CN112634630A - Vehicle speed measuring method and system under complex environment - Google Patents
Vehicle speed measuring method and system under complex environment Download PDFInfo
- Publication number
- CN112634630A CN112634630A CN202110257405.3A CN202110257405A CN112634630A CN 112634630 A CN112634630 A CN 112634630A CN 202110257405 A CN202110257405 A CN 202110257405A CN 112634630 A CN112634630 A CN 112634630A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- magnetic field
- vehicle speed
- field data
- radar sensor
- 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.)
- Pending
Links
Images
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
- G08G1/052—Detecting movement of traffic to be counted or controlled with provision for determining speed or overspeed
-
- 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
- G08G1/042—Detecting movement of traffic to be counted or controlled using inductive or magnetic detectors
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/30—Services specially adapted for particular environments, situations or purposes
- H04W4/38—Services specially adapted for particular environments, situations or purposes for collecting sensor information
Abstract
The invention discloses a method and a system for measuring vehicle speed in a complex environment, which judge vehicle entering and vehicle leaving through magnetic field data and radar analog voltage signals, acquire the time for the vehicle to enter and leave the detection range of a microwave radar sensor and the magnetic field intensity time sequence of the vehicle passing through the detection range of the microwave radar sensor, input the magnetic field intensity time sequence into an improved GoogleNet network for vehicle classification, calculate the vehicle speed and effectively realize the vehicle speed measurement in the complex environment.
Description
Technical Field
The invention relates to a method and a system for measuring vehicle speed in a complex environment, and belongs to the field of intelligent traffic.
Background
The traffic jam problem becomes more and more serious due to the development of the automobile industry and the acceleration of the urbanization process, and the traffic light has important practical significance for improving the urban traffic condition as a means for controlling the traffic flow and improving the road traffic capacity. In the control process of the traffic signal lamp in the complex environment, effective acquisition of the vehicle speed plays an important role, so that a vehicle speed measuring technology in the complex environment is urgently needed.
Disclosure of Invention
The invention provides a method and a system for measuring vehicle speed in a complex environment, which solve the problems disclosed in the background technology.
In order to solve the technical problems, the technical scheme adopted by the invention is as follows:
a vehicle speed measuring method under a complex environment is characterized in that: comprises the steps of (a) preparing a mixture of a plurality of raw materials,
acquiring magnetic field data in a detection range of the magnetoresistive sensor in real time;
if the magnetic field data changes and the changed magnetic field data is relative to the reference magnetic field data f0The variation meets the starting rule of the microwave radar sensor, a starting signal is sent to the microwave radar sensor, and a radar analog voltage signal within the detection range of the microwave radar sensor within the preset time A is obtained;
if the magnetic field data variation and the effective value number of the radar simulation voltage signals after the microwave radar sensor is started both meet the rule that the vehicle enters the vehicle speed measurement range and the magnetic field data variation after the vehicle enters the vehicle speed measurement range meets the rule that the vehicle leaves the vehicle speed measurement range, acquiring the time when the vehicle enters and leaves the detection range of the microwave radar sensor, and generating a magnetic field intensity time sequence when the vehicle passes through the detection range of the microwave radar sensor according to the magnetic field data; wherein the magnetic field data change amount after the microwave radar sensor is started is that the magnetic field data after the microwave radar sensor is started is relative to the reference magnetic field data f0The magnetic field data after the vehicle enters the vehicle speed measurement range is changed into the magnetic field data after the vehicle enters the vehicle speed measurement range relative to the reference magnetic field data f0The amount of change in (c);
and sending the time when the vehicle enters and leaves the detection range of the microwave radar sensor and the time sequence of the magnetic field intensity when the vehicle passes through the detection range of the microwave radar sensor to a background for measuring the vehicle speed.
And if the magnetic field data keeps stable state within the preset time B after the microwave radar sensor is started, sending a closing signal to the microwave radar sensor.
The detection range of the magnetic resistance sensor and the detection range of the microwave radar sensor are concentric circles, and the detection range of the magnetic resistance sensor is larger than that of the microwave radar sensor.
