CN111429791B

CN111429791B - Identity determination method, identity determination device, storage medium and electronic device

Info

Publication number: CN111429791B
Application number: CN202010276285.7A
Authority: CN
Inventors: 李冬冬; 方勇军; 李乾坤; 卢维; 殷俊; 沈达飞
Original assignee: Zhejiang Dahua Technology Co Ltd
Current assignee: Zhejiang Dahua Technology Co Ltd
Priority date: 2020-04-09
Filing date: 2020-04-09
Publication date: 2022-11-18
Anticipated expiration: 2040-04-09
Also published as: CN111429791A

Abstract

The invention provides an identity determination method, an identity determination device, a storage medium and an electronic device, wherein the method comprises the following steps: determining a motion track of a target object based on radar measurement information of the target object; determining target attribute information of a target area where the motion trail is located based on attribute information of a target map, wherein the target map comprises the target area; determining an identity of the target object based on the target attribute information. The method and the device solve the problems that monitoring efficiency of monitoring equipment is low and the identity of the target object cannot be accurately confirmed in the related technology, and further achieve the effect of accurately confirming the identity of the target object.

Description

Identity determination method, identity determination device, storage medium and electronic device

Technical Field

The present invention relates to the field of communications, and in particular, to an identity determining method, an identity determining apparatus, a storage medium, and an electronic apparatus.

Background

In modern society, security and protection are more and more valued by the public, security and protection products are also in the endlessly, the application field of security and protection is continuously expanded, security and protection technology is rapidly developed, and monitoring technology is more and more applied.

In the related art, the conventional monitoring terminal equipment is mainly a visible light camera, but the visible light camera cannot work at night; although there are drawbacks to infrared cameras that complement visible light cameras, this undoubtedly increases cost and operational difficulty. In addition, the optical sensor is also affected by weather, and the monitoring effect cannot be satisfactory in heavy fog days or rainy and snowy days.

Therefore, the problems that monitoring efficiency of monitoring equipment is low and the identity of a target object cannot be accurately confirmed exist in the related technology.

In view of the above problems in the related art, no effective solution has been proposed.

Disclosure of Invention

The embodiment of the invention provides an identity determining method, an identity determining device, a storage medium and an electronic device, which are used for at least solving the problems that monitoring equipment in the related technology is low in monitoring efficiency and cannot accurately determine the identity of a target object.

According to an embodiment of the present invention, there is provided an identity determination method including: determining a motion trajectory of a target object based on radar measurement information of the target object; determining target attribute information of a target area where the motion trail is located based on attribute information of a target map, wherein the target map comprises the target area; determining an identity of the target object based on the target attribute information.

According to another embodiment of the present invention, there is provided an identity determination apparatus including: the device comprises a first determination module, a second determination module and a third determination module, wherein the first determination module is used for determining the motion track of a target object based on radar measurement information of the target object; the second determination module is used for determining target attribute information of a target area where the motion trail is located based on attribute information of a target map, wherein the target map comprises the target area; a third determination module to determine an identity of the target object based on the target attribute information.

According to a further embodiment of the present invention, there is also provided a computer-readable storage medium having a computer program stored thereon, wherein the computer program is arranged to, when executed, perform the steps of any of the method embodiments described above.

According to yet another embodiment of the present invention, there is also provided an electronic device, comprising a memory in which a computer program is stored and a processor configured to run the computer program to perform the steps of any of the method embodiments described above.

According to the invention, the radar obtains the measurement information of the target object with high detection probability, the target track of the target object can be rapidly and accurately determined according to the radar measurement information, and the identity of the target object can be determined according to the attribute information of the target track, so that the problems that monitoring equipment in the related technology is low in monitoring efficiency and cannot accurately determine the identity of the target object can be solved, and the effect of accurately determining the identity of the target object is achieved.

Drawings

The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the invention and together with the description serve to explain the invention without limiting the invention. In the drawings:

fig. 1 is a block diagram of a hardware structure of a mobile terminal of an identity determination method according to an embodiment of the present invention;

FIG. 2 is a flow diagram of a method of identity determination according to an embodiment of the present invention;

FIG. 3 is a simplified partial map according to an alternative embodiment of the present invention;

FIG. 4 is a flowchart of determining a region type of the target region based on the target attribute information, according to an alternative embodiment of the present invention;

FIG. 5 is a diagram illustrating setting a first rule by taking a time threshold as an example according to an alternative embodiment of the invention;

FIG. 6 is a flow diagram of a pedestrian characterization sub-process and a vehicle characterization sub-process in accordance with an alternative embodiment of the present invention;

FIG. 7 is a flowchart of a vehicle clustering process according to an alternative embodiment of the present invention;

FIG. 8 is a schematic illustration of a delayed determination when the first type of trajectory is a pedestrian trajectory and the second type of trajectory is a vehicle trajectory, in accordance with an alternative embodiment of the present invention;

FIG. 9 is a flowchart of a first method for identity determination according to an embodiment of the present invention;

FIG. 10 is a diagram illustrating a determine identity of a target object sub-process in accordance with an embodiment of the present invention;

FIG. 11 is a flowchart of a second method for identity determination according to an embodiment of the present invention;

fig. 12 is a block diagram of the structure of an identity determination apparatus according to an embodiment of the present invention.

Detailed Description

The invention will be described in detail hereinafter with reference to the drawings and embodiments. It should be noted that, in the present application, the embodiments and features of the embodiments may be combined with each other without conflict.

It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order.

The method provided by the embodiment of the application can be executed in a mobile terminal, a computer terminal or a similar operation device. Taking an example of the operation on a mobile terminal, fig. 1 is a hardware structure block diagram of the mobile terminal of an identity determination method according to an embodiment of the present invention. As shown in fig. 1, the mobile terminal 10 may include one or more (only one shown in fig. 1) processors 102 (the processor 102 may include, but is not limited to, a processing device such as a microprocessor MCU or a programmable logic device FPGA) and a memory 104 for storing data, and optionally may also include a transmission device 106 for communication functions and an input-output device 108. It will be understood by those of ordinary skill in the art that the structure shown in fig. 1 is only an illustration and is not intended to limit the structure of the mobile terminal. For example, the mobile terminal 10 may include more or fewer components than shown in FIG. 1, or have a different configuration than shown in FIG. 1.

The memory 104 may be used to store computer programs, for example, software programs and modules of application software, such as a computer program corresponding to the identity determination method in the embodiment of the present invention, and the processor 102 executes various functional applications and data processing by running the computer programs stored in the memory 104, so as to implement the above-mentioned method. The memory 104 may include high speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include memory located remotely from the processor 102, which may be connected to the mobile terminal 10 via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.

The transmission device 106 is used for receiving or transmitting data via a network. Specific examples of the network described above may include a wireless network provided by a communication provider of the mobile terminal 10. In one example, the transmission device 106 includes a Network adapter (NIC), which can be connected to other Network devices through a base station so as to communicate with the internet. In one example, the transmission device 106 may be a Radio Frequency (RF) module, which is used for communicating with the internet in a wireless manner.

In this embodiment, an identity determining method is provided, and fig. 2 is a flowchart of the identity determining method according to the embodiment of the present invention, as shown in fig. 2, the flowchart includes the following steps:

step S202, determining a motion track of a target object based on radar measurement information of the target object;

step S204, determining target attribute information of a target area where the motion trail is located based on attribute information of a target map, wherein the target map comprises the target area;

step S206, the identity of the target object is determined based on the target attribute information.

In the above-described embodiments, a radar (e.g., millimeter wave radar) may actively emit electromagnetic waves and receive signals of the same frequency, and has a very high detection probability for a moving target object or a target object having a large radar reflection area (RCS) and a low detection probability (detection probability is not zero) for a stationary object, so that a motion trajectory of the target object may be accurately determined using the radar. The radar may set a measurement period (signal transceiving period) as required, and generally set the measurement period to be 0.1 second, i.e. the operating frequency is 10Hz (of course, other measurement periods may be set, such as 0.05 second, 0.15 second, 0.2 second, etc.). The target object may be a person, an animal, a vehicle, etc., and the radar measurement information may include a distance, an angle, a radial velocity (radial speed), an RCS, etc. The state X of the motion trajectory of the target object may be a vector of four rows and one column, composed of [ X, vx, y, vy ], and the vector elements represent a rectangular coordinate position X, a velocity component vx, a rectangular coordinate position y, and a velocity component vy in a two-dimensional space, respectively. The state covariance matrix PX of the motion trajectory may be a matrix of four rows and four columns.

Optionally, the main body of the above steps may be a background processor, or other devices with similar processing capabilities, and may also be a machine integrating at least a radar transmitting device and a data processing device, where the data processing device may include a terminal such as a computer, a mobile phone, and the like, but is not limited thereto.

In an optional embodiment, before determining the target attribute information of the target area where the motion trail is located based on the attribute information of the target map, the method further includes: loading a drawn initial map; rasterizing the initial map; and assigning corresponding node attributes to each map node obtained after rasterizing the target map to obtain the target map, wherein the attribute information of the target map comprises the node attributes corresponding to each map node. In this embodiment, the map may be rasterized, and the node attributes in the map are allowed to be different, where the map node attributes may include: 1) An unknown region; 2) A tree region; 3) A tree shadow area; 4) A building area; 5) A building block area; 6) An open area; 7) A motor vehicle drivable region; 8) A human travelable area; 9) An area that cannot be detected; 10 High quality measurement area; 11 Poor quality measurement area. The simple local map shown in fig. 3, wherein a region denoted by "1" represents an unknown region, a region denoted by 2 represents a building region, a region denoted by 3 represents a building-sheltered region, a region denoted by 4 represents a tree region, a region denoted by 5 represents a tree-shaded region, a region denoted by 6 represents a human travelable region, a region denoted by 7 represents a vehicle travelable region, a region denoted by 8 represents an open region, and a region denoted by 9 represents a region that cannot be detected by a radar.

In this embodiment, the node motion has directionality, that is, the node motion can be represented by a vector map, for example, a square (with a side length of 1 meter) with coordinates (CartX =10, carty = 40) in the map, the motion direction is a unidirectional travel area, the direction is 0 degrees (0 degrees is defined as north), the allowable error is 45 degrees, that is, if there is a moving object in the square with coordinates (CartX =10, carty = 40), the speed direction of the moving object must be north, and the allowable direction error is 45 degrees. For another example, if there is no requirement for the direction of movement in a square with coordinates (CartX = -10, carty = -20) in the map, it indicates that there is an object that can move in any direction at this point.

In this embodiment, after determining the attribute corresponding to each node in the map, the attribute of the motion trajectory of the target object may be determined according to the target area where the motion trajectory of the target object is located, so as to determine the identity of the target object. It should be noted that the map needs to be rasterized, and each map node is assigned with the correct attributes. The structure describing the map is as follows:

in an alternative embodiment, loading the initial map drawn includes one of: loading the manually drawn initial map; and loading the initial map generated on line. In this embodiment, the drawn initial map is loaded, that is, a reliable and accurate monitoring area map is provided for the target identification program. The map can be loaded, a map of the known environment can be drawn manually, and a program can be imported, and the map can be generated on line (without any manual auxiliary operation). The method for generating the map on line can build and update the environmental map in real time by accumulating radar measurement for a period of time based on the existing environmental target type knowledge base. The advantage of manually drawing the known environment is that the map accuracy is high and no additional time is consumed (compared to the online generation of the map, which requires additional time to generate the environment map); the disadvantage is that the labor cost is high, and when the environment information is changed, a new map needs to be imported again. The method for generating the map on line has the advantages that no manual auxiliary operation is needed; the disadvantage is that it is less accurate than manually drawn maps and requires additional time to build the map when the procedure is initiated. Target tracking and target identification cannot be performed during map construction. In addition, the contents of the manually drawn map and the online generated map may have a large difference, for example, there are many undetected areas in the manually drawn map and many unknown areas in the online generated map. Therefore, the method for loading and drawing the initial map can be selected according to the environment and the requirement of the map to be drawn and the advantages and disadvantages of loading the map in different modes.

In an optional embodiment, determining the identity of the target object based on the target attribute information comprises: determining a region type of the target region based on the target attribute information; determining a measurement rule corresponding to the area type; determining the type of the motion track based on the measurement rule; determining an identity of the target object based on the type of the motion trajectory. In this embodiment, the area type of the target area where the target track is located may be determined by determining the target attribute information. Fig. 4 is a flowchart for determining the area type of the target area based on the target attribute information, and as shown in fig. 4, the process includes:

and Step 1, obtaining the map node attribute corresponding to any measurement. Suppose there are M measurements for a track, and each measurement uniquely corresponds to a map node attribute.

And Step 2, counting the measurement number corresponding to the map node type. The measurement number corresponding to each map node attribute can be counted. And satisfy

∑N(P _i )

＝

M

The measurement quantity corresponding to the ith map node attribute is represented.

And Step 3, obtaining the track area attribute. Is calculated by the formula

I.e. max N (P) _i ) The corresponding map node attribute is the area type of the target area.

In an optional embodiment, determining the characteristic of the motion trajectory based on the metrology rule comprises: when the measurement rule is determined to be used for starting a first type track, judging whether the motion track meets a first rule corresponding to the first type track; judging whether the motion track is the first type track or not under the condition that the judgment result is that the first rule is satisfied, determining the type of the motion track to be the first type track under the condition that the judgment result is that the motion track is the first type track, executing the operation of judging whether the motion track is the second type track under the condition that the judgment result is not the first type track, and determining the type of the motion track based on the judgment result; under the condition that the judgment result is that the first rule is not satisfied, executing operation of judging whether the motion track is a second type track, and determining the type of the motion track based on the judgment result; wherein the first type of track is different from the second type of track. In this embodiment, the first type trajectory may be a pedestrian trajectory, the second type trajectory may be a vehicle trajectory, or the first type trajectory may be a vehicle trajectory, the second type trajectory may be a pedestrian trajectory, and the like, and the first rule may include a time threshold rule, as shown in fig. 5, the time threshold is taken as an example to set the first rule content. The time threshold is defined as the M/N rule (M ≦ N) that is the correlation relationship between a sufficient number of measurements (M frames) within a specified time (N frames). When the value of N is unchanged, the smaller the value of M is, the easier the track is to start; when the value of M is constant, the smaller the value of N, the harder the trajectory is to start. Therefore, the starting difficulty/speed of the track can be adjusted by setting the M/N value. For example, the pedestrian is 7/8, and the vehicle is 8/8 (this value is just one possible implementation, and the specific M/N value may be set according to the attribute of the target area, for example, it may also be set that the pedestrian is 6/8,7/9, and the vehicle is 7/8,8/9, etc.). The value of N is equivalent to a time window, and M is equivalent to the minimum measured number satisfying the RCS association rule, the spatial distance association rule, and the radial velocity association rule in the time window. Let M =7 and n =8, as indicated by the arrow-labeled time window in fig. 5. In both example 1 and example 2, within the time window, there are 7 measurements that satisfy the correlation, and there are

measurements

3 and 6 that do not satisfy the correlation, respectively, and thus it can be determined that they are a trace. For example 3, there are 2 measurements (4 and 6) that do not satisfy the correlation, i.e., there are at most 6 measurements that satisfy the correlation, within the time window, and thus the target trajectory (time threshold) cannot be formed by the potential trajectory. Therefore, whether the motion track meets a first rule or not can be judged, whether the motion track is the first type track or not is judged under the condition that the judgment result meets the first rule, the judgment method can adopt a target object characteristic calling sub-process to determine whether the motion track is the first type track or not, for example, when the first type track is a pedestrian track, the pedestrian characteristic sub-process is called for judgment, when the first type track is a vehicle track, the vehicle characteristic sub-process is called for judgment, and when the judgment result is that the motion track is the first type track, the motion track type is determined to be the first type track. Referring to fig. 6, as shown in fig. 6, the pedestrian characteristic determining process (i.e., the pedestrian characteristic sub-process) determines whether the trajectory measurement is within a known pedestrian characteristic interval, and if so, it is the pedestrian trajectory. The determination basis can be RCS interval, radial velocity interval, pedestrian measurement position fluctuation interval, etc. The vehicle characteristic determination is similar to the pedestrian characteristic determination, and whether the trajectory measurement is located in the known vehicle characteristic interval may also be determined according to the RCS interval, the radial velocity interval, the pedestrian measurement position fluctuation interval, and the like.

In this embodiment, when the motion trajectory is not the first type trajectory, it is determined whether the motion trajectory is the second type trajectory, and when the second type trajectory is the vehicle trajectory, it may be determined whether the motion trajectory is the vehicle trajectory by invoking a vehicle clustering process.

In this embodiment, when the motion trajectory does not satisfy the first rule, it is determined whether the motion trajectory is the second type trajectory, and the type of the motion trajectory can be determined by the determination.

In an optional embodiment, before determining whether the motion trajectory satisfies a first rule corresponding to the first type trajectory, the method further comprises at least one of: setting the first rule; setting a second rule corresponding to the second type of track. In this embodiment, when the first type of trajectory is a pedestrian trajectory, the purpose of setting the first rule is to adjust the relevant parameters so that the pedestrian trajectory is easier to initiate and the vehicle trajectory is more difficult to initiate. The relevant parameters may include a start time threshold, a measurement and measurement RCS association threshold, a radial velocity association threshold, a spatial location association threshold, and a clustering threshold association threshold. Similarly, when the second type of trajectory is a vehicle trajectory, the purpose of setting the second rule is to adjust the relevant parameters so that the vehicle trajectory is easier to start and the pedestrian trajectory is more difficult to start.

In an alternative embodiment, the first rule includes at least one of: the method comprises the steps of starting time threshold, measurement and radar emission area RCS correlation threshold, radial velocity correlation threshold, spatial position correlation threshold and clustering threshold correlation threshold. In this embodiment, the first type of track may be initiated more easily by adjusting at least one of a start time threshold, a measurement and radar transmission area RCS correlation threshold, a radial velocity correlation threshold, a spatial location correlation threshold, and a clustering threshold correlation threshold.

In an optional embodiment, before determining whether the motion trajectory satisfies a first rule corresponding to the first type trajectory, the method further comprises: when the first type track is a pedestrian track, matching measurement included in the motion track with the first type track to determine a first target measurement; storing the first target measurement into a first predetermined sequence to obtain a first target sequence; determining whether the motion trajectory satisfies a first rule corresponding to the first type trajectory includes: and judging whether the motion track meets a first rule corresponding to the first type track or not based on the first target sequence. In this embodiment, when the first type of trajectory is a pedestrian trajectory, before determining whether the motion trajectory satisfies the first rule, it is necessary to match the measurement in the motion trajectory with the pedestrian trajectory, and if so, the pedestrian trajectory is initiated or associated. Wherein the starting pedestrian trajectory or the associated pedestrian trajectory may include the following: and matching the current frame measurement with the pedestrian track, selecting proper measurement and storing the proper measurement into the pedestrian track sequence, namely storing the first target measurement into a first preset sequence to obtain a first target sequence. The measurement included in the motion trajectory may include measurement time, X, Y, RCS, radial velocity information, map area information, and the like.

In an optional embodiment, before determining whether the motion trajectory satisfies a first rule corresponding to the first type trajectory, the method further comprises: when the first type track is a vehicle track, clustering the measurements in the current frame, and determining a second target measurement belonging to the same vehicle in the measurements included in the motion track based on a clustering result; determining whether the motion trajectory satisfies a first rule corresponding to the first type trajectory includes: and judging whether the motion track meets a first rule corresponding to the first type track or not based on the second target measurement. In this embodiment, the vehicle clustering process replaces the multiple vehicle measurements with an equivalent measurement. One vehicle has a plurality of radar measurements, so that the vehicle needs to be clustered firstly, all the measurements belonging to the same vehicle are selected, and the interference measurement is eliminated; and then calculating the equivalent measurement.

In an optional embodiment, clustering the metrics in the current frame includes: and correlating all the measurements included in the current frame pairwise, and grouping the correlated measurements meeting a preset clustering threshold into a group. In this embodiment, the clustering threshold may be determined according to the distance between the radar and the measurement.

In an optional embodiment, before correlating all measurements included in the current frame two by two, the method further comprises: according to the distance between the measured radar and the radar, determining at least one of the following thresholds included in the clustering threshold: a distance correlation threshold between measurements, an RCS correlation threshold between measurements, and a radial velocity correlation threshold between measurements. In this embodiment, a flowchart of a vehicle clustering process can be seen in fig. 7, as shown in fig. 7, the process is as follows:

and Step 1, determining a clustering threshold according to the distance between the measured radar and the radar. The clustering threshold comprises a distance correlation threshold, an RCS correlation threshold and a radial speed correlation threshold between measurement and measurement.

And Step 2, clustering. All measurements are correlated two by two within the same frame. The measurements that meet the clustering threshold are grouped together.

Step 3: an equivalence measurement is obtained. The clustering equivalence measure is calculated by the formula

X	＝	∑α _i X _i
			Y	＝	∑α _i Y _i
RCS	＝	∑α _i RCS _i
			RadialSpeed	＝	∑α _i RadialS _p eed _i
∑α _i	＝	1

Wherein alpha is _i Is the weight of the ith measurement.

In an optional embodiment, the determining whether the motion trail is the second type trail, and the determining the type of the motion trail based on the determination result includes: judging whether the motion track meets a second rule corresponding to the second type track; judging whether the motion trail is the second type trail or not under the condition that the judgment result is that the second rule is satisfied, determining the type of the motion trail as the second type trail under the condition that the judgment result is that the motion trail is the second type trail, and determining the type of the motion trail as a false trail under the condition that the judgment result is that the motion trail is not the second type trail; and under the condition that the second rule is not satisfied as a result of the judgment, repeatedly executing the operations of determining the target attribute information and determining the identity information of the target object based on the next frame image of the current frame. In this embodiment, the second rule may be set as a time threshold, and when the second type of trajectory is a vehicle trajectory, the second rule is set as a vehicle measurement time threshold, that is, it is determined whether the vehicle trajectory satisfies the M/N rule, and when the second type of trajectory is a pedestrian, the second rule is set as a pedestrian measurement time threshold, that is, it is determined whether the pedestrian trajectory satisfies the M/N rule. And under the condition that the motion trail meets a second rule, judging whether the motion trail is a second type trail or not, outputting the identity of the target object when the motion trail is the second type trail, and determining that the motion trail is a false trail and deleting the false trail when the motion trail is not the second type trail. The method for judging whether the motion trajectory meets the second rule may adopt a mode of calling a pedestrian feature subprocess or a vehicle feature subprocess as shown in fig. 6, and when the second type of trajectory is a pedestrian trajectory, the pedestrian feature subprocess is called, and when the second type of trajectory is a vehicle trajectory, the vehicle feature subprocess is called.

In an optional embodiment, before determining whether the motion trajectory satisfies a second rule corresponding to the second type of trajectory, the method further includes: circularly judging whether each measuring point in the motion trail can form the first type trail or not; in the event that it is determined that the first type of track cannot be formed, performing the following: when the second type track is determined to be a vehicle track, clustering the measurement in the current frame, and determining a second target measurement belonging to the same vehicle in the measurements included in the motion track based on a clustering result; judging whether the motion trajectory satisfies a second rule corresponding to the second type of trajectory includes: and judging whether the motion track meets a second rule corresponding to the second type track or not based on the second target measurement. In this embodiment, when each measurement point in the motion trajectory cannot form the first type trajectory, the measurements are clustered to determine whether each measurement point includes the second target measurement. Alternatively, the determination method may adopt a delay determination, and the determination method is as follows:

fig. 8 is a schematic diagram of the delay determination when the first type of trajectory is a pedestrian trajectory and the second type of trajectory is a vehicle trajectory, as shown in fig. 8, an open circle is used for the initial pedestrian trajectory, a circle filled with a horizontal line is used for the initial vehicle trajectory, a circle filled with a vertical line represents an ineffective measurement point, and paired arrows represent a current time window range. The delay determination process is illustrated with 7, and assuming that M =7/N =8 and the current time is 8, the pedestrian trajectory cannot be formed in the current window range indicated by the arrow 1. The arrow 1 window slides to the right, at the current time 9, becoming the arrow 2 window. Point 1 must not be used to form the pedestrian trajectory and the open circle is changed to a circle filling the transverse line and an attempt is made to form the vehicle trajectory. The arrow 2 window, which still fails to form a pedestrian trajectory, continues to slide backwards, becoming the arrow 3 time window, at which point 2 also changes from a hollow circle to a circle filling the transverse line. The start pedestrian trajectory is a time window based on the current time (e.g., a time window indicated by a pair of arrows) relative to the current time, but the start vehicle trajectory lags in time (e.g., a range indicated by a circle filling a horizontal line), which is a delayed start/associated vehicle trajectory process, and more generally, a delayed determination process. Therefore, the second target measurement in each measurement point can be judged, and whether the motion track meets the second rule or not is judged according to the second target measurement.

In an optional embodiment, before determining whether the motion trajectory satisfies a second rule corresponding to the second type of trajectory, the method further includes: circularly judging whether each measuring point in the motion trail can form the first type trail or not; in the event that it is determined that the first type of track cannot be formed, performing the following: matching the measurement included in the motion track with the second type track to determine a second target measurement; storing the second target measurement into a second predetermined sequence to obtain a second target sequence; judging whether the motion track meets a second rule corresponding to the second type track comprises the following steps: and judging whether the motion track meets a second rule corresponding to the second type track or not based on the second target sequence. In this embodiment, when the measuring points in the target trajectory cannot form the first type trajectory, an attempt is made to form or initiate the second type trajectory. For example, when the target trajectory cannot form a pedestrian trajectory, whether each measurement point matches the vehicle trajectory is determined according to a delay determination method, and when the measurement points match the vehicle trajectory, whether the second rule is satisfied is determined, and if the second rule is satisfied, a vehicle trajectory of the origin is formed or initiated.

In an optional embodiment, determining whether the motion trajectory is the first type trajectory comprises: determining whether the motion trajectory is the first type trajectory based on at least one of: RCS interval, radial velocity interval, first type measurement position fluctuation interval. In this embodiment, whether the motion trajectory is the first type trajectory may be determined according to the RCS interval, the radial velocity interval, the first type measurement position fluctuation interval, and the like. The RCS interval, the radial velocity interval, the first type measurement position fluctuation interval, and the like may be set to different intervals according to the first type trajectory, the target area, and the like, and the present invention does not limit the intervals. For example, when the first type track is a pedestrian track, the RCS interval may be (0.5 square meter, 2 square meters), the radial speed interval may be (0.5 m/s,1.5 m/s), the first type measurement position fluctuation interval may be (0 m, 30m), when the first type track is a vehicle, the RCS interval may be (50 square meters, 150 square meters), the radial speed interval may be (20 km/h,120 km/h), and the first type measurement position fluctuation interval may be (0 m, 50m).

In an alternative embodiment, determining the metrology rule corresponding to the area type comprises: under the condition that the area type is a pedestrian path area, determining a measurement rule corresponding to the area type to measure a pedestrian track first and then a vehicle track; under the condition that the area type is a vehicle driving area, determining a measurement rule corresponding to the area type as measuring a vehicle track first and then measuring a pedestrian track; and under the condition that the area type is an unknown area, determining that the measurement rule corresponding to the area type is to simultaneously measure the vehicle track and the pedestrian track. In the present embodiment, when the area type is a pedestrian road area, the probability of pedestrians on the sidewalk is higher than the probability of vehicles on the sidewalk, therefore, a measurement is set to be performed first for the pedestrians and then the vehicles, the measurement is first used to start the pedestrian track, and when the measurement determines that the pedestrian track cannot be formed, the possibility of forming the vehicle track is considered. Similarly, when the area type is a vehicle driving area, the measurement is performed first for vehicles and then for pedestrians, the measurement is first used for starting the vehicle track, and when the measurement determines that the vehicle track cannot be formed, the possibility of forming the pedestrian track is considered. When the region type is an unknown region, the probability of the occurrence of the pedestrian and the vehicle in the unknown region is basically the same, and therefore, the pedestrian and the vehicle are arranged to be measured simultaneously.

In an optional embodiment, when it is determined that the region type is another region type, ending the operation of determining the identity of the target object; wherein the other zone types are zone types other than a sidewalk zone, a vehicle driving zone, and an unknown zone. In this embodiment, if there is a target trajectory in other areas, such as a building area, and whether it is a pedestrian target or a vehicle trajectory, the target tracking algorithm considers that it is a false trajectory, and performs deletion or delayed reporting.

How to determine the identity is described below with reference to specific embodiments:

FIG. 9 is a flowchart of a first identity determination method according to an embodiment of the present invention, including an initialization step, loading a map, inputting ordered measurements, and determining a target identity. As shown in fig. 9, the process includes:

step S902, an initialization step is to open up a map storage space, measure a storage space, and other necessary preprocessing steps. It only needs to be executed once.

Step S904, a map is loaded, that is, a reliable and accurate monitoring area map is provided for the target identification program. The map can be loaded, a map of the known environment can be drawn manually, and a program can be imported, and the map can be generated on line (without any manual auxiliary operation).

Step S906, inputting the ordered measurement, wherein the radar measurement information comprises measurement time, X, Y, RCS, radial velocity information and map area information. The structure is as follows:

wherein, the sequential measurement means that the measurement is arranged in a non-decreasing order according to the measurement time.

In step S908, four sub-processes are required for determining the identity of the target object, as shown in fig. 10, namely a process of determining the attribute area of the track area (corresponding to the process of determining the attribute information of the target), a process of clustering vehicles, a process of determining the characteristics of pedestrians (corresponding to the sub-process of determining the characteristics of pedestrians), and a process of determining the characteristics of vehicles (corresponding to the sub-process of determining the characteristics of vehicles).

Fig. 11 is a flowchart of a second method for determining an identity according to an embodiment of the present invention, as shown in fig. 11, the method includes:

step 1: track area attributes are determined. And skipping to the step 2.

Step 2: and judging the sidewalk area. If the sidewalk area is the sidewalk area, skipping to the step 3; otherwise, jumping to step 17.

And 3, step 3: the measurement is carried out before the people and after the vehicles. This step is intended to measure first for the initial pedestrian trajectory, and then to take into account the possibility of vehicle trajectory formation when the measurement determines that the pedestrian trajectory cannot be formed. Jump to step 4.

And 4, step 4: a start rule is set. The purpose of this step is to adjust the relevant parameters so that the pedestrian trajectory is easier to initiate and the vehicle trajectory is more difficult to initiate. The relevant parameters comprise a starting time threshold, a measurement and RCS (radar cross section) correlation threshold, a radial velocity correlation threshold, a spatial position correlation threshold and a clustering threshold correlation threshold. And skipping to the step 5.

And 5, step 5: an initial pedestrian trajectory or an associated pedestrian trajectory. The current frame measurement is matched with the pedestrian track, and proper measurement is selected and stored in the pedestrian track sequence. And 6, jumping to the step 6.

And 6, step 6: and judging the pedestrian measurement time threshold. Whether the pedestrian track meets the M/N rule or not, and if not, skipping to the step 7; and if so, jumping to the 8 th step.

And 7, step 7: the start/associated vehicle trajectory is delayed. Each of the measurement points in this pedestrian trajectory attempts to form a vehicle trajectory when it is determined that the pedestrian trajectory cannot be formed, which is a delay determination process. Jump to step 11.

And 8, step 8: and judging the characteristics of the pedestrians. And calling a subprocess, namely judging the pedestrian characteristic, and judging whether the pedestrian trajectory is the pedestrian trajectory. And jumping to the 9 th step.

Step 9: and the pedestrian characteristic is satisfied. If the pedestrian features, jumping to a step 10; otherwise, jumping to step 11.

Step 10: and outputting the pedestrian target identity. And marking the track as a pedestrian and outputting the track.

And 11, a step of: and (5) vehicle clustering process. A subprocess is invoked-the vehicle clustering process-attempts to determine if it is a vehicle trajectory.

And (12) step: vehicle measurement time thresholds. Whether the vehicle track meets the M/N rule or not, and if not, skipping to the step 13; if yes, jump to step 14.

Step 13: the next frame is cycled. And jumping to the next cycle, and starting from the step 1.

Step 14: and judging the characteristics of the vehicle. And invoking a subprocess, namely judging the vehicle characteristics, and judging whether the vehicle trajectory is the vehicle trajectory. If the vehicle track is not the vehicle track, jumping to the step 15; and if the vehicle track is the vehicle track, jumping to the 16 th step.

Step 15: false trace, delete.

Step 16: and outputting the vehicle target identity. The track is marked as a vehicle and output.

Step 17: and judging a vehicle travelable area. It is determined whether it is a vehicle travelable region. If yes, jumping to the step 18; if not, jump to step 33.

Step 18: the measurement is carried out after the vehicle is started. The purpose of this step is that the measurements are first used to initiate vehicle trajectories, and then to take into account the possibility of developing pedestrian trajectories when the measurements determine that vehicle trajectories cannot be developed. Jump to step 19.

Step 19: a start rule is set. The purpose of this step is to adjust the relevant parameters so that the vehicle trajectory is easier to initiate and the pedestrian trajectory is more difficult to initiate. Jump to step 20.

Step 20: and (5) vehicle clustering process. And calling a subprocess, namely a vehicle clustering process, to judge whether the vehicle track is the vehicle track.

Step 21: vehicle measurement time thresholds. Whether the vehicle track meets the M/N rule or not, and if not, skipping to the step 22; if yes, jumping to the 23 rd step.

Step 22: delaying the start/associated pedestrian trajectory. And when each measuring point in the vehicle track is determined to be incapable of forming the vehicle track, a pedestrian track is formed in an attempt mode. Go to step 26.

Step 23: and judging the characteristics of the vehicle. And invoking a subprocess, namely vehicle characteristic judgment, so as to judge whether the vehicle track is the vehicle track.

Step 24: and judging that the vehicle characteristics are met. If the vehicle track characteristic is not satisfied, jumping to the 26 th step; if yes, jumping to the 25 th step.

Step 25: and outputting the vehicle target identity. The track is marked as a vehicle and output.

Step 26: the initial/associated pedestrian trajectory. This step belongs to the delay judgment. Any measurement point in the vehicle trajectory, when it is determined that the vehicle trajectory cannot be formed, then an attempt is made to initiate or correlate a pedestrian trajectory. Go to step 27.

Step 27: the pedestrian measurement time threshold is met. If not, jumping to the step 31; and if yes, jumping to the 28 th step.

Step 28: and judging the characteristics of the pedestrian. And calling a pedestrian characteristic judgment process. Jump to step 29.

Step 29: and the pedestrian characteristic is satisfied. If the pedestrian characteristics are not met, jumping to the 32 nd step; and if the pedestrian characteristic is met, jumping to the 30 th step.

And (30) step: and outputting the pedestrian target identity.

Step 31: the loop is ended and the next frame loop is awaited.

Step 32: and deleting the false track.

Step 29: and outputting the pedestrian target identity. And marking the track as a pedestrian and outputting the track.

Step 33: an unknown region. And judging whether the area is in an unknown area. If not, jumping to step 34. If yes, skipping 35 steps.

Step 35: the sequence of the measuring people and the vehicles is not arranged. This step is intended to measure the initial pedestrian and vehicle trajectories simultaneously. Go to step 36.

Step 36: a start rule is set. This step aims to equalize the probability of the starting pedestrian trajectory and the starting vehicle trajectory. I.e. there is no difference in order of priority. Go to step 37.

Step 37: a vehicle trajectory and a pedestrian trajectory are initiated simultaneously. Step 37 begins at both steps 11 and 26 (parallel), i.e., the vehicle trajectory and the pedestrian trajectory compete for trajectory identity, which trajectory is formed first, is output first, and the process of forming the other trajectory is terminated.

In the embodiment, the radar obtains the measurement information of the moving target with high detection probability, the background target tracking algorithm quickly and accurately starts a real target track based on the radar measurement input information, confirms the identity and motion information of the real moving target, filters a false track and a final target track in time, and then outputs the accurate identity and motion information of the target to other links. The millimeter wave radar can monitor various targets, extract the targets in which the user is interested from the various targets, and terminate/filter the targets which are not interested by the user or false targets as soon as possible. One of the purposes of object trajectory classification is to filter/filter objects. For example, in a park, a 3-level wind is occasionally blown, trees shake to form a low-speed and small-range moving target track, the target type is a non-human, non-vehicle or non-animal target, and the target type does not need to be reported or a track ending method is called as soon as possible to delete the target type. If a small dog is going through the garden, the trajectory should also be terminated in time since it is not the target of the user's attention (whether the user is a person or a car). If the track is formed by the pedestrian, the radar outputs the track information of the pedestrian to the camera, and the camera takes pictures or records the pictures according to the track space position information provided by the radar.

The algorithm of the invention has strong adaptability: the method is suitable for various environments such as open environments (such as airports), complex environments (such as parks, roads, gates and parks) and the like, and is also suitable for severe weather such as heavy foggy days and rainy and snowy days; the target identity recognition rate is high: by means of map area attributes, the starting rule of the program mark track is self-adapted, and therefore the target identity identification accuracy rate is improved; the real-time performance is high: by means of the map information, the target track can be started quickly; allowing for multi-threaded parallel computing. Can be applied to parks, construction sites, crossroads, roads, park entrances and exits, gate machines and the like. If a target track exists in the building area, whether the target track is a pedestrian target or a vehicle track, the target tracking algorithm considers the target track to be a false track, and deletion or delayed report is given. If a pedestrian track is found in the sidewalk area, giving deletion; if a vehicle track is found in the sidewalk area, reporting as soon as possible; if the target track of the motor vehicle appears in the motor vehicle driving area, the track does not need to be paid attention to and deleted, but the track of the pedestrian appears in the motor vehicle driving area, and the track needs to be reported as soon as possible.

Through the above description of the embodiments, those skilled in the art can clearly understand that the method according to the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but the former is a better implementation mode in many cases. Based on such understanding, the technical solutions of the present invention may be embodied in the form of a software product, which is stored in a storage medium (e.g., ROM/RAM, magnetic disk, optical disk) and includes instructions for enabling a terminal device (e.g., a mobile phone, a computer, a server, or a network device) to execute the method according to the embodiments of the present invention.

In this embodiment, an identity determining apparatus is further provided, and the apparatus is used to implement the foregoing embodiments and preferred embodiments, and the description already made is omitted. As used below, the term "module" may be a combination of software and/or hardware that implements a predetermined function. Although the means described in the embodiments below are preferably implemented in software, an implementation in hardware, or a combination of software and hardware is also possible and contemplated.

Fig. 12 is a block diagram of an identity determination apparatus according to an embodiment of the present invention, and as shown in fig. 12, the apparatus includes:

a first determining module 1202, configured to determine a motion trajectory of a target object based on radar measurement information of the target object;

a second determining module 1204, configured to determine, based on attribute information of a target map, target attribute information of a target area where the motion trajectory is located, where the target map includes the target area;

a third determining module 1206 for determining an identity of the target object based on the target property information.

In an optional embodiment, before determining the target attribute information of the target area where the motion trail is located based on the attribute information of the target map, the apparatus may be configured to: loading a drawn initial map; rasterizing the initial map; and assigning corresponding node attributes to each map node obtained after rasterizing the target map to obtain the target map, wherein the attribute information of the target map comprises the node attributes corresponding to each map node.

In an alternative embodiment, the apparatus may load the initial map drawn by one of: loading the manually drawn initial map; and loading the initial map generated on line.

In an alternative embodiment, the third determining module 1206 may determine the identity of the target object based on the target attribute information by: determining a region type of the target region based on the target attribute information; determining a measurement rule corresponding to the region type; determining the type of the motion track based on the measurement rule; determining an identity of the target object based on the type of the motion trajectory.

In an alternative embodiment, the third determining module 1206 may determine the characteristic of the motion trajectory based on the measurement rule by: when the measurement rule is determined to be used for starting a first type track, judging whether the motion track meets a first rule corresponding to the first type track; judging whether the motion track is the first type track or not under the condition that the judgment result is that the first rule is met, determining the type of the motion track to be the first type track under the condition that the judgment result is that the motion track is the first type track, executing the operation of judging whether the motion track is the second type track under the condition that the judgment result is not that the motion track is the first type track, and determining the type of the motion track based on the judgment result; under the condition that the judgment result is that the first rule is not satisfied, executing operation of judging whether the motion track is a second type track, and determining the type of the motion track based on the judgment result; wherein the first type of track is different from the second type of track.

In an alternative embodiment, the apparatus may be configured to set the first rule before determining whether the motion trajectory satisfies the first rule corresponding to the first type trajectory; and setting a second rule corresponding to the second type of track.

In an alternative embodiment, the first rule includes at least one of: the method comprises a starting time threshold, a measurement and radar emission area RCS correlation threshold, a radial velocity correlation threshold, a spatial position correlation threshold and a clustering threshold correlation threshold.

In an optional embodiment, before determining whether the motion trajectory satisfies the first rule corresponding to the first type trajectory, when the first type trajectory is a pedestrian trajectory, the apparatus may be further configured to match a measurement included in the motion trajectory with the first type trajectory to determine a first target measurement; storing the first target measurement into a first predetermined sequence to obtain a first target sequence; the third determining module 1206 may determine whether the motion trajectory satisfies a first rule corresponding to the first type trajectory by: and judging whether the motion track meets a first rule corresponding to the first type track or not based on the first target sequence.

In an optional embodiment, before determining whether the motion trajectory satisfies a first rule corresponding to the first type trajectory, when the first type trajectory is a vehicle trajectory, the device may be further configured to perform clustering processing on measurements in a current frame, and determine, based on a clustering result, a second target measurement belonging to the same vehicle among the measurements included in the motion trajectory; the third determining module 1206 may determine whether the motion trajectory satisfies a first rule corresponding to the first type trajectory by: and judging whether the motion track meets a first rule corresponding to the first type track or not based on the second target measurement.

In an alternative embodiment, the apparatus may perform the clustering process on the metrics in the current frame by: and correlating all the measurements included in the current frame pairwise, and grouping the correlated measurements meeting a preset clustering threshold into a group.

In an optional embodiment, the apparatus may be further configured to determine, before correlating all measurements included in the current frame two by two, at least one of the following thresholds included in the clustering threshold according to a distance between the measurements to the radar: a distance correlation threshold between measurements, an RCS correlation threshold between measurements, and a radial velocity correlation threshold between measurements.

In an alternative embodiment, the third determining module 1206 may implement the operation of determining whether the motion trail is the second type trail, and determine the type of the motion trail based on the determination result by: judging whether the motion track meets a second rule corresponding to the second type track; judging whether the motion trail is the second type trail or not under the condition that the judgment result is that the second rule is satisfied, determining the type of the motion trail as the second type trail under the condition that the judgment result is that the motion trail is the second type trail, and determining the type of the motion trail as a false trail under the condition that the judgment result is that the motion trail is not the second type trail; and under the condition that the second rule is not satisfied as a result of the judgment, repeatedly executing the operations of determining the target attribute information and determining the identity information of the target object based on the next frame image of the current frame.

In an optional embodiment, the apparatus may be further configured to, before determining whether the motion trajectory satisfies a second rule corresponding to the second type of trajectory, cyclically determine whether each measurement point included in the motion trajectory is capable of forming the first type of trajectory; in the event that it is determined that the first type of track cannot be formed, performing the following: when the second type track is determined to be a vehicle track, clustering the measurement in the current frame, and determining a second target measurement belonging to the same vehicle in the measurements included in the motion track based on a clustering result; the third determining module 1206 may determine whether the motion trajectory satisfies a second rule corresponding to the second type of trajectory by: and judging whether the motion track meets a second rule corresponding to the second type track or not based on the second target measurement.

In an optional embodiment, the apparatus may be further configured to, before determining whether the motion trajectory satisfies a second rule corresponding to the second type of trajectory, circularly determine whether each measurement point included in the motion trajectory is capable of forming the first type of trajectory; in the event that it is determined that the first type of track cannot be formed, performing the following: matching the measurement included in the motion track with the second type track to determine a second target measurement; storing the second target measurement into a second predetermined sequence to obtain a second target sequence; the third determining module 1206 may determine whether the motion trajectory satisfies a second rule corresponding to the second type of trajectory by: and judging whether the motion track meets a second rule corresponding to the second type track or not based on the second target sequence.

In an alternative embodiment, the third determining module 1206 may determine whether the motion trajectory is the first type trajectory by: judging whether the motion track is the first type track based on at least one of the following judgment: RCS interval, radial velocity interval, first type of measurement position fluctuation interval.

In an alternative embodiment, the third determining module 1206 may determine the metrology rule corresponding to the area type by: under the condition that the area type is a pedestrian path area, determining a measurement rule corresponding to the area type as measuring a pedestrian track first and then measuring a vehicle track; under the condition that the area type is a vehicle driving area, determining a measurement rule corresponding to the area type as measuring a vehicle track first and then measuring a pedestrian track; and under the condition that the area type is an unknown area, determining that the measurement rule corresponding to the area type is to simultaneously measure the vehicle track and the pedestrian track.

In an optional embodiment, the apparatus may be further configured to end the operation of determining the identity of the target object when it is determined that the area type is another area type; wherein the other zone types are zone types other than a sidewalk zone, a vehicle driving zone, and an unknown zone.

It should be noted that the above modules may be implemented by software or hardware, and for the latter, the following may be implemented, but not limited to: the modules are all positioned in the same processor; alternatively, the modules are respectively located in different processors in any combination.

Embodiments of the present invention also provide a computer-readable storage medium having a computer program stored thereon, wherein the computer program is arranged to perform the steps of any of the above-mentioned method embodiments when executed.

Alternatively, in the present embodiment, the above-mentioned computer-readable storage medium may be configured to store a computer program for executing the steps of:

s1, determining a motion track of a target object based on radar measurement information of the target object;

s2, determining target attribute information of a target area where the motion trail is located based on attribute information of a target map, wherein the target map comprises the target area;

and S3, determining the identity of the target object based on the target attribute information.

Optionally, in this embodiment, the computer-readable storage medium may include, but is not limited to: various media capable of storing computer programs, such as a usb disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic disk, or an optical disk.

Embodiments of the present invention also provide an electronic device comprising a memory having a computer program stored therein and a processor arranged to run the computer program to perform the steps of any of the above method embodiments.

Optionally, the electronic apparatus may further include a transmission device and an input/output device, wherein the transmission device is connected to the processor, and the input/output device is connected to the processor.

Optionally, in this embodiment, the processor may be configured to execute the following steps by a computer program:

Optionally, the specific examples in this embodiment may refer to the examples described in the above embodiments and optional implementation manners, and this embodiment is not described herein again.

It will be apparent to those skilled in the art that the modules or steps of the present invention described above may be implemented by a general purpose computing device, they may be centralized on a single computing device or distributed across a network of multiple computing devices, and alternatively, they may be implemented by program code executable by a computing device, such that they may be stored in a storage device and executed by a computing device, and in some cases, the steps shown or described may be performed in an order different than that described herein, or they may be separately fabricated into individual integrated circuit modules, or multiple ones of them may be fabricated into a single integrated circuit module. Thus, the present invention is not limited to any specific combination of hardware and software.

The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. An identity determination method, comprising:

determining a motion track of a target object based on radar measurement information of the target object;

determining target attribute information of a target area where the motion trail is located based on attribute information of a target map, wherein the target map comprises the target area;

determining an identity of the target object based on the target attribute information;

determining the identity of the target object based on the target attribute information comprises: determining a region type of the target region based on the target attribute information; determining a measurement rule corresponding to the area type; determining the type of the motion track based on the measurement rule; determining an identity of the target object based on the type of the motion trajectory;

determining the type of the motion trajectory based on the metrology rules comprises: when the measurement rule is determined to be used for starting a first type track, judging whether the motion track meets a first rule corresponding to the first type track or not to obtain a judgment result; judging whether the motion track is the first type track or not to obtain a judgment result; and determining the type of the motion trail based on the judgment result and the judgment result.

2. The method of claim 1, wherein prior to determining the target attribute information of the target area in which the motion trajectory is located based on the attribute information of the target map, the method further comprises:

loading a drawn initial map;

rasterizing the initial map;

and assigning corresponding node attributes to each map node obtained after rasterizing the target map to obtain the target map, wherein the attribute information of the target map comprises the node attributes corresponding to each map node.

3. The method of claim 2, wherein loading the initial map as drawn comprises one of:

loading the manually drawn initial map;

and loading the initial map generated on line.

4. The method of claim 1, wherein determining the type of the motion trajectory based on the determination and the determination comprises:

determining the type of the motion track as the first type track when the judgment result is that the first rule is met and the judgment result is that the motion track is the first type track, executing operation of judging whether the motion track is a second type track when the judgment result is that the first rule is met and the judgment result is that the motion track is not the first type track, and determining the type of the motion track based on the judgment result;

under the condition that the judgment result is that the first rule is not satisfied, executing operation of judging whether the motion track is a second type track, and determining the type of the motion track based on the judgment result;

wherein the first type of track is different from the second type of track.

5. The method of claim 4, wherein prior to determining whether the motion trajectory satisfies a first rule corresponding to the first type of trajectory, the method further comprises at least one of:

setting the first rule;

and setting a second rule corresponding to the second type of track.

6. The method of claim 1 or 5, wherein the first rule comprises at least one of:

the method comprises a starting time threshold, a measurement and radar emission area RCS correlation threshold, a radial velocity correlation threshold, a spatial position correlation threshold and a clustering threshold correlation threshold.

7. The method of claim 1,

before determining whether the motion trajectory satisfies a first rule corresponding to the first type trajectory, the method further includes: when the first type track is a pedestrian track, matching measurement included in the motion track with the first type track to determine a first target measurement; storing the first target measurement into a first predetermined sequence to obtain a first target sequence;

determining whether the motion trajectory satisfies a first rule corresponding to the first type trajectory includes: and judging whether the motion track meets a first rule corresponding to the first type track or not based on the first target sequence.

8. The method of claim 1,

before determining whether the motion trajectory satisfies a first rule corresponding to the first type trajectory, the method further includes: when the first type track is a vehicle track, clustering the measurement in the current frame, and determining a second target measurement belonging to the same vehicle in the measurements included in the motion track based on a clustering result;

judging whether the motion track meets a first rule corresponding to the first type track comprises the following steps: and judging whether the motion track meets a first rule corresponding to the first type track or not based on the second target measurement.

9. The method of claim 8, wherein clustering measurements in a current frame comprises:

and correlating all the measurements included in the current frame pairwise, and grouping the correlated measurements meeting a preset clustering threshold into a group.

10. The method of claim 9, wherein before correlating all measurements included in the current frame two by two, the method further comprises:

according to the distance between the measured radar and the radar, determining at least one of the following thresholds included in the clustering threshold:

a distance correlation threshold between measurements, an RCS correlation threshold between measurements, and a radial velocity correlation threshold between measurements.

11. The method of claim 4, wherein performing the operation of determining whether the motion trajectory is a second type of trajectory and determining the type of the motion trajectory based on the determination result comprises:

judging whether the motion track meets a second rule corresponding to the second type track;

judging whether the motion trail is the second type trail or not under the condition that the judgment result meets the second rule, determining the type of the motion trail as the second type trail under the condition that the judgment result is the second type trail, and determining the type of the motion trail as a false trail under the condition that the judgment result is not the second type trail;

and under the condition that the second rule is not satisfied in the judgment result, repeatedly executing the operations of determining the target attribute information and determining the identity information of the target object based on the next frame image of the current frame.

12. The method of claim 11,

before determining whether the motion trajectory satisfies a second rule corresponding to the second type of trajectory, the method further includes: circularly judging whether each measuring point in the motion trail can form the first type trail or not; in the event that it is determined that the first type of track cannot be formed, performing the following: when the second type track is determined to be a vehicle track, clustering the measurement in the current frame, and determining a second target measurement belonging to the same vehicle in the measurements included in the motion track based on a clustering result;

judging whether the motion track meets a second rule corresponding to the second type track comprises the following steps: and judging whether the motion track meets a second rule corresponding to the second type track or not based on the second target measurement.

13. The method of claim 11,

before determining whether the motion trajectory satisfies a second rule corresponding to the second type of trajectory, the method further includes: circularly judging whether each measuring point in the motion trail can form the first type trail or not; in the event that it is determined that the first type of track cannot be formed, performing the following: matching the measurement included in the motion track with the second type track to determine a second target measurement; storing the second target measurement in a second predetermined sequence to obtain a second target sequence;

judging whether the motion track meets a second rule corresponding to the second type track comprises the following steps: and judging whether the motion track meets a second rule corresponding to the second type track or not based on the second target sequence.

14. The method of claim 1, wherein determining whether the motion profile is the first type of profile comprises:

determining whether the motion trajectory is the first type trajectory based on at least one of:

RCS interval, radial velocity interval, first type measurement position fluctuation interval.

15. The method of claim 1, wherein determining the metrology rule corresponding to the region type comprises:

under the condition that the area type is a pedestrian path area, determining a measurement rule corresponding to the area type as measuring a pedestrian track first and then measuring a vehicle track;

under the condition that the area type is a vehicle driving area, determining a measurement rule corresponding to the area type as measuring a vehicle track first and then measuring a pedestrian track;

and under the condition that the area type is an unknown area, determining the measurement rule corresponding to the area type to simultaneously measure the vehicle track and the pedestrian track.

16. The method according to claim 1, wherein when the region type is determined to be another region type, the operation of determining the identity of the target object is ended;

wherein the other area types are area types other than a sidewalk area, a vehicle driving area, and an unknown area.

17. An identity determination device, comprising:

the device comprises a first determination module, a second determination module and a third determination module, wherein the first determination module is used for determining the motion track of a target object based on radar measurement information of the target object;

the second determination module is used for determining target attribute information of a target area where the motion trail is located based on attribute information of a target map, wherein the target map comprises the target area;

a third determining module for determining an identity of the target object based on the target attribute information;

the third determination module enables determining the identity of the target object based on the target attribute information by: determining a region type of the target region based on the target attribute information; determining a measurement rule corresponding to the area type; determining the type of the motion track based on the measurement rule; determining an identity of the target object based on the type of the motion trajectory;

the third determination module determines the type of the motion trajectory based on the measurement rule by: determining the type of the motion trajectory based on the metrology rules comprises: when the measurement rule is determined to be used for starting a first type track, judging whether the motion track meets a first rule corresponding to the first type track or not to obtain a judgment result; judging whether the motion track is the first type track or not to obtain a judgment result; and determining the type of the motion trail based on the judgment result and the judgment result.

18. A computer-readable storage medium, in which a computer program is stored, wherein the computer program is arranged to perform the method of any of claims 1 to 16 when executed.

19. An electronic device comprising a memory and a processor, wherein the memory has a computer program stored therein, and the processor is configured to execute the computer program to perform the method of any of claims 1 to 16.