Target Tracking Method Based on Millimeter Wave Radar

Abstract

The present application discloses a target tracking method based on millimeter-wave radar, the method comprising: obtaining position information of a first target, the position information of the first target being obtained by millimeter-wave radar detection; determining a target area to which the first target belongs based on the position information and the division of a preset monitoring area, the target area being a sub-area in the monitoring area; controlling a camera in the target area to adjust a monitoring direction based on the azimuth information, and to adjust a focal length based on the distance information, so as to capture a facial image of the first target.

Description

Technical Field

[0001] The present invention relates to the field of monitoring technology, and in particular to a target tracking method based on millimeter wave radar. Background Art

[0002] In tasks such as train stations and bus stations that require face recognition of key people, in order to improve the accuracy of face recognition, the face images taken by the camera must have a certain degree of clarity. However, the area that the camera needs to monitor is usually large, and it is difficult for the camera to have the same clarity at both long and short distances and to be able to focus.

[0003] Common autofocus methods include active and passive. Active laser ranging autofocus uses infrared laser to detect the distance from the target to the camera to focus. It is easily affected by light and has a short working distance and small range. Passive phase detection autofocus has high requirements on light and hardware performance.

[0004] It can be seen that the current positioning and tracking solutions are not accurate and fast enough, and the image accuracy collected by the camera is not high enough. Summary of the invention

[0005] The present application provides a target tracking method based on millimeter wave radar.

[0006] In a first aspect, a target tracking method based on millimeter wave radar is provided, the method comprising:

[0007] Acquiring position information of a first target, where the position information of the first target is obtained through millimeter wave radar detection;

[0008] Determine, according to the location information and the division of the preset monitoring area, a target area to which the first target belongs, wherein the target area is a sub-area in the monitoring area;

[0009] The camera of the target area is controlled to adjust the monitoring direction according to the orientation information, and to adjust the focal length according to the distance information, so as to collect the facial image of the first target.

[0010] In a second aspect, a target tracking device is provided, comprising:

[0011] An acquisition module, used to acquire position information of a first target, where the position information of the first target is obtained through millimeter wave radar detection;

[0012] A determination module, configured to determine a target area to which the first target belongs according to the location information and a preset division of a monitoring area, wherein the target area is a sub-area in the monitoring area;

[0013] A control module is used to control the camera of the target area to adjust the monitoring direction according to the orientation information and adjust the focal length according to the distance information to collect the facial image of the first target.

[0014] In a third aspect, an electronic device is provided, comprising a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of the target tracking method based on millimeter wave radar as described in the first aspect.

[0015] In a fourth aspect, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores one or more instructions, wherein the one or more instructions are suitable for being loaded by a processor and executing the steps of the first aspect and any possible implementation thereof.

[0016] An embodiment of the present application provides a target tracking method based on millimeter-wave radar, which obtains position information of a first target by millimeter-wave radar detection; determines a target area to which the first target belongs based on the position information and a preset division of a monitoring area, wherein the target area is a sub-area in the monitoring area; controls a camera in the target area to adjust a monitoring direction based on the azimuth information and a focal length based on the distance information to capture a facial image of the first target, and can utilize the azimuth and distance information of each target located by the millimeter-wave radar to control the camera to perform fast, automatic and precise focusing to capture clearer images, thereby facilitating timely and high-precision face recognition. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the background technology, the drawings required for use in the embodiments of the present application or the background technology will be described below.

[0018] Figure 1 A schematic diagram of a target tracking method based on millimeter wave radar provided in an embodiment of the present application;

[0019] Figure 2 A flowchart of another target tracking method based on millimeter wave radar provided in an embodiment of the present application;

[0020] Figure 3 A schematic diagram of the structure of a target tracking device provided in an embodiment of the present application;

[0021] Figure 4 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0022] In order to enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present application.

[0023] The terms "first", "second", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices.

[0024] Reference to "embodiments" in this application means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described in this application may be combined with other embodiments.

