CN110276950A - A kind of urban transportation Trip chain reconstructing method based on bayonet video data - Google Patents
A kind of urban transportation Trip chain reconstructing method based on bayonet video data Download PDFInfo
- Publication number
- CN110276950A CN110276950A CN201910550349.5A CN201910550349A CN110276950A CN 110276950 A CN110276950 A CN 110276950A CN 201910550349 A CN201910550349 A CN 201910550349A CN 110276950 A CN110276950 A CN 110276950A
- Authority
- CN
- China
- Prior art keywords
- path
- decision
- bayonet
- attribute
- track
- 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
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
- G08G1/0125—Traffic data processing
- G08G1/0129—Traffic data processing for creating historical data or processing based on historical data
-
- 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
- G08G1/017—Detecting movement of traffic to be counted or controlled identifying vehicles
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Traffic Control Systems (AREA)
Abstract
The present invention uses PPA path search algorithm (potential path area path search algorithm), carries out building initial decision path, the true path restored using decision attribute factor model training method final output algorithm；And choose five kinds of decision optimization factors: path forms time, path length, path number of turns, path are more had environmental suitability by the decision factor that signal controller mouth number restores track as decision attribute；The setting of decision weights of the present invention is by leading, objective data is comprehensive establishes, more scientific practice, and algorithm speed is fast, can handle fairly large data；Suitable for the reconstructing path of middle-size and small-size road network, the recovery of missing inspection track of vehicle being completed with high precision, is had good robustness, the statistics for further statistics urban road network micro-parameter lays the foundation.
Description
Technical field
The present invention relates to intelligent transportation fields, go out more particularly, to a kind of urban transportation based on bayonet video data
Row chain reconstructing method.
Background technique
With the laying of the advanced means of transportation in city, the continuous variation of traffic administration means and traffic circulation model is adjusted,
Traditional resident's traffic trip investigation labor intensive cost and financial resources time cost are larger, and timeliness and accuracy are all very low,
It is unable to satisfy the demand of new era traffic programme and management.
Currently, big data storage and data mining technology are just like a raging fire in the growth momentum of intelligent transportation field industry,
Big data storage is based primarily upon traffic base data with data mining technology, such as automatic license plate identification data (Automatic
Number Plate Recognition, ANPR), GPS data (Global Positioning System,
GPS) data, loop data, mobile phone signaling etc., by carrying out the extraction of data to traffic trip track, the anti-traffic trip that pushes away is risen
Settled point (Origin Destination, OD) information and duty are lived than information, for traffic policy formulation, traffic programme and can be set
The decisions such as meter, traffic control and management, Traffic information demonstration provide reliable Informational support.
And currently based on technology used by traffic control and management of the big data storage with data mining technology for vehicle
The accuracy rate of trip track reduction is poor, to formulate traffic policy, traffic programme and design, traffic control and management, friendship
The decisions such as communication breath publication exert a certain influence.
Summary of the invention
In order to solve the deficiency for the accuracy rate difference that the prior art restores vehicle driving track, the present invention provides one kind
Urban transportation Trip chain reconstructing method based on bayonet video data.
In order to solve the above technical problems, technical scheme is as follows:
A kind of urban transportation Trip chain reconstructing method based on bayonet video data, comprising the following steps:
Step S1: pass through the vehicle license plate data of bayonet by video acquisition, collected license plate data are located in advance
Reason, extraction obtain the wheelpath of each car；
Step S2: the path continuously arrived by 4 and the above bayonet test in each car wheelpath is saved as history
Path data collection, by each car wheelpath exist by 2 discontinuous bayonet tests to data save conduct need to restore
Track；
Step S3: the track two for needing to restore is determined according to PPA (potential path area path search algorithm) routing algorithm
All possible driving trace set T between bayoneti；
Step S4: corresponding possible driving trace set T in historical path data set is calculatediEach path path
Journey time, section minimum discharge, path length, path number of turns and path are sought by signal controller mouth number
To about path forms time, section minimum discharge, path length, path number of turns and path by signal controller mouth number
Attribute decision factor；
Step S5: the path locus of identical starting bayonets all in historical path data set and terminal bayonet is all single
It solely takes out, each identical starting bayonet and terminal bayonet path locus is calculated by the method based on entropy weight Vague collection
The anti-weight parameter for pushing away path decision model；
Step S6: with the path locus and possibility of identical starting bayonets and terminal bayonet all in historical path data set
Driving trace set TiPath forms time, path length, path number of turns and path by signal controller mouth number
Input of the attribute decision factor as path decision model obtain final track rehabilitation programs in conjunction with weight parameter.
Preferably, historical path data set described in step S2 includes track fullpath, track starting point bayonet, track
Terminal bayonet, track starting point are detected the time, final on trajectory is detected time, path forms time.
