CN111239727B

CN111239727B - Passenger counting method and communication equipment

Info

Publication number: CN111239727B
Application number: CN202010121725.1A
Authority: CN
Inventors: 石绍应; 周畅
Original assignee: Shenzhen Leiyan Technology Co ltd
Current assignee: Shenzhen Leiyan Technology Co ltd
Priority date: 2020-02-26
Filing date: 2020-02-26
Publication date: 2020-12-29
Anticipated expiration: 2040-02-26
Also published as: CN111239727A

Abstract

The embodiment of the application discloses a passenger counting method and communication equipment. The method is applied to the communication device which comprises a millimeter wave radar and a computing device. The method comprises the following steps: the millimeter wave radar transmits a millimeter wave radar signal and receives an echo signal; the computing device determines the positions of a plurality of targets according to the monitoring data of the millimeter wave radar and determines the mass centers at different moments according to the positions of the targets; the calculating device determines the mass centers of the same passenger from the mass centers at different moments and establishes the moving track of the passenger; the computing device determines the number of passengers getting on and off the vehicle according to the number and the direction of the moving tracks. By implementing the embodiment of the application, the number of passengers can be determined by establishing the movement track of the passengers, and the accuracy of passenger counting is improved.

Description

Passenger counting method and communication equipment

Technical Field

The application relates to the technical field of millimeter wave detection, in particular to a passenger counting method and communication equipment.

Background

With the development of public transportation systems, more and more people choose to take public transportation vehicles such as buses and subways when going out. In the time periods such as holidays, morning and evening peaks of commuting and the like, the situations of crowded personnel and overlong waiting time of passengers often occur. If the number of passengers and the number of waiting passengers in the public transportation system can be counted, the reasonable dispatching of public transportation, the guidance of waiting passengers and the like can be realized according to the number counting data, so that the passengers can conveniently go out.

The depth camera may implement passenger counting by time-of-flight ranging. In particular, the depth camera may continuously send light pulses to the target and receive light pulses back from the target. By calculating the time of the light pulse from emission to return, i.e. the time of flight, the depth camera can obtain the distance information from the target to the depth camera, thereby generating a 3D image of the target and realizing passenger counting.

However, the detection range of the depth camera is limited by the installation height, the height of the subway door is generally 1.9 meters, and the depth camera cannot meet the requirement of passenger counting required by low installation height. The depth camera is sensitive to light line parts, and under the condition that light intensity is weak, weather such as rain haze appears, the passenger counting accuracy rate greatly reduces. In addition, the 3D image generated by the depth camera has low resolution, and when people are crowded, people may be blocked, and the accuracy of passenger counting by the depth camera may be reduced.

Disclosure of Invention

The embodiment of the application provides a passenger counting method and a communication device, which can be used for establishing a movement track of passengers to determine the number of the passengers and improve the accuracy of passenger counting.

In a first aspect, an embodiment of the present application provides a passenger counting method, wherein:

the communication equipment transmits millimeter wave radar signals and receives echo signals;

the communication equipment determines the positions of a plurality of targets detected in a first time period according to monitoring data of the millimeter wave radar in the first time period; the monitoring data comprise millimeter wave radar signals transmitted to a target by the millimeter wave radar, transmitting time, echo signals reflected by the target and receiving time; the position of the target is determined by the distance and the direction of the target relative to the millimeter wave radar, and the distance and the direction are determined by the monitoring data;

the communication equipment determines the mass centers at different moments according to the positions of the multiple targets detected in the first time period; the number of objects within a first region centered at the centroid exceeds a first value; a centroid represents the position of a passenger at a time;

the communication equipment determines the mass centers belonging to the same passenger from the mass centers at different moments, and connects the mass centers belonging to the same passenger according to the time sequence to generate the moving track of the same passenger;

the communication device determines the number of passengers according to the number of the movement tracks.

The communication equipment transmits the millimeter wave radar signal in a first time period and receives the echo signal; the doors of the vehicle compartment are open during the first time period.

And the communication equipment stops transmitting the millimeter wave radar signal when the door of the carriage is closed.

The direction is represented by an included angle between a connecting line between the target and a projection point of the millimeter wave radar on the horizontal plane and the first direction; the first direction is perpendicular to an extension direction of the train.

The echo signals comprise first echo signals reflected by passengers and second echo signals reflected by interferents, before the communication equipment determines the mass centers at different moments according to the positions of a plurality of targets detected in the first time period, the communication equipment performs distance dimension constant false alarm rate detection on the plurality of targets by utilizing ordered statistics constant false alarm rate detection, and screens out a first target set; the distance dimension constant false alarm rate detection is used for judging whether the echo signals received by the millimeter wave radar from the same direction and different distances in the monitoring range are the first echo signals, and the targets in the first target set are determined by the first echo signals judged by the distance dimension constant false alarm rate detection;

the communication equipment detects the constant false alarm rate of the speed dimension of the multiple targets by using the average constant false alarm rate detection of the unit, and screens out a second target set; the speed dimension constant false alarm rate detection is used for judging whether the multi-pulse echo signal is a first echo signal according to a multi-pulse echo signal received by the millimeter wave radar from a monitoring range of the same distance, and a target in the second target set is determined by the first echo signal judged by the speed dimension constant false alarm rate detection;

the communication equipment utilizes unit average constant false alarm rate detection to carry out direction dimension constant false alarm rate detection on the multiple targets, and screens out a third target set; the direction dimension constant false alarm rate detection is used for judging whether the echo signals received by the millimeter wave radar from the monitoring ranges of the same distance and different directions are the first echo signals, and the targets in the third target set are determined by the first echo signals judged by the direction dimension constant false alarm rate detection;

the communication device determines the centroids of the plurality of targets at different times according to the positions of the plurality of targets in the intersection of the first target set, the second target set and the third target set.

The communication device generates a first set according to a plurality of targets detected in the first time period, wherein the first set comprises one or more first targets and a plurality of second targets, the number of targets contained in the neighborhood of the first targets is larger than or equal to the number of clustering points, and any one target in the plurality of first targets is in the neighborhood of another first target; the second target is positioned in the neighborhood of the first target, and the number of targets contained in the neighborhood of the second target is less than the number of the clustering points;

the neighborhood of the first target is a circular area which takes the first target as a center and takes a first length as a radius; the neighborhood of the second target is a circular region which takes the second target as a center and takes the first length as a radius;

the communication device determines the centroid from the locations of the objects in the first set.

The plurality of targets detected during the first time period comprises the first set and a third target; the third target is not positioned in the neighborhood of the first target, and the number of targets contained in the neighborhood of the third target is less than the number of the clustering points;

the third target has a circular area centered on the third target and having the first length as a radius.

The centroid is an average of the locations of the objects in the first set.

Alternatively, the centroid is a location of one of the objects selected from the first set.

The communication equipment determines the predicted centroid of the same passenger at the i +1 th moment according to the centroids of the passengers at the i th moment and the centroid speed of the same passenger at the i th moment, and establishes a first wave gate by taking the predicted centroid of the i +1 th moment as the center of a circle; the mass center of the passengers at the ith time is used for determining the direction of the same passenger from the ith time to the (i +1) th time, the mass center speed of the same passenger at the ith time is representative of the speed of the same passenger at the ith time, and the mass center speed is used for determining the distance of the same passenger from the ith time to the (i +1) th time; the radius of the first wave gate enables the probability that the centroid falling into the first wave gate at the (i +1) th moment is the centroid of the same passenger at the (i +1) th moment to be a preset probability;

the communication device determines the centroid of the same passenger at the moment i +1 from the centroids at the moment i +1 within the first wave gate; the centroid of the same passenger at the moment i +1 is the centroid closest to the predicted centroid of the same passenger at the moment i +1 among the centroids of the same passenger at the moment i +1 in the first wave gate.

The centroids at the previous H moments are connected to form an initial track of the passenger in the centroids of the same passenger at different moments; the centroids of the previous H moments comprise the centroid of the mth moment to the centroid of the m + H-1 moment determined by the communication device;

in the centroids at the previous H moments, the distance between the centroid at the mth moment and the centroid at the m +1 moment is less than the radius of the second wave gate; the first wave gate is a circular area with the centroid at the mth moment as a circle center, and the radius of the first wave gate is the maximum distance which can be reached by a passenger in the interval time of continuously transmitting the millimeter wave radar signal twice by the communication equipment;

of the centroids at the previous H moments, the centroid of the same passenger at the m + g moment is the centroid closest to the predicted centroid of the same passenger at the m + g moment in the centroids at the m + g moment in the first wave gate; the predicted centroid of the same passenger at the m + g moment is determined by the centroids of the multiple passengers at the m + g-1 moment and the centroid speed of the same passenger at the m + g-1 moment; the centroids of the passengers at the m + g-1 moment are used for determining the directions of the same passenger from the m + g-1 moment to the m + g moment, the centroid speed of the same passenger at the m + g-1 moment represents the speed of the same passenger at the m + g-1 moment, and the distance of the same passenger from the m + g-1 moment to the m + g moment is determined; m and H are positive integers, and g is a positive integer which is more than 1 and less than H.

The moving track of the same passenger is generated by connecting the centroids of the same passenger at W moments, and the centroids of the last continuous Q moments in the centroids at the W moments are the predicted centroids of the same passenger; and W and Q are positive integers.

The communication device determines the number of passengers getting on the train and/or the number of passengers getting off the train; wherein the number of passengers getting on the train is equal to the number of first movement tracks, and the first movement tracks extend into the carriage; the number of the passengers getting off the vehicle is equal to the number of second moving tracks, and the second moving tracks extend outwards of the carriage.

In a second aspect, the present application provides a communication device for passenger counting, the communication device comprising a millimeter wave radar and a computing device; wherein:

the millimeter wave radar is used for transmitting a millimeter wave radar signal and receiving an echo signal;

the computing device is used for determining the positions of a plurality of targets detected in a first time period according to the monitoring data of the millimeter wave radar in the first time period; the monitoring data comprise millimeter wave radar signals transmitted to a target by the millimeter wave radar, transmitting time, echo signals reflected by the target and receiving time; the position of the target is determined by the distance and the direction of the target relative to the millimeter wave radar, and the distance and the direction are determined by the monitoring data;

the computing device is further used for determining the mass centers at different moments according to the positions of the multiple targets detected in the first time period; the number of objects within a first region centered at the centroid exceeds a first value; a centroid represents the position of a passenger at a time;

the computing device is further used for determining the mass centers belonging to the same passenger from the mass centers at different moments, and connecting the mass centers belonging to the same passenger according to a time sequence to generate the moving track of the same passenger;

the computing device is further used for determining the number of passengers according to the number of the movement tracks.

The communication equipment utilizes the characteristics that millimeter wave radar signal resolution is high, not influenced by environments such as light intensity, rain haze and the like, and can count passengers under the environments with poor light conditions and crowded personnel. And the communication device executes the passenger counting method of the first aspect described above, taking into account that one passenger may reflect a plurality of millimeter wave radar signals, from which a plurality of targets may be determined. The plurality of objects are most dense in the head, chest and back area of a passenger, and by clustering the plurality of objects, the communication device can establish the movement trajectory of the passenger. And determining the number of passengers according to the number of the moving tracks. Therefore, the accuracy of passenger counting in the environment with poor light conditions and crowded personnel can be improved.

Drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.

Fig. 1 is a schematic structural diagram of a communication device according to an embodiment of the present application;

fig. 2 is a schematic diagram of a millimeter wave radar monitoring range provided in an embodiment of the present application;

FIG. 3 is a schematic diagram of a passenger including multiple targets according to an embodiment of the present disclosure;

fig. 4 is a block diagram of a communication device performing constant false alarm rate detection according to an embodiment of the present disclosure;

fig. 5 is a block diagram of another communication device for constant false alarm rate detection according to an embodiment of the present disclosure;

fig. 6 is a schematic diagram of target clustering performed by a communication device according to an embodiment of the present application;

FIG. 7 is a flowchart of a method for counting passengers by a communication device according to an embodiment of the present application;

fig. 8 is a schematic diagram of a communication device provided in an embodiment of the present application for establishing a movement track of a passenger;

fig. 9 is a schematic diagram of another communication device provided in the embodiment of the present application for establishing a movement track of a passenger;

FIG. 10 is a schematic diagram of a communication device for evaluating a movement track of a passenger according to an embodiment of the present application;

FIG. 11 is a schematic diagram of another communication device for evaluating a movement trajectory of a passenger according to an embodiment of the present application;

fig. 12 is a schematic structural diagram of another communication device provided in an embodiment of the present application.