[0025] The millimeter wave radar mentioned in the embodiments of the present application is a radar that works in the millimeter wave band (millimeter wave). Usually, millimeter waves refer to the 30-300 GHz frequency domain (wavelength is 1-10 mm). The wavelength of millimeter waves is between microwaves and centimeter waves, so millimeter wave radar has some advantages of both microwave radar and photoelectric radar.

[0026] The embodiments of the present application are described below in conjunction with the drawings in the embodiments of the present application.

[0027] See also Figure 1 , Figure 1 : is a flow chart of a target tracking method based on millimeter wave radar provided in an embodiment of the present application. The method may include:

[0028] 101. Obtain position information of a first target, where the position information of the first target is obtained through millimeter wave radar detection.

[0029] The execution subject of the embodiment of the present application may be a target tracking device, which may be an electronic device, including a terminal device or a server, such as a desktop computer. In some embodiments, the terminal device may also be other portable devices such as a laptop computer or a tablet computer. In an optional implementation, it may be implemented by a software module, which may be called a monitoring platform or system.

[0030] In the embodiment of the present application, the millimeter wave radar can track the target and obtain the position information of the target, which can be a moving target person. The millimeter wave radar can track one or more targets, and the first target can be any target tracked by the radar.

[0031] The above-mentioned location information is information that identifies the specific location of the target, such as coordinates, and may specifically include two aspects: direction information and distance information.

[0032] In order to achieve target tracking and face image acquisition in the embodiments of the present application, a specific processing method of first detecting and tracking the target using millimeter wave radar is described in subsequent embodiments.

[0033] 102. Determine the target area to which the first target belongs based on the position information and the distance information, as well as the division of the preset monitoring area, where the target area is a sub-area in the monitoring area.

[0034] Specifically, the monitoring area can be divided in advance. The monitoring area can be divided into multiple sub-areas as needed, such as partitioning for monitoring. After obtaining the location information of the first target, the sub-area where the first target is located is further determined.

[0035] In an optional implementation, the above method further includes:

[0036] Before determining the target area to which the first target belongs according to the position information and the distance information and the division of the preset monitoring area, wherein the target area is a sub-area in the monitoring area, the method further includes:

[0037] The monitoring area is divided into a plurality of sub-areas according to the rotatable angle and zoom range of the camera in the monitoring area, and the division of the preset monitoring area is determined.

[0038] In the embodiment of the present application, the rotation angle and zoom range of each camera in the monitoring area can be considered, so as to adaptively divide the monitoring area into multiple sub-areas, so that each camera can monitor all parts of the monitoring area as comprehensively and clearly as possible. The sub-area division can also be planned according to conditions such as geographical environment and community requirements, and the embodiment of the present application does not limit this.

[0039] Optionally, the correspondence between each sub-area identifier and the camera identifier can be stored, that is, the camera corresponding to each sub-area is determined, so that the data of the corresponding camera can be directly called when the sub-area monitoring needs to be viewed, and efficient management of multiple cameras can be facilitated.

[0040] 103. Control and adjust the monitoring direction and focal length of the camera in the target area according to the position information to collect the facial image of the first target.

[0041] After determining the target area to which the first target belongs, the platform can send a control command to the camera in the target area to control the camera in the target area to focus. Specifically, the monitoring direction and focal length of the camera can be adjusted according to the obtained position information to assist in achieving accurate focus on the first target.

[0042] In an optional implementation, after the above step 103, the above method further includes:

[0043] Perform feature extraction on the above face image to obtain online face features;

[0044] Matching the online facial features with the facial feature templates in the local facial feature library to obtain the similarity between the online facial features and the facial feature templates in the local facial feature library;

[0045] Obtaining the highest similarity value among the above similarities; if the highest similarity value is greater than a preset similarity threshold, the match is successful;

[0046] The character information corresponding to the facial feature template with the highest similarity value is obtained, and the character information corresponding to the matching facial feature template is output.