Preferably, specific step is as follows by step S3:
It delimit different road network sub-districts in advance on the full wafer road network of investigation, judges whether bayonet belongs to identical road network
Area carries out inter-two-point path search with Depth Priority Algorithm if belonging to identical road network sub-district,
If belonging to different road network sub-districts, after two sub-districts carry out route searching, engaged according to bayonet is overlapped, from
And tentatively obtain feasible trajectory set Tpre；
It is introduced into historical path data set, judges set TpreWhether each element goes out in historical path data set
It now crosses, if do not occurred, weeds out set TpreThe middle element for representing the path, to obtain feasible trajectory set
Thisto；
The vehicle import direction for restoring the terminal bayonet point of track as needed, further screens out ThistoMiddle generation
Can walking along the street through collecting, it is final determine under all two bayonets of parked track possible driving trace set Ti。
Preferably, possible driving trace set T is calculated in step S4iPath forms time of each path, section
The specific step of minimum discharge, path length, path number of turns and path by the attribute decision factor of signal controller mouth number
It is rapid as follows:
Define stroke time match degree attribute factor GTT(Ti), section minimum discharge attribute factor GForce(Ti), path length
Spend attribute factor GLen(Ti), path number of turns attribute factor GC(Ti), path signal controls bayonet amount attribute factor GI(Ti)5
A attribute decision factor, and G is sought by standardizing evaluation functionTT(Ti)、GForce(Ti)、GLen(Ti)、GC(Ti)、GI(Ti), institute
The standardization evaluation function stated includes:
(a) journey time matching degree standardized nature evaluation function；
(b) traffic zone Attraction Degree standardized nature evaluation function；
(c) path length criterion attribute evaluation function；
(d) path number of turns standardized nature evaluation function；
(e) path signal controls bayonet amount standardized nature evaluation function；
Journey time matching degree standardized nature evaluation function calculation formula is as follows:
Wherein,It is TiIn theoretical path journey time, tiFor TiIn true journey time；J represents TiIn set
A kind of each element, that is, the route scheme restored, is denoted as scheme j；It is the theoretical path journey time in scheme j, tjFor side
True journey time in case j；
Traffic zone Attraction Degree standardized nature evaluation function calculation formula is as follows:
Wherein, FiFor TiIn import direction approach traffic zone attraction, FjFor the import direction way in scheme j
The attraction of the traffic zone of diameter, specific calculate refer to Gravity Models, the attraction between the adjacent bayonet passed through according to track
Power is accumulated to calculate, specific as follows,
Wherein QentranceIndicate TiThe flow in first section that import is passed through, FcarRepresent the automobile unit attracted, value
Link travel time is indicated for 1, t, is equivalent to journey time needed for completing track；
Path length criterion attribute evaluation function calculation formula is as follows:
Wherein, LiFor TiIn path length；LjFor the path length in scheme j
Path number of turns standardized nature evaluation function calculation formula is as follows:
Wherein, NiFor TiThe middle number for needing to turn；NjFor the number for needing to turn in scheme j；
It is as follows that path signal controls bayonet amount standardized nature evaluation function calculation formula:
Wherein, IiFor TiIn by signal controller mouth number；IjFor the number in scheme j by signal controller mouth；
Initialize feasible path locus set Ti, acquire GTT(Ti)、GForce(Ti)、GLen(Ti)、GC(Ti)、GI(Ti)。
Preferably, specific step is as follows by step S5:
5 attribute decision factor G are setTT(Ti)、GForce(Ti)、GLen(Ti)、GC(Ti)、GI(Ti) weight w1,w2,w3,
w4,w5, the determination of decision-making power weight values is trained fitting by historical path data set and obtains；
The input of model is with identical starting bayonets all in historical path data set and terminal bayonet and TiDecision category
Sex factor GTT(Ti)、GForce(Ti)、GLen(Ti)、GC(Ti)、GI(Ti), wherein i=1, K, n, the scheme of model are possible traveling
Track set T={ T1,T2,Ti,K,Tn}；
The objective weight of the decision attribute factor is calculated by entropy assessment, steps are as follows,
It enablesλijFor decision scheme j decision attribute i attribute factor standard value；
The calculating of the entropy of decision system can pass through formula:It calculates
It arriving, the comentropy of decision attribute is smaller, and the information provided is bigger, then the weight that the decision attribute Factor minute is matched also should be bigger,
Weight that is on the contrary then distributing also should be smaller；
Normalized after benefit is taken to obtain the objective weight of decision attribute decision attribute entropy are as follows:
To decision attribute objective weight vector are as follows: w'=(w1',w'2,K,w'5)
Subjective decision attribute weight w "=(w1”,w'2',K,w'5'), to obtain decision attribute weight vectors section are as follows:
Remember W=([w11,w12],[w21,w22],K,[w51,w52])。
Preferably, specific step is as follows by step S6:
If d=(d1,d2,K,d5)TIndicate the vector of decision attribute, diIn include category of the every kind of scheme at decision attribute i
Sex factor standard value:
Sj={ di∈d|λij>λU}
Oj={ di∈d|λij<λL}
Nj={ di∈d|λL≤λij≤λU}
Sj,Oj,NjIt is the decision neutrality collection of the decision support collection of scheme j, the decision opposition collection of scheme j, scheme j respectively；
To alternative T={ T1,T2,Ti,K,Tn, the degree Vague value that it meets the requirements on 5 decision attributes
Vt∈TIt indicates, wherein t represents every kind of alternative, Vt∈T=[lt∈T,CIdt∈T], I is weight complete or collected works, i.e., each element is all 1,
lt∈T=[αt∈T,βt∈T], dt∈T=[μt∈T,ηt∈T]
Wherein
Define objective function of decision-making:
Wherein ft∈T∈ [- 1,1]
Then final track rehabilitation programs are as follows: max (ft∈T)。
Compared with prior art, the beneficial effect of technical solution of the present invention is:
The present invention carries out building initial decision path using PPA algorithm, most using decision attribute factor model training method
The true path that whole output algorithm restores；And choose five kinds of decision optimization factors: path forms time, path length, path turn
Curved number, path are more had environment adaptation by the decision factor that signal controller mouth number restores track as decision attribute
Property；The setting of decision weights of the present invention is by leading, objective data is comprehensive establishes, more scientific practice, and algorithm speed is fast, can handle
Fairly large data；Suitable for the reconstructing path of middle-size and small-size road network, the recovery of missing inspection track of vehicle can be completed with high precision, is had
Good robustness, the statistics for further statistics urban road network micro-parameter lay the foundation.
Detailed description of the invention
Fig. 1 is flow chart of the method for the present invention.
Fig. 2 is the PPA route searching figure of the embodiment of the present invention two.
Fig. 3 is that the entropy weight decision process of the embodiment of the present invention two is illustrated.
Specific embodiment
The attached figures are only used for illustrative purposes and cannot be understood as limitating the patent；
In order to better illustrate this embodiment, the certain components of attached drawing have omission, zoom in or out, and do not represent actual product
Size；
To those skilled in the art, it is to be understood that certain known features and its explanation, which may be omitted, in attached drawing
's.
The following further describes the technical solution of the present invention with reference to the accompanying drawings and examples.
