CN105355047A - Data fusion processing method for dynamic time granularity of multiple traffic detection sources - Google Patents
Data fusion processing method for dynamic time granularity of multiple traffic detection sources Download PDFInfo
- Publication number
- CN105355047A CN105355047A CN201510736033.7A CN201510736033A CN105355047A CN 105355047 A CN105355047 A CN 105355047A CN 201510736033 A CN201510736033 A CN 201510736033A CN 105355047 A CN105355047 A CN 105355047A
- Authority
- CN
- China
- Prior art keywords
- data
- detection
- traffic
- time
- detection resources
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 142
- 238000000034 method Methods 0.000 title claims abstract description 38
- 238000007499 fusion processing Methods 0.000 title claims abstract description 5
- 230000004927 fusion Effects 0.000 claims abstract description 31
- 230000008859 change Effects 0.000 claims abstract description 14
- 238000012545 processing Methods 0.000 claims abstract description 11
- 230000008569 process Effects 0.000 claims description 14
- 238000007500 overflow downdraw method Methods 0.000 claims description 13
- 230000007613 environmental effect Effects 0.000 claims description 12
- 238000000605 extraction Methods 0.000 claims description 12
- 238000013480 data collection Methods 0.000 claims description 7
- 238000010790 dilution Methods 0.000 claims description 7
- 239000012895 dilution Substances 0.000 claims description 7
- 239000000284 extract Substances 0.000 claims description 6
- 238000005259 measurement Methods 0.000 claims description 4
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 238000001914 filtration Methods 0.000 claims description 3
- 230000008676 import Effects 0.000 claims description 3
- 239000004615 ingredient Substances 0.000 claims description 3
- 239000011159 matrix material Substances 0.000 claims description 3
- 238000003908 quality control method Methods 0.000 claims description 3
- 230000008439 repair process Effects 0.000 claims description 3
- 238000011156 evaluation Methods 0.000 claims description 2
- 230000008901 benefit Effects 0.000 abstract description 2
- 238000007405 data analysis Methods 0.000 abstract description 2
- 238000005516 engineering process Methods 0.000 description 3
- 230000001939 inductive effect Effects 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 230000007812 deficiency Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000010365 information processing Effects 0.000 description 2
- 238000013341 scale-up Methods 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 1
- 238000005267 amalgamation Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008034 disappearance Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000005389 magnetism Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- NJPPVKZQTLUDBO-UHFFFAOYSA-N novaluron Chemical compound C1=C(Cl)C(OC(F)(F)C(OC(F)(F)F)F)=CC=C1NC(=O)NC(=O)C1=C(F)C=CC=C1F NJPPVKZQTLUDBO-UHFFFAOYSA-N 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
- 238000011144 upstream manufacturing Methods 0.000 description 1
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
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0108—Measuring and analyzing of parameters relative to traffic conditions based on the source of data
- G08G1/012—Measuring and analyzing of parameters relative to traffic conditions based on the source of data from other sources than vehicle or roadside beacons, e.g. mobile networks
Landscapes
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a data fusion processing method for the dynamic time granularity of multiple traffic detection sources, and belongs to the technical field of urban traffic data analysis. The method comprises the following steps: detecting the data acquisition time interval to extract a time base; loading space information for detection data, and generalizing the data structure of traffic data; evaluating the data correlation degree, equipment data accuracy and environment influence degree of each detection source to obtain the credibility coefficient of the detection source; obtaining the time granularity application requirement based on dynamic changing and updating of location check-in data of a mobile terminal in a detection area; and carrying out traffic parameter fusion of the multiple detection sources according to the application requirement and the credibility of the detection sources. According to the invention, urban traffic data processing based on the traffic data acquired by a basic sensor and the location check-in data of the mobile terminal is in line with the development trend of big data, and the rate of dynamic data fusion according to the change of time granularity is effectively improved. The method has the advantages of quick operation getting and storage redundancy reduction.
Description
Technical field
The invention belongs to urban transportation data analysis technique field, particularly relate to the Data Fusion method of a kind of many Vehicle Detection source dynamic time granularity.
Background technology
Along with the rise of smart city, the pattern of the common gather data in real time of the various roads sensors such as earth magnetism wagon detector, inductive coil, vehicle flowrate radar is popularized gradually.The collection of companion data and the continuous enhancing of storage data capability on the other hand, particularly the universal and mobile terminal client terminal such as microblogging, the micro-letter user of individual mobile terminal increases gradually, and mobile terminal positioning technology is wherein the data source that traffic data collection provides magnanimity.Under the propelling of these two aspects technology, data space under novel traffic data collection pattern interweaves jointly with traditional data drainage pattern lacks and associates, and causes actual traffic application aspect to be made slow progress becoming the bottleneck of Modern City Traffic data processing.
