Target Tracking Method, Device, Equipment and Storage Medium Based on Ultra-Wideband Radar

Abstract

The present application discloses a target tracking method, device, equipment and storage medium based on ultra-wideband radar, belonging to the technical field of environment-assisted living. The method includes: obtaining a radar frame obtained by sampling an echo signal by an ultra-wideband radar; extracting scatter points based on the radar frame to obtain a measurement corresponding to the radar frame, where the measurement refers to the range cell where the scatter point is located, and the measurement corresponds to the scatter point one by one; performing an aggregation process on the measurements corresponding to the radar frame to obtain an aggregated measurement corresponding to the radar frame; determining the position information of at least one target object according to the aggregated measurement corresponding to the radar frame. In the embodiments of the present application, since the measurements are aggregated, the number of measurements is reduced, effectively alleviating the storage pressure of the computer device and reducing the computing overhead of the computer device. In addition, in the embodiments of the present application, by applying the ultra-wideband radar to the detection and tracking of target objects, the user's usage habits are fully considered, which helps to protect the privacy of users.

Description

Technical Field

[0001] The embodiments of the present application relate to the technical field of ambient assisted living, and in particular, to a target tracking method, device, equipment and storage medium based on ultra-wideband radar. Background Art

[0002] An Ambient Assisted Living (AAL) system refers to a modern sensing and transmission device that connects various instruments in a home to an expandable intelligent technology platform, thereby constructing an environment that can be immediately reflected to analyze the status of the home residents, make immediate judgments and responses, etc.

[0003] In an ambient assisted living system, target tracking is a very important link. Through target tracking, the position and speed of the target object can be calculated, and then, combined with certain environmental prior knowledge, the activity level of the target object and the degree of disability can be estimated. In related technologies, target tracking is mainly achieved through cameras and / or intelligent wearable devices. Cameras can collect image and video information of the target object, and intelligent wearable devices can collect information such as the motion state and physical sign state of the target object. After the cameras and / or intelligent wearable devices collect the corresponding information, the information can be transmitted to the computer device on the platform for further analysis and processing. However, for the method of target tracking through cameras, generally, cameras have certain requirements for the brightness of the acquisition environment, and it is easy to leak privacy when cameras collect image or video information; for the method of target tracking through intelligent wearable devices, since intelligent wearable devices have a certain degree of invasiveness, many people do not have the habit of wearing intelligent wearable devices.

[0004] Therefore, due to the above-mentioned many defects in target tracking in related technologies, how to take into account the usage habits of the target object and ensure the privacy of the target object while performing target tracking still needs further discussion and research. Summary of the Invention

[0005] The embodiments of the present application provide a target tracking method, device, equipment and storage medium based on ultra-wideband radar. The technical solutions are as follows:

[0006] On the one hand, the embodiments of the present application provide a target tracking method based on ultra-wideband radar, and the method includes:

[0007] Obtain a radar frame obtained by sampling an echo signal by an ultra-wideband radar;

[0008] Extract scatter points based on the radar frame to obtain the measurement corresponding to the radar frame. The measurement refers to the range bin where the scatter point is located, and the measurement corresponds one-to-one with the scatter point;

[0009] Perform aggregation processing on the measurements corresponding to the radar frame to obtain the aggregated measurement corresponding to the radar frame;

[0010] Determine the position information of at least one target object according to the aggregated measurement corresponding to the radar frame.

[0011] On the other hand, an embodiment of the present application provides a target tracking device based on an ultra-wideband radar. The device includes:

[0012] An information acquisition module, configured to acquire a radar frame obtained by sampling an echo signal by an ultra-wideband radar;

[0013] A measurement determination module, configured to extract scatter points based on the radar frame to obtain the measurement corresponding to the radar frame. The measurement refers to the range bin where the scatter point is located, and the measurement corresponds one-to-one with the scatter point;

[0014] An aggregation processing module, configured to perform aggregation processing on the measurements corresponding to the radar frame to obtain the aggregated measurement corresponding to the radar frame;

[0015] A position determination module, configured to determine the position information of at least one target object according to the aggregated measurement corresponding to the radar frame.

