CN102881162A - Data processing and fusion method for large-scale traffic information - Google Patents

Abstract

The invention discloses a data processing and fusion method for large-scale traffic information and belongs to real-time traffic information processing technologies. The method includes: obtaining normal data of a truth value according to multisource traffic data acquired by a test vehicle and each sensor, and determining a dynamic assignment method for parameters; rejecting abnormal data in data sets acquired by the sensors, and performing historical data compensation; and fusing real-time grading information of the multisource traffic data with data compensation completed. The truth value system is set up for obtaining correct initial assignment parameters of various acquisition modes and rejecting acquired abnormal data, missing data are reasonably filled according to the historical data to guarantee accuracy and integrity of the data, and the data acquired by different acquisition modes are graded and fused gradually to guarantee reliability of the data. Moreover, quickness in the fusion process is achieved, and influences of traffic incidents, traffic control, land occupation construction and traffic accidents on data in the fusion process are considered.

Description

The data of extensive transport information are processed and fusion method

Technical field

The present invention relates to the transport information real-time processing technique field of intelligent transportation system, particularly a kind of data of extensive transport information are processed and fusion method.

Background technology

Information fusion is applied to military field the earliest, is multi-level, many-sided process that combination multi-source information and data are finished target detection, related, state estimation.The purpose of this information fusion is to obtain accurately target identification, complete and timely situation of battlefield and threat assessment.Development along with sensor technology, computer science and infotech, various multisensor systes towards the complicated applications background emerge in multitude, so that acquisition of information by all kinds of means, processing and fusion become possibility, and at numerous areas such as Financial Management, psychological assessment and prediction, medical diagnosis, weather forecast, organization and administration decision-making, robot vision, traffic control, remote sensing remote measurements, people recognize the informix in a plurality of data sources are got up to improve the achievement of work.Therefore, multisource information fusion technology has obtained paying attention to widely and successful application in military field and civil area, and its theory and method have become an important research direction of Intelligent Information Processing and control.

Prior art more concentrates on the data level information fusion, and it directly carries out comprehensive to not pretreated sensor original observed data and analyzes.Advantage is to have kept object information as much as possible, and information dropout or omission do not occur substantially; Shortcoming is that deal with data is too many, expends time in oversize, and real-time is poor.Another kind of information fusion is the feature level information fusion, also claims the file-level information fusion, is to passing through after the preliminary pre-service of sensor, realizing the comprehensive analysis processing that essential characteristic extracts, provides the basis of files and reports to carry out at sensor.Its advantage is the important information that had both kept sufficient amount, has passed through again permissible data compression, has greatly diluted data volume, can improve the real-time of processing procedure; And valuable especially be in the Modern High-Techs such as pattern-recognition, graphical analysis, computer vision use, reality all take feature extraction as the basis, is all carried out extensive work in this respect.The shortcoming of feature level information fusion is to have inevitably some information loss, thereby need the sensor pre-service is proposed stricter requirement.

Because the polyphyly of traffic data must use a kind of effective method reasonable coordination multi-source data, fully comprehensive useful information improves the ability of correct decisions in changeable environment.Data fusion technique is a kind of good tool that satisfies this requirement.The polyphyly of traffic data and complicacy require transport information to process must have Data fusion technique, and the robustness of transport information so just can be provided.

Existing traffic data integration technology more concentrates on the data level information fusion, fusion process is not carried out classification to data according to the stability of sensor, and the data that sensor do not collected are carried out verification and are rejected, data merge step by step, do not consider the impact that traffic events, traffic control, occupation of land construction, traffic hazard bring to data in fusion process.

Summary of the invention

In view of this, the object of the present invention is to provide a kind of data of extensive transport information to process and fusion method, be used for realizing the efficient fusion of traffic information data.

The data that the invention provides a kind of extensive transport information are processed and fusion method, comprising:

The multi-source traffic data that collects according to test carriage and each sensor obtains the normal data of true value system, and the dynamic assignment method of definite parameter; Reject the abnormal data in the data acquisition that described sensor collects, and carry out the compensation of historical data; To finishing the multi-source traffic data real-time graded information fusion of compensation data.