Traffic data merges and refers to that the traffic data of multisensor is comprehensive under certain criterion, the transport information processing procedure of carrying out to complete required communications policy and assessment.The transport information of multiple sensors collection is carried out effective integration, not only effectively can improve the cost performance of acquisition of information, accuracy and fiduciary level, and the judgement single information source can avoided to lose efficacy and cause and decision error.According to the position of each Loop detector layout in current domestic communication data fusion method, by certain hour granularity, traffic data fusion is carried out to the roadway element comprising crossing, upstream and section, during such transport information handling and storage redundancy is too much, and practical application effect cannot be ensured.
Road traffic fusion method traditional under novel traffic data collection pattern remains in many deficiencies, and its main manifestations number exists: in current data fusion method, time granularity is set as definite value, expends time in and storage space; Information processing only rests on public presupposed information demand aspect, and cannot be formed with regional traffic customer volume change so that dynamic change time granularity carry out traffic data fusion; Magnanimity locating information for individual mobile terminal generation does not effectively become the data foundation of traffic characteristic.
Summary of the invention
Fixedly causing to overcome time granularity in data fusion the deficiency expended time in storage space, the invention provides the Data Fusion method of a kind of many Vehicle Detection source dynamic time granularity.The method detects data for research object with urban highway traffic, time-space attribute according to detecting data extracts Uniform data format, by surveyed area mobile terminal APP position register Data Dynamic change determine traffic application demand, and then by information source degree of belief coefficient, traffic parameter fusion is carried out to the data of detection resources many in surveyed area, realize the flexible analyzing and processing of urban transportation data.
The present invention comprises the dynamic time granularity Fusion Module of Vehicle Detection data generalization processing module and traffic data, and the method concrete steps are as follows:
(1), Vehicle Detection data generalization process
The process of Vehicle Detection data generalization mainly realizes multi-source ground fundamental mode traffic detector normalization of data structure; Its processing procedure mainly comprises multi-source and detects the time interval feature extraction of data and data structure generalized two steps of traffic data:
I) extract time interval of image data, under the prerequisite ensureing data precision extraction time radix; To acquisition detector data temporally radix carry out data quality control;
Ii) extract space position parameter for each Vehicle Detection source, spatial information loading is carried out to detection data, and the generalized data structure to traffic data;
According to above-mentioned basic implementing procedure, described Vehicle Detection data generalization module is specifically implemented to comprise the following steps:
Step 1, traffic parameter is extracted to data record, and by Import data records database;
Step 2, the acquisition time interval of data is extracted to the adjacent record of same detection source historical data;
The average that step 3, extraction multi-source detect the expectation value of data collection interval is time radix, namely at time period [t
s, t
e] in, data have recorded m kind extraction time in time interval radix t
bfor
wherein p
ikit is a kth acquisition time interval of delta t in i-th detection resources
kthe probability occurred, r
ibe the ratio that the image data amount of i-th detection resources accounts for all detection data, n is detection resources number in region.
Step 4, with time radix for standard adjustment interval writing time, and repair missing data record by the time interval after adjustment
The spatial information of step 5, over the ground fundamental mode detecting device, obtain the unified field DLatitude of traffic flow parameter, DLongitude, LaneNo, TimeStamp, Flow, Speed, Occ, wherein DLatitude is detector location latitude, DLongitude is detector location longitude, LaneNo is road track numbering, and TimeStamp is label detection time, and Flow detects the magnitude of traffic flow obtained, Speed detects the vehicle location speed obtained, and Occ detects the time occupancy obtained.
According to the concrete implementer's case of Vehicle Detection data generalization of the present invention process, the time interval feature of described traffic detector data is fiduciary level and the degree of accuracy of the Vehicle Detection data for analyzing collection, the corresponding time interval attribute obtaining data, specifically comprises: 1) acquisition time interval: refer to the time interval detecting data acquisition time at traffic detector; 2) time radix: the expectation value referring to Vehicle Detection data collection interval; 3) time granularity: refer to the time interval setting that multi-source traffic data merges, the time granularity of this method depends on the transport need of registering mobile terminal APP in corresponding region position data volume change determining.
(2), the dynamic time granularity of traffic data merges
Traffic parameter Fusion Module three ingredients that dynamic time granularity fusion part mainly comprises detection resources Trust Values Asses module, Data Update statistical module and dynamic time granularity are registered in position of traffic data.Wherein detection resources Trust Values Asses module and position Data Update statistical module of registering is the forerunner of the traffic parameter Fusion Module of dynamic time granularity, and both are enforcement relation in parallel:
I) detection resources Trust Values Asses module: to the aspect qualitative assessment such as the historical data degree of correlation factor, device data dilution of precision, Environmental Factors of detection resources, comprehensively obtain detection resources Trust Values Asses coefficient;
Ii) register Data Update statistical module in position: to register data filtering to mobile terminal APP position, reject traffic participant positional information abnormity record and repeat record, and travel through mobile terminal APP in region and to register position data, statistics dynamic change update;
Iii) the traffic parameter Fusion Module of dynamic time granularity: obtain time granularity application demand by position data variation of registering, according to application demand and detection resources degree of belief, traffic parameter fusion is carried out to many detection resources.