[0047] In the embodiment of the present application, the above-mentioned local face feature library can be pre-set, and the local face feature library can store multiple face feature templates, which can be understood as the face features of the person to be monitored. For the face image collected by the camera, feature extraction can be performed through a preset feature extraction network to obtain the corresponding face features, which are called online face features; then the online face features are matched with the face feature templates in the local face feature library to obtain the similarity between the online face features and the face feature templates in the local face feature library, and the highest similarity value is selected from them. If the highest similarity value is greater than the preset similarity threshold, the identity of the first target can be determined. For example, if the online face feature a of the first target has the highest similarity value with the face feature template b of person X, and is higher than the preset similarity threshold, it can be determined that the first target and person X are the same person.

[0048] Through the above steps, the position of the moving target can be accurately located, the camera can be controlled to focus quickly to obtain a clear image, face recognition and comparison can be performed, and the person to be monitored can be quickly found, which has broad application prospects.

[0049] In an optional implementation, the location information includes orientation information and first distance information, and the step 103 includes:

[0050] Controlling and adjusting the monitoring direction of the camera of the target area according to the above-mentioned position information, determining the focusing distance according to the above-mentioned first distance information, and controlling and adjusting the focal length of the camera of the target area according to the above-mentioned focusing distance, so as to control the above-mentioned camera to continuously obtain image data containing the above-mentioned first target;

[0051] Image data containing the first target is acquired, and a face image of the first target is extracted from the image data.

[0052] Specifically, the position information obtained by radar detection may include azimuth information and first distance information. The azimuth information and the first distance information may be obtained relative to a reference point P, and therefore may be converted on the platform. The platform records the position information of each camera, and therefore may output the position information (including direction and distance) of the first target relative to the camera to be adjusted based on the above existing information, thereby controlling the adjustment of the camera and focusing on the first target.

[0053] On this basis, the camera can periodically capture images or continuously record videos, that is, the image data of the first target mentioned above. When target recognition is required, the face image can be extracted based on the image data for face recognition processing.

[0054] Obtaining image data containing the first target, extracting the face image of the first target from the image data In specific applications, such as at train stations and bus stations, face recognition of key persons is required. In order to improve the accuracy of face recognition, the face image captured by the camera is required to have a certain clarity. However, the area that the camera needs to monitor is usually large, and it is difficult for the camera to have the same clarity at both long and short distances, which requires the camera to automatically focus.

[0055] The commonly used active laser ranging autofocus can focus by detecting the distance from the target to the camera through infrared laser, but it is easily affected by light, has a short effective distance and a small range; while the passive phase detection autofocus method has very high requirements on light and hardware performance.

[0056] The target tracking method based on millimeter-wave radar in the embodiment of the present application has the advantages of not requiring joint calibration of the camera and radar, fast detection speed, long range, not easily affected by light and can be used all day long, and compared with general methods that can only locate one target at a time, radar can locate multiple targets at the same time. On this basis, using artificial intelligence algorithms - face detection and recognition networks, people in the monitoring area can be accurately tracked, and the false detection rate and missed detection rate of face recognition can be improved.

[0057] In an embodiment of the present application, a target tracking method based on millimeter-wave radar is provided, by acquiring position information of a first target, the position information of the first target being obtained by millimeter-wave radar detection; according to the position information, and the division of a preset monitoring area, a target area to which the first target belongs is determined, the target area being a sub-area in the monitoring area; a camera in the target area is controlled to adjust the monitoring direction according to the azimuth information, and to adjust the focal length according to the distance information, so as to collect a facial image of the first target; the azimuth and distance information of each target located by the millimeter-wave radar can be used to control the camera to perform fast automatic and precise focusing, collect clearer images, and facilitate timely and high-precision face recognition.

[0058] Figure 2 A flow chart of another method for obtaining target location information by millimeter wave radar detection provided in an embodiment of the present application, such as Figure 2 As shown, the method includes:

[0059] 201. Perform moving target display processing on the to-be-processed signal of the preset frequency band received by the millimeter-wave radar, filter out static detection points, obtain a first signal, and then process the first signal based on fast Fourier transform and beamforming to determine multiple detection points.