The present invention obtains the correct initial assignment parameter of various acquisition modes by setting up the true value system, the data that truly collect are carried out abnormity removing, missing data rationally fills up to guarantee accuracy and the integrality of data according to historical data, the data that different classes of acquisition mode is obtained carry out classification step by step fusion treatment to guarantee the reliability of the data, the rapidity of fusion process, and in fusion process, consider the impact that traffic events, traffic control, occupation of land construction, traffic hazard bring to data.Through this fusion process, realize quick, accurate, the reliable texts of fusion, the true value system has solved the inaccurate problem of prior art initial parameter assignment; Rejecting abnormal data, missing data filled up overcome prior art acquisition terminal unstable properties, and the difficult problem damaged of acquisition terminal; Adopt the D-S theory that the data after processing are carried out the classification fusion treatment, solved the polyphyly problem of data fusion; Also take into full account traffic events, traffic control, occupation of land construction, traffic hazard, overcome the impact that data is caused because of above factor.

Description of drawings

Fig. 1 processes and the fusion method process flow diagram for the data of the extensive transport information that the embodiment of the invention provides;

Fig. 2 is to the method flow diagram of dynamic state of parameters assignment in the embodiment of the invention.

Embodiment

For making the purpose, technical solutions and advantages of the present invention clearer, the present invention is described in further detail below in conjunction with accompanying drawing.

The traffic data fusion process that the embodiment of the invention provides can realize merging fast, accurately, reliable texts, the true value system has solved the inaccurate problem of prior art initial parameter assignment; Rejecting abnormal data, missing data filled up overcome prior art acquisition terminal unstable properties, and the difficult problem damaged of acquisition terminal; Adopt the D-S theory that the data after processing are carried out the classification fusion treatment, solved the polyphyly problem of data fusion; Also take into full account traffic events, traffic control, occupation of land construction, traffic hazard, overcome the impact that data is caused because of above factor.

Fig. 1 processes and the fusion method process flow diagram for the data of the extensive transport information that the embodiment of the invention provides, and may further comprise the steps:

Step 101, obtain the true value system, and definite D-S(Dempster-Sharer evidence theory multi-source data fusion method) in the dynamic assignment method of parameter.

Described true value system standard data are the test carriages by many high sampling rates, repeatedly test in the different periods, and obtain the mean value of period t, as standard value:

X _{I, j}(t) represent at the measured value of period t test, n car carries out m measurement the j time of i test carriage.

Fig. 2 is to the method flow diagram of dynamic state of parameters assignment, may further comprise the steps:

The data that step 1011, the data that period t test carriage is collected and each sensor collect, split out taxi data, bus data, microwave/loop data, video monitoring data, and license plate identification data, as all kinds of traffic information datas of period t.Because different collecting devices all can collect the data of same type, but each collecting device acquisition precision and influenced factor thereof are different, therefore, substep can occur and merge in subsequent step.

Step 1012, calculate its standard deviation at the mean value of period t as standard value take taxi data, bus data, microwave/loop data, video monitoring data and license plate identification data respectively:

$D\left(X\right)=\sqrt{\frac{1}{N}\underset{i=1,..}{\mathrm{\Σ}}{(\mathrm{Xi}-E\left(X\right))}^2}$

Wherein, E (X) tests the mean value that obtains all data, X for the t period _iI test data of expression Various types of data.

The dispersion degree of standard deviation response data, the i.e. degree of stability of data.

Step 1013, use described standard deviation and standard value, obtain respectively the normal distribution of every class data, determine credibility interval (being the generated data reception interval), according to normal curve, computational data is at the probability of credibility interval:

$P(a<X<b)={\&Integral;}_a^b\frac{1}{D\left(X\right)\sqrt{2\mathrm{\&Pi;}}}{e}^{\frac{1}{2}{\left(\frac{X-E\left(X\right)}{D\left(x\right)}\right)}^2}$

Wherein, a, b represent respectively test data depart from standard value X about can accept the boundary value of data, D (X) is standard deviation, E (X) is mean value.

Step 1014, with described data at the probability of credibility interval to every class data basic probability assignment function m (A) assignment.For example taxi data basic probability assignment function m (A) assignment procedure is that (a＜A＜b), A represents the taxi data to m (A)=P, and (a＜A＜b) represent the taxi image data at the probability of credibility interval as above calculates P.