According to basic implementing procedure of the present invention, described detection resources Trust Values Asses module is specifically implemented to comprise the following steps:
Step 1, determine n the data detection resources that section is to be fused, to i-th detection resources data x
icalculate and a jth detection resources data x
jdiscrete data correlation coefficient r in one day
ijfor
Step 2, calculate the Data mutuality degree factor C of i-th detection resources according in detection resources discrete data related coefficient
ifor
wherein r
ijbe i-th detection resources data x
icalculate and a jth detection resources data x
jrelated coefficient.
Step 3, to i-th detection resources computing equipment data precision factors A
i, and
wherein a
ifor such detection resources innate detection precision.
Step 4, according to i-th detection resources characteristic assignment Environmental Factors S
i, and
Step 5, calculating i-th independent detection source Trust Values Asses coefficient ω
i, and
wherein C
ibe i-th detection resources Data mutuality degree factor, A
ibe the device data dilution of precision of i-th detection resources, S
iit is the Environmental Factors of i-th detection resources.
According to the concrete implementer's case of detection resources Trust Values Asses module of the present invention, described detection resources Trust Values Asses is the transport information to comprising the many detection resources acquisitions in same section, from the degree of belief of the quantitative comprehensive evaluation detection resources in Data mutuality degree, equipment degree of accuracy and environmental sensitivity index three aspects, be embodied as and comprise: 1) the multi-source data degree of correlation factor: refer to data that certain section traffic detector to be evaluated records with other class detector data correlation proportion coefficients of section; 2) device data dilution of precision: the scale-up factor referring to certain Vehicle Detection equipment innate detection precision and all kinds of detecting device precision ratio; 3) Environmental Factors: refer to certain traffic detector under the condition of environmental change testing result affect scale-up factor.
According to basic implementing procedure of the present invention, described position Data Update statistical module of registering specifically is implemented to comprise the following steps:
Step 1, information data of registering to mobile terminal APP position are filtered, conversion and loading, and reject traffic participant positional information abnormity record and repeat record.To obtain unified field Venueid, Venuename, Latitude, Longitude, CheckedUserID of traffic participant positional information, wherein Venueid is that position registers that data number, Venuename are location name of registering, Latitude is position latitude of registering, Longitude is position longitude of registering, CheckedUserID is register Data Source mobile terminal numbering in position;
Step 2, all adjacent detection intersections are linked to be triangle, make the perpendicular bisector on each limit of triangle, so the some perpendicular bisectors around each crossing surround Thiessen polygon.Unique intersection is forgiven in unique Thiessen polygon.Initialization δ is 1, and wherein δ is the time radix multiple in dynamic time cycle.
Step 3, before current time t [t-2 δ * t
b, t-δ * t
b] interval and [t-δ * t
b, t] in interval, judge in the polygonal region belonging to location tags, and add up position in each region and to register the number m of data
0and m
1.
Step 4, with current statistic cycle [t-δ * t
b, t] and measurement period [t-2 δ * t
b, t-δ * t
b] in position to register data variation amount Δ m=|m
1-m
0| with upper limit threshold M
max, lower threshold M
minrelatively; If Δ m<M
min, so δ=δ+1 repeat step 3; If Δ m>M
max, so δ=δ-1 repeat step 3; If Δ m ∈ is [M
min, M
max], then determine that dynamic time granularity is δ time radix doubly.
To register Data Update statistical technique embodiment according to position of the present invention, described filtration refers to traffic participant positional information rejecting abnormalities record and repeats record.
According to basic implementing procedure of the present invention, the traffic parameter Fusion Module of described dynamic time granularity is specifically implemented to comprise the following steps:
In step 1, same surveyed area Thiessen polygon, section is at dynamic time cycle [t, t+ δ * t
b] in the weight matrix W={ ω of n detecting device degree of belief
1, ω
2... ω
n}
t, wherein ω
irepresent i-th detecting device data measured weight ratio in fusion process.
Step 2, at dynamic time cycle [t, t+ δ * t
b] the interior common n to i-th detection resources
iindividual data calculate the information fusion in i-th independent detection source
wherein x
afor the traffic data of to be fused i-th detector acquisition.
Step 3, at dynamic time cycle [t, t+ δ * t
b] in the information fusion result that obtains of multiple traffic information collecting method be:
wherein
the information fusion result in i-th independent detection source.
Beneficial effect of the present invention:
1) utilize pedestal sensor to obtain traffic data to agree with mutually urban transportation data processing and the trend that large data develop in conjunction with mobile terminal APP position data of registering.
