CN106971539A - A kind of information of vehicles obtains comprehensive vehicle detecting system - Google Patents

Abstract

Comprehensive vehicle detecting system is obtained the invention provides a kind of information of vehicles, vehicle is detected based on wireless senser, including data acquisition module, vehicle speed detection module, track of vehicle detection module, Vehicle length detection module and vehicles classification module, the data acquisition module is used to obtain vehicle detection data, the vehicle speed detection module is used to detect car speed according to vehicle detection data, the track of vehicle detection module is used for according to vehicle detection data estimation track of vehicle, the Vehicle length detection module is used to detect Vehicle length according to vehicle detection data, the vehicles classification module is used to classify to vehicle according to the Vehicle length.Beneficial effects of the present invention are：Realize the complete detection to information of vehicles.

Description

A kind of information of vehicles obtains comprehensive vehicle detecting system

Technical field

The present invention relates to technical field of vehicle detection, and in particular to a kind of information of vehicles obtains comprehensive vehicle detection system System.

Background technology

Vehicle testing techniques are one of key technologies in City ITS.Pass through advanced vehicle testing techniques Accurate telecommunication flow information is obtained, is the key for carrying out traffic flow monitoring, traffic signalization and induction, is also that auxiliary drives system The important component of system and various traffic information systems, is the basis of intelligent transportation application.

Magneto-dependent sensor has the advantages that over the horizon, relatively small by such environmental effects, has very in vehicle detection Good application prospect.

The content of the invention

In view of the above-mentioned problems, the present invention is intended to provide a kind of information of vehicles obtains comprehensive vehicle detecting system.

The purpose of the present invention is realized using following technical scheme：

Comprehensive vehicle detecting system is obtained there is provided a kind of information of vehicles, vehicle is examined based on wireless senser Survey, including data acquisition module, vehicle speed detection module, track of vehicle detection module, Vehicle length detection module and vehicle Sort module, the data acquisition module is used to obtain vehicle detection data, and the vehicle speed detection module is used for according to car Detection data detect that the track of vehicle detection module is for according to vehicle detection data estimation vehicle to car speed Track, the Vehicle length detection module according to vehicle detection data to Vehicle length for detecting, the vehicle classification Module is used to classify to vehicle according to the Vehicle length.

Beneficial effects of the present invention are：Realize the complete detection to information of vehicles.

Brief description of the drawings

Using accompanying drawing, the invention will be further described, but the embodiment in accompanying drawing does not constitute any limit to the present invention System, for one of ordinary skill in the art, on the premise of not paying creative work, can also be obtained according to the following drawings Other accompanying drawings.

Fig. 1 is the structural representation of the present invention；

Reference：

Data acquisition module 1, vehicle speed detection module 2, track of vehicle detection module 3, Vehicle length detection module 4, Vehicles classification module 5.

Embodiment

The invention will be further described with the following Examples.

Referring to Fig. 1, a kind of information of vehicles of the present embodiment obtains comprehensive vehicle detecting system, based on wireless senser pair Vehicle detected, it is characterized in that, including data acquisition module 1, vehicle speed detection module 2, track of vehicle detection module 3, Vehicle length detection module 4 and vehicles classification module 5, the data acquisition module 1 are used to obtain vehicle detection data, the car Velocity measuring module 2 is used to detect car speed according to vehicle detection data, and the track of vehicle detection module 3 is used According to vehicle detection data estimation track of vehicle, the Vehicle length detection module 4 is used for according to vehicle detection data to car Length is detected that the vehicles classification module 5 is used to classify to vehicle according to the Vehicle length.

The present embodiment realizes the complete detection to information of vehicles.

It is preferred that, the data acquisition module 1 is detected using geomagnetic sensor to vehicle, in the detection zone of sensor In domain, headstock and entering and leaving for the tailstock can all produce significant magnetic line of force disturbance, including sensor model determining unit sum According to processing unit, the sensor model determining unit is used to determine sensor node sensor model, the perception mould of sensor node Type：

In formula, x represents vehicle and sensor node distance, and p (x) represents to detect the probability of vehicle, R_maxFor sensor section Point maximum detectable range；

The data processing unit is used to handle the data of collection, and processing mode is：

The first step, if the original signal data that sensor is detected is a (k), low pass is carried out to initial data and band logical is filtered The denoising of ripple device, reduce sample frequency, ask energy spectrum to handle, obtaining signal b (k)；

Second step：Signal is handled using weighting is slided, the signal after weighting is slided and is represented by：

In formula, M represents sliding window length, δ_iRepresent weights.

Detection accuracy of this preferred embodiment based on Geomagnetic signal has exceeded induction coil and the first-class tradition of video camera Equipment, is detected using geomagnetic sensor to vehicle, improves the vehicle detection degree of accuracy；Vehicle sensor model according to vehicle with The distance of sensor determines vehicle detection probability, more accurately reflects actual conditions of the sensor in detection process；Number Signal is handled using weighting is slided according to processing, the influence of burst noise can be eliminated.

It is preferred that, the vehicle speed detection module 2 determines car speed using following steps：

The first step, sets a signal amplitude threshold value y (k), thinks there is car if current signal sample continues to exceed threshold value Exist, when signal continuously then thinks that vehicle is not present less than threshold value, wherein, y (k) is iterated more according to b ' (k) change Newly, it is assumed that threshold value initial value is Y₀, y (k) is updated using following formula：

In formula, α and β are updating factor, and G is that threshold value updates delay, 0 ＜ α ＜ 1, β ＞ 1；

Second step, according to amplitude thresholds obtain detection signal at the beginning of between t_startWith deadline t_down, speed use Following formula is asked for：

In formula, t_B,startAnd t_A,startRepresent respectively between the detecting at the beginning of vehicle of sensor B and sensors A, t_B,endAnd t_A,endThe deadline for detecting vehicle of sensor B and sensors A, d are represented respectively_A,BRepresent two sensors it Between distance, Δ t_BWith Δ t_ASensor B and the clock and the difference of standard time clock of sensors A are represented respectively.

This preferred embodiment is updated to threshold value, can adapt to the change of ambient noise in actually detected environment, is improved The robustness of vehicle detection, it is ensured that the accuracy and reliability of vehicle detection；When being asked for car speed, it is contemplated that The clock synchronization issue of sensor, obtains more correct time, so as to obtain more accurate vehicle speed detection.

It is preferred that, the track of vehicle detection module 3 sets up unit and model simplification unit including model, and the model is built Vertical unit is used to set up track of vehicle detection universal model, and the model simplification unit is used to set up the vehicle rail parallel with track Mark detection model：

The track of vehicle detects that universal model is：According to sensor node sensor model, it is assumed that sensor network is by m Node is constituted, and vehicle is periodically detected and reports aggregation node in interval at a fixed time, obtain a m tie up to Quantity set S=(+1,0, -1)^m, wherein ,+1 represents that vehicle is moved towards the detection range direction of sensor node, and 0 expression free time did not had Vehicle is found, -1 represents vehicle toward the direction movement away from sensor node detection range, according to vector set S and corresponding Timestamp is estimated track of vehicle.

The track of vehicle detection model parallel with track be：The running orbit of vehicle is the straight line parallel with track, Aggregation node is spaced in T to vehicle data with certain frequency sampling at a fixed time, then sampled result is expressed as one two First detection sequence o (t_j)：

In formula, t_jRepresent sampling instant, s (t_j) it is the vehicle existence state output detected according to amplitude thresholds.

This preferred embodiment track of vehicle detection module realizes the estimation to track of vehicle, and universal model can be for each Plant track to be estimated, when vehicle operation is parallel with track, track of vehicle can be estimated, improved using simplified model Computational efficiency, saves the time.

It is preferred that, the Vehicle length detection module 4 determines Vehicle length in the following ways：

If sensor node p and q are at a time detected respectively, headstock enters and the tailstock leaves event, in threshold test The middle terrestrial magnetic disturbance signal for corresponding to vehicle respectively exceedes threshold value and at the time of last time is less than threshold value first, then the length of vehicle L is represented by：

In formula, Γ represents error transfer factor parameter,T₀、H₀、P₀Respectively standard Temperature, standard humidity, standard pressure, T, H, P are respectively temperature in actual environment, humidity, air pressure, d_p,qRepresent two sensings The distance between device node p and q, d_offRepresent the distance of two sensor lines of vehicle shift, R_pAnd R_qRespectively represent vehicle with Sensor node p and q distance.

This preferred embodiment introduces error transfer factor parameter, can reduce warp during being detected to Vehicle length The magnetic disturbance characteristic signal of vehicle calculates the error of obtained magnetic length and physical length, because magnetic signal is by environmental factor Influence, using humiture and air pressure as according to calculating error transfer factor parameter, the Vehicle length of acquisition is more accurate.

Comprehensive vehicle detecting system is obtained using information of vehicles of the present invention to detect vehicle, when G takes different value, Vehicle speed detection accuracy rate and vehicle classification accuracy rate are counted, compared with using other vehicle detecting systems, produced Have the beneficial effect that shown in table：

G	Vehicle speed detection accuracy rate	Vehicle classification accuracy rate is improved
			10	36%	30%
15	32%	25%
			20	30%	20%
25	27%	18%
			30	25%	15%

Finally it should be noted that the above embodiments are merely illustrative of the technical solutions of the present invention, rather than to present invention guarantor The limitation of scope is protected, although being explained with reference to preferred embodiment to the present invention, one of ordinary skill in the art should Work as understanding, technical scheme can be modified or equivalent substitution, without departing from the reality of technical solution of the present invention Matter and scope.

Claims (6)

1. a kind of information of vehicles obtains comprehensive vehicle detecting system, vehicle is detected based on wireless senser, its feature It is, including data acquisition module, vehicle speed detection module, track of vehicle detection module, Vehicle length detection module and vehicle Sort module, the data acquisition module is used to obtain vehicle detection data, and the vehicle speed detection module is used for according to car Detection data detect that the track of vehicle detection module is for according to vehicle detection data estimation vehicle to car speed Track, the Vehicle length detection module according to vehicle detection data to Vehicle length for detecting, the vehicle classification Module is used to classify to vehicle according to the Vehicle length.

2. information of vehicles according to claim 1 obtains comprehensive vehicle detecting system, it is characterized in that, the data acquisition Module is detected using geomagnetic sensor to vehicle, in the detection zone of sensor, and headstock and the tailstock enter and leave Significant magnetic line of force disturbance, including sensor model determining unit and data processing unit will be produced, the sensor model is determined Unit is used to determine sensor node sensor model, the sensor model of sensor node：

$p\left(x\right)=\left\{\begin{array}{c}0,x>R_{max}\\ 1+e^{-x}-\frac{2}{\mathrm{\&pi;}}\arctan x,0<x\&le;R_{max}\end{array}\right.$

In formula, x represents vehicle and sensor node distance, and p (x) represents to detect the probability of vehicle, R_maxFor sensor node most Big detection range；

The data processing unit is used to handle the data of collection, and processing mode is：

The first step, if the original signal data that sensor is detected is a (k), lowpass and band-pass filter is carried out to initial data Denoising, reduce sample frequency, ask energy spectrum to handle, obtaining signal b (k)；

Second step：Signal is handled using weighting is slided, the signal after weighting is slided and is represented by：

$b^{\&prime;}\left(k\right)=\underset{i=0}{\overset{M-1}{\&Sigma;}}{\mathrm{\&delta;}}_i\&times;b(k-i)=\underset{i=0}{\overset{M-1}{\&Sigma;}}\frac{2i}{M(M-1)}\&times;b(k-i)$

In formula, M represents sliding window length, δ_iRepresent weights.

3. information of vehicles according to claim 2 obtains comprehensive vehicle detecting system, it is characterized in that, the car speed Detection module determines car speed using following steps：

The first step, sets a signal amplitude threshold value y (k), thinks have vehicle to deposit if current signal sample continues to exceed threshold value , when signal continuously then thinks that vehicle is not present less than threshold value, wherein, y (k) is iterated renewal according to b ' (k) change, false If threshold value initial value is Y₀, y (k) is updated using following formula：

In formula, α and β are updating factor, and G is that threshold value updates delay, 0 ＜ α ＜ 1, β ＞ 1；

Second step, according to amplitude thresholds obtain detection signal at the beginning of between t_startWith deadline t_down, speed uses following formula Ask for：

$v=\frac{1}{2}\&lsqb;\frac{d_{A,B}}{(t_{B,start}+{\mathrm{\&Delta;t}}_B)-(t_{A,start}+{\mathrm{\&Delta;t}}_A)}+\frac{d_{A,B}}{(t_{B,end}+{\mathrm{\&Delta;t}}_B)-(t_{A,end}+{\mathrm{\&Delta;t}}_A)}\&rsqb;$

In formula, t_B,startAnd t_A,startRepresent respectively between the detecting at the beginning of vehicle of sensor B and sensors A, t_B,endWith t_A,endThe deadline for detecting vehicle of sensor B and sensors A, d are represented respectively_A,BRepresent two sensors between away from From Δ t_BWith Δ t_ASensor B and the clock and the difference of standard time clock of sensors A are represented respectively.

4. information of vehicles according to claim 3 obtains comprehensive vehicle detecting system, it is characterized in that, the track of vehicle Detection module sets up unit and model simplification unit including model, and the model, which sets up unit, to be used to set up track of vehicle detection one As model, the model simplification unit is used to set up the track of vehicle detection model parallel with track：

The track of vehicle detects that universal model is：According to sensor node sensor model, it is assumed that sensor network is by m node Composition, is periodically detected to vehicle in interval and reports aggregation node, obtain a m dimensional vector collection at a fixed time S=(+1,0, -1)^m, wherein ,+1 represents that vehicle is moved towards the detection range direction of sensor node, and 0 represents that the free time is not sent out Existing vehicle, -1 represents vehicle toward the direction movement away from sensor node detection range, according to vector set S and corresponding time Stamp is estimated track of vehicle.

5. information of vehicles according to claim 4 obtains comprehensive vehicle detecting system, it is characterized in that, it is described to be put down with track Capable track of vehicle detection model is：The running orbit of vehicle is the straight line parallel with track, and aggregation node is at a fixed time It is spaced in T to vehicle data with certain frequency sampling, then sampled result is expressed as a binary detection sequence o (t_j)：

$o\left(t_j\right)=\left\{\begin{array}{c}+1,ifs\left(t_j\right)\&NotEqual;0ands(t_j-T)=0\\ 0,ifs\left(t_j\right)=0ands(t_j-T)=0\\ -1,ifs\left(t_j\right)=0ands(t_j-T)\&NotEqual;0\end{array}\right.$

In formula, t_jRepresent sampling instant, s (t_j) it is the vehicle existence state output detected according to amplitude thresholds.

6. information of vehicles according to claim 5 obtains comprehensive vehicle detecting system, it is characterized in that, the Vehicle length Detection module determines Vehicle length in the following ways：

If sensor node p and q are at a time detected respectively, headstock enters and the tailstock leaves event, divides in threshold test Not Dui Ying vehicle terrestrial magnetic disturbance signal first exceed threshold value and last time be less than threshold value at the time of, then the length L of vehicle can It is expressed as：

$L=(\mathrm{\&Gamma;}+1)(d_{p,q}-\sqrt{R_p^2-d_{off}^2}-\sqrt{R_q^2-d_{off}^2})$

In formula, Γ represents error transfer factor parameter,T₀、H₀、P₀Respectively normal temperature, Standard humidity, standard pressure, T, H, P are respectively temperature in actual environment, humidity, air pressure, d_p,qRepresent two sensor nodes The distance between p and q, d_offRepresent the distance of two sensor lines of vehicle shift, R_pAnd R_qVehicle and sensor are represented respectively Node p and q distance.