CN107564285A - Vehicle queue length detection method and system based on microwave - Google Patents

Abstract

The invention discloses a microwave-based vehicle queue length detection method and system, including an array antenna module and a radio frequency module for transmitting multiple beams in the detection coverage area and receiving the returned multiple beams; a model database is used for detecting the coverage area The coordinate system is established in the area, and each lane is numbered to determine the coordinate range of each lane on the Y axis; the tracking algorithm module is used to analyze multiple beams returned in one scanning cycle; it is also used to determine the vehicle in the next The estimated area that will appear in the scanning cycle; it is also used to analyze multiple beams returned in the next scanning cycle; the data processing module is used to synthesize the data of the model database and the tracking algorithm module, and judge whether the speed of the vehicle is less than the predetermined value, to calculate the queue length. The invention can track the state of the vehicle in real time, analyze the queuing situation of the vehicle in real time, avoid being affected by the environment, and provide a basis for the control of traffic signals.

Description

Method and system for detecting vehicle queue length based on microwave

technical field

The invention relates to the field of traffic control, in particular to a microwave-based vehicle queue length detection method and system.

Background technique

Transportation is the lifeblood of a city and the most important infrastructure in the city's economy and people's lives. Traffic control is a social public welfare undertaking related to the national economy and the people's livelihood. It is closely related to the production and life of the public. The stable and sustainable development of cities and the improvement of people's living standards play an important role. Over the past 30 years of reform and opening up, with the rapid economic and social development of our country and the gradual expansion of urban population, the number of motor vehicles has shown a trend of rapid growth. The existing road network has been unable to meet the growing traffic demand, resulting in urban traffic accidents A series of problems such as frequent traffic congestion, increasingly severe traffic congestion, and serious environmental pollution have become serious problems that cities across the country urgently need to address, and are also important factors that plague urban development and restrict urban economic construction.

Due to the control of traffic lights, the queuing behavior of vehicles in the urban traffic network under high saturation will inevitably occur, and accurate acquisition and estimation of vehicle queuing length is the basis for evaluating the degree of traffic congestion, controlling timing of intersection signal lights, and controlling traffic flow overflow. important premise.

In the prior art, the maximum queuing length obtained by weighting the vehicle entering the intersection is generally obtained based on the geomagnetism of the intersection, and the microwave section on the cross section. However, this method cannot track and calculate the specific vehicles in the two sections of the lane, and can only obtain the maximum queue length on the road section but cannot obtain the queue length of each lane.

Moreover, the video sensor in the prior art collects vehicle images, generally including vehicle queuing presence detection, queue tail detection, and conversion of pixel distance to actual distance, which mainly converts pixel distance into actual length. In the real environment, the lane lines are parallel, but due to the imaging of the camera lens, the imaged lane lines are no longer parallel. In addition, there are many vehicles at traffic intersections, and the lane lines are severely worn and polluted, so it is not easy to divide the detection area by the method of identifying lanes. Moreover, if the image is collected by light, shadows, bad weather, and passing pedestrians, it will cause a large-area occlusion problem in the vehicle image, making it difficult to accurately segment the vehicle in the image, and ultimately reduce the number of vehicles at the intersection. The accuracy of queue length detection cannot provide an accurate basis for intelligent transportation system command. Due to the difference in brightness between the gray histograms of the daytime and night scenes, different algorithms are required for the video to detect vehicle queuing during the day and night, so it is necessary to automatically switch between daytime and night vehicle queuing detection algorithms.

Contents of the invention

The technical problem to be solved by the present invention is to provide a microwave-based vehicle queuing length detection method and system, which can track the status of vehicles in real time, analyze the queuing situation of vehicles in real time, avoid being affected by the environment, and provide a basis for the control of traffic signals.