Embodiment 1
As shown in Figure 1, a kind of urban transportation Trip chain reconstructing method based on bayonet video data, comprising the following steps:
Step S1: pass through the vehicle license plate data of bayonet by video acquisition, collected license plate data are located in advance
Reason, extraction obtain the wheelpath of each car；
Step S2: the path continuously arrived by 4 and the above bayonet test in each car wheelpath is saved as history
Path data collection, by each car wheelpath exist by 2 discontinuous bayonet tests to data save conduct need to restore
Track；
Step S3: all possible driving trace between two bayonet of track for needing to restore is determined according to PPA routing algorithm
Set Ti；
Step S4: corresponding possible driving trace set T in historical path data set is calculatediEach path path
Journey time, section minimum discharge, path length, path number of turns and path are sought by signal controller mouth number
To about path forms time, section minimum discharge, path length, path number of turns and path by signal controller mouth number
Attribute decision factor；
Step S5: the path locus of identical starting bayonets all in historical path data set and terminal bayonet is all single
It solely takes out, each identical starting bayonet and terminal bayonet path locus is calculated by the method based on entropy weight Vague collection
The anti-weight parameter for pushing away path decision model；
Step S6: with the path locus and possibility of identical starting bayonets and terminal bayonet all in historical path data set
Driving trace set TiPath forms time, path length, path number of turns and path by signal controller mouth number
Input of the attribute decision factor as path decision model obtain final track rehabilitation programs in conjunction with weight parameter.
As a preferred embodiment, historical path data set described in step S2 includes track fullpath, rail
Mark starting point bayonet, final on trajectory bayonet, track starting point are detected the time, final on trajectory is detected time, path forms time.
As a preferred embodiment, specific step is as follows by step S3:
It delimit different road network sub-districts in advance on the full wafer road network of investigation, judges whether bayonet belongs to identical road network
Area carries out inter-two-point path search with Depth Priority Algorithm if belonging to identical road network sub-district,
If belonging to different road network sub-districts, after two sub-districts carry out route searching, engaged according to bayonet is overlapped, from
And tentatively obtain feasible trajectory set Tpre；
It is introduced into historical path data set, judges set TpreWhether each element goes out in historical path data set
It now crosses, if do not occurred, weeds out set TpreThe middle element for representing the path, to obtain feasible trajectory set
Thisto；
The vehicle import direction for restoring the terminal bayonet point of track as needed, further screens out ThistoMiddle generation
Can walking along the street through collecting, it is final determine under all two bayonets of parked track possible driving trace set Ti。
As a preferred embodiment, possible driving trace set T is calculated in step S4iEach path path
The attribute decision of journey time, section minimum discharge, path length, path number of turns and path by signal controller mouth number
Specific step is as follows for the factor:
Define stroke time match degree attribute factor GTT(Ti), section minimum discharge attribute factor GForce(Ti), path length
Spend attribute factor GLen(Ti), path number of turns attribute factor GC(Ti), path signal controls bayonet amount attribute factor GI(Ti)5
A attribute decision factor, and G is sought by standardizing evaluation functionTT(Ti)、GForce(Ti)、GLen(Ti)、GC(Ti)、GI(Ti), institute
The standardization evaluation function stated includes:
(a) journey time matching degree standardized nature evaluation function；
(b) traffic zone Attraction Degree standardized nature evaluation function；
(c) path length criterion attribute evaluation function；
(d) path number of turns standardized nature evaluation function；
(e) path signal controls bayonet amount standardized nature evaluation function；
Journey time matching degree standardized nature evaluation function calculation formula is as follows:
Wherein,It is TiIn theoretical path journey time, tiFor TiIn true journey time；J represents TiIn set
A kind of each element, that is, the route scheme restored, is denoted as scheme j；It is the theoretical path journey time in scheme j, tjFor side
True journey time in case j；
Traffic zone Attraction Degree standardized nature evaluation function calculation formula is as follows:
Wherein, FiFor TiIn import direction approach traffic zone attraction, FjFor the import direction way in scheme j
The attraction of the traffic zone of diameter, specific calculate refer to Gravity Models, the attraction between the adjacent bayonet passed through according to track
Power is accumulated to calculate, specific as follows,
Wherein QentranceIndicate TiThe flow in first section that import is passed through, FcarRepresent the automobile unit attracted, value
Link travel time is indicated for 1, t, is equivalent to journey time needed for completing track；
Path length criterion attribute evaluation function calculation formula is as follows:
Wherein, LiFor TiIn path length；LjFor the path length in scheme j
Path number of turns standardized nature evaluation function calculation formula is as follows:
Wherein, NiFor TiThe middle number for needing to turn；NjFor the number for needing to turn in scheme j；
It is as follows that path signal controls bayonet amount standardized nature evaluation function calculation formula:
Wherein, IiFor TiIn by signal controller mouth number；IjFor the number in scheme j by signal controller mouth；
Initialize feasible path locus set Ti, acquire GTT(Ti)、GForce(Ti)、GLen(Ti)、GC(Ti)、GI(Ti)。
As a preferred embodiment, specific step is as follows by step S5:
5 attribute decision factor G are setTT(Ti)、GForce(Ti)、GLen(Ti)、GC(Ti)、GI(Ti) weight w1,w2,w3,
w4,w5, the determination of decision-making power weight values is trained fitting by historical path data set and obtains；
The input of model is with identical starting bayonets all in historical path data set and terminal bayonet and TiDecision category
Sex factor GTT(Ti)、GForce(Ti)、GLen(Ti)、GC(Ti)、GI(Ti), wherein i=1, K, n, the scheme of model are possible traveling
Track set T={ T1,T2,Ti,K,Tn}；
The objective weight of the decision attribute factor is calculated by entropy assessment, steps are as follows,
It enablesλijFor decision scheme j decision attribute i attribute factor standard value；
The calculating of the entropy of decision system can pass through formula:It calculates
It arriving, the comentropy of decision attribute is smaller, and the information provided is bigger, then the weight that the decision attribute Factor minute is matched also should be bigger,
Weight that is on the contrary then distributing also should be smaller；
Normalized after benefit is taken to obtain the objective weight of decision attribute decision attribute entropy are as follows:
To decision attribute objective weight vector are as follows: w'=(w1',w'2,K,w'5)
Subjective decision attribute weight w "=(w "1,w”2,K,w”5), to obtain decision attribute weight vectors section are as follows:
Remember W=([w11,w12],[w21,w22],K,[w51,w52])。
As a preferred embodiment, specific step is as follows by step S6:
If d=(d1,d2,K,d5)TIndicate the vector of decision attribute, diIn include category of the every kind of scheme at decision attribute i
Sex factor standard value:
Sj={ di∈d|λij>λU}
Oj={ di∈d|λij<λL}
Nj={ di∈d|λL≤λij≤λU}
Sj,Oj,NjIt is the decision neutrality collection of the decision support collection of scheme j, the decision opposition collection of scheme j, scheme j respectively；
To alternative T={ T1,T2,Ti,K,Tn, the degree Vague value that it meets the requirements on 5 decision attributes
Vt∈TIt indicates, wherein t represents every kind of alternative, Vt∈T=[lt∈T,CIdt∈T], I is weight complete or collected works, i.e., each element is all 1,
lt∈T=[αt∈T,βt∈T], dt∈T=[μt∈T,ηt∈T]
Wherein
Define objective function of decision-making:
Wherein ft∈T∈ [- 1,1]
Then final track rehabilitation programs are as follows: max (ft∈T)。
Embodiment 2
As shown in Figure 1, Figure 2 and shown in Fig. 3, in the present embodiment, a data system was carried out by every 30min by 24 hours one day
Meter, available 48 time statistic windows after division
According to the data prediction that statistical time window is acquired, journey time sample after being sampled, estimation is every
Link Travel Time Estimation method under a statistical time window is as follows,
Firstly, by the Link Travel Time data acquired under statistical time window, it is different for traffic congestion in one day
Situation has carried out noise processed respectively；
Firstly for the Link Travel Time of different periods, the journey time that should all meet this moment is greater than the free flow time,
T is setl=Tfreeflow* α, TfreeflowFor the free flow time in section, exceed the speed limit the certain threshold space of sample to give urban road,
α generally takes 0.8-0.9, guarantees the adequacy of sampling；
For peak time (arriving and recession of peak time can be judged according to the historical data of specific urban transportation,
General to determine that morning peak is 7:00-9:00 or 7:30:00-9:30:00, evening peak is 17:00:00-19:00:00 or 16:30:
00-18:30:00), rejecting journey time is more than TuSample, TuFor the upper limit of Link Travel Time, 1800s can be taken as here,
It is classified as noise data；
For flat peak period (being generally determined as 10:00:00-16:00:00), TuDesirable Tu=β * Tfreeflow, β generally takes
3.5 or so, threshold value is adjusted according to section characteristic, flat peak period city road network is under normal traffic operation conditions, congestion in road
Grade is in medium or unimpeded state, therefore is likely to occur vehicle for individual larger journey time samples and goes out in two bayonet point interdigits
Existing of short duration parking phenomenon；
For time morning at night (0:00:00-6:00:00,19:00:00-23:59:59), TuDesirable Tu=γ *
Tfreeflow, γ generally takes 1.5 or so, excludes the influence of noise sample during this period；
By above-mentioned several steps, journey time sample data after obtaining preliminary screening, outlier when counting statistics in window is pressed
It needs to set suitable parameters and rejects the noise sample that peels off,
TT”'N=(TT "Ni|TT'N.mean-2σN.mean≤TT”Ni≤TT'N.mean+2σN.mean)
TT”'N=(TT "Ni|TT”N.median-3DNf.mean≤TT”'Ni≤TT”N.median+3DNa.mean)
Wherein TT "N.medianFor TT "NMedian,
(the case where n is even number, m=n/2, the rest may be inferred for odd number) is sample
The mean absolute deviation of this and sample median；
Above-mentioned steps are repeated as many times according to real data situation, until noise data rejects the stroke for completely guaranteeing to study
The sociability and representativeness of time data；
By the corresponding affiliated statistical time window of initial time corresponding to the journey time vehicle sample after cleaning, when taking statistics
Between all journey times of window be averaged to obtain the Link Travel Time Estimation value in the statistical time window, and record all systems
Count the Link Travel Time Estimation value of time window；
The travel time estimation value of all statistical time windows in all sections is calculated, and is saved and is used for subsequent stroke
The path theory journey time of time match calculates；
By the data prediction that statistical time window is acquired, the vehicle flow of each flow direction in each section is obtained；
According to urban road grade to limiting vehicle speed and section range time threshold and road topology structure to trip
It is tentatively extracted in path；
The path wherein continuously arrived by 4 and the above bayonet test is saved as historical path data set, data set packet
Include track fullpath, track starting point bayonet, final on trajectory bayonet, track starting point be detected the time, final on trajectory be detected when
Between, the path forms time；
It is recorded existing in each car wheelpath by the data that discontinuous two bayonet tests point detects, by it
The orbit segment restored labeled as needs；
(the road that do not detected by adjacent bayonet tollgate devices i.e. in road network topology between determining two bayonets for needing to restore track
Diameter) all possible driving trace set；
Assuming that Fig. 2 show certain piece road network of city road network, this road network includes 25 nodes, and 35 sections are drawn by road network
Separate 2 route searching sub-districts；
If two discontinuous bayonet test points are divided into ' 6 ' in the road network in Fig. 2, ' 22 ' can be according to PPA route searching
Algorithm determines feasible path, and specific step is as follows,
It delimit different road network sub-districts in advance on the full wafer road network of investigation, judges whether bayonet belongs to identical road network
Area carries out inter-two-point path search with depth-first search (DFS) algorithm if belonging to identical road network sub-district；
If belonging to different road network sub-districts, route searching engagement is carried out according to the intersection that two sub-districts are overlapped；
If belonging to different road network sub-districts, after two sub-districts carry out route searching, it is glutinous that path is carried out according to linking bayonet
It closes, to obtain feasible trajectory set Tpre={ T1,T2,K,Tk, wherein k is that the preparation track of satisfaction recovery tracking condition is total
Number；
Historical path data set is introduced, judges set TpreWhether each element occurs in historical path data set
It crosses, if do not occurred, weeds out set TpreThe middle element for representing the path, to obtain feasible trajectory set Thisto
={ T1,T2,K,Tm}；
The vehicle import direction for restoring the terminal bayonet point of track as needed, can further screen out the feasible of generation
Road is through collecting, the possible driving trace set T={ T of all two bayonets of parked track under finally determining1,T2,Ti,K,Tn,