Detailed Description

The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some, but not all, embodiments of the present application. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.

The terms "first," "second," "third," and "fourth," etc. in the description and claims of this application and in the accompanying drawings are used for distinguishing between different objects and not for describing a particular order. Furthermore, the terms "include" and "have," as well as any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those steps or elements listed, but may alternatively include other steps or elements not listed, or inherent to such process, method, article, or apparatus.

Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the application. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. It is explicitly and implicitly understood by one skilled in the art that the embodiments described herein can be combined with other embodiments.

In order to count passengers in an environment with low installation height requirements and improve the accuracy of passenger counting, the communication device in the embodiment of the application utilizes the millimeter wave radar and the computing device to count passengers. The communication device may continuously transmit millimeter wave radar signals through a millimeter wave radar and receive echo signals reflected by the target. By processing the millimeter wave radar signal transmitted by the millimeter wave radar and the received echo signal, the communication device can calculate the distance, speed and direction of the passenger through the calculation means, thereby establishing the movement trajectory of the passenger. According to the number and the direction of the moving tracks, the communication device can calculate the number of passengers entering and exiting the carriage through the calculating device, so that the passenger counting is realized.

Compared with a depth camera, the millimeter wave radar has lower requirement on installation height, and is suitable for low-height monitoring environments such as buses and subways. Moreover, radar signals transmitted by the millimeter wave radar are not influenced by environments such as light intensity, rain, haze and the like, and the accuracy of passenger counting cannot be reduced. In addition, the resolution ratio of millimeter wave radar is higher to the millimeter wave radar signal of transmission can pierce through material such as plastics, wallboard and clothes, and is very little at passenger and passenger's interval, perhaps appears under the condition that the passenger sheltered from, and the communication equipment that utilizes millimeter wave radar still can carry out passenger counting with higher accuracy.

The communication equipment can monitor the number of people in the carriage in real time and send the passenger counting result to an external data application system such as a train dispatching center or an intelligent traffic system. For example, the communication equipment counts the number of people in each shift train of the subway, and the counting result of passengers can be sent to a subway dispatching center, so that the reasonable dispatching of the subway is realized. The communication equipment can also count the number of people in each carriage of the subway, and sends the counting result of the passengers in each carriage to the intelligent traffic system, so that the passengers can conveniently select the platform and the working personnel reasonably to guide the passengers waiting for the subway according to the number of people in each carriage.

In one possible implementation, the millimeter wave radar and the computing means may be integrated in one communication device. The communication device can obtain the passenger counting result through the millimeter wave radar and the calculating device, and sends the passenger counting result to the external data application system.

In another possible implementation, the millimeter wave radar and the computing device may be two separate devices, which together constitute the communication apparatus. The millimeter wave radar can transmit millimeter wave radar signals and receive echo signals. The computing device can receive monitoring data sent by the millimeter wave radar, and count passengers according to the monitoring data to obtain a passenger counting result. The computing device may send the passenger count results to an external data application. The computing device may be a cloud-end virtual server for computing or a physical computer or the like. The millimeter wave radar can establish connection with a computing device in a wireless or wired manner, and form communication equipment. In the embodiment of the present application, a millimeter wave radar and a computing device are specifically described as two separate devices.

Referring to fig. 1, fig. 1 is a schematic structural diagram of a communication device according to an embodiment of the present disclosure. As shown in fig. 1, the communication apparatus includes a millimeter wave radar 101 and a computing device 102. Wherein the content of the first and second substances,

the millimeter wave radar 101 may be mounted on a door of a compartment of the subway 104, continuously transmits a millimeter wave radar signal, and receives a reflected echo signal. The echo signal is also a millimeter wave radar signal. The installation position of millimeter wave radar 101 is not specifically limited in the embodiment of the present application, and may be installed in a door of a carriage of subway 104, or in a position of a waiting area of a subway or in other positions such as a door of a bus.

The application scenario of counting the number of people is not limited in the embodiment of the application, and the number of people or articles can be counted under other application scenarios besides counting the number of passengers in the carriage. For example, the number of people in the venue is counted. In the embodiment of the present application, an application scenario in which a millimeter wave radar is installed on a door of a carriage of a subway to count the number of passengers is specifically described as an example.

Millimeter-wave radar 101 may be a phased array radar in which each antenna element may be configured with a phase shifter. The phased array radar can emit millimeter wave radar signals from a certain point position, the phase of the millimeter wave radar signals is changed by controlling the phase shifter, and the scanning monitoring function can be realized under the condition that the antenna unit does not need to be mechanically rotated. The number of antenna elements in the millimeter wave radar 101 is not limited in the embodiment of the present application.

The monitoring angle θ 105 of the millimeter wave radar 101 may be determined by the distance between the respective adjacent antenna elements. For example, when the distance between the respective adjacent antenna elements in the millimeter wave radar 101 is half the wavelength, the monitoring angle θ of the millimeter wave radar 101 is 120 °. Specifically, referring to fig. 2, fig. 2 is a schematic diagram of a millimeter wave radar monitoring range according to an embodiment of the present disclosure. Among them, the millimeter wave radar 101 may be mounted on a door 106 of a compartment of the subway 104. The monitoring range of the millimeter wave radar 101 may be an outer region of the vehicle door 106, and a sector region with the millimeter wave radar signal emission position as a vertex and the angle θ as a monitoring range. Because the rule that the passengers are guided to enter and exit the carriage by the subway is that the passengers enter and exit from the middle of the vehicle door and enter from two sides of the vehicle door, the passengers entering and exiting the carriage pass through the outer area of the carriage, and the number of the passengers getting on and off can be counted by the millimeter wave radar only by taking the outer area of the vehicle door 106 as a monitoring range.

The above-mentioned wavelength is a wavelength of an electromagnetic wave emitted by the millimeter wave radar, i.e., a wavelength of a millimeter wave radar signal. The distance between the adjacent antenna units is not specifically limited in the embodiments of the present application, and may be half of the wavelength or other values.

Millimeter-wave radar 101 may send the monitoring data to computing device 102. The monitoring data includes the transmission time and signal waveform of the millimeter wave radar signal, and the reception time and signal waveform of the echo signal. The embodiment of the present application does not limit the content included in the monitoring data, and may include more content.

The computing device 102 may be configured to calculate the number of passengers getting on and off the vehicle based on the received monitoring data and send the passenger count results to the external data application 103. The calculating device 102 may calculate the distance, the direction, and the speed of the target between the target reflecting the echo signal and the millimeter wave radar. From the distance and direction between the target and the millimeter wave radar, the computing device 102 may determine the position of the target. When determining the location of each object, the computing device 102 may perform an object clustering process that clusters multiple objects from one passenger into a class and extracts the centroids of the clustered objects. Depending on where the centroid is located at different times, the computing device 102 may track a trajectory that represents the centroid of the same passenger. Based on the number and direction of the tracks, the computing device 102 may implement passenger counting.

In the embodiment of the present application, one target may represent a position point at which a millimeter wave radar signal is reflected. Typically a passenger may contain multiple targets.

It should be noted that the resolution of the millimeter wave radar is high, and one passenger includes a plurality of body parts such as the head, the chest, the arms, and the legs. Usually, the plurality of body parts have different motion characteristics, for example, the directions of motion, the magnitudes of motion, and the like of the head, shoulders, arms, and crotch of the passenger are not uniform when the passenger walks. Multiple body parts of a passenger may reflect radar signals, i.e., a passenger may contain multiple targets.

As shown in fig. 3, fig. 3 is a schematic diagram of a passenger including multiple targets according to an embodiment of the present application. When the millimeter-wave radar transmits a millimeter-wave radar signal, a plurality of echo signals reflected by one passenger can be received. From the plurality of echo signals, the computing device may form a plurality of targets. Wherein the computing device may form a point cloud 107 containing a plurality of targets. Since the millimeter wave radar signal emitted by the millimeter wave radar 101 may be at an angle, for example, 25 ° or 30 ° or the like, with respect to the horizontal plane direction, the above-described millimeter wave radar signal obliquely hits the body part of the passenger. The computing device forms a cloud 107 of dots as a two-dimensional plan. The objects contained by one passenger in cloud 107 may form a projection of the one passenger in a horizontal plane.

The included angle between the millimeter wave radar signal and the horizontal plane direction is not limited in the embodiment of the application.

Since one passenger may include a plurality of objects, when counting passengers, the passenger counting result cannot be determined according to the number of the objects alone, and it is necessary to perform object clustering on the objects first and then extract the centroid of the objects clustered into one class. The computing device may count passengers according to the centroid.

In the present embodiment, a centroid may represent the position of a passenger at a certain time. The position of a passenger at different times can be represented by a plurality of centroids as the passenger is moving. For example, the millimeter wave radar may continuously transmit the millimeter wave radar signal 5 times, and may receive an echo signal reflected by the target for the millimeter wave radar signal 5 times. The computing device can obtain the target of the echo signal reflected at the 5 moments according to the echo signal reflected by the millimeter wave radar. The computing device may cluster these objects, resulting in a centroid at these 5 moments. Wherein one centroid may represent the position of a passenger at one time and a plurality of centroids may represent the position of a passenger at different times.

Since the embodiment of the application relates to a calculation device which calculates the distance of a target, the speed of the target and the direction of the target by using millimeter wave radar signals, and performs constant false alarm rate detection, target clustering and centroid extraction on the target, the following introduces the principle of the algorithm used for calculating the distance of the target, the speed of the target and the direction of the target and constant false alarm rate detection, target clustering and centroid extraction.

Calculating the distance of the target:

the calculation means may process the millimeter wave radar signal using a Fast Fourier Transform (FFT) to calculate a distance of the target, which may represent a distance between the target and the millimeter wave radar. The distance dimension FFT may represent FFT performed on echo signals at different distances received from the same millimeter wave radar signal transmitted by the millimeter wave radar. The millimeter wave radar signal transmitted by the millimeter wave radar may be a chirp signal. The computing device can perform difference frequency processing on a millimeter wave radar signal transmitted by the millimeter wave radar and a received echo signal, and obtain an intermediate frequency signal. The calculating device performs distance dimension FFT on the intermediate frequency signal to obtain an intermediate frequency. According to the intermediate frequency, the calculating device can calculate the distance of the target. The specific calculation method is as follows:

the millimeter-wave radar may transmit millimeter-wave radar signals and receive echo signals reflected from the target. The calculation means may calculate the distance between the target and the millimeter wave radar based on the time interval between the transmitted millimeter wave radar signal and the received echo signal and the propagation speed of the electromagnetic wave. The millimeter wave radar signal and the echo signal are both electromagnetic waves, and the propagation speed of the millimeter wave radar signal and the echo signal is the propagation speed of the electromagnetic waves. The target distance calculation formula can be represented by the following formula (1):

where τ is a time interval between the transmitted millimeter wave radar signal and the received echo signal, c is an electromagnetic wave propagation speed, and d is a distance between the target and the millimeter wave radar.

In one possible implementation, the calculation means may calculate the time interval τ from a difference in frequency between the transmitted millimeter wave radar signal and the received echo signal.

Specifically, the millimeter wave radar signal transmitted by the millimeter wave radar may be a chirp pulse that is subjected to chirp by the millimeter wave radar. The frequency of the chirp varies linearly with time. Due to the time interval between the transmitted millimeter wave radar signal and the received echo signal, a frequency difference exists between the transmitted millimeter wave radar signal and the received echo signal. The frequency difference is a fixed value according to the frequency characteristics of the chirp.

The computing device may perform difference frequency processing on the transmitted millimeter wave radar signal and the received echo signal to obtain an intermediate frequency signal. And performing FFT on the intermediate frequency signal, and obtaining the intermediate frequency by the computing device. According to the intermediate frequency, the calculating device can calculate the time interval tau, and further calculate the distance between the target and the millimeter wave radar.

For example, the millimeter wave radar may transmit a chirp whose initial frequency may be 77GHz and whose bandwidth B may be 4 GHz. The chirp duration T may be 40 microseconds (us), and the chirp rate μmay be the bandwidth B divided by the duration T, i.e., 100 MHz/us. FFT processing is carried out on the intermediate frequency signal, and the calculating device can obtain the intermediate frequency S_τ. Wherein the intermediate frequency S_τCan be represented by the following formula (2):

then, as can be seen from equation (2), the distance between the target and the millimeter wave radar may be calculated by using the intermediate frequency, and the specific calculation formula may be shown as following equation (3):

the fourier transform method is not limited in the embodiment of the present application, and may be other methods besides FFT.

The initial frequency of the chirp is not particularly limited in the embodiment of the present application, and may be other open frequency bands besides 77 GHz.

The bandwidth and the duration of the chirp are not specifically limited in the embodiments of the present application.

Calculating the speed of the target:

because the millimeter wave radar transmits the linear frequency modulation pulse at intervals of the pulse repetition period, the millimeter wave radar can receive echo signals reflected by the same target in different time. According to the echo signals of two adjacent linear frequency modulation pulses from the same target, the calculating device can respectively calculate the distance between the target and the millimeter wave radar so as to obtain the pulse repetition period T_cThe distance of movement of the inner target. According to the moving distance and the pulse repetition period T_cThe computing device may calculate the velocity of the target. The above pulse repetition period T_cAnd transmitting the time interval of two adjacent linear frequency modulation pulses for the millimeter wave radar.

Since the target is moving relative to the millimeter wave radar, there is a doppler effect. The calculation device may perform two-dimensional FFT on the intermediate frequency signal, that is, perform doppler-dimensional FFT on the basis of performing distance-dimensional FFT. The doppler dimension FFT described above may represent FFT of echo signals at the same distance received by a plurality of chirps transmitted by a millimeter wave radar. By means of a two-dimensional FFT, the calculation means can obtain an amplitude spectrogram of the chirp. Wherein, according to the angular frequency corresponding to the peak position of the amplitude in the amplitude spectrogram, the calculating device can calculate the Doppler frequency f of the target_d. The specific calculation formula can be shown as the following formula (4):

where ω is the angular frequency corresponding to the peak position of the amplitude in the amplitude spectrogram, T_cIs a pulse repetition period.

From the doppler frequency, the calculation means can calculate the velocity of the target. The specific calculation formula can be shown as the following formula (5):

wherein λ is the wavelength of the millimeter wave radar signal.

In a possible implementation manner, when multiple targets with different speeds are within the monitoring range of the millimeter wave radar and the distances between the multiple targets and the millimeter wave radar are the same, the millimeter wave radar may receive echo signals from the multiple targets at the same time. An amplitude spectrogram obtained by performing a distance-dimensional FFT on the plurality of echo signals received simultaneously includes phase components of the plurality of targets. The calculation means may obtain doppler frequencies of the plurality of targets by performing doppler dimension FFT on the basis of the distance dimension FFT, thereby discriminating a plurality of targets which cannot be discriminated in the distance dimension.

For example, when there are two targets that are equal in distance from the millimeter wave radar, and the millimeter wave radar transmits a chirp frame to the two targets, N echo signals may be received. Wherein the one frame of chirp may comprise a set of N chirps, and the pulse repetition period of the N chirps may be T_c. The calculation means may perform distance dimension FFT on the N echo signals, respectively. On the basis of distance dimension FFT, the calculating device performs N-point FFT on N vectors generated by the N distance dimension FFT to obtain an amplitude spectrogram with two amplitude peaks. The calculating means may calculate the doppler frequencies of the two targets respectively using formula (4) and calculate the velocities of the two targets respectively using formula (5) according to the angular frequencies corresponding to the two amplitude peaks.

Calculating the direction of the target:

the direction of the target can be represented by a connecting line between the target and a projection point of the millimeter wave radar on the horizontal plane and an included angle between the connecting line and the direction perpendicular to the extending direction of the train. The direction of the target may be a direction of a projected point of the target on a horizontal plane with respect to the millimeter wave radar. The method and the device adopt a CAPON beam forming algorithm to calculate the direction of the target. The basic idea of calculating the direction of the target by the CAPON beamforming algorithm is to determine an angle, so that the power of an echo signal received by the millimeter wave radar from the angle is the maximum, and the angle is an included angle between a connecting line between the target and a projection point of the millimeter wave radar on a horizontal plane and a direction perpendicular to the extending direction of the train.

The calculation device can calculate the power of the echo signal at each monitoring angle in the monitoring range of the millimeter wave radar, select the monitoring angle which enables the power of the echo signal to be maximum, and represent the direction of a target reflecting the echo signal relative to the projection point of the millimeter wave radar on the horizontal plane by using the monitoring angle.

The essence of the CAPON beamforming algorithm is to estimate the target spatial spectrum using a spatial filter. When the millimeter wave radar receives a plurality of echo signals, the output power of the millimeter wave radar may include the power of the echo signal reflected from the target and the power of the interference signal. The overall goal of the CAPON beamforming algorithm is to minimize the output power, and the gain constraint in the target direction is a fixed value, so that the power in the interference direction can be guaranteed to be minimal, thereby minimizing the influence of the interference signal on the estimated target spatial spectrum, and forming a beam in the desired direction.

In a possible implementation manner, the specific steps of the computing device using the CAPON beamforming algorithm to compute the direction of the target may be:

a. after performing the distance dimension FFT processing, the computing device may obtain echo signals of the target at different receiving antenna units:

X＝[x₁，x₂，x₃，…，x_M]^T (6)

where M represents the number of virtual receive antenna elements.

In a possible implementation manner, the virtual receiving antenna unit may be generated by performing oversampling processing on an output signal of the echo signal receiving end filter for the millimeter wave radar. The sampled signal can be regarded as a single signal source, and the dimension of the whole received echo signal can be increased. Thus, these separate signal sources may be considered as echo signals received by the virtual receive antenna. The millimeter wave radar can reduce the number of actual physical receiving antenna units by using the virtual receiving antenna units, thereby reducing the complexity of the millimeter wave radar.

b. Calculating a covariance matrix of echo signals received by the millimeter wave radar receiving antenna unit:

R＝XX^H (7)

wherein, X^HThe complex conjugate transposed vector of X may be represented.

c. Calculating a steering vector with an angle in the alpha direction:

a_r(α)＝[1，e^j2πdsin(α)，e^{j2πdsin(α)·2}，…，e^{j2πdsin(α)·(M-1)}]^T (8)

d. calculating the power of an echo signal with an angle in the alpha direction:

wherein R is^-1An inverse matrix of R may be represented.

In one possible implementation, the computing device is computing R^-1In the process, it is required to ensure that R is not a singular matrix, and a small value can be added to diagonal elements of the covariance matrix R. The specific numerical value of the above-mentioned small value is not limited in the embodiment of the present application.

e. The maximum value of the echo signal power P (α) is calculated. The angle α at which the value of P (α) is maximized is the angle between the target and the normal direction of the plane of the receiving antenna unit, so that the calculation device can obtain the direction of the target.

Constant False Alarm Rate (CFAR) detection:

the constant false alarm rate detection means that the computing device judges whether the echo signal received by the millimeter wave radar comes from the echo signal reflected by the passenger or not under the condition of keeping the false alarm probability constant. When the millimeter wave radar receives the echo signal, the echo signal also contains various interference signals such as noise and clutter. These interference signals may interfere with passenger counting by the computing device. In order to determine whether the echo signal received by the millimeter wave radar is from an echo signal reflected by a passenger, the computing device may set a signal threshold. When the power of the echo signal exceeds the signal threshold, the computing device may consider the echo signal as an echo signal reflected by the passenger. Therefore, the interference of interference signals can be reduced, and the accuracy of the passenger counting result is improved.

Since the power of the interference signal may change with time, place, etc., it is not suitable to set a fixed signal threshold when performing detection. For example, when the signals received by the millimeter wave radar are interference signals, and the computing device determines the interference signals as echo signals from passengers, a false alarm occurs. When the signals received by the millimeter wave radar are echo signals from passengers, and the computing device judges the echo signals as interference signals, the missing report occurs. In order to set an adaptive signal threshold to determine whether the signal received by the millimeter wave radar is from an echo signal reflected by a passenger, the computing device may perform constant false alarm rate detection. When the interference signal power is large, the computing device may raise the adaptive signal threshold. When the interference signal power is small, the computing device can lower the adaptive signal threshold to ensure that the false alarm probability is constant.

To determine whether a passenger is present in the area to be monitored, the computing device may divide the monitoring range into a plurality of sub-ranges when determining the size of the adaptive signal threshold. Wherein, the sub-range of the region to be monitored can be used as a detection unit. Several sub-ranges near the detection unit may serve as protection units. The remaining sub-ranges may be referred to as reference units. Based on the power of the signal received in the reference cell, the computing device may estimate the interference signal power level and thereby determine the magnitude of the adaptive signal threshold.

According to different methods for estimating the power level of the interference signal, CFAR detection can be divided into a cell averaging-constant false alarm rate (CA-CFAR), a maximum selection-constant false alarm rate (GO-CFAR), a minimum selection-constant false alarm rate (SO-CFAR), an ordered statistics-constant false alarm rate (OS-CFAR), and the like.

Referring to fig. 4, fig. 4 is a block diagram of a communication device for constant false alarm rate detection according to an embodiment of the present disclosure. As shown in fig. 4, the millimeter wave radar determines the magnitude of the adaptive signal threshold using CA-CFAR, i.e., the average of the power of the signal received in the reference cell as the estimate of the interfering signal power level. The CA-CFAR includes a detection unit 301, a protection unit 302, a reference unit 303, and a decision unit 304.

When an estimate Z of the interference signal power level is obtained, the calculation means may multiply said estimate Z by a threshold factor T, i.e. may determine an adaptive signal threshold S for determining whether a passenger is present in the detection unit. The threshold factor T may be calculated according to a constant false alarm probability, and a specific calculation method may refer to a method for calculating a threshold factor by using a CA-CFAR in the prior art, which is not limited in the embodiment of the present application.

The determiner 304 may be configured to determine whether a passenger is present in the detection unit, i.e., whether the echo signal received by the millimeter wave radar in the detection unit is from an echo signal reflected by the passenger. Specifically, when the power of the signal received in the detection unit is greater than the adaptive signal threshold S, the output result of the decision device 304 is H₁The computing device may consider that a passenger is present in the detection unit. When the power of the signal received in the detection unit is smaller than the adaptive signal threshold S, the output result of the decision device 304 is H₀The computing device may consider that no passenger is present in the detection unit.

Referring to fig. 5, fig. 5 is a block diagram of another communication device for constant false alarm rate detection according to an embodiment of the present disclosure. As shown in fig. 5, the computing device determines the magnitude of the adaptive signal threshold using OS-CFAR, i.e. the power of the signal received in each reference cell is sorted according to the magnitude of the values, and the computing device may rank the kth minimum detection cell x therein_(k)As an estimate of the interference signal power level. The above k is an integer of 1 or more and n or less. n is the number of reference cells. The detection unit, the protection unit, the reference unit, and the decision device may refer to the description in fig. 4, and are not described herein again.

Target clustering and centroid extraction:

the calculation means may establish a two-dimensional rectangular coordinate system based on the distance of the target and the direction of the target, and calculate position coordinate data of each target in the rectangular coordinate system. Since the millimeter wave radar has a high resolution, one passenger may contain a plurality of targets, and the computing device may perform target clustering using a density-based clustering method (DBSCAN) with noise. With the object clustering process, the computing device can cluster objects from the same passenger into one class to achieve passenger counting.

DBSCAN is an algorithm based on density clustering. The principle of DBSCAN is to divide all objects into core points, boundary points and noise points according to the density of objects around the object. The core point and the boundary point thereof may be grouped into a category, and the computing device may consider that the category of the object formed by the core point and the boundary point thereof is from the same passenger.

Specifically, the method of determining whether the target is a core point, a boundary point, or a noise point includes: and setting the clustering radius and the clustering point number. The computing device may use the position of the target as the center of a circle, and the circular area with the clustering radius as the neighborhood of the target. If the number of targets included in the neighborhood of the target is greater than or equal to the above cluster point number, the computing device may mark the target as a core point. If the number of objects included in the neighborhood of the object is less than the number of the cluster points, and the object is in the neighborhood of the core point, the computing device may mark the object as a boundary point. If the number of objects included in the neighborhood of the object is less than the number of the cluster points, and the object is not in the neighborhood of any core point, the computing device may mark the object as a noise point.

The shape of the neighborhood is not limited in the embodiment of the present application, and may be a circle or other shapes such as a circular ring.

In one possible implementation manner, the step of the computing device performing target clustering by using DBSCAN may be:

a. and marking all the targets as core points, boundary points or noise points according to the position coordinate data of the targets in the rectangular coordinate system.

b. And grouping the core points and the objects contained in the neighborhood of the core points into one type.

c. If the neighborhood of the core point includes other core points, the target clustering in the step b is expanded, and the targets included in the core point and the neighborhood thereof are clustered with the targets included in the other core points and the neighborhood thereof. For example, if the neighborhood of core point a includes a plurality of boundary points and core point B, and the neighborhood of core point B includes a plurality of boundary points, the computing device may group the core point a and the object included in the neighborhood thereof into one type, and the core point B and the object included in the neighborhood thereof into one type. If the neighborhood of the core point B further includes the core point C, and the neighborhood of the core point C includes a plurality of boundary points, the computing device may group the core point a and the object included in the neighborhood thereof, the core point B and the object included in the neighborhood thereof, and the core point C and the object included in the neighborhood thereof into one type.

Referring to fig. 6, fig. 6 is a schematic diagram of a communication device performing object clustering according to an embodiment of the present application. As shown in fig. 6, the computing device may establish a two-dimensional rectangular coordinate system 108. The origin of the two-dimensional rectangular coordinate system 108 may be a projection point of the millimeter wave radar on a horizontal plane, and the direction of the y-axis may be a direction in which the carriage of the subway extends. The plane in which the two-dimensional rectangular coordinate system 108 is located is a horizontal plane.

When the cluster point number is 5, the neighborhood of the object a includes 9 objects, and the computing device may mark the object a as a core point and group the core point a and the objects in the neighborhood into one class. The neighborhood of the object B in the neighborhood of the core point a includes 8 objects, and the computing device may mark the object B as the core point and expand the clustering range of the core point a, that is, the core point a and the objects in the neighborhood thereof are clustered together with the object B and the objects in the neighborhood thereof. The neighborhood of the object C in the neighborhood of the core point B includes 7 objects, and the computing device may mark the object C as the core point, and expand the clustering range of the core point a and the core point B, that is, the core point a and the object included in the neighborhood thereof, the core point B and the object included in the neighborhood thereof, and the core point C and the object included in the neighborhood thereof are clustered into one class.

The embodiment of the present application does not limit the establishment manner of the two-dimensional rectangular coordinate system 108.

In the present embodiment, considering that the targets formed by the head, chest and back of one passenger are generally the most dense, the targets formed by the arms and legs are generally sparse. By adjusting the value of the clustering points, the computing device can cluster a passenger to the target formed by the head, the chest and the back. At least sparse targets formed by the arms of the passengers exist among dense targets formed by the head, chest and back of each passenger, so that the computing device can effectively utilize core points to realize target clustering, and the accuracy of a passenger counting result is improved.

It should be noted that whether the echo signal received by the millimeter wave radar is a millimeter wave radar signal reflected by the chest of the passenger or a millimeter wave radar signal reflected by the back of the passenger depends on the installation angle of the millimeter wave radar and the moving direction of the passenger.

In one possible implementation, the millimeter wave radar transmits millimeter wave radar signals to an outside area of a car of the train. When a passenger gets on the vehicle, the millimeter wave radar may receive a millimeter wave radar signal reflected by the chest of the passenger. When the passenger gets off the vehicle, the millimeter wave radar may receive the millimeter wave radar signal reflected by the back of the passenger.

After clustering of the objects, the computing device may perform an operation of extracting the centroid based on the objects clustered into one class.

In one possible implementation, the calculation means may calculate an average value of the position coordinate data of each of the objects grouped into one class, and the average value of the position coordinate data obtained by performing the averaging process is used as the centroid of the class of objects. The one centroid may represent a position of one passenger at a time. The centroid velocity may be the average of the velocities of the above objects grouped into a class, and may represent the velocity of a passenger at a certain time.

In another possible implementation, the computing device may select a position of one object as the centroid from the objects grouped into the same class. The velocity of the selected object is the centroid velocity.

Through the target clustering and the centroid extraction, the position of each passenger in the monitoring range at different moments can be obtained by the computing device. To achieve passenger counting, the computing device may associate the centroids corresponding to the same passenger at different times, and establish the movement trajectory of the passenger. Based on the number of movement trajectories, the computing device may determine a passenger count result.

Since the computing device needs to consider the influence of the passenger near the passenger on the movement track of the passenger when establishing the movement track of the passenger, and needs to predict the position of the passenger at the next moment, the above process involves the use of a neural network, and the related principle of the neural network is described first.

Neural Network (NN):

the neural network mainly comprises an input layer, a hidden layer and an output layer. Wherein the layers are input. Both the hidden layer and the output layer may be composed of a plurality of neurons. Each neuron in the input layer may represent a feature. For example, in the embodiment of the present application, in order to calculate the influence of other passengers on the movement trajectory of the first passenger, it is necessary to calculate the correlation between the positions of the other passengers and the position of the first passenger. The neural network input may be a difference between the position coordinate data of the other passengers and the position coordinate data of the first passenger, and the neurons in the input layer may represent relative position relationships of the other passengers and the first passenger.

The value of each neuron in the hidden layer and the output layer of the neural network can be obtained by the operation of weighted summation and nonlinear transformation of the neuron in the previous layer. The nonlinear transformation function may be activation functions (e.g., sigmoid, tanh, relu, etc.), and may be used to introduce nonlinear characteristics into the neural network to convert the input signal of the neuron into the output signal.

The neural network can calculate parameters in the neural network through forward propagation and backward propagation, and the output result is close to the expected result. The forward propagation is from the input layer to the output layer, and the activation value of each neuron of each layer is calculated. The backward propagation refers to calculating the gradient of neuron parameters of each layer according to the activation value calculated by the forward propagation, and updating the parameters from back to front. Therefore, in the process of training the neural network, the neural network can continuously adjust parameters in the neural network according to the difference between the output result and the expected result, and the accuracy of the output result is improved.

Long short-term memory neural network (LSTM):

LSTM is a special recurrent neural network. Recurrent neural networks introduce memory characteristics by sharing parameters in time so that previous information can be applied in the current task. LSTM can achieve long-term memory compared to a general recurrent neural network.

The LSTM also contains an input layer, a hidden layer and an output layer. Each neuron in the input layer, the hidden layer and the output layer can comprise an input gate, a forgetting gate and an output gate. The input gate may determine how much input data for the neuron is saved to the neuron state at the current time. The forgetting gate can determine how much the neuron state at the previous moment is reserved to the neuron state at the current moment. The output gate can control how many neuron states at the current moment need to be output to the current output value. To realize long-term memory, the LSTM needs to reasonably utilize storage resources, i.e., retain valuable information and discard worthless information. Through the input gate, the LSTM can determine the value of the information input into the neuron and determine the information that needs to be retained. With the forgotten gate, the LSTM can determine the information that needs to be discarded. The LSTM thus performs the function of long-term memory.

In the embodiment of the present application, in order to predict the position of the first passenger at the next time, the LSTM may be input as the position coordinate data of the first passenger at the current time, the speed at the current time, and the correlation between the positions of the other passengers and the position of the first passenger at the current time, and the neurons in the input layer may represent the current position of the first passenger and the relative position relationship between the current position of the first passenger and the other passengers.

By predicting the position of the first passenger at the next time, the calculation means can determine which measurement position is the position of the first passenger at the next time from the actual measurement positions at the next time. In this way, the position of the first passenger at the current time can be associated with the position of the next time, so as to establish the moving track of the first passenger.

When the number of passengers getting on and off the vehicle is calculated to count the passengers, the millimeter wave radar transmits millimeter wave radar signals at different moments because the passengers are in a moving state, and echo signals reflected by the same target at different positions can be received. The computing device may compute a plurality of centroids representing different positions of the same passenger. In addition, during the continuous monitoring by the millimeter wave radar, it may occur that a previously unmonitored passenger enters the monitoring range and a previously unmonitored passenger leaves the monitoring range. The position and number of the centroids calculated by the calculating device are constantly changing, and therefore it is not suitable to determine the passenger counting result according to the number of the centroids.

The method for tracking the centroid to form the track is adopted, the number of passengers in the compartment is counted through the track of the centroid, and the accuracy of the passenger counting result can be effectively improved.

The following describes a method for implementing passenger counting by the communication device. Referring to fig. 7, fig. 7 is a flowchart illustrating a method for counting passengers by a communication device according to an embodiment of the present application. As shown in fig. 7, the communication apparatus includes a millimeter wave radar and a calculation device. The passenger counting method may include steps S101 to S1010.

Wherein:

and S101, the millimeter wave radar transmits a millimeter wave radar signal.

The millimeter wave radar can perform linear frequency modulation on the transmitted millimeter wave radar signal and continuously transmit linear frequency modulation pulse obtained through linear frequency modulation.

In one possible implementation, the initial frequency of the chirp is 77GHz, the duration of the chirp is 40us, and the bandwidth is 4 GHz.

Note that the chirp transmitted by the millimeter wave radar is at an angle, for example, 25 ° or 30 ° with respect to the horizontal plane direction.

In a possible implementation, the millimeter wave radar may start to continuously transmit the millimeter wave radar signal when the door of the subway is opened, and stop transmitting the millimeter wave radar signal when the door of the subway is closed, since the number of passengers in the compartment may change only when the door of the subway is opened and closed. Thus, the communication device can realize passenger counting and save power consumption of the millimeter wave radar for transmitting the millimeter wave radar signal.

The parameter for the millimeter wave radar to perform linear frequency modulation on the transmitted millimeter wave radar signal also comprises a linear frequency modulation pulse repetition period. In one possible implementation, the chirp repetition period may be determined by a maximum monitoring distance of the millimeter wave radar. The chirp repetition period may be the time required for the millimeter wave radar to transmit a chirp to receive an echo signal from the maximum monitored distance. In this way, the millimeter wave radar can receive echo signals of the millimeter wave radar signals transmitted for the first time reflected by all the targets in the monitoring range within the time interval from the first time of transmission of the millimeter wave radar signals to the second time of transmission of the millimeter wave radar signals.

The embodiment of the application does not limit the parameters for performing linear frequency modulation on the millimeter wave radar. The parameters of the chirp include the initial frequency of the chirp, the duration bandwidth chirp repetition period, and the like.

And S102, receiving the echo signal by the millimeter wave radar.

The millimeter wave radar may receive an echo signal reflected by the target. The echo signal may also be a chirp.

And S103, sending the monitoring data to the computing device by the millimeter wave radar.

The monitoring data may include a transmission time and a signal waveform of a millimeter wave radar signal transmitted by the millimeter wave radar, and a reception time and a signal waveform of a received echo signal.

The embodiment of the application does not limit the data content contained in the monitoring data, and can also contain more data content.

It should be noted that the millimeter wave radar may transmit the monitoring data to the computing device once every predetermined time interval, for example, 1 millisecond, 2 milliseconds, or the like. The monitoring data may include time and signal waveform of a millimeter wave radar signal transmitted by the millimeter wave radar multiple times, and time and signal waveform of an echo signal received multiple times.

In one possible implementation, the millimeter wave radar may send the monitoring data to the computing device together over a period of time during which the door is opened once. The computing device may count the number of passengers getting on and off the vehicle within a time period in which the door is opened once.

The embodiment of the application does not limit the preset time interval for the millimeter wave radar to send the monitoring data to the computing device.

And S104, calculating the distance of the target by the calculating device.

When receiving the monitoring data transmitted by the millimeter wave radar, the computing device can perform difference frequency processing on all echo signals received by the millimeter wave radar between the millimeter wave radar signals transmitted twice and the millimeter wave radar signals transmitted last time respectively according to the time of the transmitted millimeter wave radar signals and the time of the received echo signals in the monitoring data, and obtain intermediate frequency signals. For example, millimeter wave radar receives echo signals reflected by a plurality of targets between the first transmission of a millimeter wave radar signal and the second transmission of a millimeter wave radar signal. The echo signals reflected by the targets can be echo signals reflecting millimeter wave radar signals transmitted for the first time. The computing device may perform difference frequency processing on the echo signals reflected by the plurality of targets and the millimeter wave radar signal transmitted for the first time, respectively.

By performing distance dimension FFT on the intermediate frequency signal, the computing device may obtain the intermediate frequency, thereby calculating the distance between the target and the millimeter wave radar.

The specific method for calculating the distance of the target by the calculating device can refer to the description of calculating the distance of the target in the above principle description, and is not described herein again.

It should be noted that the range resolution of the millimeter-wave radar is related to the bandwidth of the chirp. The above distance resolution may represent a minimum distance at which the millimeter wave radar can distinguish two targets when the two targets are located in the same direction of the millimeter wave radar but at different distances from the millimeter wave radar. The above calculation formula of the distance resolution may be represented by the following formula (10):

where c is the electromagnetic wave propagation velocity. B is the bandwidth of the chirp.

According to the formula (10), the larger the bandwidth of the chirp transmitted by the millimeter wave radar, the higher the range resolution. For example, when the bandwidth of the chirp is 4GHz, the range resolution of the millimeter wave radar is 3.7 cm. That is, when the distance between two targets located in the same direction of the millimeter wave radar is greater than 3.7 cm, the millimeter wave radar can distinguish the two targets.

The bandwidth of the chirp is not limited in the embodiments of the present application.

The maximum monitoring distance of the millimeter wave radar is related to the maximum intermediate frequency bandwidth and is limited by the sampling frequency during the linear frequency modulation. The relationship between the maximum monitoring distance and the maximum intermediate frequency bandwidth may be represented by the following equation (11):

wherein S is_{τ_max}Can represent the maximum intermediate frequency bandwidth, mu can represent the chirp rate, R_maxMay represent the maximum monitoring distance of the millimeter wave radar,

the limitation of the sampling frequency to the maximum monitoring distance can be shown as the following equation (12):

in a possible implementation manner, the maximum intermediate frequency bandwidth of the millimeter wave radar is 10MHz, the maximum sampling frequency is 20MHz, and the chirp rate is 100MHz/us, so that the theoretical maximum monitoring distance of the millimeter wave radar is 15 meters. In conjunction with the monitoring angle θ in fig. 1, the millimeter wave radar can determine the maximum monitoring range.

The embodiment of the application does not limit the maximum intermediate frequency bandwidth, the maximum sampling frequency and the specific numerical value of the frequency modulation slope of the millimeter wave radar.

S105, the calculating device calculates the speed of the target.

Because the target is moving relative to the millimeter wave radar, there is a doppler effect, and there is a frequency difference between the millimeter wave radar signal transmitted by the millimeter wave radar and the received echo signal. The computing device can perform difference frequency processing on a millimeter wave radar signal transmitted by the millimeter wave radar and a received echo signal in the monitoring data, and obtain an intermediate frequency signal. The computing device may then perform two-dimensional FFT on the intermediate frequency signal and compute the doppler frequency of the target. From the doppler frequency of the target, the computing means can determine the target velocity using equation (5). The specific process of calculating the speed of the target by the calculating device can refer to the description of calculating the speed of the target in the above principle description, and is not described herein again.

It should be noted that the speed resolution of the millimeter wave radar is related to the time for transmitting one frame of chirp. The velocity resolution may represent a minimum velocity to distinguish between two objects. The above calculation formula of the velocity resolution can be expressed as the following equation (13):

wherein λ is the wavelength of the millimeter wave radar signal, T_cIs the repetition period of the chirp, N being the chirp in a frame of chirpNumber of frequency pulses, T_fIs the time at which a frame of chirp is transmitted. As can be seen from equation (13), increasing the time to transmit a frame of chirp increases the speed resolution.

S106, the calculating device calculates the direction of the target.

In one possible implementation, the computing device may employ a CAPON beamforming algorithm to calculate the direction of the target. The calculation means may determine an angle at which the received echo signal power is at a maximum, the angle being the angle between the target and the normal direction of the plane of the receiving antenna element. In this way, the computing device can calculate the direction of the target.

In one possible implementation, the computing device may establish a two-dimensional rectangular coordinate system as shown in FIG. 6. Because the monitoring angle theta of the millimeter wave radar can be 120 degrees, the target can be positioned in the area which forms an included angle of 60 degrees with the positive direction of the x axis in the two-dimensional rectangular coordinate system. When the angle that maximizes the received echo signal power is determined using equation (9), the calculation means may take the value of the angle α in equation (9) to range from minus 60 ° to plus 60 °. The calculation means may select an angle in the range of minus 60 ° to plus 60 ° that maximizes the received echo signal power, and take the angle as the direction of the projected point of the target on the horizontal plane with respect to the millimeter wave radar.

For a specific implementation process of calculating the direction of the target, reference may be made to the description of the direction of the target in the above description, and details are not repeated here.

The method and the device for calculating the direction of the target do not limit the algorithm used by the calculating device for calculating the direction of the target, except that the direction of the target can be calculated by adopting a CAPON beam forming algorithm, and the direction of the target can also be calculated by calculating the wave path difference between echo signals received by different receiving antenna units of the millimeter wave radar.

It should be noted that the angular resolution of the millimeter-wave radar may be determined by the number of antenna elements. By a Multiple Input Multiple Output (MIMO) technology, that is, by providing a plurality of transmitting antenna units and a plurality of receiving antenna units, the millimeter wave radar can improve the angular resolution. The plurality of receiving antenna units may include a virtual antenna unit. The number of the transmitting antenna units and the number of the receiving antenna units of the millimeter wave radar are not limited in the embodiment of the application.

Depending on the distance and direction of each target, the computing device may form a cloud of points 107 as shown in FIG. 3. Each point in the point cloud 107 may represent a target that reflects an echo signal. The computing device may establish a two-dimensional rectangular coordinate system as shown in fig. 6. The calculation means may determine position coordinate data of each object in the two-dimensional rectangular coordinate system based on the distance and direction of each object.

For example, the distance from the target to the millimeter wave radar is d, the direction of the target relative to the millimeter wave radar is α, and the height of the millimeter wave radar is h, that is, the distance from the millimeter wave radar to the origin of the two-dimensional rectangular coordinate system is h. The distance from the target to the origin of the two-dimensional rectangular coordinate system is l. Wherein the content of the first and second substances,

the calculation means may determine position coordinate data (x, y) of the target in the two-dimensional rectangular coordinate system, based on the direction α of the target with respect to the millimeter wave radar and the distance l of the target from the origin of the two-dimensional rectangular coordinate system. Where x is l × cos α and y is l × sin α.

And S107, the computing device detects the constant false alarm rate of the echo signals in the monitoring data.

When the millimeter wave radar receives the echo signal, the echo signal also contains various interference signals such as noise, clutter and interference. These interfering signals may cause interference to the millimeter wave radar to correctly determine whether the passenger is present. Through constant false alarm rate detection, the target formed by the echo signal that the passenger reflected can be screened out to computing device to reduce interference of interfering signal, improve the rate of accuracy of passenger counting result.

In one possible implementation, the computing means processes the FFT-ed signal through a detector, such as a square-rate envelope detector, a synchronous detector, or the like. The computing means may derive the power levels of the signals received in the detection unit, the protection unit and the reference unit. The embodiment of the present application does not limit the types of detectors.

In the embodiment of the application, the computing device can perform multi-dimensional constant false alarm rate detection from the target distance, the target speed and the target direction. The computing device detects the distance dimension constant false alarm rate, and can judge whether the echo signals received in the monitoring ranges in the same direction and different distances come from passengers. The computing device is used for detecting the speed dimension constant false alarm rate, and whether the multi-pulse echo signals come from passengers can be judged according to the multi-pulse echo signals received by the millimeter wave radar from the monitoring range of the same distance. The multi-pulse echo signal may be a signal that the millimeter wave radar transmits a chirp multiple times and reflects the multiple transmitted chirp received from within a monitoring range of the same distance. The computing device detects the constant false alarm rate of the direction dimension, and can judge whether the echo signals received in the monitoring ranges in the same distance and different directions come from passengers.

In one possible implementation, the computing device may use the OS-CFAR for detection when performing distance dimension constant false alarm rate detection. Specifically, the computing device may process the signals subjected to the distance dimension FFT by the detector, sort the power levels of the obtained signals in the reference unit, and select the kth smallest power level as the estimated value of the power level of the interference signal. The computing device may obtain the adaptive signal threshold based on the threshold factor and the estimate of the interfering signal power level. The power level of the signal within the detection cell is compared to an adaptive signal threshold. If the power level of the signal in the detection cell is greater than the adaptive signal threshold, the computing device may consider that a passenger is present in the detection cell. If the power level of the signal in the detection cell is less than the adaptive signal threshold, the computing device may assume that no passenger is present in the detection cell.

Through the distance dimension constant false alarm rate detection, the position of a passenger in the monitoring range of the millimeter wave radar can be preliminarily screened out by the computing device. Further, the computing device may use CA-CFAR for detection when performing velocity dimension constant false alarm rate detection. Specifically, the calculation means may process the two-dimensional FFT-processed signal by a detector, and calculate a mean value of the signal power levels in the reference unit, and use the mean value as an estimated value of the interference signal power level. Based on the estimate of the interference signal power level and the threshold factor, the computing device may derive an adaptive signal threshold and determine whether a passenger is present in the detection cell. Thus, the computing device can further screen out the positions of passengers in the monitoring range of the millimeter wave radar.

After the distance dimension constant false alarm rate detection and the speed dimension constant false alarm rate detection, the calculation device can further perform direction dimension constant false alarm rate detection. The computing device can use CA-CFAR to detect when detecting the direction dimension constant false alarm rate. Specifically, the computing device may perform three-dimensional FFT on the echo signal received by the millimeter wave radar, that is, perform FFT on the signal subjected to two-dimensional FFT again in the antenna dimension according to different receiving antenna units. The calculation means may process the three-dimensional FFT-processed signal by a detector, and calculate a mean value of signal power levels in the reference unit according to the processing result, and use the mean value as an estimated value of the power level of the interference signal. Based on the estimate of the interference signal power level and the threshold factor, the computing device may derive an adaptive signal threshold and determine whether a passenger is present in the detection cell. Thus, the computing device can achieve direction dimension constant false alarm rate detection.

Through the multi-dimensional constant false alarm rate detection, the computing device can screen out the target formed by the echo signal reflected by the passenger, so that the detection accuracy is improved, and the interference of interference signals is reduced. Therefore, the accuracy of the centroid position obtained during target clustering and centroid extraction processing is improved, and the accuracy of the passenger counting result is improved.

And S108, the computing device carries out target clustering and mass center extraction.

Since the millimeter wave radar resolution is high, one passenger can form a plurality of targets. The calculation device may cluster the objects formed according to the echo signals reflected from different body parts of the same passenger into one class and extract the centroid of the clustered objects to realize passenger counting.

The computing device may utilize DBSCAN for object clustering. Wherein the computing device needs to set the cluster radius and the cluster number to distinguish whether the object is a core point, a boundary point, or a noise point. The above-mentioned clustering radius and the above-mentioned clustering point number can be set up according to the width of the person and the range resolution of millimeter wave radar.

In one possible implementation manner, the computing device may set the above-mentioned cluster radius and cluster point number in segments according to the distance between the target and the millimeter wave radar. Specifically, when the target distance is less than 0.5 m, the calculation device may set the clustering radius to 0.2 m and the number of clustering points to 5. When the target distance is greater than or equal to 0.5 m and less than 0.8 m, the calculation means may set the clustering radius to 0.3 m and the number of clustering points to 8. When the target distance is greater than or equal to 0.8 m, the calculation means may set the above-mentioned clustering radius to 0.4 m and the above-mentioned clustering point number to 12.

The target distance for segmentation, the clustering radius and the clustering point number in each segment are not limited in the embodiment of the present application, and may be other values besides the specific values in the above examples.

When the cluster radius and the cluster point number are confirmed, the computing device may mark the object as one of a core point, a boundary point, or a noise point. The process of the computing device using the DBSCAN algorithm to perform object clustering may refer to the description of object clustering and centroid extraction in the above description of the principles, and will not be described herein again.

The computing device may extract a centroid from the results of the target clustering.

In one possible implementation, the calculation means may calculate an average value of the position coordinate data of the objects grouped into a class, and the average value of the position coordinate data obtained by performing the above-described averaging process is taken as the centroid of the class of objects. Wherein the centroid velocity may be the average of the velocities of the above objects grouped into a class.

The method for extracting the centroid is not limited in the embodiment of the application, and the position and the speed of the centroid can be obtained by other methods besides the above method for obtaining the average value of the position coordinate data of the objects gathered into one type. For example, the computing device may select the position of one object as the centroid from the objects grouped into a class, and the velocity of the object is the centroid velocity.

And S109, the computing device tracks the center of mass to establish a moving track.

The computing device tracks the mass centers to establish the moving track, the track start needs to be confirmed, the mass centers of the same passenger at different moments are sequentially connected according to the time sequence, and finally the track stop is confirmed, namely whether the same passenger stops moving or not is confirmed. In this way, the computing device can establish the movement trajectory of the same passenger. The following describes the track start, track formation and track termination in detail.

(1) Track initiation

Trajectory initiation is the first step in establishing a passenger's movement trajectory. In confirming the start of the trajectory, the computing device may determine a location where the passenger began moving.

In one possible implementation, the computing device may use a logic method to confirm the track start. The logic method uses multiple assumptions to identify potential trajectories from which a complete trajectory of movement of the passenger is likely to be formed by predicting and setting the relevant gates.

In particular, for two centroids at the current time and the next time, the computing means may compute the square of the normalized distance between the two centroids. If the two centroids are the positions of the same passenger at the current time and the next time respectively, and the monitoring errors of the millimeter wave radar are independent, zero mean value and gaussian distribution, the square of the normalized distance obeys the chi-square (χ) with the degree of freedom p²) And (4) distribution. The above-mentioned degree of freedom p may represent the dimension of the position coordinate data of the centroid. For example, representing the centroid in a two-dimensional rectangular coordinate system, the degree of freedom p may be 2. The size of the dimension of the position coordinate data representing the centroid is not limited in the embodiment of the application, and the dimension may be two-dimensional or three-dimensional. According to givenChi with p degree of freedom for threshold probability search²The radius gamma of the relevant wave gate can be obtained by the computing device through the distribution table. If the square of the normalized distance of two centroids at the current time and the next time is less than or equal to the radius γ of the associated gate, the probability that the two centroids are from the same passenger can be considered as the threshold probability. For example, when the square of the normalized distance described above is subject to χ with degree of freedom of 2²Distribution, and when the threshold probability is 90%, according to x²The distribution table may result in a correlation gate radius γ of 0.21. If the square of the normalized distance of two centroids at the current time and the next time is less than or equal to 0.21, then the two centroids may be considered to be 90% likely from the same passenger.

The threshold probability is not particularly limited in the embodiment of the present application, and may be other values greater than 0 and less than 100% in addition to 90%.

The following describes the process of the computing device using the logic method to confirm the start of the trace.

a. The computing device may use the centroid obtained from the first monitoring by the millimeter wave radar as the trajectory header and determine the radius of the initial correlation gate using a velocity method. The centroid obtained by the first monitoring can represent the centroid obtained by the calculation device according to the echo signal received by the millimeter wave radar signal transmitted by the millimeter wave radar for the first time.

In a possible implementation manner, the radius of the initial correlation gate determined by the speed method may be set to be the maximum distance which can be reached by a passenger between the first monitoring and the second monitoring of the millimeter wave radar. Wherein the maximum distance is obtained by the calculation means on the basis of the time interval between two detections by the millimeter wave radar of a passenger and the maximum speed of movement of a passenger. A typical value for the maximum speed of movement of the one passenger is 3 meters per second.

The computing device can establish a circular correlation wave gate by taking the track head as a circle center and taking the maximum distance as the radius of the initial correlation wave gate. For centroids falling into the initial correlation gates and obtained by secondary monitoring according to the millimeter wave radar, the computing device can establish potential trajectories for the centroids and the trajectory head. The potential track contains a centroid obtained by twice monitoring according to the millimeter wave radar.

The shape of the initial correlation gate is not limited in the embodiments of the present application, and may be a correlation gate having other shapes such as an elliptical correlation gate and a rectangular correlation gate, in addition to a circular correlation gate.

b. Extrapolating all the potential tracks, taking the extrapolation point as the center of a circle, and searching the χ with the degree of freedom p according to the threshold probability²A distribution table, which identifies the radii of subsequent correlation gates, the computing device can establish the subsequent correlation gates. The extrapolated point can be a predicted position of the centroid of the millimeter wave radar during third monitoring according to each potential track.

If one of the centroids obtained by the third monitoring of the millimeter wave radar falls on a subsequent correlation gate established by taking the extrapolated point as the center of the circle, the computing device may interconnect the one centroid and a potential trajectory corresponding to the extrapolated point to complete the trajectory initiation.

If a plurality of centroids fall in the subsequent correlation gates established by taking the extrapolation point as the center of a circle in the centroids obtained by the third monitoring according to the millimeter wave radar, the computing device may interconnect the centroid closest to the extrapolation point with the potential trajectory corresponding to the extrapolation point to complete the trajectory initiation.

In one possible implementation, the calculation means may determine the centroid closest to the extrapolated point by calculating a square of a normalized distance between the extrapolated point and the centroid, which is obtained from the third monitoring by the millimeter wave radar and falls within the subsequent correlation gate.

If no centroid falls on a subsequent correlation gate established by taking the extrapolation point as a circle center in the centroids obtained by the third monitoring of the millimeter wave radar, the computing device may interconnect the extrapolation point and a potential track corresponding to the extrapolation point to complete track initiation.

The track of the completed track is the existing track, and the existing track may include at least three centroids. The three centroids are centroids obtained according to three times of monitoring of the millimeter wave radar.

In one possible implementation, the computing device may use the LSTM to make a location prediction when predicting the location of a passenger at the next time. Specifically, the computing device may first establish and train a neural network to calculate correlations between the location of one passenger and the locations of other passengers. For example, in N centroids monitored according to the millimeter wave radar at time t, the calculation means may calculate the correlation vector of the other centroids with the first centroid from the position coordinate data of the first centroid and the position coordinate data of the other centroids. The calculation formula may be represented by the following formula (14):

wherein the content of the first and second substances,

position coordinate data of the ith centroid at time t can be represented,

the correlation vectors of the other centroids to the first centroid at time t can be represented. The calculated function f may represent a neural network. The neural network may be a convolutional neural network, or may be another type of neural network, and the type of the neural network is not limited in the embodiment of the present application.

In one possible implementation, the training set for training the neural network f may be obtained through simulation. Namely, according to the position coordinate data of different centroids, the correlation between the positions of different centroids is simulated. According to the training set, the calculating device can train the neural network f to adjust parameters in the network, so that when the position coordinate data of each centroid obtained by monitoring once is input to the neural network f, the calculating device has higher accuracy in obtaining the correlation vectors of different centroids.

According to the position coordinates of a mass center at the current momentFrom the centroid velocity and the correlation vectors of the one centroid with the other centroids at the current time, the computing device can use the LSTM to predict the location of the centroid at the next time. For example, when obtaining the correlation vector of the first centroid and other centroids at the time t

The computing device may predict the location of the first centroid at time t +1 using equation (15):

wherein the content of the first and second substances,

the velocity of the first centroid at time t can be represented. The calculated function g may represent the long-short term memory neural network LSTM.

It can be understood that when the position of one passenger at the current time, the speed of the one passenger at the current time, and the relative position relationship between the one passenger and other passengers are known, the moving direction and the moving distance of the one passenger can be predicted, that is, the position of the one passenger at the next time can be predicted. For example, knowing the position of one passenger at the present time and the positions of the left side, right side, and rear of the one passenger, there is a high probability that the position of the one passenger at the next time is in front of the position at the present time. And, the calculation means may calculate the moving distance of the one passenger from the present time to the next time, based on the speed of the one passenger at the present time. In this way, the computing device can predict where the passenger will be at the next time.

c. For all centroids obtained by each monitoring of the millimeter wave radar, if the centroids do not fall into the relevant gates of the existing track, the computing device can judge whether the centroids fall into the relevant gates of the potential track. If there is a centroid that falls within the relevant gates of the potential trajectory, the computing device may interconnect the centroid with the potential trajectory according to step b above to complete the trajectory initiation. If there is a correlation gate whose centroid does not fall within the potential trajectory, the computing device may take the centroid as a new trajectory header and repeat steps a and b above to complete the trajectory initiation.

The method for judging whether the centroid falls into the correlation gate of the existing track or the potential track may be: the position of the newly determined centroid in the existing track or the potential track is taken as the position of the centroid at the current moment, the computing device can predict the position of the centroid at the next moment by using the neural network, and the predicted position of the centroid at the next moment is taken as an extrapolation point to establish the correlation wave gate. In this way, the computing device can determine whether the centroid falls within the associated gates of the existing or potential trajectories.

The method for determining the track initiation is not limited in the embodiment of the application, and may be other track initiation algorithms such as an intuitive method, besides the above logic method.

(2) Track formation

For an existing trajectory, the computing device may determine a centroid that may be interconnected with the existing trajectory based on the centroids from subsequent measurements to form a complete trajectory.

In one possible implementation, the computing device may determine a centroid that may be interconnected with the existing trajectory using a probabilistic nearest neighbor approach. The probability nearest neighbor method is to primarily screen the centroids according to the correlation gates so as to limit the number of the centroids participating in the correlation judgment. The correlation gate may be a sub-range of the millimeter wave radar monitoring range, and the center of the sub-range may be a predicted position of the centroid at the next time. The correlation gates may ensure that the centroid falling within the correlation gate has a certain probability of including the actual monitored position of the one centroid at the next moment. When the centroids falling within the correlation gates are obtained, the computing device may interconnect the centroids closest to the predicted location with the existing trajectories to form the trajectories.

It should be noted that the probability nearest neighbor method considers the situation that no centroid exists in the relevant wave gate when confirming the centroid interconnected with the trajectory, so that the accuracy of trajectory formation can be improved, and the situation of tracking loss can be reduced.

The following describes a process of trajectory formation by a computing device using a probability nearest neighbor method.

a. A correlation gate is determined.

Determining the correlation gate includes determining a shape and a size of the gate.

In one possible implementation, the computing device may establish a circular correlation gate based on the centroid predicted using the neural network. Because when the centers of mass obtained by the calculation device through two continuous detections according to the millimeter wave radar come from the same passenger, the square of the normalized distance of the two centers of mass obeys χ with degree of freedom p²And (4) distribution. The radius of the circular correlation wave gate can be used for inquiring chi with the degree of freedom p²And obtaining a distribution table. In this way, the computing device can determine the correlation gates. The above-mentioned degree of freedom p is the dimension of the centroid position coordinates.

The shape and size of the above-mentioned related wave gate are not limited in the embodiments of the present application.

b. If one of the centroids obtained by monitoring according to the millimeter wave radar has a centroid falling into the relevant gate, the computing device may interconnect the centroid falling into the relevant gate with the existing trajectory.

If a plurality of centroids falling into the relevant wave gates exist in the centroids obtained by monitoring according to the millimeter wave radar, the calculating device can calculate the statistical distances between the centroids falling into the relevant wave gates and the predicted positions, and interconnects the centroid with the minimum statistical distance with the existing track. The statistical distance is the square of the normalized distance, and a specific calculation formula can be shown as the following formula (16):

wherein z (t +1) may represent position coordinate data that is monitored at time t +1 according to the millimeter wave radar and falls within any centroid of the associated wave gate.

It may represent the predicted position coordinate data of the centroid at time t +1 from the position of the centroid at time t in the existing trajectory. S (k +1) may represent a covariance matrix of position coordinate data of the centroid monitored at time t +1 according to the millimeter wave radar, S^-1(k +1) may represent the inverse of the covariance matrix described above.

If there is no centroid falling into the relevant gate in the centroids obtained by monitoring according to the millimeter wave radar, the computing device may interconnect the centroid obtained by using the neural network prediction with the existing trajectory.

(3) Track termination

The calculating means may repeat step b of the above-described trajectory formation according to the centroid obtained by the millimeter wave radar through multiple monitoring. When the centroids interconnected with the existing track are centroids obtained by utilizing neural network prediction in the centroids obtained by three times of continuous monitoring according to the millimeter wave radar, the computing device stops tracking the centroids of the existing track, and the track is terminated.

Referring to fig. 8, fig. 8 is a schematic diagram illustrating a communication device establishing a movement track of a passenger according to an embodiment of the present application. As shown in fig. 8, the communication device establishes the movement track of the passenger, including three parts of track start, track formation and track end confirmation.

The millimeter wave radar transmits a millimeter wave radar signal at a first moment and receives a plurality of echo signals of the millimeter wave radar signal reflected by a plurality of body parts of a passenger. A. the₁The calculated centroid may be calculated for the computing device based on the plurality of echo signals of the one passenger at the first time. The computing device may have a centroid of A₁Is a track head. The calculating device can calculate the radius of the initial correlation gate by using a speed method and uses the centroid A₁An initial correlation gate 401 is established for the center of the circle.

The millimeter wave radar transmits a millimeter wave radar signal at a second time and receives a plurality of echo signals reflecting the millimeter wave radar signal. The calculation device may calculate from the plurality of echo signals at the second timeCenter of mass A₂、B₂、C₂、D₂、E₂And F₂And the like. Wherein the center of mass A₂、B₂、C₂、D₂、E₂And F₂All fall into the center of mass A₁In the initial correlation gate of (a). The computing device may compare A₁Respectively with the centroid A₂、B₂、C₂、D₂、E₂And F₂And interconnecting to establish potential tracks.

The computing device may pair centroid A based on the potential trajectory₁The indicated position of the passenger at the third time is predicted. The computing devices may each have a centroid A₂、B₂、C₂、D₂、E₂And F₂Is the center of mass A₁The position of the passenger at the second moment in time is shown, in combination with the center of mass A₂、B₂、C₂、D₂、E₂And F₂And its correlation vector with the centroids of the surrounding objects at the same time, using LSTM to predict the location of the centroid of each potential trajectory at the third time. For example, the computing device is based on centroid A₂Predicting the position coordinate data, the speed and the related vector of the center of mass at the second moment to obtain the center of mass at the third moment

The computing device can look up x²The distribution table obtains the radius of the subsequent correlation gate 402. For example, the computing device may be configured to determine χ²The value corresponding to the degree of freedom of 2 and the quantile of 0.9 in the distribution table is taken as the relevant gate radius. The magnitude of the above degrees of freedom may represent the dimensionality of the position coordinate data of the centroid, and the quantile may represent the probability that the centroid falling into the associated gate is the centroid of the potential trajectory at the next time. The computing device may establish a subsequent correlation gate 402. Wherein the center of the subsequent correlation gate 402 may be the predicted centroid, e.g.

And the like.

The millimeter wave radar transmits a millimeter wave radar signal at a third moment and receives a plurality of echo signals reflecting the millimeter wave radar. The calculating device can calculate the centroid A according to the echo signals at the third moment₃、B₃、C₃、D₃And E₃And the like. Wherein the center of mass A₃、B₃、C₃、D₃And E₃All fall into the mass center

In the subsequent correlation gate 402, which is the center of the circle. The computing means may calculate the centroids A separately₃、B₃、C₃、D₃And E₃And the center of mass

And selecting the distance to the centroid

The centroid with the smallest square of the normalized distance is compared to the potential trajectory A₁A₂And (4) interconnection. The computing means thus complete the start of the trajectory and form an existing trajectory A₁A₂A₃. Wherein the center of mass A₂And A₃The positions can respectively represent the centroid A₁The position of the passenger at the second time and the third time is indicated.

The computing means may calculate the centroids from the echo signals after the third time instant and determine whether these centroids can be compared with the existing trajectory a₁A₂A₃Interconnect to connect the existing track A₁A₂A₃And performing extrapolation.

For the existing track A₁A₂......A_NWhen the computing means are extrapolating the existing trajectory A₁A₂......A_NIf the current track and the existing track are mutually matched at the N +1 th time, the N +2 th time and the N +3 th timeAnd if the centroids of the contacts are the centroids predicted by the calculation device, the calculation device does not extrapolate the track. Existing track A₁A₂……A_NAnd (6) terminating.

When the calculated centroid at a certain moment does not exist in the wave gate established by the calculating device by taking the predicted centroid at the certain moment as the center of the circle, the calculating device can interconnect the predicted centroid at the moment and the existing track. The above N is an integer of more than 3.

Referring to fig. 9, fig. 9 is a schematic diagram of a communication device for establishing a movement track of a passenger according to an embodiment of the present application. The computing device may establish the movement locus of the passenger according to the calculated centroid and the centroid predicted by using the neural network, and as shown in fig. 9, the computing device may establish the

movement loci

211, 212, 213, and 214 in conjunction with a plurality of centroids 210 obtained by multiple monitoring by the millimeter wave radar. The 4 movement tracks can be established by the computing device according to the processing procedures of track starting, track forming and track ending.

And S1010, evaluating the moving track by the computing device to determine the number of passengers.

The computing means may evaluate the direction of the movement trajectory based on the positions of the start and end of the trajectory and the corresponding time sequence to determine the number of passengers.

In one possible implementation, the computing device may determine the moving direction of the centroid according to the positions of the start and end of the trajectory and the corresponding time sequence. When the moving direction is judged to point to the outside direction of the carriage, the calculating device can subtract the track number of the moving direction pointing to the outside direction of the carriage on the basis of the number of people in the carriage. When the moving direction is judged to point to the direction inside the carriage, the calculating device can add the track number of the moving direction pointing to the direction inside the carriage on the basis of the number of people in the carriage. The above-mentioned moving direction pointing in the outside direction of the vehicle compartment may mean that the moving locus extends outward of the vehicle compartment. The direction of the movement toward the inside of the vehicle compartment may indicate that the movement locus extends inward of the vehicle compartment.

Referring to fig. 10, fig. 10 is a schematic diagram illustrating a communication device for estimating a moving track of a passenger according to an embodiment of the present application. As shown in fig. 10, the trajectory 213 includes centroids detected by a plurality of computing devices at different times according to the millimeter-wave radar. The computing device monitors the millimeter wave radar at the time t to obtain the centroid 2131, and monitors the millimeter wave radar at the time t + q to obtain the centroid 2132. T and q are positive numbers. Centroid 2131 is the head of the trace and centroid 2132 is the location where the trace terminates. From the positions of the

centroids

2131 and 2132 and the time sequence when monitored, the computing device can determine that the moving direction of the trajectory 213 points in the direction outside the vehicle compartment. When the direction of travel of the trajectory 213 is determined, the computing device may decrement by one based on the number of people in the cabin.

Referring to fig. 11, fig. 11 is a schematic diagram of another communication device for estimating a movement track of a passenger according to an embodiment of the present application. As shown in fig. 11, the trajectory 211 includes centroids obtained by monitoring by a plurality of computing devices at different times according to the millimeter wave radar. The computing device monitors the millimeter-wave radar to obtain a centroid 2111 at the time t, and monitors the millimeter-wave radar to obtain a centroid 2112 at the time t + p. T and p are positive numbers. Then centroid 2111 is the head of the trajectory and centroid 2112 is the location where the trajectory terminates. From the positions of the centroid 2111 and the centroid 2112 and the time sequence at the time of monitoring, the calculation apparatus can determine that the moving direction of the trajectory 211 points in the vehicle compartment interior direction. When the moving direction of the track 211 is determined, the calculating device may add one to the number of people in the car.

The communication equipment utilizes the characteristics that millimeter wave radar signal resolution is high, not influenced by environments such as light intensity, rain haze and the like, and can count passengers under the environments with poor light conditions and crowded personnel. In addition, the passenger counting method provided by the embodiment of the application considers that one passenger can reflect a plurality of millimeter wave radar signals, and a plurality of targets can be determined according to the plurality of millimeter wave radar signals reflected by the passenger. The plurality of objects are most dense in the head, chest, and back regions of a passenger, and by clustering the plurality of objects, the communication device can establish the movement trajectory of the passenger. And determining the number of passengers according to the number of the moving tracks. Therefore, the accuracy of passenger counting in the environment with poor light conditions and crowded personnel can be improved.

In the application, the communication device determines the positions of a plurality of targets detected in a first time period according to the monitoring data of the millimeter wave radar in the first time period through the computing device. The first time period may be a time period in which a door of a carriage of the subway is opened once. The first time period is not particularly limited in the embodiments of the present application.

In this application, the communication device generates, by the computing device, a first set from a plurality of targets detected during the first time period, the first set including one or more first targets and a plurality of second targets. Wherein the first target may be a core point. The second target may be a boundary point. The communication device performs target clustering processing on the multiple targets detected in the first time period according to the first target and the second target by using the computing device, and the specific processing procedure may refer to step S108 in fig. 7, which is not described herein again.

In this application, the plurality of targets detected in the first time period may include the first set and the third target. Wherein the third target may be a noise point.

It should be noted that the radii used for determining the neighborhood of the first object, the neighborhood of the second object, and the neighborhood of the third object may be cluster radii, that is, the first length may be a cluster radius.

In the application, the communication device can determine the predicted mass center of a certain passenger at the moment i +1 according to the mass centers of a plurality of passengers at the moment i and the mass center speed of the certain passenger at the moment i through the computing device. The communication device can establish a first wave gate by using the computing device with the predicted centroid at the (i +1) th moment as a center. Wherein, according to the centroids of a plurality of passengers at the ith moment, the communication device can obtain the correlation vector of one passenger and other centroids carried at the ith moment by using the neural network through the computing device. According to the correlation vector, the centroid of the passenger at the ith moment and the centroid speed at the ith moment, the communication device can obtain the predicted centroid of the passenger at the (i +1) th moment by using the LSTM through the computing device. The specific process of calculating the correlation vector and the predicted centroid of the certain passenger at the i +1 th time may refer to step S109 in fig. 7, and is not described herein again.

In this application, the first gate may be a subsequent correlation gate. The radius of the first wave gate can be determined by x²And obtaining a distribution table. The second gate may be an initial correlation gate. The radius of the second gate may be determined according to the time interval between two detections of one passenger in the millimeter wave radar and the maximum moving speed of one passenger.

Referring to fig. 12, fig. 12 is a schematic structural diagram of another communication device according to an embodiment of the present disclosure. As shown in fig. 12, the communication apparatus includes a millimeter wave radar 101 and a computing device 102. Wherein the content of the first and second substances,

the millimeter wave radar 101 may include a transmitting antenna 101a and a receiving antenna 101 b. The millimeter wave radar 101 may transmit a millimeter wave radar signal through the transmitting antenna 101a and receive a reflected echo signal through the receiving antenna 101 b. The modules included in the millimeter wave radar 101 in the embodiment of the present application are not limited, and may include more modules besides the transmitting antenna 101a and the receiving antenna 101 b.

Millimeter-wave radar 101 may send the monitoring data to computing device 102. The monitoring data may include a millimeter wave radar signal transmitted by the millimeter wave radar to a target, a transmission time, and a reception time and a reception echo signal reflected by the target.

The calculation means 102 may determine the distance and direction between the target reflecting the echo signal and the millimeter wave radar based on the monitoring data, thereby determining the position of the target. Wherein a plurality of body parts of one passenger may reflect a plurality of millimeter wave radar signals. The computing device 102 may determine the location of multiple targets from one passenger. The computing device 102 may determine the centroids at different times from the locations of the multiple targets. The centroid at a time represents the position of a passenger at a time. The computing device 102 may determine the centroids belonging to the same passenger from the centroids at different times and connect the centroids belonging to the same passenger in time sequence to generate the movement trajectory of the same passenger.

From the number of movement trajectories, the communication device, via the computing means 102, can determine the number of passengers.

While the present application has been described in connection with various embodiments, other variations to the disclosed embodiments can be understood and effected by those skilled in the art in practicing the claimed application, from a review of the drawings, the disclosure, and the appended claims. In the claims, the word "comprising" does not exclude other elements or steps, and the word "a" or "an" does not exclude a plurality. A single processor or other unit may fulfill the functions of several items recited in the claims. The mere fact that certain measures are recited in mutually different dependent claims does not indicate that a combination of these measures cannot be used to advantage.

As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, apparatus (device), 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. A computer program stored/distributed on a suitable medium supplied together with or as part of other hardware, may also take other distributed forms, such as via the Internet or other wired or wireless telecommunication systems.