In order to solve the problems of the technologies described above, the technical solution of the present invention is:

The microwave-based vehicle queue length detection method comprises the following steps:

S1: Take the position of the microwave sensor as the origin, take the direction parallel to the lane and the direction of microwave emission as the positive direction of the X-axis, and take the direction perpendicular to the lane and the direction of microwave emission as the positive direction of the Y-axis to establish a coordinate system;

S2: Number each lane, and determine the coordinate range of each lane on the Y axis;

S3: Scan the detection coverage area of the microwave sensor within a scanning period to obtain the X coordinate value, Y coordinate value, X speed value, Y speed value, along The length of the car in the direction of the X axis;

S4: matching each vehicle with the corresponding ID number;

S5: Determine the lane where the vehicle is located according to the Y coordinate value and the coordinate range;

S6: In the one scanning period, determine the estimated area where the vehicle will appear in the next scanning period;

S7: In the next scanning cycle, scan the detection coverage area to re-determine the X coordinate value, the Y coordinate value, the X speed value, and the Y speed value corresponding to the ID number , said lane;

S8: On the same lane, judge whether the speed of the vehicle closest to the stop line is less than a predetermined value, if “Yes”, proceed to S9, and if “No”, proceed to S3;

S9: On the same lane, judge whether the vehicle speed of the vehicle is less than the predetermined value one by one starting from the vehicle farthest from the stop line, until "Yes", then find the rear vehicle, and proceed to S10;

S10: Calculate the queue length according to the coordinates of the vehicle closest to the stop line, the coordinates and the length of the vehicle at the end of the queue.

Preferably, the following steps are further included between S2 and S3,

S201: Scan the lane without vehicles or people to obtain a background power spectrum;

Wherein, from S3 to S10, the value of the power spectrum obtained by the microwave sensor after each scan is subtracted from the value of the corresponding background power spectrum.

Preferably, between S7 and S8, the following steps are also included:

S701: Clear the information corresponding to the ID number after the vehicle leaves the detection coverage area.

In order to solve the above technical problems, the technical solution of the present invention can also be: a microwave-based vehicle queue length detection system, comprising:

An array antenna module and a radio frequency module, configured to transmit multiple beams in the detection coverage area and receive the returned multiple beams;

The model database is used to establish a coordinate system in the detection coverage area, and number each lane to determine the coordinate range of each lane on the Y axis, wherein the coordinate system is based on the position of the microwave sensor as The origin, the direction parallel to the lane and the microwave emission is the positive direction of the X-axis, and the direction perpendicular to the lane and the microwave emission is the positive direction of the Y-axis;

The tracking algorithm module is used to analyze the plurality of beams returned within one scan period to obtain the power spectrum diagram and the X coordinate value, Y coordinate value, X speed value, Y speed value, vehicle length along the X-axis direction, and match each vehicle with the corresponding ID number; it is also used to determine the estimated area where the vehicle will appear in the next scanning cycle; it is also used for analysis The plurality of beams returned in the next scanning cycle to re-determine the X coordinate value, the Y coordinate value, the X velocity value, the Y velocity value, the driveway;

The data processing module is used for synthesizing the data of the model database and the tracking algorithm module, and judging whether the speed of the vehicle is less than a predetermined value, so as to calculate the queue length.

Preferably, it also includes a background suppression module, which is used to save the background power spectrum obtained by scanning the array antenna module and the radio frequency module on the lane without vehicles or people; value minus the value of the background power spectrum.

Preferably, a storage module is also included, configured to store the data of the queue length, and transmit the data of the queue length to the data feedback module.

Preferably, the width of the beam is 1°, and the width of the plurality of beams is 36°.

Compared with the prior art, the beneficial effect of the present invention is that: the present invention utilizes the microwave detection technology to set the road information in the detector in advance (the microwave detector is calibrated during installation, and the lane coordinates are adjusted in the host computer and sent to the microwave detector). Based on the pre-set road information, the present invention can scan the running conditions of road vehicles in real time and detect the position and speed of each vehicle in real time without selecting a certain position as a sampling position. Therefore, the present invention can output the queuing length in real time with high accuracy as long as there is a queuing situation within the covered lane range. The present invention can also calculate the queuing length of each lane, and output the queuing length of each lane.

In the preferred solution of the present invention, the present invention suppresses the background noise through the two-dimensional radar image method in order to avoid the impact of the environment on the detection accuracy for some conditions on the road, such as isolation strips or metal railings, which will affect the radar performance. influences.

In the preferred solution of the present invention, the present invention uses a very narrow beam to quickly scan the detection area to improve the resolution of multi-target detection.

Description of drawings

Hereinafter, some specific embodiments of the present invention will be described in detail by way of illustration and not limitation with reference to the accompanying drawings. The same reference numerals in the drawings designate the same or similar parts or parts. Those skilled in the art will appreciate that the drawings are not necessarily drawn to scale. In the attached picture:

Fig. 1 is the flow chart of an embodiment of the microwave-based vehicle queue length detection method of the present invention;

Fig. 2 is the system block diagram of an embodiment of the microwave-based vehicle queue length detection system of the present invention;

Fig. 3 is a schematic diagram of the connection relationship between the array antenna module and the radio frequency module in the vehicle queuing length detection system of the present invention;

Fig. 4 is the schematic diagram of the working state of the vehicle queuing length detection system on the road of the present invention;

Fig. 5 is the schematic diagram of the detection coverage area of vehicle queuing length detection system of the present invention;

Fig. 6 is a schematic diagram of the detection coverage area of the detection system in Fig. 5 on the road;

Fig. 7 is the schematic diagram of the estimated area of the vehicle by the vehicle queuing length detection system of the present invention;

Fig. 8 is the background power spectrum graph that obtains when the vehicle queuing length detection system of the present invention scans the lane without car;

Fig. 9 is the power spectrum diagram that obtains when the vehicle queuing length detection system of the present invention scans the daily lane;

Fig. 10 is a schematic diagram of a continuous chirp wave;

Fig. 11 is a schematic diagram of a continuous chirp wave with Doppler frequency shift added.

The meanings of the symbols in the figure are as follows:

0-microwave sensor, 1-array antenna module, 11-transmitting antenna, 12-36 receiving antennas, 2-radio frequency module, 3-data processing module, 31-model database, 32-background suppression module, 33-tracking algorithm module , 34-storage module, 4-data feedback module, 5-power supply system, 6-estimated area, θ-sensor vertical pitch angle, α-sensor horizontal deflection angle, Dr-radial distance.

detailed description

The specific embodiments of the present invention will be further described below in conjunction with the accompanying drawings. It should be noted here that the descriptions of these embodiments are used to help understand the present invention, but are not intended to limit the present invention. In addition, the technical features involved in the various embodiments of the present invention described below may be combined with each other as long as they do not constitute a conflict with each other.

As shown in FIG. 2 , the present invention includes an array antenna module 1 , a radio frequency module 2 , a data processing module 3 , and a data feedback module 4 . The array antenna module 1 and the radio frequency module 2 can be used to transmit multiple beams in the detection coverage area, and receive the multiple beams returned. See Figure 3 for the schematic diagram of transmitting and receiving. The radio frequency module 2 is composed of a single-chip microwave integrated circuit, multiple low-noise amplifiers and local oscillators. The radio frequency module 2 transmits multiple beams to the outside through the transmitting antenna 11 . Then, the array antenna module 1 receives multiple returning beams through 36 receiving antennas 12 . The signal enters the data processing module 3 through a low-pass filter and an analog-to-digital converter for processing.

The present invention uses millimeter waves as the detection medium. Because the millimeter wave frequency band is a special frequency band between radio waves and light waves, it has optical detection accuracy and radio wave all-weather working characteristics, and its environmental adaptability and equipment maintenance are far superior. Compared with detection equipment in other frequency bands, at the same time, because the microwave sensor itself adopts the millimeter wave band, the antenna size is small, and the microwave sensor itself is also small, which is convenient for the construction and installation of subsequent devices on site. The detection coverage area of specific beams is shown in Fig. 5 and Fig. 6 . The invention uses a scanning antenna to quickly scan the detection coverage area through a very narrow beam, so as to obtain a fan-shaped detection coverage area. In this embodiment, the width of one beam is 1°, and 36 such beams are scanned in the detection coverage area. Such a narrow beam can improve the resolution of multi-target detection. The effective radial length of the detection coverage area ranges from 0 meters to 200 meters, which basically covers the queuing length of general vehicles on the lane. The coordinate system and related data are established in the model database 31 .

Fig. 4 shows the specific working mode of the vehicle queue length detection system of the present invention. The microwave sensor 0 of the detection system is set at the intersection, its installation height from the ground is H, and the vertical pitch angle of the sensor is θ. Then, take the position of the microwave sensor 0 as the origin O, take the direction parallel to the roadway and microwave emission as the positive direction of the X-axis, and take the direction perpendicular to the roadway and the direction of microwave emission as the positive direction of the Y-axis to establish a coordinate system. The sensor horizontal deflection angle between the microwave sensor 0 and the X axis is α. Then, number each lane, and determine the coordinate range of each lane on the Y axis. For example, the coordinate range of the first lane is Y0<Lane1<Y1, the coordinate range of the second lane is Y1<Lane2<Y2, and the coordinate range of the third lane is Y2<Lane3<Y3. In this embodiment, the actual coordinates are the origin O of the microwave sensor 0 (radar), the X axis is perpendicular to the direction of the radar antenna, and the direction of microwave emission is the positive direction of the X axis; the direction parallel to the radar antenna is the Y axis, That is, the direction perpendicular to the lane and microwave emission is the positive direction of the Y axis. Since the detection effect of installing the radar facing the driveway is better, the general installation method is to install it facing the driveway. Therefore, it can be interpreted that the "line" parallel to the lane is the X axis, and the "line" perpendicular to the lane is the Y axis. Therefore, in an embodiment, the two sides of the fan-shaped area may be symmetrical with respect to the X axis. In another embodiment, as shown in Figure 5, one side of the sector can be the X axis, and the other side of the sector is the farthest from the detection system on the stop line at the intersection. points intersect.

The microwave sensor 0 of the present invention obtains the power spectrum of each angle range through receiving in turn at each angle. Since the outer shell of the vehicle is made of metal, while the materials used in ordinary roads are asphalt and cement, the reflected power value of the vehicle is much higher than that of the road. In order to avoid the interference of background factors, after determining the coordinate system, the staff operates the microwave sensor 0 and scans the lane without vehicles to obtain the background power spectrum. The specific background power spectrum diagram is shown in FIG. 8 , which is the background power spectrum diagram obtained through a certain beam in a detection environment without people and vehicles on the road. The small grid on the abscissa in the figure represents the radial distance of the beam; the abscissa represents the difference frequency value fb, in kHz; the ordinate represents the energy power value P of each distance point, in dBm. The power spectrum obtained when the microwave sensor 0 is scanned under normal conditions is shown in Figure 9. The function of the background power spectrum map is to superimpose it with the power spectrum map to subtract the influence of the background environment and highlight the position of the vehicle. This step is also called background noise suppression. As shown in Fig. 2, the present invention saves the background power spectrum map obtained by scanning on the described lane without cars and people through the background suppression module 32, and then subtracts the value of the background power spectrum map from the value of the power spectrum map In order to avoid the interference of the detection structure by environmental factors.

The modulation method of the microwave beam in the present invention is specifically as follows. The radar system adopts frequency modulation continuous wave system and symmetrical triangular wave modulation. The frequency of the transmitted signal is modulated by a symmetrical triangle wave. Figure 10 shows the schematic diagram of the continuous chirp wave, the amplitude of the transmitted signal is constant, and within a period T, the frequency of the signal is:

in:

f ₀ is the effective center frequency of the signal;

△F is the effective bandwidth of the signal;

is the frequency modulation coefficient;

T is the period of the triangle wave;

is the initial phase.

Therefore, in one cycle, the downhill sweep frequency band of the transmitted signal can be expressed as:

in:

A is the signal amplitude (and represents the energy value of the echo).

During the effective signal period, the signal echo is:

in:

R is the radial distance of the target vehicle, and c is the speed of light.

Then, during the active signal period with In , subtract the instantaneous phase of formula (4) and formula (2), or subtract the instantaneous phase of formula (3) and formula (1), and the difference frequency signal obtained by mixing the transmitted signal and the echo signal can be obtained The instantaneous phase of is:

Then take the derivative of formula (7) to get the difference frequency signal frequency, which is:

It can be known from formula (8) that the distance of the target is proportional to the frequency of the difference frequency signal, so as long as the frequency of the output intermediate frequency signal is measured, the distance of the target can be calculated. Formulas (7) and (8) are for the case where the target vehicle to be detected is stationary. If the target vehicle moves along the radial direction of the microwave sensor beam at a speed of v, the echo of the microwave sensor will increase the Doppler frequency shift f _d . The Doppler frequency shift increases or decreases the frequency-time curve of the echo, resulting in an increase of a Doppler frequency shift on a part of the difference frequency, or a decrease of a Doppler frequency shift on another part of the difference frequency. Figure 11 shows a schematic diagram of a continuous chirp with Doppler shift added.

If the target vehicle is close to the microwave sensor, the difference frequency in the frequency modulation period is:

in:

is the difference frequency of the up-sweep frequency band;

is the difference frequency of the downsweep frequency band.

The distance and speed information of the target can be calculated by formula (11) and formula (12):

It can be seen from formula (11) that as long as the average frequency of the output beat frequency signal is measured, the distance of the target vehicle can be obtained. If the speed of the target vehicle is to be measured, the difference frequency signals output by the upper and lower sweep bands must be measured respectively, as shown in formula (12).

According to the derivation of fuzzy function, the distance resolution of triangular wave FM continuous wave is:

The speed resolution of triangular wave FM CW is:

According to the modulation method of the microwave beam mentioned above, after the microwave sensor scans, the radial velocity and radial distance Dr of the target vehicle are obtained (as shown in Figure 4), and the radial velocity V of the target vehicle relative to the sensor is obtained. The wave signal is extracted to obtain the RCS value (radar cross section) of the target vehicle, thereby obtaining the vehicle length and vehicle width of the target vehicle.

The tracking algorithm module 33 analyzes the multiple beams returned within one scan period to obtain the power spectrum diagram and the X coordinate value, Y coordinate value, X velocity value, Y velocity value, The length of the vehicle along the X-axis direction, and match each vehicle with the corresponding ID number. For example, scan the target vehicle, get its coordinates (X, Y), and get its velocity Vx in the X direction, and Vy in the Y direction. Among them, X and Y are calculated as:

X＝(Dr×sinθ)×cosα (15)

Y＝(Dr×sinθ)×sinα (16)

The calculation method of the speed in the X direction:

Vx＝(V×sinθ)×cosα (17)

Vy＝(V×sinθ)×sinα (18)

Then, determine which lane the target vehicle is in according to the Y value and the coordinate range of each lane. Carry out target classification (big car, small car, pedestrian, motorcycle, bicycle, etc.) according to the radar cross section RCS of the target vehicle, and obtain the vehicle length and vehicle width of the target vehicle.

On the basis of the above scanning, track the target vehicle. Fig. 7 shows an embodiment of the estimated area 6 when trajectory tracking is performed. The specific way of trajectory tracking is as follows. First, the tracking algorithm module 33 analyzes the multiple beams returned within one scan period to obtain the power spectrum and the X coordinate value, Y coordinate value, X velocity value, Y velocity of each vehicle in the detection coverage area. value, the length of the vehicle along the X-axis direction, and match each scanned vehicle with the corresponding ID number. The tracking algorithm module 33 also obtains the lane where the target vehicle is located. Then, in this scanning period, the tracking algorithm module 33 determines the estimated area 6 where the vehicle will appear in the next scanning period according to the previously obtained data. The estimated area 6 is an area extending from the head of the target vehicle to its running direction, wherein the starting point of the estimated area 6 is the position of the head of the target vehicle within this scanning period. Then, in the next scanning cycle, the tracking algorithm module 33 analyzes the returned beams again to re-determine the X coordinate value, Y coordinate value, X velocity value, Y velocity value, The lane, so as to update the data of the target vehicle under this ID number.

When more than one target exists in an estimated area, the point closest to the starting point of the estimated area 6 is the target point at the moment, and the information of this coordinate point is updated to the ID number. Generally in urban traffic, if the moving speed of a target is 120km/h, the size of the trajectory gate is about 1.6 meters, and the size of the 40km/h trajectory gate is about 0.5 meters. Can be captured by microwave sensors in real time. If the target leaves the detection coverage area, the ID number information of the target is initialized, that is, the information corresponding to the ID number is cleared, and this ID number will be free, and will be given to the target vehicle that newly enters the detection coverage area.

Preferably, one scanning cycle may be 60ms or other suitable cycle time.

On the basis of real-time tracking and detection of vehicles within the coverage area, the vehicle queue length detection system of the present invention calculates the queue length. The queuing length is defined as the queuing length of vehicles in each lane within a specified time period (starting at the stop line position and ending at the last stopped vehicle in the lane). After the target tracking processing in the detection coverage area, real-time statistics are made on the vehicles in the area, and the queue length is output by lane. As shown in Figure 2, the present invention synthesizes the data of the model database 31 and the tracking algorithm module 33 through the data processing module 3, and judges whether the speed of the vehicle is less than a predetermined value to calculate the queue length.

Because the X coordinate of the stop line of the lane under the coordinate system and the coordinates of each lane have been obtained when the coordinates are established before, and the Y coordinate of each vehicle is divided into lanes according to the coordinate range of each lane. And the X coordinate value of each target is the coordinate value of its head position. After the lane is divided, the queuing length is calculated for the vehicles in the same lane. When the speed of the target vehicle at the front of the lane (the vehicle closest to the stop line) is 0 km/h, and the speed of the last vehicle in the lane (the vehicle farthest from the stop line) is also 0 km/h, calculate the distance from the stop line The length of the distance between the farthest vehicle and the vehicle closest to the stop line, plus the length of the vehicle farthest from the stop line, is the queue length of the lane. However, if the speed of the last vehicle in the lane is not 0km/h, then calculate the speed of the previous vehicle of the target, and so on until the vehicle that is farthest from the stop line and has a speed of 0km/h is verified. Rear vehicles. Then calculate the distance between the vehicle at the tail of the queue and the vehicle closest to the stop line, and add the length of the vehicle at the tail of the queue to get the queue length of the lane.

Preferably, the data processing module 3 judges whether the speed of the vehicle is lower than a predetermined value, and the predetermined value may be 0 km/h or 0.2 km/h.

In summary, the queue length is equal to the X coordinate value of the vehicle at the end of the line minus the coordinate value of the vehicle closest to the stop line plus the length of the vehicle at the end of the line.

Preferably, the queue length detection system of the present invention further includes a storage module 34 , a power supply system 5 and a data feedback module 4 . The storage module 34 is used to store the data of the queue length, and transmit the data of the queue length to the data feedback module 4 . And the power supply system 5 will provide electric energy for each component of the system of the present invention.

As shown in Figure 1, according to another aspect of the present invention, the present invention also provides microwave-based vehicle queue length detection method, comprising the following steps:

S1: Take the position of the microwave sensor as the origin, take the direction parallel to the lane and the direction of microwave emission as the positive direction of the X-axis, and take the direction perpendicular to the lane and the direction of microwave emission as the positive direction of the Y-axis to establish a coordinate system;

S2: Number each lane, and determine the coordinate range of each lane on the Y axis;

S3: Scan the detection coverage area of the microwave sensor within a scanning period to obtain the X coordinate value, Y coordinate value, X speed value, Y speed value, along The length of the car in the direction of the X axis;

S4: matching each vehicle with the corresponding ID number;

S5: Determine the lane where the vehicle is located according to the Y coordinate value and the coordinate range;

S6: In the one scanning period, determine the estimated area where the vehicle will appear in the next scanning period;

S7: In the next scanning cycle, scan the detection coverage area to re-determine the X coordinate value, Y coordinate value, X speed value, Y speed value, and the lane corresponding to the ID number;

S8: On the same lane, judge whether the speed of the vehicle closest to the stop line is less than a predetermined value, if “Yes”, proceed to S9, and if “No”, proceed to S3;

S9: On the same lane, judge whether the vehicle speed of the vehicle is less than the predetermined value one by one starting from the vehicle farthest from the stop line, until "Yes", then find the rear vehicle, and proceed to S10;

S10: Calculate the queue length according to the coordinates of the vehicle closest to the stop line, the coordinates and the length of the vehicle at the end of the queue.

In the above steps, S1 to S2 are steps for establishing coordinates. S3 to S7 are the real-time trajectory tracking steps of the target vehicle in the present invention. S8 to S10 are the queue length calculation steps of the present invention. The implementation of the specific steps has been described in detail above.

Preferably, when establishing the coordinates, the following steps are further included between S2 and S3, S201: scanning the lane without vehicles and people to obtain a background power spectrum. The value of the power spectrum obtained by the microwave sensor after each scan is subtracted from the value of the corresponding background power spectrum, so as to prevent the scanning result from being affected by environmental factors.

Preferably, during track tracking, between S7 and S8, the following steps are further included: S701: Clear the information corresponding to the ID number after the vehicle leaves the detection coverage area.

The embodiments of the present invention have been described in detail above with reference to the accompanying drawings, but the present invention is not limited to the described embodiments. For those skilled in the art, without departing from the principle and spirit of the present invention, various changes, modifications, substitutions and modifications to these embodiments still fall within the protection scope of the present invention.

Claims (7)

1. the vehicle queue length detection method based on microwave, it is characterised in that comprise the following steps：

S1：Using microwave remote sensor position as origin, using the direction parallel to track and Microwave emission as X-axis positive direction, with It is Y-axis positive direction perpendicular to the track and the direction of Microwave emission, establishes coordinate system；

S2：Each track is numbered, and determines coordinate range of each track in Y-axis；

S3：Within a scan period, the detection overlay area of the microwave remote sensor is scanned, to obtain covering in the detection The X-coordinate value of each vehicle in region, Y-coordinate value, X velocity amplitudes, Y velocity amplitudes, the vehicle commander along X-direction；

S4：Each vehicle is matched with corresponding ID number；

S5：The place track of the vehicle is determined according to the Y-coordinate value and the coordinate range；

S6：Within one scan period, determine the vehicle in the discreet area that next scan period will appear from；

S7：Within next scan period, the detection overlay area is scanned, to redefine the institute of the corresponding ID number State X-coordinate value, the Y-coordinate value, the X velocity amplitudes, the Y velocity amplitudes, the track；

S8：On same track, whether the speed of the nearest vehicle of judging distance stop line is less than predetermined value, "Yes", then carries out S9, "No", then carry out S3；

S9：On the same track, judge whether the speed of vehicle is small forward since apart from the farthest vehicle of stop line one by one In the predetermined value, until "Yes", then tail of the queue vehicle is found, and carry out S10；

S10：According to described apart from the coordinate of the nearest vehicle of stop line, the coordinate of the tail of the queue vehicle and vehicle commander, calculate and be lined up length Degree.

2. vehicle queue length detection method according to claim 1, it is characterised in that：Between S2 and S3 also include with Lower step,

S201：Scanning is without nobody track of car, to obtain background power spectrogram；

Wherein, from S3 to S10, corresponding to the value of power spectrum chart that the microwave remote sensor obtains after scanning each time all subtracts The value of the background power spectrogram.

3. vehicle queue length detection method according to claim 1, it is characterised in that：Between S7 and S8, in addition to Following steps：

S701：After the vehicle leaves the detection overlay area, the information of the corresponding ID number is emptied.

4. the vehicle queue length detecting system based on microwave, it is characterised in that including：

Array antenna module and radio-frequency module, for launching multiple wave beams in detection overlay area, and receive the described more of return Individual wave beam；

Model database, for establishing coordinate system in the detection overlay area, and each track is numbered, to determine Coordinate range of each track in Y-axis is stated, wherein, the coordinate system is using microwave remote sensor position as origin, with parallel In track and the direction of Microwave emission be X-axis positive direction, using square as Y-axis perpendicular to the direction in the track and Microwave emission To；

Track algorithm module, for analyzing the multiple wave beam that is returned within a scan period, with obtain power spectrum chart and The X-coordinate value of each vehicle, Y-coordinate value, X velocity amplitudes, Y velocity amplitudes in the detection overlay area, along X-direction Vehicle commander, and each vehicle is matched with corresponding ID number；It is additionally operable to determine that the vehicle will in next scan period The discreet area of appearance；The multiple wave beam that analysis returns within next scan period is additionally operable to, to redefine The X-coordinate value of the corresponding ID number, the Y-coordinate value, the X velocity amplitudes, the Y velocity amplitudes, the track；

Data processing module, for integrating the data of the model database and the track algorithm module, and judge vehicle Whether speed is less than predetermined value, to calculate queue length.

5. vehicle queue length detecting system according to claim 4, it is characterised in that also including background suppression module, Obtained background work(is scanned for preserving the array antenna module and the radio-frequency module on without nobody track of car Rate spectrogram；It is additionally operable to subtract the value of the power spectrum chart value of the background power spectrogram.

6. vehicle queue length detecting system according to claim 4, it is characterised in that also including memory module, be used for The data of the queue length are stored, and the data of the queue length are sent to data feedback module.

7. the vehicle queue length detecting system according to claim 4 or 5, it is characterised in that the width of the wave beam is 1 °, the width of the multiple wave beam is 36 °.