2) the mobile terminal APP class statistic of registering position, is divided time granularity demand online by position number change of registering.
3) effectively can improve speed according to time granularity change tread data fusion, have and obtain the advantage that computing is quick, reduce storage redundancy.
Accompanying drawing explanation
Fig. 1 is process flow diagram of the present invention.
Fig. 2 is multi-source checkout equipment acquisition interval characteristic pattern of the present invention.
Fig. 3 is intersection Thiessen polygon organigram of the present invention.
Fig. 4 is the process flow diagram of judgement location tags of the present invention in Thiessen polygon region.
Embodiment
The present invention is based on multi-source ground fundamental mode traffic detector data, and the mobile terminal APP dynamic position that additional transport participant participates in is registered data, proposes a kind of section multi-source traffic data method for amalgamation processing of Data Dynamic determination time granularity of registering with position.Below in conjunction with accompanying drawing and embodiment, technical scheme of the present invention is described.
As shown in Figure 1, the flow process of embodiment specifically comprises the following steps:
Step 1: extract example section geomagnetism detecting device, inductive coil detecting device and video monitor acquisition time interval and extraction time radix.From example section geomagnetism detecting device (DE537919498), video monitor (DC00004838) and inductive coil detecting device (COIL1518017) be at time period [t
s, t
e] in the historical data time interval feature of multiple detecting device, as shown in Figure 2.
The flow process of this step extraction time radix specifically comprises the following steps:
1. traffic parameter is extracted to multi-source data record and import database, and adjust data field DetectorID, LaneNo, TimeStamp, Flow, Speed, Occ, wherein DetectorID is detecting device numbering, LaneNo is road track numbering, and TimeStamp is label detection time, and Flow detects the magnitude of traffic flow obtained, Speed detects the vehicle location speed obtained, and Occ detects the time occupancy obtained.
2. to historgraphic data recording extraction time sequence, then traffic data time series the finite set { (t gathered
1, o
1), (t
2, o
2) ..., (t
n, o
n) meet t
s≤ t
i≤ t
eand t
i<t
i+1(i=1,2 ..., n-1), o
ifor corresponding time t
itraffic parameter collection comprises magnitude of traffic flow Flow, vehicle location speed Speed, time occupancy Occ, computing time section [t
s, t
e] time interval { the Δ t of image data
k| Δ t
k=t
i+1-t
iand i=1,2 ..., n-1};
3. the time radix that multi-source detects data collection interval is calculated, namely at time period [t
s, t
e] in, data have recorded m kind extraction time in time interval radix t
bfor
wherein p
ikit is a kth acquisition time interval of delta t in i-th detection resources
kthe probability occurred, r
ibe the ratio that the image data amount of i-th detection resources accounts for all detection data, n is detection resources number in region.
Step 2, by fundamental mode Vehicle Detection source, various places extract space position parameter DLatitude, DLongitude, unified field DetectorID, DLatitude, DLongitude, LaneNo, TimeStamp, Flow, Speed, Occ that spatial information loading obtains traffic data is carried out to detecting data, wherein DLatitude is detector location latitude, and DLongitude is detector location longitude.
In this step, single detection resources data specifically comprise the following steps based on the data quality control flow process of time radix:
If 1. unique
then data (t
i, o
i) be adapted to (
o
i);
If 2. multiple
then k is according to being set to data (t respectively
i_1, o
i_1), (t
i_2, o
i_2) ..., (t
i_k, o
i_k), data
obtain generalized data
If 3. there is no (t
i, o
i) ∈ (nT
b, (n+1) t
b], then traffic data has continuity in time domain, and before and after thus utilizing, two time cycles carried out time cycle data translation reparation.If front and back cycle data is set to data (t respectively
i-2, o
i-2), (t
i-1, o
i-1) and (t
i+1, o
i+1), (t
i+2, o
i+2), data
Obtain generalized data
Step 3, to the aspect qualitative assessment such as the historical data degree of correlation factor, device data dilution of precision, Environmental Factors relating to detection resources, comprehensively obtain detection resources Trust Values Asses coefficient;
This step detection resources Trust Values Asses flow process specifically comprises the following steps:
1. n the data detection resources that section is to be fused is determined, to i-th detection resources data x
icalculate and a jth detection resources data x
jdiscrete data correlation coefficient r in one day
ijfor
2. according to the Data mutuality degree factor calculating i-th detection resources in detection resources discrete data related coefficient be
wherein r
ijbe i-th detection resources data x
icalculate and a jth detection resources data x
jrelated coefficient.
3. to i-th detection resources computing equipment data precision factor
wherein a
ifor such detection resources innate detection precision.