Although the present application has been described in conjunction with specific features and embodiments thereof, it will be evident that various modifications and combinations can be made thereto without departing from the spirit and scope of the application. Accordingly, the specification and figures are merely exemplary of the present application as defined in the appended claims and are intended to cover any and all modifications, variations, combinations, or equivalents within the scope of the present application. It will be apparent to those skilled in the art that various changes and modifications may be made in the present application without departing from the spirit and scope of the application. Thus, if such modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is intended to include such modifications and variations as well.

Claims

1. A passenger counting method, comprising:

the communication equipment determines the mass centers at different moments according to the positions of the multiple targets detected in the first time period; generating a first set by the communication equipment according to a plurality of targets detected in the first time period, wherein the first set comprises one or more first targets and a plurality of second targets, the number of targets contained in the neighborhood of the first targets is larger than or equal to the number of clustering points, and any one target in the plurality of first targets is positioned in the neighborhood of another first target; the second target is positioned in the neighborhood of the first target, and the number of targets contained in the neighborhood of the second target is less than the number of the clustering points; the neighborhood of the first target is a circular area which takes the first target as a center and takes a first length as a radius; the neighborhood of the second target is a circular region which takes the second target as a center and takes the first length as a radius; the communication device determines the centroid from the positions of the objects in the first set; the number of objects within a first region centered at the centroid exceeds a first value; a centroid represents the position of a passenger at a time;

the communication equipment determines the mass centers belonging to the same passenger from the mass centers at different moments, and connects the mass centers belonging to the same passenger according to the time sequence to generate the moving track of the same passenger; the communication equipment determines the predicted center of mass of the same passenger at the i +1 th moment according to the centers of mass of a plurality of passengers at the i th moment and the center of mass speed of the same passenger at the i th moment, and establishes a first wave gate by taking the predicted center of mass of the i +1 th moment as the center of a circle; the centroid of the passengers at the ith moment is used for determining the direction of the same passenger from the ith moment to the (i +1) th moment, the centroid speed of the same passenger at the ith moment represents the speed of the same passenger at the ith moment, and the centroid speed is used for determining the distance of the same passenger from the ith moment to the (i +1) th moment; the radius of the first wave gate enables the probability that the centroid falling into the first wave gate at the (i +1) th moment is the centroid of the same passenger at the (i +1) th moment to be a preset probability; the communication device determines the centroid of the same passenger at the moment i +1 from the centroids at the moment i +1 within the first wave gate; the centroid of the same passenger at the moment i +1 is the centroid closest to the predicted centroid of the same passenger at the moment i +1 in the centroids of the first wave gate at the moment i + 1;

2. The method according to claim 1, wherein the communication device transmits millimeter wave radar signals and receives echo signals, and specifically comprises:

the communication equipment transmits the millimeter wave radar signal in a first time period and receives the echo signal; the doors of the compartment are open during the first time period.

3. The method of claim 2, further comprising: and the communication equipment stops transmitting the millimeter wave radar signal when the door of the carriage is closed.

4. The method according to claim 1, wherein the direction is represented by an angle between a connecting line between the target and a projection point of the millimeter wave radar on a horizontal plane and a first direction; the first direction is perpendicular to the extension direction of the train.

5. The method of claim 1, wherein the echo signals include a first echo signal reflected by a passenger and a second echo signal reflected by an interferer, and wherein the communications device determines the centroid at different times based on the positions of the plurality of targets detected during the first time period, the method further comprising:

the communication equipment performs distance dimension constant false alarm rate detection on the multiple targets by utilizing ordered statistics constant false alarm rate detection, and screens out a first target set; the distance dimension constant false alarm rate detection is used for judging whether the echo signals received by the millimeter wave radar from the same direction and different distances in the monitoring range are the first echo signals, and the targets in the first target set are determined by the first echo signals judged by the distance dimension constant false alarm rate detection;

6. The method of claim 1, wherein the plurality of targets detected during the first time period comprises the first set and a third target; the third target is not positioned in the neighborhood of the first target, and the number of targets contained in the neighborhood of the third target is less than the number of the clustering points;

the neighborhood of the third target is a circular region centered on the third target and having the first length as a radius.

7. The method of claim 1, further comprising:

when the distance between the target and the millimeter wave radar is less than a first distance X₁The communication device determines the number of clustering points to be N₁When the distance between the target and the millimeter wave radar is greater than or equal to the first distance X₁And is less than the second distance X₂The communication device determines the number of clustering points to be N₂When the distance between the target and the millimeter wave radar is greater than or equal to the second distance X₂The communication device determines the number of clustering points to be N₃；

The first distance X₁The second distance X₂Are all positive numbers, and the first distance X₁Is less than the second distance X₂(ii) a Said N is₁The N₂The N₃Are all positive integers, and N₁Less than said N₂Said N is₂Less than said N₃。

8. The method according to any one of claims 1 or 7, further comprising:

when the distance between the target and the millimeter wave radar is less than a first distance Y₁The communication device determines the first length as R₁When the distance between the target and the millimeter wave radar is greater than or equal to the first distance Y₁And is less than the second distance Y₂The communication device determines the first length as R₂When the distance between the target and the millimeter wave radar is greater than or equal to the second distance Y₂The communication device determines the first length as R₃；

The first distance Y₁The second distance Y₂Are all positive numbers, and the first distance Y₁Less than the second distance Y₂(ii) a The R is₁The R is₂The R is₃Are all positive numbers, and R₁Less than R₂Said R is₂Less than R₃。

9. The method of claim 1, wherein the centroid is an average of the locations of the objects in the first set.

10. The method of claim 1, wherein the centroid is a location of a selected one of the objects from the first set.

11. The method of claim 1, wherein of the centroids of the same passenger at different times, the centroids of the preceding H times are connected to form an initial trajectory of the passenger; the centroids of the previous H moments comprise the centroid of the mth moment to the centroid of the m + H-1 moment determined by the communication device;

12. The method according to any one of claims 1 or 11, wherein the movement trajectory of the same passenger is generated by connecting W time centroids of the same passenger, the last Q consecutive ones of the W time centroids being predicted centroids of the same passenger; and W and Q are positive integers.

13. The method of claim 1, wherein the communication device determines the number of passengers based on the number of movement trajectories, comprising:

the communication device determines the number of passengers getting on the train and/or the number of passengers getting off the train; the number of passengers getting on the train is equal to the number of first moving tracks, and the first moving tracks extend into a carriage; the number of the passengers getting off the vehicle is equal to the number of second moving tracks, and the second moving tracks extend outwards of the carriage.

14. A communication apparatus, characterized in that the communication apparatus comprises a millimeter wave radar and a computing device;

the computing device is further used for determining the mass centers at different moments according to the positions of the multiple targets detected in the first time period; the computing device is specifically configured to generate a first set according to a plurality of targets detected within the first time period, and determine the centroid according to positions of the targets in the first set; the first set comprises one or more first targets and a plurality of second targets, the number of targets contained in the neighborhood of the first targets is larger than or equal to the number of clustering points, and any one target in the plurality of first targets is positioned in the neighborhood of another first target; the second target is positioned in the neighborhood of the first target, and the number of targets contained in the neighborhood of the second target is less than the number of the clustering points; the neighborhood of the first target is a circular area which takes the first target as a center and takes a first length as a radius; the neighborhood of the second target is a circular region which takes the second target as a center and takes the first length as a radius; the number of objects within a first region centered at the centroid exceeds a first value; a centroid represents the position of a passenger at a time;

the computing device is further used for determining the mass centers belonging to the same passenger from the mass centers at different moments, and connecting the mass centers belonging to the same passenger according to a time sequence to generate the moving track of the same passenger; the computing device is specifically used for determining a predicted centroid of the same passenger at the i +1 th moment according to centroids of a plurality of passengers at the i th moment and a centroid speed of the same passenger at the i th moment, and establishing a first wave gate by taking the predicted centroid of the i +1 th moment as a center of a circle; the centroid of the passengers at the ith moment is used for determining the direction of the same passenger from the ith moment to the (i +1) th moment, the centroid speed of the same passenger at the ith moment represents the speed of the same passenger at the ith moment, and the centroid speed is used for determining the distance of the same passenger from the ith moment to the (i +1) th moment; the radius of the first wave gate enables the probability that the centroid falling into the first wave gate at the (i +1) th moment is the centroid of the same passenger at the (i +1) th moment to be a preset probability; the computing device is further specifically configured to determine, among the centroids at time i +1 within the first wave gate, the centroid of the same passenger at time i + 1; the centroid of the same passenger at the moment i +1 is the centroid closest to the predicted centroid of the same passenger at the moment i +1 in the centroids of the first wave gate at the moment i + 1;

15. The communications device of claim 14, wherein the echo signals include a first echo signal reflected by the passenger and a second echo signal reflected by the interferer, and wherein the computing device is further configured to, prior to determining the centroid at different times based on the positions of the plurality of targets detected during the first time period:

carrying out distance dimension constant false alarm rate detection on the multiple targets by utilizing ordered statistics constant false alarm rate detection, and screening out a first target set; the distance dimension constant false alarm rate detection is used for judging whether the echo signals received by the millimeter wave radar from the same direction and different distances in the monitoring range are the first echo signals, and the targets in the first target set are determined by the first echo signals judged by the distance dimension constant false alarm rate detection;

carrying out speed dimension constant false alarm rate detection on the multiple targets by using unit average constant false alarm rate detection, and screening out a second target set; the speed dimension constant false alarm rate detection is used for judging whether the multi-pulse echo signal is a first echo signal according to a multi-pulse echo signal received by the millimeter wave radar from a monitoring range of the same distance, and a target in the second target set is determined by the first echo signal judged by the speed dimension constant false alarm rate detection;

carrying out direction dimension constant false alarm rate detection on the multiple targets by using unit average constant false alarm rate detection, and screening out a third target set; the direction dimension constant false alarm rate detection is used for judging whether the echo signals received by the millimeter wave radar from the monitoring ranges of the same distance and different directions are the first echo signals, and the targets in the third target set are determined by the first echo signals judged by the direction dimension constant false alarm rate detection;

determining the centroids of the plurality of targets at different moments according to the positions of the plurality of targets in the intersection of the first target set, the second target set and the third target set.

16. The communications device of claim 14, wherein the computing apparatus is further configured to:

when the distance between the target and the millimeter wave radar is less than a first distance X₁Determining the number of the cluster points to be N₁When the distance between the target and the millimeter wave radar is greater than or equal to the first distance X₁And is less than the second distance X₂Determining the number of the cluster points to be N₂When the distance between the target and the millimeter wave radar is greater than or equal to the second distance X₂Determining the number of the cluster points to be N₃；

17. The communications device of any of claims 14 or 16, wherein the computing apparatus is further configured to:

when the distance between the target and the millimeter wave radar is less than a first distance Y₁Determining the first length to be R₁When the distance between the target and the millimeter wave radar is greater than or equal to the first distance Y₁And is less than the second distance Y₂Determining the first length to be R₂When the distance between the target and the millimeter wave radar is greater than or equal to the second distance Y₂Determining the first length to be R₃；

18. The communications device of claim 14, wherein the centroid is an average of the locations of the objects in the first set.

19. The communication apparatus according to claim 14, wherein among the centroids of the same passenger at different times, the centroids of the preceding H times are connected to form an initial trajectory of the passenger; the centroids of the previous H moments comprise the centroid at the m moment to the centroid at the m + H-1 moment determined by the computing device;

in the centroids at the previous H moments, the distance between the centroid at the mth moment and the centroid at the (m +1) th moment is less than the radius of the second wave gate; the first wave gate is a circular area taking the centroid of the mth moment as the center of a circle, and the radius of the first wave gate is the maximum distance which can be reached by a passenger in the interval time of the millimeter wave radar for continuously transmitting the millimeter wave radar signals twice;

20. The communication apparatus according to any one of claims 14 or 19, wherein the movement trajectory of the same passenger is generated by connecting W time centroids of the same passenger, wherein the last Q consecutive time centroids of the W time centroids are all predicted centroids of the same passenger; and W and Q are positive integers.

21. The communication device according to claim 14, wherein the computing device determines the number of passengers based on the number of movement trajectories, the computing device being specifically configured to:

determining the number of passengers getting on the train and/or the number of passengers getting off the train; the number of passengers getting on the train is equal to the number of first moving tracks, and the first moving tracks extend into a carriage; the number of the passengers getting off the vehicle is equal to the number of second moving tracks, and the second moving tracks extend outwards of the carriage.