Middle n is the preparation total number of tracks after preliminary screening；
Set journey time matching degree attribute factor, section minimum discharge attribute factor, the path length attribute factor, path
Number of turns attribute factor, path signal controls 5 attribute decision factors of bayonet amount attribute factor, and design standardization evaluates letter
Number:
Journey time matching degree standardized nature evaluation function:
Wherein,It is TiIn theoretical path journey time, tiFor TiIn true journey time；
Traffic zone Attraction Degree standardized nature evaluation function:
Wherein, T TiIn approach section set, FiFor TiIn import direction approach traffic zone attraction,
Its specific calculating refers to Gravity Models, and the attraction between the adjacent bayonet passed through according to track accumulates to calculate, specific as follows,
Wherein QentranceIndicate TiThe flow in first section that import is passed through, FcarRepresent the automobile unit attracted, value
Link travel time is indicated for 1, t, is equivalent to journey time needed for completing track；
Path length criterion attribute evaluation function:
Wherein, LiFor TiIn path length；
Path number of turns standardized nature evaluation function:
Wherein, NiFor TiThe middle number for needing to turn；
Path signal controls bayonet amount standardized nature evaluation function:
Wherein, IiFor TiIn by signal controller mouth number；
Initialize feasible path locus set Ti, acquire GTT(Ti)、GForce(Ti)、GLen(Ti)、GC(Ti)、GI(Ti)。
According to historical path data set, will own corresponding to wherein each all identical starting bayonets and terminal bayonet
Path set record individually extracts, and the historical path collective data of each all identical starting bayonets and terminal bayonet is available
In the training of subsequent attribute factor decision parameters；
5 attribute decision factor G are setTT(Ti)、GForce(Ti)、GLen(Ti)、GC(Ti)、GI(Ti) weight w1,w2,w3,
w4,w5, decision weights are worth to determine that being trained fitting according to history data set obtains；
Each all identical starting bayonets are calculated by the method based on entropy weight Vague collection and terminal bayonet is counter pushes away
The weight parameter of path decision model, the input of model are all identical starting bayonets of history and terminal bayonet being retained separately
Between track set in TiThe decision attribute factor: GTT(Ti)、GForce(Ti)、GLen(Ti)、GC(Ti)、GI(Ti), wherein i=1, K,
N, as shown in figure 3, the scheme of model is possible driving trace set T={ T1,T2,Ti,K,Tn}；
The objective weight of the decision attribute factor is calculated by entropy assessment, steps are as follows,
It enablesλijFor decision scheme j decision attribute i attribute factor standard value；
The calculating of the entropy of decision system can pass through formula:It calculates
It arriving, the comentropy of decision attribute is smaller, and the information provided is bigger, then the weight that the decision attribute Factor minute is matched also should be bigger,
Weight that is on the contrary then distributing also should be smaller；
Normalized after benefit is taken to obtain the objective weight of decision attribute decision attribute entropy are as follows:
To decision attribute objective weight vector are as follows: w'=(w1',w'2,K,w'5)
Subjective decision attribute weight w "=(w "1,w”2,K,w”5), to obtain decision attribute weight vectors section are as follows:
Remember W=([w11,w12],[w21,w22],K,[w51,w52])；
If d=(d1,d2,K,d5)TIndicate the vector of decision attribute, diIn include category of the every kind of scheme at decision attribute i
Sex factor standard value:
Sj={ di∈d|λij>λU}
Oj={ di∈d|λij<λL}
Nj={ di∈d|λL≤λij≤λU}
Sj,Oj,NjIt is the decision neutrality collection of the decision support collection of scheme j, the decision opposition collection of scheme j, scheme j respectively；
To alternative T={ T1,T2,Ti,K,Tn, the degree Vague value that it meets the requirements on 5 decision attributes
Vt∈TIt indicates, wherein t represents every kind of alternative, Vt∈T=[lt∈T,CIdt∈T], I is weight complete or collected works, i.e., each element is all 1,
lt∈T=[αt∈T,βt∈T], dt∈T=[μt∈T,ηt∈T]
Wherein
Define objective function of decision-making:
Wherein ft∈T∈ [- 1,1]
Then final track rehabilitation programs are as follows: max (ft∈T)。
The same or similar label correspond to the same or similar components；
The terms describing the positional relationship in the drawings are only for illustration, should not be understood as the limitation to this patent；
Obviously, the above embodiment of the present invention be only to clearly illustrate example of the present invention, and not be pair
The restriction of embodiments of the present invention.For those of ordinary skill in the art, may be used also on the basis of the above description
To make other variations or changes in different ways.There is no necessity and possibility to exhaust all the enbodiments.It is all this
Made any modifications, equivalent replacements, and improvements etc., should be included in the claims in the present invention within the spirit and principle of invention
Protection scope within.
Claims (6)
1. a kind of urban transportation Trip chain reconstructing method based on bayonet video data, which comprises the following steps:
Step S1: then acquisition handles video data by the video data of the vehicle of bayonet, is obtained through bayonet
The license plate data of vehicle, the wheelpath based on the vehicle license plate data building each car extracted from different bayonets；
Step S2: the path continuously arrived by 4 and the above bayonet test in each car wheelpath is saved as historical path
Data set will there are the path tag of bayonet missing inspection be to need the track restored in each car wheelpath；
Step S3: all possible traveling in the track for needing to restore between its two bayonet of head and the tail is determined according to PPA routing algorithm
Track set Ti；
Step S4: possible driving trace set T is initializedi, possible driving trace set TiEach path path forms
Time, section minimum discharge, path length, path number of turns and path are obtained by signal controlled junctions number about path
The attribute decision of journey time, section minimum discharge, path length, path number of turns and path by signal controlled junctions number
The factor；
Step S5: build path decision model, its two bayonet phase of head and the tail of track that will be restored in historical path data set with needs
Same path is taken out, and is then based on these data by the method calculating based on entropy weight Vague collection and is back-calculated to obtain path decision mould
The weight parameter of type；
Step S6: with possible driving trace set TiThe path in middle its identical path of two bayonet of head and the tail of track for needing to restore
Journey time, path length, path number of turns and path are joined by the attribute decision factor and weight of signal controlled junctions number
Input of the number as path decision model, obtains final track rehabilitation programs.