[0016] On yet another aspect, an embodiment of the present application provides a computer device. The computer device includes a processor and a memory. The memory stores a computer program, and the computer program is loaded and executed by the processor to implement the above-mentioned target tracking method based on an ultra-wideband radar.

[0017] On still another aspect, an embodiment of the present application provides a computer-readable storage medium. A computer program is stored in the storage medium, and the computer program is used to be executed by a processor of a computer device to implement the above-mentioned target tracking method based on an ultra-wideband radar.

[0018] On yet another aspect, an embodiment of the present application provides a chip. The chip includes a programmable logic circuit and / or program instructions. When the chip runs on a computer device, it is used to implement the above-mentioned target tracking method based on an ultra-wideband radar.

[0019] On still another aspect, an embodiment of the present application provides a computer program product. When the computer program product runs on a computer device, it causes the computer device to execute the above-mentioned target tracking method based on an ultra-wideband radar.

[0020] The technical solutions provided by the embodiments of the present application may include the following beneficial effects:

[0021] By obtaining the radar frames sampled from the echo signals by the ultra-wideband radar, extracting the scattering points from the radar frames, and taking the range cells where the scattering points are located as measurements to obtain the measurements corresponding to the radar frames, and then performing aggregation processing on the measurements to obtain aggregated measurements, so as to reduce the number of measurements and improve the processing speed of the computer device. Then, based on the aggregated measurements, the position information of the target object is further determined. In the technical solutions provided by the embodiments of the present application, since the measurements are aggregated, the number of measurements is reduced, thus effectively alleviating the storage pressure of the computer device and reducing the computing overhead of the computer device, avoiding waste of resources. In addition, since no images and videos need to be taken during the process of the ultra-wideband radar collecting echo signals, and the ultra-wideband radar has the characteristic of non-invasiveness, by applying the ultra-wideband radar to the detection and tracking of target objects, the embodiments of the present application fully consider the user's usage habits and help protect the user's privacy. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0023] Figure 1 It is a schematic diagram of the system architecture provided by an embodiment of the present application;

[0024] Figure 2 It is a flowchart of a target tracking method based on an ultra-wideband radar provided by an embodiment of the present application;

[0025] Figure 3 It is a flowchart of the scattering point extraction process provided by an embodiment of the present application;

[0026] Figure 4 It is a comparison diagram of the measurements before and after aggregation corresponding to the radar frames provided by an embodiment of the present application;

[0027] Figure 5 It is a waveform diagram of different forms of radar frames provided by an embodiment of the present application;

[0028] Figure 6 It is a flowchart of a target tracking method based on an ultra-wideband radar provided by another embodiment of the present application;

[0029] Figure 7 It is a schematic diagram of the target tracking result provided by an embodiment of the present application;

[0030] Figure 8 It is a block diagram of a target tracking device based on ultra-wideband radar provided by an embodiment of the present application;

[0031] Figure 9 It is a block diagram of a target tracking device based on ultra-wideband radar provided by another embodiment of the present application;

[0032] Figure 10 It is a block diagram of a server provided by an embodiment of the present application. Detailed implementation manners

[0033] To make the objectives, technical solutions, and advantages of the present application clearer, the following will further describe the embodiments of the present application in detail with reference to the accompanying drawings.

[0034] Please refer to Figure 1 , which shows the system architecture of an environment-assisted living system provided by an embodiment of the present application. The system architecture includes an ultra-wideband radar 10, a computer device, and a target object 30.

[0035] The target object 30 refers to an active object that needs to be concerned about in the environment-assisted living system. Optionally, the target object 30 is a person. Exemplarily, in the case where the environment-assisted living system is applied to the concern for empty-nest elderly people in a home environment, the target object 30 refers to an empty-nest elderly person. It should be noted that after those skilled in the art understand the technical solutions of the present application, they will easily think of applying the technical solutions of the present application to other systems or other environments, and the type of the target object will also change accordingly. For example, in the case where the technical solutions of the present application are applied to the concern for animals in an animal store, an animal hospital, etc., the target object 30 refers to an animal; in the case where the technical solutions of the present application are applied to the concern for robots in an office environment, etc., the target object 30 refers to a robot. The embodiments of the present application do not limit the number of target objects 30. Exemplarily, in the case where the environment-assisted living system is applied to the concern for empty-nest elderly people in a home environment, the number of target objects 30 is usually one or two.