Reference magnetic field data f for one-round vehicle speed measurement from the vehicle-entering vehicle speed measurement range to the vehicle-leaving vehicle speed measurement range, and for this-round vehicle speed measurement S10Comprises the following steps: the vehicle speed of the previous wheel is measured S0 and the steady magnetic field data after the vehicle has left the vehicle speed measurement range.
The microwave radar sensor is started according to the rule that,
the changed magnetic field data is relative to the reference magnetic field data f0Is not less than a first threshold;
the first threshold value is set to be,
wherein the content of the first and second substances,
is a first threshold value;
is the standard deviation of the noise distribution;
taking the value of the noise distribution;
is the mean of the noise distribution;nis the number of noise values.
The rule of the vehicle entering the vehicle speed measuring range comprises a vehicle entering rule under normal climate and a vehicle entering rule under severe climate;
the vehicle entry rules in normal climates are:
magnetic field data after microwave radar sensor is started relative to reference magnetic field data f0Is not less than a second threshold;
and the number of the first and second electrodes,
the number of effective values of the radar analog voltage signals is not less than a third threshold value;
the vehicle entering rule under the severe weather is as follows:
magnetic field data after microwave radar sensor is started relative to reference magnetic field data f0Is not less than the fourth threshold; wherein the fourth threshold is much larger than the second threshold.
The rule that the vehicle leaves the vehicle speed measuring range is that the changed magnetic field data is relative to the reference magnetic field data f0Is not greater than the fifth threshold.
A vehicle speed measuring method under a complex environment comprises the following steps,
receiving the time of the vehicle entering and leaving the detection range of the microwave radar sensor and the magnetic field intensity time sequence of the vehicle passing through the detection range of the microwave radar sensor, which are sent from the vehicle speed measuring device side;
inputting the magnetic field intensity time sequence into a pre-trained GoogLeNet network to obtain the type of the vehicle;
acquiring the length of the vehicle according to the type of the vehicle;
and calculating the speed of the vehicle according to the length of the vehicle and the time of the vehicle entering and leaving the detection range of the microwave radar sensor.
The google lenet network is a convolutional neural network that replaces the convolutional pooling layer with an initiation module, and includes a plurality of parallel classifiers for performing multi-task classification.
A vehicle speed measuring system under a complex environment comprises a vehicle speed measuring device and a background;
the vehicle speed measuring device comprises a controller, a magnetic resistance sensor, a microwave radar sensor, a communication module and a power supply; the magnetic resistance sensor, the microwave radar sensor and the communication module are all connected with the controller, the communication module is communicated with the background, the power supply supplies power to all power utilization parts of the vehicle speed measuring device, and the controller executes a vehicle speed measuring method under a complex environment at the side of the vehicle speed measuring device; and the background executes a vehicle speed measuring method under a complex environment at the background side.
The invention achieves the following beneficial effects: according to the invention, vehicle entering and vehicle leaving are judged through magnetic field data and radar analog voltage signals, the time when the vehicle enters and leaves the detection range of the microwave radar sensor and the magnetic field intensity time sequence when the vehicle passes through the detection range of the microwave radar sensor are obtained, the magnetic field intensity time sequence is input into an improved GoogleNet network for vehicle classification, the vehicle speed is calculated, and the vehicle speed measurement under a complex environment is effectively realized.
Drawings
FIG. 1 is a flow chart of the method of the present invention;
FIG. 2 is a schematic diagram of the detection ranges of a magnetoresistive sensor and a microwave radar sensor;
FIG. 3 is a diagram illustrating the variation of magnetic field;
FIG. 4 is a basic block diagram of a convolutional neural network;
FIG. 5 is a block diagram of initiation in a GoogleLeNet network;
FIG. 6 is a diagram of a multitasking data structure;
FIG. 7 is a schematic view of vehicle speed calculation;
FIG. 8 is a block diagram of a vehicle speed measurement system;
FIG. 9 is a transmission diagram of NB-IOT techniques.
Detailed Description
The invention is further described below with reference to the accompanying drawings. The following examples are only for illustrating the technical solutions of the present invention more clearly, and the protection scope of the present invention is not limited thereby.
As shown in FIG. 1, a vehicle speed measuring method in a complex environment includes a vehicle speed measuring device side method and a back-end side method.
The vehicle speed measuring device side method comprises the following steps:
11) and acquiring magnetic field data in a detection range of the magnetic resistance sensor in real time.
12) If the magnetic field data changes and the changed magnetic field data is relative to the reference magnetic field data f0The variation satisfies the starting rule of the microwave radar sensor, a starting signal is sent to the microwave radar sensor, and a radar analog voltage signal within the detection range of the microwave radar sensor within the preset time A is obtained.
The magnetic resistance sensor and the microwave radar sensor are both arranged in the same vehicle speed measuring device, as shown in fig. 2, the detection range of the magnetic resistance sensor and the detection range of the microwave radar sensor are equivalent to concentric circles, and the detection range of the magnetic resistance sensor is larger than that of the microwave radar sensor.
Microwave radar sensor start-up rule, changed magnetic field data relative to reference magnetic field data f0Amount of change M of1Not less than the first threshold. As shown in FIG. 3, M1=f1-f0Wherein f is1For changed magnetic field data, M1、f1、f0Are all vectors.
The first threshold is defined as follows:
wherein the content of the first and second substances,
is a first threshold value;
noise obeys mean as the standard deviation of the noise distribution
A normal distribution of 0, with values almost entirely centered
Interval, since the amount of change is considered, the first threshold should be
More than 6 times of the total weight of the composition,
taking the value of the noise distribution;
is the mean of the noise distribution;nis the number of noise values.
When a vehicle enters or other strong magnetic objects disturb in the detection range of the magnetic resistance sensor, the magnetic field data can be changed and compared with the reference magnetic field data f0Is not less than the first threshold value, the microwave radar sensor is started.
The microwave radar sensor can collect moving object interference information in a detection range, generate radar analog voltage signals and collect the radar analog voltage signals within preset time A, wherein the preset time A is generally several seconds.
13) If the magnetic field data after the microwave radar sensor is started is relative to the reference magnetic field data f0The number of the variable quantity and the effective value of the radar analog voltage signal meets the rule that the vehicle enters the vehicle speed measurement range, and then the vehicle enters the vehicle speed measurement range.
The rule of the vehicle entering the vehicle speed measuring range comprises a vehicle entering rule under normal climate and a vehicle entering rule under severe climate;
the vehicle entry rules in normal climates are:
magnetic field data after microwave radar sensor is started relative to reference magnetic field data f0Is not less than a second threshold; the second threshold is much greater than the first threshold;
and the number of the first and second electrodes,
the number of effective values of the radar analog voltage signals is not less than a third threshold value.
The effective values of the radar analog voltage signals are the number of voltages of which the voltage values are larger than the preset value in the radar analog voltage signals, if the number of the effective values is too small, other ferromagnetic objects (such as bicycles and the like) possibly enter the detection range of the microwave radar sensor, and only if the number of the effective values is enough, the fact that vehicles possibly enter the detection range can be judged.
The sensitivity of the microwave radar sensor can be greatly reduced under severe weather such as rain and snow coverage, the number of effective values of radar analog voltage signals is small, and therefore a single magnetic patch is introduced to improve the detection precision during rain and snow coverage, namely the following rules are met, and the condition that a vehicle enters can be directly judged;
the rule of the vehicle entering the vehicle speed measuring range under the severe weather is as follows:
magnetic field data after microwave radar sensor is started relative to reference magnetic field data f0Is not less than the fourth threshold; wherein the fourth threshold is much larger than the second threshold.
The second threshold, the third threshold and the fourth threshold are all empirical values obtained by actually measuring and analyzing vehicle speed measurement range data of the vehicle in normal climate and severe climate.
14) If the magnetic field data changes after the vehicle enters the vehicle speed measuring range and the changed magnetic field data is relative to the reference magnetic field data f0The vehicle leaving the vehicle speed measurement range is determined if the variation satisfies the vehicle leaving vehicle speed measurement range rule.
The rule of the vehicle leaving the vehicle speed measurement range is as follows: the changed magnetic field data is relative to the reference magnetic field data f0Is not greater than the fifth threshold. The magnetic field data change is not large before the vehicle enters and after the vehicle leaves; the fifth threshold value is an empirical value obtained by actually measuring and analyzing the vehicle speed measurement range data.
Setting the vehicle speed measurement range from the vehicle entering the vehicle speed measurement range to the vehicle leaving the vehicle speed measurement range as one round of vehicle speed measurement, the reference magnetic field data for the same round of vehicle speed measurement are consistent, and the reference magnetic field data f for the current round of vehicle speed measurement S10Comprises the following steps: and measuring the speed of the vehicle in the previous wheel S0 to obtain the stable magnetic field data after the vehicle leaves the speed measuring range, and measuring the speed of the vehicle in two adjacent times by S0 and S1.
If all the reference magnetic field data are consistent, the situation that whether the vehicle leaves the vehicle speed measuring range or not can not be judged under the strong magnetic interference environment occurs, and the reference magnetic field data are set to be dynamically variable, so that the situation can be effectively avoided.
In the process of measuring the vehicle speed, if the magnetic field data keeps stable state within the preset time B after the microwave radar sensor is started, a closing signal is sent to the microwave radar sensor, if: and the vehicle leaves the vehicle speed measuring range, stops in the vehicle speed measuring range and the like.
15) And after the judgment of the vehicle entering and leaving vehicle speed measuring range is made, the time of the vehicle entering and leaving the microwave radar sensor detecting range is obtained, and the magnetic field intensity time sequence of the vehicle passing through the microwave radar sensor detecting range is generated according to the magnetic field data.
And if the magnetic field data keeps stable state within the preset time B after the microwave radar sensor is started, sending a closing signal to the microwave radar sensor.
16) And sending the time when the vehicle enters and leaves the detection range of the microwave radar sensor and the time sequence of the magnetic field intensity when the vehicle passes through the detection range of the microwave radar sensor to a background for measuring the vehicle speed.
The background lateral method comprises the following steps:
21) and receiving the time sequence of the vehicle entering and leaving the detection range of the microwave radar sensor and the magnetic field intensity time sequence of the vehicle passing through the detection range of the microwave radar sensor sent from the vehicle speed measuring device side.
22) And inputting the magnetic field intensity time sequence into a pre-trained GoogLeNet network to acquire the type of the vehicle.
Due to the fact that vehicle types existing in the market have complexity, different vehicle types have different magnetic field influence values, and vehicle lengths are different, vehicle type classification can be conducted on the magnetic field intensity time sequence through the convolutional neural network. As shown in fig. 4, the convolutional neural network is basically composed of an input layer, a convolutional layer, a pooling layer, a fully-connected layer, and an output layer, the feature extractor includes the input layer, the convolutional layer, and the pooling layer, and the classifier includes the fully-connected layer and the output layer.
The input layer is for an input image, the size of which is determined by the size of the input image. The input to a convolutional neural network is typically the original imageXBy usingH i Is shown asiCharacteristic diagram of the layer, thenH 0=X。
The function of the convolutional layer is to learn features, and the larger the number of layers of the convolutional layer, the more expressive the features extracted by the convolutional core. Suppose thatH i Is a convolution ofLayers, then, can be described as:
wherein the functionfWhich represents a non-linear activation function,
which represents a convolution operation, is performed,W i represents the firstiThe weight parameters of the layer convolution kernel,b i represents the firstiThe offset parameter of the layer(s),H i-1representsH i The previous layer of (2).
The pooling layer is generally arranged after the convolution layer, and performs down-sampling operation on a local area, so that the purpose of reducing the dimension of the feature map is achieved, and the features have spatial invariance to a certain extent. Suppose thatH i Is a pooling layer, it is defined as:
wherein the content of the first and second substances,sfor pooling operations, common pooling operations are mean pooling and maximum pooling.
The function of the full connection layer is to judge the object type according to the learned characteristics, if soH i Is a fully connected network, it is defined as:
the output layer is mainly specific to a specific task, if the convolutional neural network is used for classification, the output layer uses softmax function regression, and the probability distribution is shown as the following formula:
wherein the content of the first and second substances,m l is shown aslThe number of the individual label categories is,Pthe probability is represented by the number of bits in the bit stream,
is shown aslProbability distribution corresponding to each label category.
The residual between the actual output value and the expected output value can be calculated using a loss function, in equationM(W,b) Is a loss function of the network, commonly used, has a mean square errorMean Squared Error, MSE) Function, negative log-likelihood: (Negative Log Likelihood, NLL) Functions, etc., whose formula is defined as:
wherein the content of the first and second substances,
the probability distribution is calculated for the number of probability distributions, i.e. the number of label classes,
is composed of
The predicted value of (a) is determined,Win order to be a weight parameter, the weight parameter,bis an offset parameter;
adding in loss functionM 2Norm of
The overfitting phenomenon of the weight can be effectively controlled, and is defined as:
wherein the content of the first and second substances,
which represents the strength of the control fit,E(W,b) To addM 2Loss function after norm.
Using gradient descent algorithm in training process, and weighting parameters in residual error reduction processWAnd offset parameterbUpdate is performed, which may describe:
wherein the learning rate
For controlling the strength of the residual back propagation.
The google lenet network is a convolutional neural network which uses an initiation module to replace a convolutional pooling layer, can automatically extract target category characteristics, and avoids nonstandard caused by manually pre-selecting characteristics, as shown in fig. 5, the initiation module is composed of 1 × 1 and 3 × 3 convolutional kernels, a front layer refers to an input layer, and filter cascading is actually an information integration mode, namely, information needs to be integrated before being applied to a full connection layer.
The google lenet network model introduces a multitask data structure on the basis, that is, the google lenet network comprises a plurality of parallel classifiers for performing multitask classification, as shown in fig. 6, wherein feature refers to a feature diagram, cls _ score refers to a classification layer for classification, the obtained result is a K +1 dimensional array, which refers to classification probability belonging to a certain label class, K refers to K classes, 1 refers to a background, the whole connection layer of the K +1 classes is usually calculated by using a softmax function, label refers to a label, and loss _ cls refers to a loss layer, the function of the loss layer is to judge classification loss according to the probability of real classification, the output is loss, and the total loss is the weighted sum of losses. A plurality of classification tasks are added into the GoogLeNet convolutional neural network for training at the same time, the training speed of the model can be increased, a momentum random gradient descent method is used for training, the initial learning rate is set to be 0.0001, the number of data processed each time is 10, and the rest parameters are default values.
23) The vehicle length is obtained according to the vehicle type.
24) And calculating the speed of the vehicle according to the length of the vehicle and the time of the vehicle entering and leaving the detection range of the microwave radar sensor.
As shown in figure 7 of the drawings,dis the length of the vehicle,t 1andt 2the time when the vehicle enters and leaves the detection range of the microwave radar sensor, respectively, andd 1andd 2are respectivelyt 1Andt 2the distance between the vehicle and the vehicle speed measuring device at the time point,d 1+d 2=Rthe calculation formula of the vehicle speed is as follows for the diameter of the detection range of the microwave radar sensor:
wherein the content of the first and second substances,vis the vehicle speed.
According to the method, vehicle entering and vehicle leaving are judged through magnetic field data and radar analog voltage signals, time when a vehicle enters and leaves a detection range of a microwave radar sensor and a magnetic field intensity time sequence when the vehicle passes through the detection range of the microwave radar sensor are obtained, the magnetic field intensity time sequence is input into an improved GoogleNet network to classify the vehicle, the vehicle speed is calculated, and vehicle speed measurement under a complex environment is effectively achieved.
As shown in fig. 8, a vehicle speed measuring system under a complex environment includes a vehicle speed measuring device and a background;
the vehicle speed measuring device comprises a controller, a magnetic resistance sensor, a microwave radar sensor, a memory, a narrow-band Internet of things communication module and a power supply; the magnetic resistance sensor, the microwave radar sensor, the memory and the narrow-band Internet of things communication module are all connected with the controller, the narrow-band Internet of things communication module is communicated with the background, the memory stores magnetic field data, radar analog voltage signals, magnetic field variation, radar analog voltage signal effective values and the like, the power supply supplies power for all electric components of the vehicle speed measuring device, and the controller executes a vehicle speed measuring device side method; the background performs the background-side method.
The magnetic resistance sensor adopts a three-axis AMR (anisotropic magnetic resistance) sensor which is used for collecting the data of the surrounding magnetic field in the self-detection range. The microwave radar sensor adopts a 24GHZ millimeter wave radar sensor, has strong penetration capacity and anti-interference capacity, and is used for collecting moving object interference information in a detection range and generating radar analog voltage signals. The power supply adopts a lithium battery with long service life.
The narrow-band internet of things (NB-IOT technology) communication module is used for wirelessly transmitting signals with a background, and the NB-IOT technology is adopted, as shown in fig. 9, the NB-IOT technology does not need wiring, and can be directly transmitted through an operator base station, so that the installation and maintenance cost of a gateway is saved, and meanwhile, the stability of signal transmission is ensured. The narrowband Internet of things communication module comprises an SIM card, an NB (narrowband) module and an NB antenna, wherein the SIM card is used for acquiring communication service of an operator, the NB module is used for carrying out multiband wireless communication, and the NB antenna is used for receiving and sending radio frequency signals.
All parts of speed of a motor vehicle measuring device all set up in sealed casing, and the casing includes shell body and interior casing, follows down up being fixed with power and PCB board in proper order in the interior casing, and controller, magnetic resistance sensor, microwave radar sensor, memory, communication module all set up on the PCB board, and interior casing inlays in the cavity of shell body, and the top of interior casing is the lid that can open soon, is provided with a plurality of sealing washers between lid and the interior casing opening.
The vehicle speed measuring device is directly buried on a road, the detection range of the vehicle speed measuring device is about the width of a single lane, therefore, the vehicle speed measuring device is generally buried in the middle of the single lane, in order to prevent the deformation of the road surface from crushing the vehicle speed measuring device, the vehicle speed measuring device can be placed in a reinforced road surface groove, and the outer shell of the vehicle speed measuring device is an elastic shell.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The present invention is not limited to the above embodiments, and any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention are included in the scope of the claims of the present invention which are filed as the application.
Claims (10)
1. A vehicle speed measuring method under a complex environment is characterized in that: comprises the steps of (a) preparing a mixture of a plurality of raw materials,
acquiring magnetic field data in a detection range of the magnetoresistive sensor in real time;
if the magnetic field data changes and the changed magnetic field data is relative to the reference magnetic field data f0The variation meets the starting rule of the microwave radar sensor, a starting signal is sent to the microwave radar sensor, and a radar analog voltage signal within the detection range of the microwave radar sensor within the preset time A is obtained;
if the magnetic field data variation and the effective value number of the radar simulation voltage signals after the microwave radar sensor is started both meet the rule that the vehicle enters the vehicle speed measurement range and the magnetic field data variation after the vehicle enters the vehicle speed measurement range meets the rule that the vehicle leaves the vehicle speed measurement range, acquiring the time when the vehicle enters and leaves the detection range of the microwave radar sensor, and generating a magnetic field intensity time sequence when the vehicle passes through the detection range of the microwave radar sensor according to the magnetic field data; wherein the magnetic field data change amount after the microwave radar sensor is started is that the magnetic field data after the microwave radar sensor is started is relative to the reference magnetic field data f0The magnetic field data after the vehicle enters the vehicle speed measurement range is changed into the magnetic field data after the vehicle enters the vehicle speed measurement range relative to the reference magnetic field data f0The amount of change in (c);
and sending the time when the vehicle enters and leaves the detection range of the microwave radar sensor and the time sequence of the magnetic field intensity when the vehicle passes through the detection range of the microwave radar sensor to a background for measuring the vehicle speed.
2. The vehicle speed measuring method under the complex environment according to claim 1, characterized in that: and if the magnetic field data keeps stable state within the preset time B after the microwave radar sensor is started, sending a closing signal to the microwave radar sensor.
3. The vehicle speed measurement method in a complex environment according to claim 1 or 2, characterized in that: the detection range of the magnetic resistance sensor and the detection range of the microwave radar sensor are concentric circles, and the detection range of the magnetic resistance sensor is larger than that of the microwave radar sensor.
4. The vehicle speed measuring method under the complex environment according to claim 1, characterized in that: reference magnetic field data f for one-round vehicle speed measurement from the vehicle-entering vehicle speed measurement range to the vehicle-leaving vehicle speed measurement range, and for this-round vehicle speed measurement S10Comprises the following steps: the vehicle speed of the previous wheel is measured S0 and the steady magnetic field data after the vehicle has left the vehicle speed measurement range.
5. The vehicle speed measuring method under the complex environment according to claim 1, characterized in that: the microwave radar sensor is started according to the rule that,
the changed magnetic field data is relative to the reference magnetic field data f0Is not less than a first threshold;
the first threshold value is set to be,
wherein the content of the first and second substances,
is a first threshold value;
as standard deviation of noise distribution；
Taking the value of the noise distribution;
is the mean of the noise distribution;nis the number of noise values.
6. The vehicle speed measuring method under the complex environment according to claim 1, characterized in that: the rule of the vehicle entering the vehicle speed measuring range comprises a vehicle entering rule under normal climate and a vehicle entering rule under severe climate;
the vehicle entry rules in normal climates are:
magnetic field data after microwave radar sensor is started relative to reference magnetic field data f0Is not less than a second threshold;
and the number of the first and second electrodes,
the number of effective values of the radar analog voltage signals is not less than a third threshold value;
the vehicle entering rule under the severe weather is as follows:
magnetic field data after microwave radar sensor is started relative to reference magnetic field data f0Is not less than the fourth threshold; wherein the fourth threshold is much larger than the second threshold.
7. The vehicle speed measuring method under the complex environment according to claim 1, characterized in that: the rule that the vehicle leaves the vehicle speed measuring range is that the changed magnetic field data is relative to the reference magnetic field data f0Is not greater than the fifth threshold.
8. A vehicle speed measuring method under a complex environment is characterized in that: comprises the steps of (a) preparing a mixture of a plurality of raw materials,
receiving the time of the vehicle entering and leaving the detection range of the microwave radar sensor and the magnetic field intensity time sequence of the vehicle passing through the detection range of the microwave radar sensor, which are sent from the vehicle speed measuring device side;
inputting the magnetic field intensity time sequence into a pre-trained GoogLeNet network to obtain the type of the vehicle;
acquiring the length of the vehicle according to the type of the vehicle;
and calculating the speed of the vehicle according to the length of the vehicle and the time of the vehicle entering and leaving the detection range of the microwave radar sensor.
9. The vehicle speed measuring method under the complex environment according to claim 8, characterized in that: the google lenet network is a convolutional neural network that replaces the convolutional pooling layer with an initiation module, and includes a plurality of parallel classifiers for performing multi-task classification.
10. A vehicle speed measuring system under complex environment is characterized in that: the system comprises a vehicle speed measuring device and a background;
the vehicle speed measuring device comprises a controller, a magnetic resistance sensor, a microwave radar sensor, a communication module and a power supply; the magnetic resistance sensor, the microwave radar sensor and the communication module are connected with the controller, the communication module is communicated with the background, the power supply supplies power to all electric parts of the vehicle speed measuring device, and the controller executes any one of the methods according to claims 1 to 7; background performing any of the methods of claims 8-9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110257405.3A CN112634630A (en) | 2021-03-10 | 2021-03-10 | Vehicle speed measuring method and system under complex environment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110257405.3A CN112634630A (en) | 2021-03-10 | 2021-03-10 | Vehicle speed measuring method and system under complex environment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112634630A true CN112634630A (en) | 2021-04-09 |
Family
ID=75297785
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110257405.3A Pending CN112634630A (en) | 2021-03-10 | 2021-03-10 | Vehicle speed measuring method and system under complex environment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112634630A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101874758A (en) * | 2010-05-07 | 2010-11-03 | 中国科学院深圳先进技术研究院 | Supplementary motion system and control method thereof |
| CN102339531A (en) * | 2010-07-14 | 2012-02-01 | 数伦计算机技术（上海）有限公司 | Road traffic detection system |
| CN104112359A (en) * | 2013-04-22 | 2014-10-22 | 徐州工程学院 | Vehicle type and speed detection device based on bias magnetic field and working method |
| CN105261219A (en) * | 2015-09-28 | 2016-01-20 | 万永秀 | Alarm method for maliciously running red light |
| CN109147345A (en) * | 2018-07-16 | 2019-01-04 | 国创智能设备制造股份有限公司 | Intelligent transportation micro-nano Magnetic Sensor |
| CN111524367A (en) * | 2020-07-06 | 2020-08-11 | 江苏中科院智能科学技术应用研究院 | Distance measurement fusion method and system, composite traffic flow monitoring device and monitoring system |
-
2021
- 2021-03-10 CN CN202110257405.3A patent/CN112634630A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101874758A (en) * | 2010-05-07 | 2010-11-03 | 中国科学院深圳先进技术研究院 | Supplementary motion system and control method thereof |
| CN102339531A (en) * | 2010-07-14 | 2012-02-01 | 数伦计算机技术（上海）有限公司 | Road traffic detection system |
| CN104112359A (en) * | 2013-04-22 | 2014-10-22 | 徐州工程学院 | Vehicle type and speed detection device based on bias magnetic field and working method |
| CN105261219A (en) * | 2015-09-28 | 2016-01-20 | 万永秀 | Alarm method for maliciously running red light |
| CN109147345A (en) * | 2018-07-16 | 2019-01-04 | 国创智能设备制造股份有限公司 | Intelligent transportation micro-nano Magnetic Sensor |
| CN111524367A (en) * | 2020-07-06 | 2020-08-11 | 江苏中科院智能科学技术应用研究院 | Distance measurement fusion method and system, composite traffic flow monitoring device and monitoring system |
Non-Patent Citations (1)
| Title |
|---|
| 魏东等: "基于卷积神经网络的输电线路区内外故障判断及故障选相方法研究", 《中国电机工程学报》 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107133974B (en) | Gaussian Background models the vehicle type classification method combined with Recognition with Recurrent Neural Network | |
| CN109214107A (en) | A kind of ship's navigation behavior on-line prediction method | |
| CN101964063B (en) | Method for constructing improved AdaBoost classifier | |
| CN109389136A (en) | Classifier training method | |
| CN105913450A (en) | Tire rubber carbon black dispersity evaluation method and system based on neural network image processing | |
| CN110910531B (en) | Rapid pavement friction coefficient detection method based on vehicle-mounted OBD information | |
| CN113866742A (en) | Method for point cloud processing and target classification of 4D millimeter wave radar | |
| CN106056102A (en) | Video-image-analysis-based road vehicle type classification method | |
| CN104842720B (en) | Automobile tyre state communication detection platform | |
| CN108694829B (en) | Traffic flow identification monitoring network and method based on unmanned aerial vehicle group mobile platform | |
| CN111709336B (en) | Expressway pedestrian detection method, equipment and readable storage medium | |
| CN108491859A (en) | The recognition methods of driving behavior heterogeneity feature based on automatic coding machine | |
| CN110196587A (en) | Vehicular automatic driving control strategy model generating method, device, equipment and medium | |
| CN112435356B (en) | ETC interference signal identification method and detection system | |
| CN111391831B (en) | Automobile following speed control method and system based on preceding automobile speed prediction | |
| CN114154619A (en) | Ship track prediction method based on CNN and BILSTM | |
| CN108734303A (en) | Vehicle drive data predication method, equipment and computer readable storage medium | |
| CN104200670A (en) | Vehicle model identifying method based on vehicle earth induction characteristics | |
| CN112591333A (en) | Automatic garbage classification device and method based on artificial intelligence | |
| CN105139374A (en) | Power transmission line tracking method and system | |
| CN116205024A (en) | Self-adaptive automatic driving dynamic scene general generation method for high-low dimension evaluation scene | |
| CN112634630A (en) | Vehicle speed measuring method and system under complex environment | |
| CN113361491A (en) | Method for predicting pedestrian crossing intention of unmanned automobile | |
| CN110458013B (en) | Traffic abnormal event detection method based on instance-level attention mechanism | |
| CN116946183A (en) | Commercial vehicle driving behavior prediction method considering driving capability and vehicle equipment |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210409 |
|
| RJ01 | Rejection of invention patent application after publication |