2. a kind of urban transportation Trip chain reconstructing method based on bayonet video data according to claim 1, feature
Be, historical path data set described in step S2 include track fullpath, track starting point bayonet, final on trajectory bayonet,
Track starting point is detected the time, final on trajectory is detected time, path forms time.
3. a kind of urban transportation Trip chain reconstructing method based on bayonet video data according to claim 2, feature
It is, specific step is as follows by step S3:
The section for being provided with bayonet is divided into different road network sub-districts, judges whether bayonet belongs to identical road network between any two
Sub-district carries out inter-two-point path search with Depth Priority Algorithm, if belonging to difference if belonging to identical road network sub-district
Road network sub-district is engaged, to tentatively obtain feasible rail then after two-way net area carries out route searching according to bayonet is overlapped
Trace set Tpre；
It is introduced into historical path data set, judges set TpreWhether each element occurred in historical path data set,
If do not occurred, set T is weeded outpreThe middle element for representing the path, to obtain feasible trajectory set Thisto；
The vehicle import direction for restoring the terminal bayonet point of track as needed, further screens out ThistoMiddle generation it is feasible
Path set, all possible driving trace set T under finally determining in the track of all recoveries between its two bayonet of head and the taili。
4. a kind of urban transportation Trip chain reconstructing method based on bayonet video data according to claim 3, feature
It is, possible driving trace set T is calculated in step S4iPath forms time of each path, section minimum discharge, road
Specific step is as follows by the attribute decision factor of signal controller mouth number for electrical path length, path number of turns and path:
Define stroke time match degree attribute factor GTT(Ti), section minimum discharge attribute factor GForce(Ti), path length category
Sex factor GLen(Ti), path number of turns attribute factor GC(Ti), path signal controls bayonet amount attribute factor GI(Ti) 5 belong to
Property decision factor, and by standardize evaluation function seek GTT(Ti)、GForce(Ti)、GLen(Ti)、GC(Ti)、GI(Ti), it is described
Standardizing evaluation function includes:
(a) journey time matching degree standardized nature evaluation function；
(b) traffic zone Attraction Degree standardized nature evaluation function；
(c) path length criterion attribute evaluation function；
(d) path number of turns standardized nature evaluation function；
(e) path signal controls bayonet amount standardized nature evaluation function；
Journey time matching degree standardized nature evaluation function calculation formula is as follows:
Wherein,It is TiIn theoretical path journey time, tiFor TiIn true journey time；J represents TiEach of set
A kind of element, that is, the route scheme restored, is denoted as scheme j；It is the theoretical path journey time in scheme j, tjFor in scheme j
True journey time；
Traffic zone Attraction Degree standardized nature evaluation function calculation formula is as follows:
Wherein, FiFor TiIn import direction approach traffic zone attraction, FjFor the import direction approach in scheme j
The attraction of traffic zone, specific calculate refer to Gravity Models, and the attraction between the adjacent bayonet passed through according to track is tired
Product is specific as follows to calculate,
Wherein QentranceIndicate TiThe flow in first section that import is passed through, FcarThe automobile unit that representative attracts, value 1,
T indicates link travel time, is equivalent to journey time needed for completing track；
Path length criterion attribute evaluation function calculation formula is as follows:
Wherein, LiFor TiIn path length；LjFor the path length in scheme j
Path number of turns standardized nature evaluation function calculation formula is as follows:
Wherein, NiFor TiThe middle number for needing to turn；NjFor the number for needing to turn in scheme j；
It is as follows that path signal controls bayonet amount standardized nature evaluation function calculation formula:
Wherein, IiFor TiIn by signal controller mouth number；IjFor the number in scheme j by signal controller mouth；
Initialize feasible path locus set Ti, acquire GTT(Ti)、GForce(Ti)、GLen(Ti)、GC(Ti)、GI(Ti)。
5. a kind of urban transportation Trip chain reconstructing method based on bayonet video data according to claim 4, feature
It is, the weight parameter of path decision model is sought in step S5, and specific step is as follows:
Define 5 attribute decision factor GTT(Ti)、GForce(Ti)、GLen(Ti)、GC(Ti)、GI(Ti) weight be w1,w2,w3,w4,
w5, the determination of decision-making power weight values is trained fitting by historical path data set and obtains；
The input of model is with TiDecision attribute factor GTT(Ti)、GForce(Ti)、GLen(Ti)、GC(Ti)、GI(Ti), wherein i=1,
K, n, the scheme of model are possible driving trace set T={ T1,T2,Ti,K,Tn}；
The objective weight of the decision attribute factor is calculated by entropy assessment, steps are as follows,
It enablesλijMiddle i is 5 attribute decision factor GTT(Ti)、GForce(Ti)、GLen(Ti)、GC
(Ti), j TiMiddle n possible driving trace schemes；
The calculating of the entropy of decision system can pass through formula:
Wherein,The comentropy of decision attribute is smaller, provides
Information it is bigger, then the weight that the decision attribute Factor minute is matched also should be bigger, and weight that is on the contrary then distributing also should be smaller；
Normalized after benefit is taken to obtain the objective weight of decision attribute decision attribute entropy are as follows:
To acquire 5 attribute decision factor GTT(Ti)、GForce(Ti)、GLen(Ti)、GC(Ti)、GI(Ti) decision attribute it is objective
Weight vectors are as follows: w'=(w '1,w'2,K,w'5)
If 5 attribute decision factor GTT(Ti)、GForce(Ti)、GLen(Ti)、GC(Ti)、GI(Ti) subjective decision attribute weight be
W "=(w "1,w″2,K,w″5), to obtain decision attribute weight vectors section are as follows:
Remember W=([w11,w12],[w21,w22],K,[w51,w52])。
6. a kind of urban transportation Trip chain reconstructing method based on bayonet video data according to claim 5, feature
It is, final track rehabilitation programs are sought in step S6, and specific step is as follows:
Define d=(d1,d2,K,d5)TIndicate the vector of decision attribute, diIn include each possible wheelpath in decision attribute
Under attribute factor standard value:
Sj={ di∈d|λij>λU}
Oj={ di∈d|λij<λL}
Nj={ di∈d|λL≤λij≤λU}
Sj,Oj,NjThe decision of the decision support collection, scheme j that are respectively defined as scheme j opposes the decision neutrality collection of collection, scheme j；
For T={ T1,T2,Ti,K,Tn, it is in GTT(Ti)、GForce(Ti)、GLen(Ti)、GC(Ti)、GI(Ti) 5 decision attributes
On the degree Vague value V that meets the requirementst∈TIt indicates, wherein t represents every kind of alternative, Vt∈T=[lt∈T,CIdt∈T], I is
Weight complete or collected works, i.e., each element is all 1, lt∈T=[αt∈T,βt∈T], dt∈T=[μt∈T,ηt∈T]；
WhereinΨ=i | di∈Sj,Θ=i | di∈Oj,
Define objective function of decision-making:
Wherein ft∈T∈ [- 1,1]
Then final track rehabilitation programs are as follows: max (ft∈T)。
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910550349.5A CN110276950B (en) | 2019-06-24 | 2019-06-24 | Urban traffic trip chain reconstruction method based on bayonet video data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910550349.5A CN110276950B (en) | 2019-06-24 | 2019-06-24 | Urban traffic trip chain reconstruction method based on bayonet video data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110276950A true CN110276950A (en) | 2019-09-24 |
| CN110276950B CN110276950B (en) | 2021-12-31 |
Family
ID=67961789
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910550349.5A Active CN110276950B (en) | 2019-06-24 | 2019-06-24 | Urban traffic trip chain reconstruction method based on bayonet video data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110276950B (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111768619A (en) * | 2020-06-16 | 2020-10-13 | 苏州大学 | Express way vehicle OD point determining method based on checkpoint data |
| CN112289026A (en) * | 2020-10-26 | 2021-01-29 | 山东旗帜信息有限公司 | Vehicle route restoration method, equipment and medium |
| CN112309118A (en) * | 2020-11-03 | 2021-02-02 | 广州市交通规划研究院 | Vehicle trajectory calculation method based on space-time similarity |
| CN112365711A (en) * | 2020-10-21 | 2021-02-12 | 东南大学 | Vehicle track reconstruction method based on license plate recognition data |
| CN112985442A (en) * | 2021-03-03 | 2021-06-18 | 北京嘀嘀无限科技发展有限公司 | Driving path matching method, readable storage medium and electronic device |
| CN113129589A (en) * | 2021-03-26 | 2021-07-16 | 中山大学 | Individual OD cell inference method based on bayonet detection data |
| CN113297342A (en) * | 2021-05-18 | 2021-08-24 | 北京理工大学前沿技术研究院 | Vehicle driving track reconstruction method, device, equipment and storage medium |
| CN113763696A (en) * | 2020-06-01 | 2021-12-07 | 杭州海康威视数字技术股份有限公司 | Vehicle path reconstruction method and device, electronic equipment and storage medium |
| WO2022083166A1 (en) * | 2020-10-19 | 2022-04-28 | 山东交通学院 | Method and system for reconstructing vehicle's driving trajectory when checkpoint data is missing |
| CN115512543A (en) * | 2022-09-21 | 2022-12-23 | 浙江大学 | Vehicle path chain reconstruction method based on deep reverse reinforcement learning |
| CN117711174A (en) * | 2023-12-07 | 2024-03-15 | 山东高速集团有限公司 | Data processing method and system for vehicle passing information |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103440764A (en) * | 2013-08-19 | 2013-12-11 | 同济大学 | Urban road network vehicle travel path reconstruction method based on vehicle automatic identification data |
| CN104778274A (en) * | 2015-04-23 | 2015-07-15 | 山东大学 | Wide-range urban road network travel time estimation method based on sparse taxi GPS (Global Positioning System) data |
| CN105606110A (en) * | 2015-11-03 | 2016-05-25 | 中兴软创科技股份有限公司 | Depth-first traversal-based feasible path searching method and device |
| CN105678410A (en) * | 2015-12-31 | 2016-06-15 | 哈尔滨工业大学 | Public traffic system space-time reachability modeling method of considering network connectivity time varying characteristics |
| CN106023589A (en) * | 2016-06-16 | 2016-10-12 | 北京航空航天大学 | Gate data-based vehicle trajectory reconstruction method |
| CN107195180A (en) * | 2017-06-08 | 2017-09-22 | 青岛海信网络科技股份有限公司 | A kind of traffic trip track extraction method and device based on the alert data of electricity |
| WO2018099480A1 (en) * | 2016-12-01 | 2018-06-07 | 中兴通讯股份有限公司 | Vehicle driving trajectory monitoring method and system |
| CN108335485A (en) * | 2018-01-31 | 2018-07-27 | 夏莹杰 | The method of major issue traffic dynamic emulation congestion prediction based on license plate identification data |
| CN108961747A (en) * | 2018-07-03 | 2018-12-07 | 北京航空航天大学 | A kind of urban road traffic state information extracting method under incomplete bayonet data qualification |
| CN109166309A (en) * | 2018-08-06 | 2019-01-08 | 重庆邮电大学 | A kind of missing data on flows restoration methods towards complicated urban traffic network |
| CN109190056A (en) * | 2018-08-22 | 2019-01-11 | 深圳先进技术研究院 | A kind of track of vehicle method for reconstructing, system and electronic equipment |
-
2019
- 2019-06-24 CN CN201910550349.5A patent/CN110276950B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103440764A (en) * | 2013-08-19 | 2013-12-11 | 同济大学 | Urban road network vehicle travel path reconstruction method based on vehicle automatic identification data |
| CN104778274A (en) * | 2015-04-23 | 2015-07-15 | 山东大学 | Wide-range urban road network travel time estimation method based on sparse taxi GPS (Global Positioning System) data |
| CN105606110A (en) * | 2015-11-03 | 2016-05-25 | 中兴软创科技股份有限公司 | Depth-first traversal-based feasible path searching method and device |
| CN105678410A (en) * | 2015-12-31 | 2016-06-15 | 哈尔滨工业大学 | Public traffic system space-time reachability modeling method of considering network connectivity time varying characteristics |
| CN106023589A (en) * | 2016-06-16 | 2016-10-12 | 北京航空航天大学 | Gate data-based vehicle trajectory reconstruction method |