4. according to i-th detection resources characteristic assignment Environmental Factors S
i,and
5. i-th independent detection source Trust Values Asses coefficient ω is calculated
ifor
wherein C
ibe i-th detection resources Data mutuality degree factor, A
ibe the device data dilution of precision of i-th detection resources, S
iit is the Environmental Factors of i-th detection resources.
Step 4, information data that mobile terminal APP position registered conversion and filter, and the Data Dynamic change of registering position of mobile terminal APP in surveyed area is upgraded;
This step specifically comprises the following steps:
1. check that whether the register genus information of data of position is complete, position data of registering for disappearance attribute are deleted, and data are revised according to criteria field Venueid, Venuename, Latitude, Longitude, CheckedUserID form, wherein Venueid is that position registers that data number, Venuename are location name of registering, Latitude is position latitude of registering, Longitude is position longitude of registering, CheckedUserID is register Data Source mobile terminal numbering in position;
2. data merging treatment is carried out to the repeatable position of identical CheckedUserID data of registering, reduce the redundance of data.
3. all adjacent detection intersections are linked to be triangle, make the perpendicular bisector on each limit of these triangles, so the some perpendicular bisectors around each crossing just surround Thiessen polygon, as shown in Figure 3.Unique intersection is forgiven in unique Thiessen polygon, and initialization time radix coefficient δ is 1.
4. discrete location point of registering in a large number is collected in polygon, with the δ of the time radix times time for measurement period, [t-2 δ * t before current time t
b, t-δ * t
b] interval and [t-δ * t
b, t] and in interval, judge the polygonal region belonging to location tags with scanning Beam Method, and add up position and to register the number m of data
0and m
1, flow process as shown in Figure 4.
5. with current statistic cycle [t-δ * t
b, t] and measurement period [t-2 δ * t
b, t-δ * t
b] in position to register data variation amount Δ m=|m
1-m
0| with upper limit threshold M
max, lower threshold M
minrelatively; If Δ m<M
min, so δ=δ+1 repeat 4.; If Δ m>M
max, so δ=δ-1 repeat 4.; If Δ m ∈ is [M
min, M
max], then determine that dynamic time granularity is δ time radix doubly.
Step 5, change to attributes change of being registered by position obtain time granularity demand, for obtaining unified field DLatitude, DLongitude, LaneNo, TimeStamp, Flow, Speed, Occ of traffic data, according to time granularity application demand, many detection resources are carried out to the fusion of traffic parameter field data.
In this step, time granularity application demand specifically comprises the following steps the fusion flow process that many detection resources carry out traffic data:
1. in same surveyed area Thiessen polygon section at dynamic time cycle [t, t+ δ * t
b] in the weight matrix W={ ω of n detecting device data measured
1, ω
2... ω
n}
t, wherein ω
irepresent that i-th detecting device records traffic parameter field data x
ishared weight in fusion process.
2. at dynamic time cycle [t, t+ δ * t
b] the interior common n to i-th detection resources
iindividual data calculate the information fusion in i-th independent detection source
wherein x
afor the traffic data of to be fused i-th detector acquisition.
4. at dynamic time cycle [t, t+ δ * t
b] in the information fusion result that obtains of multiple traffic information collecting method be:
wherein
the information fusion result in i-th independent detection source.
Ultimate principle of the present invention utilizes position to register the foundation that dynamically update of data as road traffic demand, and then meet the requirement of novel traffic data acquisition, wherein on the basis evaluating detection resources degree of belief, under dynamic change time granularity, data processing is carried out to the data in many Vehicle Detection source, thus realize merging the Data Dynamic in many Vehicle Detection source.
Claims (7)
1. a Data Fusion method for the source of Vehicle Detection more than dynamic time granularity, the dynamic time granularity comprising the process of Vehicle Detection data generalization and traffic data merges two ingredients, and the method comprises the following steps:
(1), Vehicle Detection data generalization process
Vehicle Detection data generalization processing procedure mainly comprises time interval feature extraction and traffic data structure generalized two steps that multi-source detects data; First extract the time interval of image data, ensure data precision prerequisite under extraction time radix; To acquisition detector data temporally radix carry out data quality control; Afterwards space position parameter being extracted to each Vehicle Detection source, carry out to detecting data the generalized data structure that spatial information loading obtains traffic data, and then dynamic time granularity data after generalized being used for highway traffic data merging;
(2), the dynamic time granularity of traffic data merges
Traffic data dynamic time granularity fusion part mainly comprises detection resources Trust Values Asses module, Data Update statistical module is registered in position and dynamic time granularity traffic parameter Fusion Module three ingredients;
I) Trust Values Asses module: to the aspect qualitative assessment such as the historical data degree of correlation factor, device data dilution of precision, Environmental Factors of detection resources, comprehensively obtain detection resources Trust Values Asses coefficient;
Ii) register Data Update statistical module in position: to register data filtering to mobile terminal APP position, reject traffic participant positional information abnormity record and repeat record, and travel through mobile terminal APP in region and to register position data, statistics dynamic change update;
Iii) dynamic time granularity traffic parameter Fusion Module: obtain time granularity application demand by position data variation of registering, according to application demand and detecting device degree of belief, traffic parameter fusion is carried out to many detection resources.