Abnormal data in the data acquisition that step 102, rejecting sensor collect.Step 101 is that test carriage is repeatedly tested the data that obtain under normal circumstances, for the Various types of data initial parameter assignment in the data fusion process is prepared.And in reality, can cause the unusual of data owing to various factors, therefore, real sensor at first will carry out rejecting abnormal data after collecting data, below is the processing that real data is carried out.

The corresponding classification of calculation interval t (comprising taxi data, bus data, microwave/loop data, video monitoring data and license plate identification data) traffic information data X(X is the data that collect under the actual environment respectively, and 101 steps narration X is the data under test carriage and all normal environment of collector) and historical information data H.H is to the storage of (comprising taxi data, bus data, microwave/loop data, video monitoring data and license plate identification data) of the traffic information data in past 1 year.Calculate mathematical expectation E (X), the E (H) of X, H, standard deviation D (X), the D (H) of all kinds of traffic information data X of calculation interval t and past historical information data H 1 year same period, if:

(1) traffic information data that collects for each sensor of period t and test carriage, mathematical expectation E (X) and mathematical expectation E (H) difference are in setting threshold values th scope, and D (X) and D (H) difference in setting threshold values th ', think that then these moment data do not have abnormal equally;

(2) traffic information data that collects for each sensor of period t and test carriage, mathematical expectation E (X) and mathematical expectation E (H) exceed setting threshold values th, but D (X) and D (H) difference are then waited for the traffic information data X of next period in setting threshold values th ' " generate; If (X ") has larger difference, exceeds to set threshold values th ', then thinks the transport information abnormal of period t, and rejecting abnormal data is fallen for the traffic information data D (X) of next period and D.

In preferred embodiment, the th Threshold is th=E (H)/2, th '=D (X)/2.

The compensation of step 103, historical data.Traffic information data that every day, each sensor and test carriage collected stores through the data that obtain after the step 102, as historical data, and data by way of compensation when shortage of data occurring for future.

According to historical data, calculate respectively mutually the on the same day road network average velocity of interior all kinds of traffic information datas, comprise taxi data road network average velocity, bus data average velocity, microwave/loop data average velocity, generate the traffic tendency curve.

After every day, each sensor and test carriage collected data, in time data are carried out in rough handling (rejecting the abnormal data in the data) process, search the Q that comprises the traffic data file (being the traffic data with similar traffic tendency curve of front classification storage) in the adjacent Z time period, calculate the road network average velocity of each time period traffic data file, and this average velocity is considered as a point, smooth connection Z dot generation transport information curve segment.Historical data in this curve segment and the same time section is mated, find out the most similar P bar curve as ancillary sources, wherein Z, P and Q be according to algorithm, historical statistics, put into practice, functional value that experience, system performance draw, Z represents the time period, Q represents the file amount of generation in Z time period, and P represents the most similar curve quantity.An adjacent Z time period, take one hour as unit, 24 time periods.General data gathers per five minutes and generates data, and a time period can generate 12 data files, and Q calculated by 24 time periods can generate 288 values, and the P value is 1 to get final product.

The time attribute of all kinds of traffic information datas that collect according to each sensor and test carriage is searched in the ancillary sources that obtains from above step with the historical data that the road chain of traffic data disappearance has identical unique number, a same time attribute absence information road chain in the compensatory zone is filled up.Wherein time attribute comprises cycle in week and residing time window characteristic of this moment.Why disappearance can appear in data, on the one hand be because rejecting abnormal data might cause the discontinuous of data, be on the other hand since each data-source device because extraneous factor or the human factor short duration failure causes data in time not gather or Acquisition Error is larger.And the latter is particularly important.

Step 104, multi-source traffic data (multi-source data herein comprises through taxi data, bus data, microwave/loop data, video monitoring data behind rejecting and the compensation data, and license plate identification data) the real-time graded information fusion to finishing compensation data.The basis that three steps in front are real-time graded information fusion, it is that rating information merges the fusion parameters when determining data fusion of all categories that step 101 produces the true value system, and provide normal data for the rejecting of step 102 abnormal data, step 103 is carried out compensation data for road chain or the shortage of data time period of shortage of data, the data that produce with step 102 and step 103 are as the data source of multi-source traffic information data, and the data of using in the following steps all are through step 101,102,103 data of processing.

In order to ensure data precision and coverage rate, at first merge extensive various taxi data and bus data, merge again microwave/loop data and license plate identification data.Step is as follows:

The most basic concept is to set up framework of identification in the D-S evidence theory, is denoted as U, and the element in the framework of identification satisfies mutual exclusive condition.Proposition A is to the assignment m(A of function m) be set to hint obliquely at, if function m satisfies following condition:

m(Ф)=0

Right $\&ForAll;A\&Element;2^u,$ M (A) 〉=0, and $\underset{A\&Element;2^U}{\mathrm{\&Sigma;}}m\left(A\right)=1$

Then claim m (A) to be the basic probability assignment function of A (BPAF).Wherein Ф represents empty set, and m (A) expression has represented the direct support to A to the accurate trusting degree of proposition A.

In following steps, for the initialization of taxi data, bus data, microwave/loop data, video monitoring data and license plate identification data, adopt equally the mode of step 1014 to the basic probability assignment function assignment.Step 1013 obtains be under normal circumstances by test carriage obtain to the probability of Various types of data in the credibility interval, less accident, the road maintenances etc. considered are on the impact of the data value range that collects, therefore in following fusion process, also to consider accident, road maintenance etc.

Step 1041, at first merge taxi and bus data.Because the high utilization rate of the equipment such as GPS can ensure data precision and coverage rate.

The initial value of the taxi data that obtain according to step 1014 and the basic probability assignment function of bus data acquisition data is expressed as m ₁(A) and m ₂(A);

The data that note merges are U, and taxi data and bus data are respectively U ₁And U ₂

$U=U_1*\frac{m_1\left(A\right)}{m_1\left(A\right)+m_2\left(A\right)}+U_2*\frac{m_2\left(A\right)}{m_1\left(A\right)+m_2\left(A\right)}$

U is the income value after taxi and the bus information fusion, and the accurate trusting degree of the U after the fusion is:

$m\left(A\right)=\frac{\underset{A_1\&cap;A_2=A}{\mathrm{\&Sigma;}}{m}_1\left(A_1\right)m_2\left(A_2\right)}{\underset{A_1\&cap;A_2\&NotEqual;\mathrm{\&Phi;}}{\mathrm{\&Sigma;}}{m}_1\left(A_1\right)m_2\left(A_2\right)}=m_1\left(A_1\right)\&CirclePlus;m_2\left(A_2\right)$

Step 1042, incorporate microwave/loop data.Microwave/loop data further ensures stability and the reliability of data.

The initial value m of the basic probability assignment function of the microwave/loop data that obtains according to step 1014 ₃(A);

The data that note merges are K, and it is K that step 1041 obtains fused data ₁(i.e. the 1014 U values that obtain), microwave/loop data is K ₂

$K=K_1*\frac{m\left(A\right)}{m\left(A\right)+m_3\left(A\right)}+K_2*\frac{m_3\left(A\right)}{m\left(A\right)+m_3\left(A\right)}$

K is the income value after taxi, bus and microwave/loop data merges, and the accurate trusting degree of the K after the fusion is:

$m_k\left(K\right)=\frac{\underset{K1\&cap;K2=K2}{\mathrm{\&Sigma;}}{m}_1\left(K_1\right)m_2\left(K_2\right)}{\underset{K1\&cap;K2\&NotEqual;\mathrm{\&Phi;}}{\mathrm{\&Sigma;}}{m}_1\left(K_1\right)m_2\left(K_2\right)}=m_1\left(K_1\right)\&CirclePlus;m_2\left(K_2\right)$

Step 1043, incorporate license plate identification data.High-definition camera generally can be equipped with in the zone, crossing, incorporates the accurate reliability of the data that the high-definition camera license plate identification data can guarantee that the bayonet socket highway section is passed through.Method is with step 1042.

Step 1044, incorporate trunk roads, through street, secondary distributor road signal lamp timing data.High-definition camera generally can be equipped with in the zone, crossing, the intersection is compiled owing to vehicle, Vehicle Speed there is considerable influence, incorporate the accurate reliability of the data that the high-definition camera license plate identification data can guarantee that the bayonet socket highway section is passed through, data are subjected to the impact of signal lamp timing data larger between trunk roads, through street, secondary distributor road highway section, incorporate respectively the high-definition camera data and signal lamp timing data can further improve data accuracy.Because the interference of signal lamp, running time and the speed of vehicle on the chain of road can change to some extent, and the scope of the data value that collects should suitably be amplified, the scope that should suitably relax interval [a, b] when namely step 1013 is calculated, and fusion method is with step 1042.

Step 1045, incorporate traffic events, traffic control, stop construction, traffic hazard data.Because traffic events, traffic control, stop construction, traffic hazard be on the impact of data, to taxi, bus, the scope of the data value that microwave/coil etc. collect should suitably be amplified, the scope that should suitably relax interval [a, b] when being step 1013 calculating, the same.

Above method has taken into full account stability, accuracy and the reliability of multiple acquisition mode.Set up the true value system and obtain the correct initial assignment parameter of various acquisition modes, the data that truly collect are carried out abnormity removing, missing data rationally fills up to guarantee accuracy and the integrality of data according to historical data, the data that different classes of acquisition mode is obtained carry out classification step by step fusion treatment to guarantee the reliability of the data, the rapidity of fusion process, and in fusion process, consider the impact that traffic events, traffic control, occupation of land construction, traffic hazard bring to data.

Through the fusion process of above step, realize quick, accurate, the reliable texts of fusion, the true value system has solved the inaccurate problem of prior art initial parameter assignment; Rejecting abnormal data, missing data filled up overcome prior art acquisition terminal unstable properties, and the difficult problem damaged of acquisition terminal; Adopt the D-S theory that the data after processing are carried out the classification fusion treatment, solved the polyphyly problem of data fusion.Take into full account traffic events, traffic control, occupation of land construction, traffic hazard, overcome the impact that data is caused because of above factor.

In a word, the above is preferred embodiment of the present invention only, is not for limiting protection scope of the present invention.

Claims (9)

1. the data of an extensive transport information are processed and fusion method, it is characterized in that, comprising:

The multi-source traffic data that collects according to test carriage and each sensor obtains the normal data of true value system, and the dynamic assignment method of definite parameter; Reject the abnormal data in the data acquisition that described sensor collects, and carry out the compensation of historical data; To finishing the multi-source traffic data real-time graded information fusion of compensation data.

2. the data of extensive transport information according to claim 1 are processed and fusion method, it is characterized in that, the step of the normal data of described acquisition true value system specifically comprises:

By the test carriage of many high sampling rates, repeatedly test in the different periods, and obtain the mean value of period t, as standard value:

Wherein, X _{I, j}(t) the j time measured value in period t test of i test carriage of expression, n car carries out m time and measures.

3. the data of extensive transport information according to claim 2 are processed and fusion method, it is characterized in that, the step of the dynamic assignment method of described definite parameter specifically comprises:

The data that the data that period t test carriage is collected and each sensor collect split out taxi data, bus data, microwave/loop data, video monitoring data and license plate identification data, as all kinds of traffic information datas of period t;

Calculate its standard deviation at the mean value of period t as standard value take taxi data, bus data, microwave/loop data, video monitoring data and license plate identification data respectively:

$D\left(X\right)=\sqrt{\frac{1}{N}\underset{i=1,..}{\mathrm{\&Sigma;}}{(\mathrm{Xi}-E\left(X\right))}^2}$

Wherein, E (X) tests the mean value that obtains all data, X for the t period _iI test data of expression Various types of data;

Use described standard value and standard deviation, obtain respectively the normal distribution of every class data, determine the credibility interval, according to normal curve, computational data is at the probability of credibility interval:

$P(a<X<b)={\&Integral;}_a^b\frac{1}{D\left(X\right)\sqrt{2\mathrm{\&Pi;}}}{e}^{\frac{1}{2}{\left(\frac{X-E\left(X\right)}{D\left(x\right)}\right)}^2}$

Wherein, a, b represent respectively test data depart from standard value X about can accept the boundary value of data, D (X) is standard deviation, E (X) is mean value;

With the probability of described data in the credibility interval every class data basic probability assignment function m (A) is carried out assignment, assignment procedure is m (A)=P (a＜A＜b), A represents every class data, P (a＜A＜b) represent that every class data are at the probability of credibility interval.

4. the data of extensive transport information according to claim 3 are processed and fusion method, it is characterized in that, the step of the abnormal data in the data acquisition that described rejecting sensor collects specifically comprises:

Difference calculation interval t corresponding classification traffic information data X and historical information data H, calculate mathematical expectation E (X), the E (H) of X, H, standard deviation D (X), the D (H) of all kinds of traffic information data X of calculation interval t and past historical information data H 1 year same period, if:

Mathematical expectation E (X) and mathematical expectation E (H) difference are in setting threshold values th scope, and D (X) and D (H) difference be equally in setting threshold values th ', and then these moment data do not have abnormal;

Mathematical expectation E (X) and mathematical expectation E (H) exceed setting threshold values th, but D (X) and D (H) difference are then waited for the traffic information data X of next period and " generated in setting threshold values th '; If the traffic information data D (X) of next period and D (difference of X ") exceeds and sets threshold values th ', the transport information abnormal of period t then, and rejecting abnormal data fallen.

5. the data of extensive transport information according to claim 4 are processed and fusion method, it is characterized in that, described threshold value th and th ' are set as: th=E (H)/2, th '=D (X)/2.

6. according to claim 4 or the data of 5 described extensive transport information are processed and fusion method, it is characterized in that, the compensation process of described historical data specifically comprises:

After every day, each sensor and test carriage collected data, search the Q that comprises a traffic data file in the adjacent Z time period, calculate the road network average velocity of each time period traffic data file, and this average velocity is considered as a point, smooth connection Z dot generation transport information curve segment; Historical data in this curve segment and the same time section is mated, find out the most similar P bar curve as ancillary sources, wherein, Z represents the time period, and Q represents the file amount of generation in Z time period, and P represents the most similar curve quantity;

The time attribute of all kinds of traffic information datas that collect according to each sensor and test carriage is searched from described ancillary sources with the historical data that the road chain of traffic data disappearance has identical unique number, a same time attribute absence information road chain in the compensatory zone is filled up.

7. the data of extensive transport information according to claim 6 are processed and fusion method, it is characterized in that, described step to the multi-source traffic data real-time graded information fusion of finishing compensation data specifically comprises and merges taxi and bus data:

Obtain the initial value of the basic probability assignment function of taxi data and bus data, be expressed as m ₁(A) and m ₂(A);

Set out hire a car and the bus data fusion after income value be U, taxi data and bus data are respectively U1 and U2; Then

$U=U_1*\frac{m_1\left(A\right)}{m_1\left(A\right)+m_2\left(A\right)}+U_2*\frac{m_2\left(A\right)}{m_1\left(A\right)+m_2\left(A\right)}$

The accurate trusting degree of U is:

$m\left(A\right)=\frac{\underset{A_1\&cap;A_2=A}{\mathrm{\&Sigma;}}{m}_1\left(A_1\right)m_2\left(A_2\right)}{\underset{A_1\&cap;A_2\&NotEqual;\mathrm{\&Phi;}}{\mathrm{\&Sigma;}}{m}_1\left(A_1\right)m_2\left(A_2\right)}=m_1\left(A_1\right)\&CirclePlus;m_2\left(A_2\right).$

8. the data of extensive transport information according to claim 7 are processed and fusion method, it is characterized in that, described step to the multi-source traffic data real-time graded information fusion of finishing compensation data further comprises fusion microwave/loop data:

Obtain the initial value of the basic probability assignment function of microwave/loop data, be expressed as m ₃(A);

The data that fusion is set are K, and the income value after described taxi and the bus data fusion is K ₁, microwave/loop data is K ₂

$K=K_1*\frac{m\left(A\right)}{m\left(A\right)+m_3\left(A\right)}+K_2*\frac{m_3\left(A\right)}{m\left(A\right)+m_3\left(A\right)}$

K is the income value after taxi, bus and microwave/loop data merges, and the accurate trusting degree of the K after the fusion is:

$m_k\left(K\right)=\frac{\underset{K1\&cap;K2=K2}{\mathrm{\&Sigma;}}{m}_1\left(K_1\right)m_2\left(K_2\right)}{\underset{K1\&cap;K2\&NotEqual;\mathrm{\&Phi;}}{\mathrm{\&Sigma;}}{m}_1\left(K_1\right)m_2\left(K_2\right)}=m_1\left(K_1\right)\&CirclePlus;m_2\left(K_2\right).$

9. the data of extensive transport information according to claim 8 are processed and fusion method, it is characterized in that, described step to the multi-source traffic data real-time graded information fusion of finishing compensation data further comprises and merges license plate identification data, video monitoring data and traffic events, traffic control, stop construction, traffic hazard data.

Images