[0060] Moving target indication radar (MTI) is a type of radar that uses the Doppler shift of echoes caused by moving targets to distinguish moving targets from fixed targets and uses MTI filters to filter out background clutter.

[0061] The signal of the above-mentioned preset frequency band can be a medium frequency signal in a broad sense. The medium frequency signal received by the millimeter wave can be processed by MTI, static detection points can be filtered out, and fast Fourier transform (FFT) and beamforming (beamform) processing can be performed to detect moving detection points (i.e., x, y coordinate points). At this time, there may be multiple detection points belonging to the same target among these detection points, or there may be some clutter points such as false detection and noise, which need to be merged and filtered out.

[0062] In an optional implementation manner, the processing of the first signal based on fast Fourier transform and beamforming to determine multiple detection points includes:

[0063] Performing fast Fourier transform and beamforming processing on the first signal to calculate a plurality of angle data and distance data;

[0064] The position coordinates corresponding to the plurality of detection points are calculated according to the plurality of angle data and distance data to determine the plurality of detection points.

[0065] Specifically, the following steps may be included:

[0066] Sample the intermediate frequency input signal signal;

[0067] Perform MTI processing to obtain an output signal s_mti of a filtered static target;

[0068] Perform FFT and beamform on the signal s_mti to calculate the angle a and distance R of the moving target, and the position coordinates of the moving target (x, y) = (R*sin(a), R*cos(a)) can be calculated.

[0069] 202. Filter out clutter points from the multiple detection points, and merge detection points belonging to the same target.

[0070] Optionally, a filtering algorithm can be used, combined with gate threshold judgment and interconnection probability judgment, to filter out clutter points, merge detection points that may belong to the same target, and update and track the motion status of the detection points in real time. In actual work, the target may be lost due to occlusion, insufficient target reflection intensity, etc., or the same target may be tracked repeatedly. Track management is required to ensure stable tracking of the target.

[0071] In an optional implementation, filtering out clutter points from the plurality of detection points includes:

[0072] The preset filtering algorithm is used to filter the above-mentioned multiple detection points and calculate the wave gate value;

[0073] Traverse all detection points and calculate the gate between each detection point and the signal of each tracked target;

[0074] A first detection point at which the gate is smaller than a preset gate threshold is obtained, a mapping relationship between the first detection point and the tracked target is determined, and clutter points other than the first detection point are filtered out.

[0075] Optionally, the above-mentioned preset filtering algorithm may include a second-order Karman filtering algorithm.

[0076] The above wave gate is calculated as follows:

[0077] Wave gate = v' / S*v, where v is the new information, which is equal to the difference between the measured value at the current moment and the predicted value obtained by Karman filtering at the current moment when the tracking target is being tracked, and S is the new information covariance calculated during the Karman filtering process.

[0078] The above wave gate judgment is as follows:

[0079] Set a gate threshold, for example, the preset gate threshold is 7 or 10. Traverse all detection points, that is, all measurement values, calculate the gate between it and all tracked targets, and when the calculated gate is less than the preset gate threshold, the detection point can be considered as a measured point belonging to the tracked target.

[0080] Optionally, the above method further includes:

[0081] If there are at least two detection points whose gates of signals with the first target are smaller than a preset gate threshold, calculate the interconnection probability of the at least two detection points, where the interconnection probability of the at least two detection points is a weighted average of the positions of the at least two detection points;

[0082] The position information of the first target is updated using the position weighted average value.

[0083] By calculating the above interconnection probability, it can be used to update the current position of the tracked target.

[0084] 203. Update and track the motion status of the above detection points.

[0085] 204. Analyze the motion states of the detection points, and determine the detection points among the detection points whose motion states are stable as the detection points corresponding to the multiple tracked targets.

[0086] 205. Obtain the position information of the detection point corresponding to each tracked target as the position information of the tracked target.

[0087] The radar signal detection and processing process can be repeated to update the position information of the detection point. In the embodiment of the present application, a track management algorithm can be used, and for the detection point of stable tracking, it can be determined to become a tracked target. The position information of the detection point is the position information of the target. Optionally, if the tracked target is lost and the loss duration reaches the timeout duration, or the conditions of the aforementioned signal processing are not met, it can be determined as unstable tracking.

[0088] In an optional implementation, the above method further includes:

[0089] When the tracked target is lost, predicting the track of the tracked target based on the existing tracked track of the tracked target until the time when the tracked target is lost and the timeout is detected and the tracking is cancelled;

[0090] Comparing the trajectories of the plurality of tracked targets to determine whether there is a situation where the same tracked target is tracked repeatedly;

[0091] If there is repeated tracking of the same tracked target, one target tracking task is selected from the repeated tracking tasks to be retained, and the tasks other than the target tracking task in the repeated tracking tasks are canceled.

[0092] When the tracked target cannot be detected due to occlusion or other reasons, the real-time position of the tracked target that has lost detection can be predicted based on the existing tracking trajectory by using trajectory extrapolation until the target is not detected and the tracking is canceled due to timeout. By comparing the correlation of the motion trajectory of the tracked target, it is determined whether the same target is tracked repeatedly. Further, for the repeatedly tracked targets, the best selection can be made according to the tracking time, such as choosing to keep the one with the longest tracking time and canceling the remaining repeated tracking.

[0093] in, Figure 1 In the embodiment shown, the first target may be one of the tracked targets described above, namely Figure 1 Step 101 of the illustrated embodiment: obtaining the location information of the first target, which may be specifically performed by Figure 2 The method in the illustrated embodiment is implemented and will not be described in detail here.

[0094] The target tracking method based on millimeter-wave radar in the embodiment of the present application can utilize radar detection to assist the camera in quickly focusing on moving targets in applications such as suspect inspection and searching for missing persons, thereby effectively improving the missed detection rate and false detection rate of face recognition and effectively improving the crime-solving rate.

[0095] Based on the description of the above-mentioned target tracking method embodiment based on millimeter wave radar, the embodiment of the present application also discloses a target tracking device. Figure 3 A schematic diagram of the structure of a target tracking device provided in an embodiment of the present application is shown in Figure 3. The target tracking device 300 includes:

[0096] An acquisition module 310 is used to acquire position information of a first target, where the position information of the first target is obtained through millimeter wave radar detection;

[0097] A determination module 320, configured to determine a target area to which the first target belongs according to the location information and a preset division of a monitoring area, wherein the target area is a sub-area in the monitoring area;

[0098] The control module 330 is used to control the camera in the target area to adjust the monitoring direction according to the orientation information, and adjust the focal length according to the distance information, so as to collect the facial image of the first target.

[0099] In one embodiment, Figure 1 or Figure 2 The method in the illustrated embodiment may be executed by the target tracking device 300 and will not be described in detail here.

[0100] The present application also discloses an electronic device. Figure 4 The electronic device 400 includes a memory 401 and a processor 402, wherein the memory 401 and the processor 402 may be connected via a bus or other means.

[0101] The computer storage medium can be stored in the memory 401 of the electronic device 400. The computer storage medium is used to store a computer program. The computer program includes program instructions. The processor 402 is used to execute the program instructions stored in the computer storage medium. The processor 402 (or CPU (Central Processing Unit)) is the computing core and control core of the electronic device 400. It is suitable for implementing one or more instructions, and is specifically suitable for loading and executing one or more instructions to implement corresponding method flows or corresponding functions. In one embodiment, the processor 402 of the embodiment of the present application can be used to perform a series of processes, including such as Figure 1 or Figure 2 The various steps involved in the method shown, etc.

[0102] The embodiment of the present application also provides a computer storage medium (Memory), which is a memory device in an electronic device for storing programs and data. It is understandable that the computer storage medium here can include both built-in storage media in electronic devices and, of course, extended storage media supported by electronic devices. The computer storage medium provides a storage space that stores the operating system of the electronic device. In addition, one or more instructions suitable for being loaded and executed by a processor are also stored in the storage space, and these instructions can be one or more computer programs (including program codes). It should be noted that the computer storage medium here can be a high-speed RAM memory, or a non-volatile memory, such as at least one disk storage; optionally, it can also be at least one computer storage medium located away from the aforementioned processor.

[0103] In one embodiment, one or more instructions stored in a computer storage medium may be loaded and executed by a processor to implement the corresponding steps in the above embodiment; in a specific implementation, one or more instructions in a computer storage medium may be loaded and executed by a processor. Figure 1 any step involved in the method shown, or Figure 2 Any steps involved in the method shown will not be repeated here.

[0104] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described devices and modules can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0105] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the division of the module is only a logical function division, and there may be other division methods in actual implementation, for example, multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. The mutual coupling, direct coupling, or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or modules, which can be electrical, mechanical or other forms.

[0106] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical modules, that is, they may be located in one place or distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0107] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function according to the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transmitted through the computer-readable storage medium. The computer instructions can be transmitted from a website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (digital subscriber line, DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media integrations. The available medium may be a read-only memory (ROM), or a random access memory (RAM), or a magnetic medium, such as a floppy disk, a hard disk, a tape, a magnetic disk, or an optical medium, such as a digital versatile disc (DVD), or a semiconductor medium, such as a solid state disk (SSD), etc.

Claims

1. A target tracking method based on millimeter wave radar, characterized in that: The method comprises: Acquire position information of a first target, where the position information of the first target is obtained through millimeter wave radar detection, and the first target is one of multiple tracked targets; Determine, according to the location information and the division of the preset monitoring area, a target area to which the first target belongs, wherein the target area is a sub-area in the monitoring area; Controlling and adjusting the monitoring direction and focal length of the camera in the target area according to the position information to collect the facial image of the first target; The method for obtaining the position information of the first target by the millimeter wave radar detection includes: The signal to be processed in the preset frequency band received by the millimeter-wave radar is subjected to moving target display processing, static detection points are filtered out, a first signal is obtained, and the first signal is processed based on fast Fourier transform and beamforming to determine a plurality of detection points; clutter points are filtered out from the plurality of detection points, and detection points belonging to the same target are merged; the motion state of the detection points is updated and tracked; the motion state of the detection points is analyzed, and the detection points with stable motion state among the detection points are determined as the detection points corresponding to the plurality of tracked targets; the position information of the detection point corresponding to each tracked target is obtained as the position information of the tracked target; The processing of the first signal based on fast Fourier transform and beamforming to determine a plurality of detection points includes: Performing fast Fourier transform and beamforming processing on the first signal to calculate a plurality of angle data and distance data; calculating the position coordinates corresponding to the plurality of detection points according to the plurality of angle data and distance data to determine the plurality of detection points; The filtering out clutter points from the multiple detection points includes: The plurality of detection points are filtered using a preset filtering algorithm to calculate a gate value; all detection points are traversed to calculate a gate between each detection point and a signal of each tracked target; the first detection point whose gate is less than a preset gate threshold is obtained, a mapping relationship between the first detection point and the tracked target is determined, and clutter points other than the first detection point are filtered out.

2. The target tracking method based on millimeter wave radar according to claim 1, characterized in that: The method further comprises: If there are at least two detection points whose gates of signals with the first target are smaller than a preset gate threshold, calculate the interconnection probability of the at least two detection points, where the interconnection probability of the at least two detection points is a weighted average of the positions of the at least two detection points; The position information of the first target is updated using the position weighted average value.

3. The target tracking method based on millimeter wave radar according to claim 2, characterized in that: The method further comprises: When the tracked target is lost, predicting the track of the tracked target based on the existing tracking track of the tracked target until the moment when the tracked target is lost and the timeout is detected and the tracking is cancelled; Comparing the trajectories of the plurality of tracked targets to determine whether there is a situation where the same tracked target is tracked repeatedly; If there is repeated tracking of the same tracked target, a target tracking task is selected from the repeated tracking tasks to be retained, and the tasks other than the target tracking task in the repeated tracking tasks are canceled.

4. The target tracking method based on millimeter wave radar according to claim 1, characterized in that: The method further comprises: Extracting features from the face image to obtain online face features; Matching the online facial features with the facial feature templates in the local facial feature library to obtain the similarity between the online facial features and the facial feature templates in the local facial feature library; Obtaining a highest similarity value among the similarities, and if the highest similarity value is greater than a preset similarity threshold, the match is successful; The character information corresponding to the facial feature template with the highest similarity value is obtained, and the character information corresponding to the facial feature template matching the facial feature template with the highest similarity value is output.

5. The target tracking method based on millimeter wave radar according to claim 1, characterized in that: The position information includes orientation information and first distance information, and the controlling and adjusting the monitoring direction and focal length of the camera of the target area according to the position information includes: Controlling and adjusting the monitoring direction of the camera of the target area according to the orientation information, determining the focusing distance according to the first distance information, and controlling and adjusting the focal length of the camera of the target area according to the focusing distance, so as to control the camera to continuously acquire image data containing the first target; Image data containing the first target is acquired, and a facial image of the first target is extracted from the image data.

6. The target tracking method based on millimeter wave radar according to claim 1, characterized in that: The method further comprises: Before determining, based on the location information and the division of the preset monitoring area, a target area to which the first target belongs, wherein the target area is a sub-area in the monitoring area, the method further includes: The monitoring area is divided into a plurality of sub-areas according to the rotatable angle and zoom range of the camera in the monitoring area, and the division of the preset monitoring area is determined.

7. A target tracking device, characterized in that: include: an acquisition module, configured to acquire position information of a first target, the position information of the first target being obtained through millimeter wave radar detection, the first target being one of a plurality of tracked targets, and the position information including azimuth information and first distance information; A determination module, configured to determine a target area to which the first target belongs according to the location information and a preset division of a monitoring area, wherein the target area is a sub-area in the monitoring area; A control module, used for controlling the camera of the target area to adjust the monitoring direction according to the orientation information, and to adjust the focal length according to the first distance information, so as to collect the facial image of the first target; The acquisition module is specifically used to perform moving target display processing on the to-be-processed signal of the preset frequency band received by the millimeter-wave radar, filter out static detection points, obtain a first signal, and then process the first signal based on fast Fourier transform and beamforming to determine multiple detection points; filtering out clutter points from the plurality of detection points, and merging detection points belonging to the same target; Updating and tracking the motion state of the detection point; Analyzing the motion states of the detection points, and determining that the detection points with stable motion states among the detection points are the detection points corresponding to the multiple tracked targets; Acquire the position information of the detection point corresponding to each tracked target as the position information of the tracked target; The acquisition module is specifically used to perform fast Fourier transform and beamforming processing on the first signal to calculate a plurality of angle data and distance data; calculate the position coordinates corresponding to the plurality of detection points according to the plurality of angle data and distance data, and determine the plurality of detection points; The acquisition module is also specifically used to filter the multiple detection points using a preset filtering algorithm to calculate a gate value; traverse all detection points to calculate the gate of the signal of each detection point and each tracked target; obtain the first detection point whose gate is less than a preset gate threshold, determine the mapping relationship between the first detection point and the tracked target, and filter out clutter points other than the first detection point.

8. An electronic device, characterized in that: The method comprises a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of the target tracking method based on millimeter wave radar as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: A computer program is stored, and when the computer program is executed by a processor, the processor executes the steps of the target tracking method based on millimeter wave radar as described in any one of claims 1 to 6.

Images