2. the Data Fusion method of many Vehicle Detection source according to claim 1 dynamic time granularity, is characterized in that: in the process of described Vehicle Detection data generalization, the time interval feature extracting method of multi-source detection data comprises the following steps:
Step 1, traffic parameter is extracted to data record, and by Import data records database;
Step 2, the acquisition time interval of data is extracted to the adjacent record of same detection source historical data;
The average that step 3, extraction multi-source detect the expectation value of data collection interval is time radix, namely at time period [t
s, t
e] in, data have recorded m kind extraction time in time interval radix t
bfor
wherein p
ikit is a kth acquisition time interval of delta t in i-th detection resources
kthe probability occurred, r
ibe the ratio that the image data amount of i-th detection resources accounts for all detection data, n is detection resources number in region;
Step 4, with time radix for standard adjustment interval writing time, and repair missing data record by the time interval after adjustment;
The spatial information of step 5, over the ground fundamental mode detecting device, obtains the unified field of traffic flow parameter.
3. the Data Fusion method of many Vehicle Detection source according to claim 1 dynamic time granularity, it is characterized in that: the data structure generalized in described Vehicle Detection data generalization processing section is that the spatial information of detecting device is loaded into the unified field detecting and obtain traffic flow parameter in data with time radix for standard adjustment data writing time repair missing data record.
4. the Data Fusion method of many Vehicle Detection source according to claim 1 dynamic time granularity, it is characterized in that: in the dynamic time granularity Fusion Module of described traffic data, register the parallel processing of Data Update statistical module in detection resources Trust Values Asses module and position, for the traffic parameter Fusion Module of dynamic time granularity provides foundation.
5. the Data Fusion method of many Vehicle Detection source according to claim 1 dynamic time granularity, is characterized in that: in the dynamic time granularity fusion part of described traffic data, the method for detection resources Trust Values Asses module comprises the following steps:
Step 1, determine n the data detection resources that section is to be fused, to i-th detection resources data x
icalculate and a jth detection resources data x
jdiscrete data correlation coefficient r in one day
ijfor
Step 2, calculate the Data mutuality degree factor C of i-th detection resources according in detection resources discrete data related coefficient
ifor
wherein r
ijbe i-th detection resources data x
icalculate and a jth detection resources data x
jrelated coefficient;
Step 3, to i-th detection resources computing equipment data precision factors A
i, and
wherein a
ifor such detection resources innate detection precision;
Step 4, according to i-th detection resources characteristic assignment Environmental Factors S
i, and
Step 5, calculating i-th independent detection source Trust Values Asses coefficient ω
i, and
wherein C
ibe i-th detection resources Data mutuality degree factor, A
ibe the device data dilution of precision of i-th detection resources, S
iit is the Environmental Factors of i-th detection resources.
6. the Data Fusion method of many Vehicle Detection source according to claim 1 dynamic time granularity, is characterized in that: the register method of Data Update statistical module of described position comprises the following steps:
Step 1, information data of registering to mobile terminal APP position are filtered, conversion and loading, and reject traffic participant positional information abnormity record and repeat record, to obtain the unified field of traffic participant positional information;
Step 2, all adjacent detection intersections are linked to be triangle, make the perpendicular bisector on each limit of these triangles, so the some perpendicular bisectors around each crossing just surround Thiessen polygon; Unique intersection is forgiven in unique Thiessen polygon, and initialization δ is 1, and wherein δ is the time radix coefficient determining the time cycle;
Step 3, before current time t [t-2 δ * t
b, t-δ * t
b] interval and [t-δ * t
b, t] and in interval, wherein t
bfor the time radix extracted, judge the polygonal region belonging to location tags, and add up position in each region and to register the number m of data
0and m
1;
Step 4, with current statistic cycle [t-δ * t
b, t] and measurement period [t-2 δ * t
b, t-δ * t
b] in position to register data variation amount Δ
m=| m
1-m
0| with upper limit threshold M
max, lower threshold M
minrelatively; If Δ
m<M
min, so δ=δ+1 repeat step 3; If Δ
m>M
max, so δ=δ-1 repeat step 3; If Δ
m∈ [M
min, M
max], then determine that dynamic time granularity is δ time radix doubly.