| WO2018099480A1 (en) * | 2016-12-01 | 2018-06-07 | 中兴通讯股份有限公司 | Vehicle driving trajectory monitoring method and system |
| CN107195180A (en) * | 2017-06-08 | 2017-09-22 | 青岛海信网络科技股份有限公司 | A kind of traffic trip track extraction method and device based on the alert data of electricity |
| CN108335485A (en) * | 2018-01-31 | 2018-07-27 | 夏莹杰 | The method of major issue traffic dynamic emulation congestion prediction based on license plate identification data |
| CN108961747A (en) * | 2018-07-03 | 2018-12-07 | 北京航空航天大学 | A kind of urban road traffic state information extracting method under incomplete bayonet data qualification |
| CN109166309A (en) * | 2018-08-06 | 2019-01-08 | 重庆邮电大学 | A kind of missing data on flows restoration methods towards complicated urban traffic network |
| CN109190056A (en) * | 2018-08-22 | 2019-01-11 | 深圳先进技术研究院 | A kind of track of vehicle method for reconstructing, system and electronic equipment |
Non-Patent Citations (2)
| Title |
|---|
| 曾令宇: "适用于不同交通状态的交通控制小区动态划分方法研究", 《中国优秀硕士学位论文全文数据库工程科技II辑》 * |
| 赵庆庆: "基于熵权Vague集的多目标决策方法", 《计算机应用》 * |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113763696A (en) * | 2020-06-01 | 2021-12-07 | 杭州海康威视数字技术股份有限公司 | Vehicle path reconstruction method and device, electronic equipment and storage medium |
| CN111768619A (en) * | 2020-06-16 | 2020-10-13 | 苏州大学 | Express way vehicle OD point determining method based on checkpoint data |
| WO2022083166A1 (en) * | 2020-10-19 | 2022-04-28 | 山东交通学院 | Method and system for reconstructing vehicle's driving trajectory when checkpoint data is missing |
| CN112365711A (en) * | 2020-10-21 | 2021-02-12 | 东南大学 | Vehicle track reconstruction method based on license plate recognition data |
| CN112365711B (en) * | 2020-10-21 | 2021-11-02 | 东南大学 | Vehicle track reconstruction method based on license plate recognition data |
| CN112289026A (en) * | 2020-10-26 | 2021-01-29 | 山东旗帜信息有限公司 | Vehicle route restoration method, equipment and medium |
| CN112309118A (en) * | 2020-11-03 | 2021-02-02 | 广州市交通规划研究院 | Vehicle trajectory calculation method based on space-time similarity |
| CN112985442A (en) * | 2021-03-03 | 2021-06-18 | 北京嘀嘀无限科技发展有限公司 | Driving path matching method, readable storage medium and electronic device |
| CN112985442B (en) * | 2021-03-03 | 2022-11-04 | 北京嘀嘀无限科技发展有限公司 | Driving path matching method, readable storage medium and electronic device |
| CN113129589A (en) * | 2021-03-26 | 2021-07-16 | 中山大学 | Individual OD cell inference method based on bayonet detection data |
| CN113297342A (en) * | 2021-05-18 | 2021-08-24 | 北京理工大学前沿技术研究院 | Vehicle driving track reconstruction method, device, equipment and storage medium |
| CN113297342B (en) * | 2021-05-18 | 2022-05-10 | 北京理工大学前沿技术研究院 | Vehicle driving track reconstruction method, device, equipment and storage medium |
| CN115512543A (en) * | 2022-09-21 | 2022-12-23 | 浙江大学 | Vehicle path chain reconstruction method based on deep reverse reinforcement learning |
| CN115512543B (en) * | 2022-09-21 | 2023-11-28 | 浙江大学 | Vehicle path chain reconstruction method based on deep reverse reinforcement learning |
| CN117711174A (en) * | 2023-12-07 | 2024-03-15 | 山东高速集团有限公司 | Data processing method and system for vehicle passing information |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110276950B (en) | 2021-12-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110276950A (en) | A kind of urban transportation Trip chain reconstructing method based on bayonet video data | |
| CN102394008B (en) | Assessing road traffic conditions using data from mobile data sources | |
| CN106197458B (en) | A kind of mobile phone user's trip mode recognition methods based on mobile phone signaling data and navigation route data | |
| CN103593974B (en) | A kind of public transport passenger capacity collection method based on locating information | |
| Li et al. | Prediction of urban human mobility using large-scale taxi traces and its applications | |
| WO2021082464A1 (en) | Method and device for predicting destination of vehicle | |
| Brockfeld et al. | Benefits and limits of recent floating car data technology–an evaluation study | |
| CN107784835A (en) | Traffic behavior model prediction system and its Forecasting Methodology based on traffic data analyzing | |
| CN104318781B (en) | Based on the travel speed acquisition methods of RFID technique | |
| CN109615851B (en) | Sensing node selection method based on key road section in crowd sensing system | |
| CN110400462B (en) | Track traffic passenger flow monitoring and early warning method and system based on fuzzy theory | |
| Chen et al. | Dynamic travel time prediction using pattern recognition | |
| Thianniwet et al. | Classification of road traffic congestion levels from GPS data using a decision tree algorithm and sliding windows | |
| CN107527501A (en) | The building method of travel time data and the method for predicting the motorway journeys time between a kind of highway station | |
| Xu et al. | Utilizing artificial neural network in GPS-equipped probe vehicles data-based travel time estimation | |
| Jiang et al. | Travel time prediction based on historical trajectory data | |
| Nandury et al. | Strategies to handle big data for traffic management in smart cities | |
| CN110827537B (en) | Method, device and equipment for setting tidal lane | |
| Weng et al. | Freeway travel speed calculation model based on ETC transaction data | |
| Habtie et al. | Cellular network based real-time urban road traffic state estimation framework using neural network model estimation | |
| CN111931968B (en) | Method for optimizing public bicycle station layout by using mobile phone GPS data | |
| KR102646880B1 (en) | Traffic light operation system according to the results of analysis of road surface conditions and traffic patterns at signal intersections to increase traffic volume | |
| CN115565388A (en) | Traffic light control method based on multi-channel vehicle detection and three-dimensional feature labeling | |
| CN111640303B (en) | City commuting path identification method and equipment | |
| CN109409731B (en) | Highway holiday travel feature identification method fusing section detection traffic data and crowdsourcing data |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |