracing point and OD, statistics obtain region OD;
Step b2, based on region OD origin and destination, with basic road, node-link object and rule search OD the beginning and the end are turned to
Point shortest path section set;
Step b3, gathered with shortest path section, regional OD is separately dispensed into path and corresponds to basic road;
Step b4, each OD flows in basic road are counted, obtain link flow.
5th step, the statistics class detection device data modification result differentiated based on the quality of data and bicycle class OD distribution knots
Fruit merges to obtain road section traffic volume parameter, specifically includes:
Step 5.1, the statistics class detection device data modification result calculating link flow and row differentiated based on the quality of data
Journey speed;
Step 5.2, fusion link flow and travel speed.
Section includes multiple sections, and link flow is equal to cross sections flow and data reliability weighted average, section car
Speed is equal to road section length/(section speed where segment length/segment).Segment rises according to midpoint and section between detection section
Terminal divides.
Fig. 1 show the 6 big modules that the present invention includes, section and node generation module and carries out processing generation to navigation figure layer
The road object of standardization, Vehicle Detection equipment are associated with road object, traffic gathered data standardized format, quality of data control
System, OD matchings and distribution, road section traffic volume Parameter fusion.
Fig. 2 show present invention navigation figure layer generation section and node module flow chart.The step first divides node
Class, is divided into four major classes:Intercommunication intersection, cell entrance, ring road division flow point, track change point, wherein intercommunication intersection is
More than three main ground Road Base this section crosspoint, cell entrance is ground main roads basic segment and cell Road Base
This section of crosspoint, ring road division flow point are two continuous stream basic roads and ring road basic road crosspoint, track change point position
Two basic road crosspoints.For example, node 1 associate basic road 11871,37179,130624,8567,227,
336807th, 4,3388, basic road road type is all mainly face road, then node type is " ground intersection ", such as
" cell entrance " is included in fruit basic road, then node type is " cell entrance ".After class has been divided to node, by base
This subsections mergence is section, if it is cell entrance to merge rule to belong to the adjacent basic road intermediate node of same road
Then merged with track change point.For example, basic road 111 and basic road 112 belong to road 1173, basic road
Section 111 is the upstream adjacent segments of basic road 112, and the downstream node of basic road 111 and the upstream node of basic road are all
For 1003,1003 be cell entrance, then merges operation to basic road 111 and basic road 112.Road is obtained in merging
Duan Hou, issues section by intelligent transportation system and section is associated according to spatial relationship, establish issue section and section contrast relationship.
Fig. 3 is associated with section flow for Vehicle Detection equipment.To issue section and section contrast relationship as medium, traffic is realized
Detection device associated road section.For example, device A is associated with issue section B, issue section B association section C, then device A associates
Section C.
Fig. 4 is traffic gathered data standardized format flow, realizes all kinds of statistics class traffic gathered data standardized formats.
Fig. 5 repairs flow for the quality of data.First parameter is set, parameter setting is mainly to wanted data initial data
Table, coil fault identification parameter and repairing weight are set.Enter offline parameter extraction module after the completion of parameter setting.Again
Offline parameter is extracted, the Each point in time that off-line data extraction is classified first with historical data extraction coil according to date type
Traffic parameter Distribution Value, specific result of calculation are shown in Fig. 6.Recycle the correlation system between correlation calculations formulas Extraction coil
Number, is shown in Fig. 7.It is invalid and scarce by history same period Distribution Value in historical data real time data correcting module and adjacent windings Data-parallel language
The patch algorithm for losing data obtains correction value, is worth result to be weighted the two according still further to the weight of setting, has obtained
Whole effective data, repair efficiency are shown in Fig. 8.
Fig. 9 is matched and distributed for OD.OD division rules are first set, determine start and end time interval of once going on a journey.Again
Recorded according to bicycle, bicycle is ranked up with the elapsed time, recording status is carried out based on front and rear two record time intervals
Differentiate, be divided into and occur starting, continue and terminating, bicycle travelling OD is divided.According to the bicycle OD statistical regions OD of acquisition,
And with search shortest path in terminus section where region, by Regional OD traffic flow be assigned to by section.Pass through section of adding up
The regional OD flows of process obtain section total flow.
Figure 10 is data fusion flow.The multi-source result obtained to section merges.
Claims (5)
1. a kind of road traffic multisource data fusion processing method based on road net model, it is characterised in that comprise the following steps:
The first step, read road guide figure layer, classifies to node-link object, and merges basic road according to classification;
Second step, traffic collecting device include statistics class Vehicle Detection equipment and bicycle class Vehicle Detection equipment, and statistics class is handed over
Logical detection device and bicycle class Vehicle Detection equipment are associated with basic road and node-link object;
3rd step, the data characteristics according to traffic collecting device, identical form and time granularity are pressed by similar gathered data
Merge;
4th step, handle the quality of data for counting class Vehicle Detection equipment, and to the number of bicycle class Vehicle Detection equipment
According to progress OD distribution, wherein:
Processing is carried out to the quality of data for counting class Vehicle Detection equipment to comprise the following steps:
Step a1, according to the gathered data feature of statistics class Vehicle Detection equipment, set and be used for what abnormal data was identified
Decision rule;
Step a2, the decision rule set to mass historical data according to step a1 differentiate by day, filters out normal data,
Based on normal data and spatial neighborhood relations, adjacent lane traffic parameter correlation is demarcated:
Step a3, the decision rule based on step a1 settings carries out quality discrimination to real time data, for being determined as abnormal number
According to the correlation of valid data and step a2 calibration based on the adjacent lane obtained in real time is repaired;
Data progress OD distribution to bicycle class Vehicle Detection equipment comprises the following steps:
Step b1, car record is crossed based on vehicle, trip track is ranked up by vehicle, elapsed time, is set with reference to trip characteristics
Between-line spacing is put out, identification bicycle trip tracing point and OD, statistics obtain region OD;
Step b2, based on region OD origin and destination, with basic road, node-link object and rule search OD origin and destination are turned to most
Gather in short path section;
Step b3, gathered with shortest path section, regional OD is separately dispensed into path and corresponds to basic road;
Step b4, each OD flows in basic road are counted, obtain link flow;
5th step, the statistics class detection device data modification result differentiated based on the quality of data and bicycle class OD allocation results are melted
Conjunction obtains road section traffic volume parameter, specifically includes:
Step 5.1, the statistics class detection device data modification result calculating link flow and travel vehicle differentiated based on the quality of data
Speed;
Step 5.2, fusion link flow and travel speed.
2. a kind of road traffic multisource data fusion processing method based on road net model as claimed in claim 1, its feature
It is, the first step includes:
Step 1.1, read road guide figure layer, reads node figure layer and basic road figure layer, reads node and is closed with basic road
Connection relation, obtains the category of roads of basic road associated by node, classifies to node type, is divided into road intercommunication intersection
Mouth, cell entrance, ring road division flow point, track change point, wherein road intercommunication intersection and ring road division flow point are section
Interrupt a little, cell entrance and track change point position subsections mergence point;
Step 1.2, according to basic road upstream and downstream combination of nodes type, classify to basic road, be divided into:The initial segment, i.e.,
Starting point node is that point is interrupted in section, terminal section is subsections mergence point;Interlude, i.e. starting point node are subsections mergence point, terminal
Node is subsections mergence point;Termination section, i.e. starting point node are subsections mergence point, peripheral node is that section is interrupted a little;Section, that is, rise
Point node interrupts a little for section, and peripheral node interrupts a little for section;
Step 1.3, obtain the basic road that type is the initial segment, and it is basic to search downstream straight trip according to basic road downstream node
Section, if tract is terminates section, poll-final, the basic segment that Fusion query arrives, if tract is interlude, repeats
This step;
Step 1.4, based on basic road and node relationships, generation basic road to the feasible steering relation of downstream road section theory,
With reference to actual intersection rule, the actual connectivity for turning to relation is marked.
3. a kind of road traffic multisource data fusion processing method based on road net model as claimed in claim 1, its feature
It is, the second step includes:
Step 2.1, read information system segmentation figure layer, based on basic road and segmentation geometric position, to basic road and segmentation
Correspondence is identified, and establishes basic road and segmentation correspondence, and segmentation ID and attribute are copied to basic road;
Step 2.2, based on traffic collecting device, facility, traffic events, road construction with segmentation incidence relation, establish section and
Equipment, facility, traffic events and the incidence relation of road construction.
4. a kind of road traffic multisource data fusion processing method based on road net model as claimed in claim 1, its feature
It is, in the 4th step, adjacent lane traffic parameter correlation includes adjacent windings relevance parameter, the adjacent windings phase
The extracting method of closing property parameter includes:
Correlation of the target coil between coil within the scope of the same travel direction interval 2km of road is calculated, as score
Enclose the data modification source of data modification, note target coil traffic parameter be X (i, t, d), adjacent windings traffic parameter be Y (i, t,
D), in formula, i represents coil numbering, and t represents process cycle, and d represents the date, and correlation uses parameter a, b, R2Represent, respectively generation
Slope, intercept and the related coefficient of table linear equations, then have:
<mrow>
<mi>a</mi>
<mo>=</mo>
<mo>&lsqb;</mo>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>i</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>n</mi>
</munderover>
<mi>X</mi>
<mrow>
<mo>(</mo>
<mi>i</mi>
<mo>,</mo>
<mi>t</mi>
<mo>,</mo>
<mi>d</mi>
<mo>)</mo>
</mrow>
<mi>Y</mi>
<mrow>
<mo>(</mo>
<mi>i</mi>
<mo>,</mo>
<mi>t</mi>
<mo>,</mo>
<mi>d</mi>
<mo>)</mo>
</mrow>
<mo>-</mo>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>i</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>n</mi>
</munderover>
<mi>X</mi>
<mrow>
<mo>(</mo>
<mi>i</mi>
<mo>,</mo>
<mi>t</mi>
<mo>,</mo>
<mi>d</mi>
<mo>)</mo>
</mrow>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>i</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>n</mi>
</munderover>
<mi>Y</mi>
<mrow>
<mo>(</mo>
<mi>i</mi>
<mo>,</mo>
<mi>t</mi>
<mo>,</mo>
<mi>d</mi>
<mo>)</mo>
</mrow>
<mo>&rsqb;</mo>
<mo>/</mo>
<mo>&lsqb;</mo>
<mrow>
<mo>(</mo>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>i</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>n</mi>
</munderover>
<mi>X</mi>
<msup>
<mrow>
<mo>(</mo>
<mrow>
<mi>i</mi>
<mo>,</mo>
<mi>t</mi>
<mo>,</mo>
<mi>d</mi>
</mrow>
<mo>)</mo>
</mrow>
<mn>2</mn>
</msup>
<mo>-</mo>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>i</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>n</mi>
</munderover>
<mi>Y</mi>
<msup>
<mrow>
<mo>(</mo>
<mrow>
<mi>i</mi>
<mo>,</mo>
<mi>t</mi>
<mo>,</mo>
<mi>d</mi>
</mrow>
<mo>)</mo>
</mrow>
<mn>2</mn>
</msup>
<mo>)</mo>
</mrow>
<mo>/</mo>
<mi>n</mi>
<mo>&rsqb;</mo>
</mrow>
<mrow>
<mi>b</mi>
<mo>=</mo>
<mfrac>
<mrow>
<mo>(</mo>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>i</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>n</mi>
</munderover>
<mi>Y</mi>
<mo>(</mo>
<mrow>
<mi>i</mi>
<mo>,</mo>
<mi>t</mi>
<mo>,</mo>
<mi>d</mi>
</mrow>
<mo>)</mo>
<mo>/</mo>
<mi>m</mi>
<mo>-</mo>
<mi>a</mi>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>i</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>n</mi>
</munderover>
<mi>X</mi>
<mrow>
<mo>(</mo>
<mrow>
<mi>i</mi>
<mo>,</mo>
<mi>t</mi>
<mo>,</mo>
<mi>d</mi>
</mrow>
<mo>)</mo>
</mrow>
<mo>)</mo>
</mrow>
<mi>n</mi>
</mfrac>
</mrow>
<mrow>
<mi>R</mi>
<mo>=</mo>
<mfrac>
<mrow>
<mo>&lsqb;</mo>
<mrow>
<munderover>
<mi>&Sigma;</mi>
<mrow>
<mi>i</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>n</mi>
</munderover>
<mi>X</mi>
<mrow>
<mo>(</mo>
<mrow>
<mi>i</mi>
<mo>,</mo>
<mi>t</mi>
<mo>,</mo>
<mi>d</mi>
</mrow>
<mo>)</mo>
</mrow>
<mi>Y</mi>
<mrow>
<mo>(</mo>
<mrow>
<mi>i</mi>
<mo>,</mo>
<mi>t</mi>
<mo>,</mo>
<mi>d</mi>
</mrow>
<mo>)</mo>
</mrow>
<mo>-</mo>
<munderover>
<mi>&Sigma;</mi>
<mrow>
<mi>i</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>n</mi>
</munderover>
<mi>X</mi>
<mrow>
<mo>(</mo>
<mrow>
<mi>i</mi>
<mo>,</mo>
<mi>t</mi>
<mo>,</mo>
<mi>d</mi>
</mrow>
<mo>)</mo>
</mrow>
<munderover>
<mi>&Sigma;</mi>
<mrow>
<mi>i</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>n</mi>
</munderover>
<mi>Y</mi>
<mrow>
<mo>(</mo>
<mrow>
<mi>i</mi>
<mo>,</mo>
<mi>t</mi>
<mo>,</mo>
<mi>d</mi>
</mrow>
<mo>)</mo>
</mrow>
<mo>/</mo>
<mi>n</mi>
</mrow>
<mo>&rsqb;</mo>
</mrow>
<msqrt>
<mrow>
<mo>&lsqb;</mo>
<munderover>
<mi>&Sigma;</mi>
<mrow>
<mi>i</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>n</mi>
</munderover>
<mi>X</mi>
<msup>
<mrow>
<mo>(</mo>
<mi>i</mi>
<mo>,</mo>
<mi>t</mi>
<mo>,</mo>
<mi>d</mi>
<mo>)</mo>
</mrow>
<mn>2</mn>
</msup>
<mo>-</mo>
<munderover>
<mi>&Sigma;</mi>
<mrow>
<mi>i</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>n</mi>
</munderover>
<mi>X</mi>
<msup>
<mrow>
<mo>(</mo>
<mi>i</mi>
<mo>,</mo>
<mi>t</mi>
<mo>,</mo>
<mi>d</mi>
<mo>)</mo>
</mrow>
<mn>2</mn>
</msup>
<mo>/</mo>
<mi>n</mi>
<mo>&rsqb;</mo>
<mo>&lsqb;</mo>
<munderover>
<mi>&Sigma;</mi>
<mrow>
<mi>i</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>n</mi>
</munderover>
<mi>Y</mi>
<msup>
<mrow>
<mo>(</mo>
<mrow>
<mi>i</mi>
<mo>,</mo>
<mi>t</mi>
<mo>,</mo>
<mi>d</mi>
</mrow>
<mo>)</mo>
</mrow>
<mn>2</mn>
</msup>
<mo>)</mo>
<mo>-</mo>
<munderover>
<mi>&Sigma;</mi>
<mrow>
<mi>i</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>n</mi>
</munderover>
<mi>Y</mi>
<msup>
<mrow>
<mo>(</mo>
<mrow>
<mi>i</mi>
<mo>,</mo>
<mi>t</mi>
<mo>,</mo>
<mi>d</mi>
</mrow>
<mo>)</mo>
</mrow>
<mn>2</mn>
</msup>
<mo>)</mo>
<mo>/</mo>
<mi>n</mi>
<mo>&rsqb;</mo>
</mrow>
</msqrt>
</mfrac>
</mrow>
In formula, m represents the number of days for having data in statistical interval.
5. a kind of road traffic multisource data fusion processing method based on road net model as claimed in claim 1, its feature
It is, in the 4th step, when being repaired, adjacent lane method for repairing and mending comprises the following steps:
If it is invalid or missing data that x (i, t, d) is corresponding,It is to hand over the history same period identical with d days date types
Logical mean parameter, in formula, k represents date type,It is j-th of coil linear estimate, RjIt is the phase of j-th of coil
Relation number,It is the average of multiple adjacent windings linear estimates, λ (i, t, d) is weighting weight, utilizes the following formula pair
The corresponding data of x (i, t, d) are repaired:
<mrow>
<mover>
<mi>x</mi>
<mo>^</mo>
</mover>
<mrow>
<mo>(</mo>
<mi>i</mi>
<mo>,</mo>
<mi>t</mi>
<mo>,</mo>
<mi>d</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>j</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>m</mi>
</munderover>
<msub>
<mover>
<mi>x</mi>
<mo>^</mo>
</mover>
<mi>j</mi>
</msub>
<mrow>
<mo>(</mo>
<mi>i</mi>
<mo>,</mo>
<mi>t</mi>
<mo>,</mo>
<mi>d</mi>
<mo>)</mo>
</mrow>
<msub>
<mi>R</mi>
<mi>j</mi>
</msub>
<mo>/</mo>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>j</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>m</mi>
</munderover>
<msub>
<mi>R</mi>
<mi>j</mi>
</msub>
</mrow>
<mrow>
<mi>R</mi>
<mrow>
<mo>(</mo>
<mi>i</mi>
<mo>,</mo>
<mi>t</mi>
<mo>,</mo>
<mi>d</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>j</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>m</mi>
</munderover>
<msub>
<mi>R</mi>
<mi>j</mi>
</msub>
<mo>/</mo>
<mi>m</mi>
</mrow>
In formula, R (i, t, d) represents the related coefficient after fusion.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711133277.1A CN108010316A (en) | 2017-11-15 | 2017-11-15 | A kind of road traffic multisource data fusion processing method based on road net model |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711133277.1A CN108010316A (en) | 2017-11-15 | 2017-11-15 | A kind of road traffic multisource data fusion processing method based on road net model |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108010316A true CN108010316A (en) | 2018-05-08 |
Family
ID=62052507
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711133277.1A Withdrawn CN108010316A (en) | 2017-11-15 | 2017-11-15 | A kind of road traffic multisource data fusion processing method based on road net model |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108010316A (en) |
Cited By (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108960428A (en) * | 2018-06-22 | 2018-12-07 | 北京易华录信息技术股份有限公司 | A kind of road network operation construction of knowledge base method based on artificial intelligence technology |
CN109101743A (en) * | 2018-08-28 | 2018-12-28 | 武汉市众向科技有限公司 | A kind of construction method of high-precision road net model |
CN109540164A (en) * | 2018-11-22 | 2019-03-29 | 广州小狗机器人技术有限公司 | A kind of paths planning method, system and equipment |
CN110097756A (en) * | 2019-05-07 | 2019-08-06 | 四川咖范网络科技有限公司 | Intelligent traffic administration system method based on multisource data fusion technology |
CN110399364A (en) * | 2019-07-11 | 2019-11-01 | 北京航空航天大学 | A kind of data fusion method based on a variety of highway detector datas |
CN110823234A (en) * | 2018-08-10 | 2020-02-21 | 北京搜狗科技发展有限公司 | Data processing method and device and electronic equipment |
CN111275965A (en) * | 2020-01-20 | 2020-06-12 | 交通运输部科学研究院 | Real-time traffic simulation analysis system and method based on internet big data |
WO2020135141A1 (en) * | 2018-12-29 | 2020-07-02 | 阿里巴巴集团控股有限公司 | Traffic road network description method and device |
CN111435450A (en) * | 2019-01-11 | 2020-07-21 | 阿里巴巴集团控股有限公司 | Road data processing method and device |
CN111613046A (en) * | 2019-02-26 | 2020-09-01 | 阿里巴巴集团控股有限公司 | Information processing method, device and system |
CN111862588A (en) * | 2019-12-18 | 2020-10-30 | 北京嘀嘀无限科技发展有限公司 | Method and device for controlling information release, electronic equipment and storage medium |
CN112258835A (en) * | 2020-09-29 | 2021-01-22 | 航天科工广信智能技术有限公司 | Intelligent traffic system based on cloud side end fusion technology |
CN113742330A (en) * | 2021-09-18 | 2021-12-03 | 广州交信投科技股份有限公司 | Multidimensional transportation data fusion and data quality detection method |
CN114020860A (en) * | 2021-12-28 | 2022-02-08 | 北京市智慧交通发展中心(北京市机动车调控管理事务中心) | Heterogeneous road data fusion method and system |
CN114387410A (en) * | 2021-12-10 | 2022-04-22 | 阿波罗智能技术(北京)有限公司 | Road data fusion map generation method and device and electronic equipment |
CN114973641A (en) * | 2021-02-26 | 2022-08-30 | 阿里巴巴集团控股有限公司 | Data processing method and device, electronic equipment and readable storage medium |
CN115037629A (en) * | 2022-03-02 | 2022-09-09 | 电子科技大学长三角研究院(湖州) | Network multi-propagation source selection method based on ring structure |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101546478A (en) * | 2009-04-29 | 2009-09-30 | 上海电器科学研究所(集团)有限公司 | Traffic flow integrated and distributed analytic system based on license plate identification data and processing method thereof |
CN101571997A (en) * | 2009-05-31 | 2009-11-04 | 上海宝康电子控制工程有限公司 | Method and device for fusion processing of multi-source traffic information |
CN101783069A (en) * | 2009-12-29 | 2010-07-21 | 北京世纪高通科技有限公司 | Traffic information fusion processing method and system |
CN101930668A (en) * | 2009-04-29 | 2010-12-29 | 上海电器科学研究所(集团)有限公司 | Road traffic OD (Optical Density) information collection system for license plate recognition and processing method thereof |
DE102010021666A1 (en) * | 2010-05-26 | 2011-01-05 | Daimler Ag | Method for dynamic data fusion of vehicle-related traffic information on express highways, involves verifying, changing or disabling output of traffic message channel traffic signal information based on data fusion result |
CN102169630A (en) * | 2011-03-31 | 2011-08-31 | 上海电科智能系统股份有限公司 | Quality control method of road continuous traffic flow data |
CN103646187B (en) * | 2013-12-27 | 2017-02-08 | 中国科学院自动化研究所 | Method for obtaining vehicle travel path and OD (Origin-Destination) matrix in statistic period |
CN106846805A (en) * | 2017-03-06 | 2017-06-13 | 南京多伦科技股份有限公司 | A kind of dynamic road grid traffic needing forecasting method and its system |
-
2017
- 2017-11-15 CN CN201711133277.1A patent/CN108010316A/en not_active Withdrawn
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101546478A (en) * | 2009-04-29 | 2009-09-30 | 上海电器科学研究所(集团)有限公司 | Traffic flow integrated and distributed analytic system based on license plate identification data and processing method thereof |
CN101930668A (en) * | 2009-04-29 | 2010-12-29 | 上海电器科学研究所(集团)有限公司 | Road traffic OD (Optical Density) information collection system for license plate recognition and processing method thereof |
CN101571997A (en) * | 2009-05-31 | 2009-11-04 | 上海宝康电子控制工程有限公司 | Method and device for fusion processing of multi-source traffic information |
CN101783069A (en) * | 2009-12-29 | 2010-07-21 | 北京世纪高通科技有限公司 | Traffic information fusion processing method and system |
DE102010021666A1 (en) * | 2010-05-26 | 2011-01-05 | Daimler Ag | Method for dynamic data fusion of vehicle-related traffic information on express highways, involves verifying, changing or disabling output of traffic message channel traffic signal information based on data fusion result |
CN102169630A (en) * | 2011-03-31 | 2011-08-31 | 上海电科智能系统股份有限公司 | Quality control method of road continuous traffic flow data |
CN103646187B (en) * | 2013-12-27 | 2017-02-08 | 中国科学院自动化研究所 | Method for obtaining vehicle travel path and OD (Origin-Destination) matrix in statistic period |
CN106846805A (en) * | 2017-03-06 | 2017-06-13 | 南京多伦科技股份有限公司 | A kind of dynamic road grid traffic needing forecasting method and its system |
Cited By (24)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108960428A (en) * | 2018-06-22 | 2018-12-07 | 北京易华录信息技术股份有限公司 | A kind of road network operation construction of knowledge base method based on artificial intelligence technology |
CN110823234A (en) * | 2018-08-10 | 2020-02-21 | 北京搜狗科技发展有限公司 | Data processing method and device and electronic equipment |
CN109101743A (en) * | 2018-08-28 | 2018-12-28 | 武汉市众向科技有限公司 | A kind of construction method of high-precision road net model |
CN109101743B (en) * | 2018-08-28 | 2023-01-17 | 武汉市众向科技有限公司 | Method for constructing high-precision road network model |
CN109540164A (en) * | 2018-11-22 | 2019-03-29 | 广州小狗机器人技术有限公司 | A kind of paths planning method, system and equipment |
WO2020135141A1 (en) * | 2018-12-29 | 2020-07-02 | 阿里巴巴集团控股有限公司 | Traffic road network description method and device |
CN111383450A (en) * | 2018-12-29 | 2020-07-07 | 阿里巴巴集团控股有限公司 | Traffic network description method and device |
CN111435450A (en) * | 2019-01-11 | 2020-07-21 | 阿里巴巴集团控股有限公司 | Road data processing method and device |
CN111613046A (en) * | 2019-02-26 | 2020-09-01 | 阿里巴巴集团控股有限公司 | Information processing method, device and system |
CN110097756B (en) * | 2019-05-07 | 2021-10-15 | 四川咖范网络科技有限公司 | Intelligent traffic management method based on multi-source data fusion technology |
CN110097756A (en) * | 2019-05-07 | 2019-08-06 | 四川咖范网络科技有限公司 | Intelligent traffic administration system method based on multisource data fusion technology |
CN110399364A (en) * | 2019-07-11 | 2019-11-01 | 北京航空航天大学 | A kind of data fusion method based on a variety of highway detector datas |
CN111862588A (en) * | 2019-12-18 | 2020-10-30 | 北京嘀嘀无限科技发展有限公司 | Method and device for controlling information release, electronic equipment and storage medium |
CN111862588B (en) * | 2019-12-18 | 2022-04-22 | 北京嘀嘀无限科技发展有限公司 | Method and device for controlling information release, electronic equipment and storage medium |
CN111275965A (en) * | 2020-01-20 | 2020-06-12 | 交通运输部科学研究院 | Real-time traffic simulation analysis system and method based on internet big data |
CN111275965B (en) * | 2020-01-20 | 2021-02-05 | 交通运输部科学研究院 | Real-time traffic simulation analysis system and method based on internet big data |
CN112258835A (en) * | 2020-09-29 | 2021-01-22 | 航天科工广信智能技术有限公司 | Intelligent traffic system based on cloud side end fusion technology |
CN114973641A (en) * | 2021-02-26 | 2022-08-30 | 阿里巴巴集团控股有限公司 | Data processing method and device, electronic equipment and readable storage medium |
CN114973641B (en) * | 2021-02-26 | 2024-05-07 | 阿里巴巴集团控股有限公司 | Data processing method, device, electronic equipment and readable storage medium |
CN113742330A (en) * | 2021-09-18 | 2021-12-03 | 广州交信投科技股份有限公司 | Multidimensional transportation data fusion and data quality detection method |
CN114387410A (en) * | 2021-12-10 | 2022-04-22 | 阿波罗智能技术(北京)有限公司 | Road data fusion map generation method and device and electronic equipment |
CN114020860A (en) * | 2021-12-28 | 2022-02-08 | 北京市智慧交通发展中心(北京市机动车调控管理事务中心) | Heterogeneous road data fusion method and system |
CN115037629A (en) * | 2022-03-02 | 2022-09-09 | 电子科技大学长三角研究院(湖州) | Network multi-propagation source selection method based on ring structure |
CN115037629B (en) * | 2022-03-02 | 2023-11-10 | 电子科技大学长三角研究院(湖州) | Network multi-propagation source selection method based on ring structure |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108010316A (en) | A kind of road traffic multisource data fusion processing method based on road net model | |
CN109887288B (en) | Urban road network guidance scheme publishing method and system based on travel structure | |
CN105913661B (en) | A kind of express highway section traffic state judging method based on charge data | |
CN108961747B (en) | A kind of urban road traffic state information extracting method under incomplete bayonet data qualification | |
CN104021671B (en) | The determination methods of the road real-time road that a kind of svm combines with fuzzy Judgment | |
CN104809112B (en) | A kind of city bus development level integrated evaluating method based on multi-source data | |
CN109493620A (en) | A kind of traffic analysis system, method and device | |
CN108629973A (en) | Road section traffic volume congestion index computational methods based on fixed test equipment | |
CN107766808A (en) | The method and system that Vehicle Object motion track clusters in road network space | |
CN107134142A (en) | A kind of urban road method for predicting based on multisource data fusion | |
CN109191605B (en) | Highway charging rate accuracy evaluation method considering charging path | |
CN103903433A (en) | Real-time dynamic judgment method and device for road traffic state | |
CN101930668A (en) | Road traffic OD (Optical Density) information collection system for license plate recognition and processing method thereof | |
CN101783074A (en) | Method and system for real-time distinguishing traffic flow state of urban road | |
CN108108859A (en) | A kind of traffic administration duties optimization method based on big data analysis | |
CN109147329A (en) | Regional traffic operating status index based on the traffic capacity calculates and method for visualizing | |
CN106856049A (en) | Crucial intersection demand clustering analysis method based on bayonet socket number plate identification data | |
CN102968900A (en) | Method for processing RFID (Radio Frequency Identification) traffic data | |
CN109377757A (en) | The vehicle driving track extraction method of license plate identification data based on the rough error containing multi-source | |
CN108648445A (en) | Dynamic traffic Tendency Prediction method based on traffic big data | |
CN106910350A (en) | A kind of method for finding signalized crossing group's critical path | |
CN105575120B (en) | The floating car data parking behavior pattern cleaning method calculated towards road real-time speed | |
CN105139670A (en) | Video-based regional self-optimizing signal control method and apparatus | |
CN108681717A (en) | City-level traffic video detection equipment quality detection method | |
CN106373399A (en) | Identification system for transit bottleneck between bus stops |
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 | ||
WW01 | Invention patent application withdrawn after publication |
Application publication date: 20180508 |
|
WW01 | Invention patent application withdrawn after publication |