7. the Data Fusion method of many Vehicle Detection source according to claim 1 dynamic time granularity, it is characterized in that: the traffic parameter Fusion Module of described dynamic time granularity is according to weight shared in the evaluation right value matrix determination data fusion process of each detecting device in surveyed area, the time cycle is determined by position Data Update statistical module of registering, the traffic data of many discrete times point collection of polytype detection resources in the same surveyed area time cycle is required to carry out data fusion by evaluating weights than weighting scheme, and then obtain more accurate data result.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510736033.7A CN105355047B (en) | 2015-11-03 | 2015-11-03 | The Data Fusion method of many Vehicle Detection source dynamic time granularities |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510736033.7A CN105355047B (en) | 2015-11-03 | 2015-11-03 | The Data Fusion method of many Vehicle Detection source dynamic time granularities |
Publications (2)
Publication Number | Publication Date |
---|---|
CN105355047A true CN105355047A (en) | 2016-02-24 |
CN105355047B CN105355047B (en) | 2017-06-06 |
Family
ID=55331011
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510736033.7A Expired - Fee Related CN105355047B (en) | 2015-11-03 | 2015-11-03 | The Data Fusion method of many Vehicle Detection source dynamic time granularities |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105355047B (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105792110A (en) * | 2016-03-30 | 2016-07-20 | 上海申腾信息技术有限公司 | Data fusion and intelligent searching processing method for multiple data sources |
CN106710238A (en) * | 2017-01-26 | 2017-05-24 | 深圳市迅朗科技有限公司 | Mechanism and method for improving accuracy of geomagnetism vehicle inspection device |
CN110111563A (en) * | 2019-04-08 | 2019-08-09 | 东南大学 | A kind of real-time traffic states estimation method of city expressway |
CN110133685A (en) * | 2019-05-22 | 2019-08-16 | 吉林大学 | Street lamp based on OCC assists the detailed location of communication system of mobile phone |
CN110322688A (en) * | 2019-05-20 | 2019-10-11 | 华为技术有限公司 | A kind of method of data processing, the method for data query and relevant device |
CN114333301A (en) * | 2021-12-06 | 2022-04-12 | 北京东土正创科技有限公司 | Traffic signal control optimization method and system and traffic signal optimization equipment |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20040217881A1 (en) * | 2003-04-29 | 2004-11-04 | Innovative Technology Licensing, Llc | Modular wireless integrated network sensor (WINS) node with a dual bus architecture |
US20060095518A1 (en) * | 2004-10-20 | 2006-05-04 | Davis Jesse H Z | Software application for modular sensor network node |
CN101493991A (en) * | 2009-02-20 | 2009-07-29 | 北京交通大学 | Method and device for obtaining traffic status based on sensor network |
CN101710361A (en) * | 2009-11-13 | 2010-05-19 | 北京航空航天大学 | Distributed traffic simulating platform based on Service-Oriented Architecture (SOA) and simulating 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 |
CN102074126A (en) * | 2011-01-19 | 2011-05-25 | 清华大学 | Historical radar data based air traffic flow analysis system and method |
CN102254001A (en) * | 2011-07-14 | 2011-11-23 | 青岛海信网络科技股份有限公司 | Efficient data management method and system |
CN103220340A (en) * | 2013-03-28 | 2013-07-24 | 北京交通大学 | Semantic coding method for road transport sensor network nodes |
CN103456163A (en) * | 2012-06-04 | 2013-12-18 | 北京市市政工程设计研究总院 | City expressway interchange traffic capacity and running status discrimination method and system |
CN104765974A (en) * | 2015-04-24 | 2015-07-08 | 北京城建设计发展集团股份有限公司 | Urban rail transit passenger flow density index calculating method |
-
2015
- 2015-11-03 CN CN201510736033.7A patent/CN105355047B/en not_active Expired - Fee Related
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20040217881A1 (en) * | 2003-04-29 | 2004-11-04 | Innovative Technology Licensing, Llc | Modular wireless integrated network sensor (WINS) node with a dual bus architecture |
US20060095518A1 (en) * | 2004-10-20 | 2006-05-04 | Davis Jesse H Z | Software application for modular sensor network node |
CN101493991A (en) * | 2009-02-20 | 2009-07-29 | 北京交通大学 | Method and device for obtaining traffic status based on sensor network |
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 |
CN101710361A (en) * | 2009-11-13 | 2010-05-19 | 北京航空航天大学 | Distributed traffic simulating platform based on Service-Oriented Architecture (SOA) and simulating method thereof |
CN102074126A (en) * | 2011-01-19 | 2011-05-25 | 清华大学 | Historical radar data based air traffic flow analysis system and method |
CN102254001A (en) * | 2011-07-14 | 2011-11-23 | 青岛海信网络科技股份有限公司 | Efficient data management method and system |
CN103456163A (en) * | 2012-06-04 | 2013-12-18 | 北京市市政工程设计研究总院 | City expressway interchange traffic capacity and running status discrimination method and system |
CN103220340A (en) * | 2013-03-28 | 2013-07-24 | 北京交通大学 | Semantic coding method for road transport sensor network nodes |
CN104765974A (en) * | 2015-04-24 | 2015-07-08 | 北京城建设计发展集团股份有限公司 | Urban rail transit passenger flow density index calculating method |
Non-Patent Citations (3)
Title |
---|
刘俊岭 等: ""空间区域中对象流动模式构建方法研究"", 《空计算机工程与科学》 * |
张汝华 等: ""基于视频技术的微观交通流信息采集系统研究"", 《交通与计算机》 * |
陈昕 等: ""城市交通控制与诱导系统协同的信息分析与组织研究"", 《公路交通科技》 * |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105792110A (en) * | 2016-03-30 | 2016-07-20 | 上海申腾信息技术有限公司 | Data fusion and intelligent searching processing method for multiple data sources |
CN105792110B (en) * | 2016-03-30 | 2019-04-30 | 上海申腾信息技术有限公司 | A kind of data fusion of multiple data origin, the processing method of intelligent search |
CN106710238A (en) * | 2017-01-26 | 2017-05-24 | 深圳市迅朗科技有限公司 | Mechanism and method for improving accuracy of geomagnetism vehicle inspection device |
CN106710238B (en) * | 2017-01-26 | 2023-09-05 | 深圳市迅朗科技有限公司 | Method for improving accuracy of geomagnetic vehicle detector |
CN110111563A (en) * | 2019-04-08 | 2019-08-09 | 东南大学 | A kind of real-time traffic states estimation method of city expressway |
CN110322688A (en) * | 2019-05-20 | 2019-10-11 | 华为技术有限公司 | A kind of method of data processing, the method for data query and relevant device |
CN110133685A (en) * | 2019-05-22 | 2019-08-16 | 吉林大学 | Street lamp based on OCC assists the detailed location of communication system of mobile phone |
CN114333301A (en) * | 2021-12-06 | 2022-04-12 | 北京东土正创科技有限公司 | Traffic signal control optimization method and system and traffic signal optimization equipment |
CN114333301B (en) * | 2021-12-06 | 2023-09-26 | 北京东土正创科技有限公司 | Traffic signal control optimization method, system and traffic signal optimization equipment |
Also Published As
Publication number | Publication date |
---|---|
CN105355047B (en) | 2017-06-06 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105355047A (en) | Data fusion processing method for dynamic time granularity of multiple traffic detection sources | |
Xu et al. | Context-aware real-time population estimation for metropolis | |
CN104330089B (en) | A kind of method that map match is carried out using history gps data | |
Noor et al. | Determination of spatial factors in measuring urban sprawl in Kuantan using remote sensing and GIS | |
CN104134349B (en) | A kind of public transport road conditions disposal system based on traffic multisource data fusion and method | |
CN106323301B (en) | Method and device for acquiring road information | |
CN102708680B (en) | Commute travel mode identification method based on AGPS technology | |
CN105206057B (en) | Detection method and system based on Floating Car resident trip hot spot region | |
Hanson et al. | Evaluation of low-cost consumer-level mobile phone technology for measuring international roughness index (IRI) values | |
CN109544932A (en) | A kind of city road network flow estimation method based on GPS data from taxi Yu bayonet data fusion | |
CN102968900B (en) | Method for processing RFID (Radio Frequency Identification) traffic data | |
CN101571997A (en) | Method and device for fusion processing of multi-source traffic information | |
CN104164829A (en) | Pavement smoothness detection method based on mobile terminal and intelligent pavement information real-time monitoring system | |
CN103903437B (en) | The Vehicle emission OD matrix acquisition methods of data is detected based on video traffic | |
Turner et al. | Quality counts for pedestrians and bicyclists: Quality assurance procedures for nonmotorized traffic count data | |
CN113487105B (en) | Landslide geological disaster space prediction method and device and computer equipment | |
CN116363524A (en) | Monitoring and early warning method and device for highway geological disaster high-risk area | |
CN104408923A (en) | Method and device for evaluating traffic state | |
Li et al. | A two-phase clustering approach for urban hotspot detection with spatiotemporal and network constraints | |
CN103810855A (en) | Multi-characteristic quantity comprehensive traffic detection system oriented to multi-user group | |
CN108154387B (en) | Method and device for evaluating bus body advertisement delivery route scheme | |
Miller et al. | Scaling GPS trajectories to match point traffic counts: A convex programming approach and Utah case study | |
Duan et al. | MobilePulse: Dynamic profiling of land use pattern and OD matrix estimation from 10 million individual cell phone records in Shanghai | |
Jonker et al. | Modeling trip-length distribution of shopping center trips from GPS data | |
Soe et al. | Haversine formula and RPA algorithm for navigation system |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20170606 Termination date: 20191103 |
|
CF01 | Termination of patent right due to non-payment of annual fee |