[0036] Ultra-wideband (UWB) radar 10 refers to a radar whose fractional bandwidth (FBW) of the transmitted signal is greater than 0.25, and it can implement functions such as communication and detection. In the embodiments of the present application, the ultra-wideband radar 10 can detect a target object 30 and collect echo signals. Exemplarily, after the transmitted signal of the ultra-wideband radar 10 encounters the target object 30, an echo signal corresponding to the transmitted signal is returned, so that the ultra-wideband radar 10 can collect the echo signal. Optionally, the ultra-wideband radar 10 in the embodiments of the present application is a radar sensor with a pulse system. Exemplarily, a maintainer terminal 22 in a computer device can control the ultra-wideband radar 10 to intermittently transmit pulse period signals and receive the reflected echo signals during the transmission interval. That is, the processes of transmitting and receiving signals by the ultra-wideband radar 10 are carried out alternately. Compared with a radar sensor with a continuous wave system, the ultra-wideband radar 10 with a pulse system in the embodiments of the present application can avoid interference caused by the leakage of the transmitted signal to the receiver when receiving the echo signal. In the embodiments of the present application, after the ultra-wideband radar 10 collects the echo signal, the echo signal can be further digitally sampled to obtain a radar frame, and subsequent data processing processes are all analyzed and processed based on the sampled radar frame.

[0037] The embodiments of the present application do not limit the number of ultra-wideband radars 10. Optionally, the number of ultra-wideband radars 10 is one or more. In practical applications, the specific number of ultra-wideband radars 10 can be determined in combination with the spatial size, spatial distribution of the environment-assisted living system, and the cost of the ultra-wideband radar 10. Exemplarily, in the case where the environment-assisted living system includes a home environment, assuming that the home environment includes four spaces, namely a bedroom, a bathroom, a living room, and a kitchen, then the number of ultra-wideband radars 10 can be set to four, that is, one ultra-wideband radar 10 is set in each space of the environment-assisted living system.

[0038] In the embodiments of the present application, the position of the ultra-wideband radar 10 is not limited either. Optionally, the ultra-wideband radar 10 is arranged at the corners of each space in the environmental assisted living system; or, the ultra-wideband radar 10 is arranged at the center of each space in the environmental assisted living system. Among them, arranging at the corner can avoid obstructing the movement of the target object 30, the arrangement of items in each space, etc. compared with arranging at the center. Exemplarily, in the case where the environmental assisted living system includes a home environment, assuming that the home environment includes three spaces, namely a bedroom, a living room, and a bathroom, and assuming that the ultra-wideband radar 10 is distributed in each space, then in each space, the ultra-wideband radar 10 can be arranged at the corner of the space in the horizontal direction and facing the activity area of the target object 30 in the space, so as to avoid obstructing the movement of the target object 30 while mastering the overall situation of the space; the ultra-wideband radar 10 can be arranged at half of the height of the target object 30 in the vertical direction to reduce the number of scatter points extracted in the subsequent processing process and reduce the processing overhead of the computer device. Optionally, in the case where the number of target objects 30 is multiple, the ultra-wideband radar 10 is arranged at half of the highest height of the target object 30 in the vertical direction; or, arranged at half of the average height of the target object 30.

[0039] A computer device refers to a device with data analysis and processing capabilities. In the embodiments of the present application, the computer device can be further refined into a maintainer terminal 22, a server 24, and a user terminal 26. Among them, the maintainer terminal 22 and the user terminal 26 can be terminal devices such as mobile phones, tablet computers, embedded terminals, wearable devices, etc.; the server 24 can be a single server or a server cluster composed of multiple servers.

[0040] In addition to having data processing capabilities, the maintainer terminal 22 also has the ability to control the ultra-wideband radar 10. In the embodiments of the present application, the maintainer terminal 22 can control the ultra-wideband radar 10 to intermittently transmit pulse period signals, and receive the radar frames sampled by the ultra-wideband radar 10, and further send the radar frames to the server 24 for subsequent data processing. Optionally, the user sets the period of the transmission signal of the ultra-wideband radar 10 through the maintainer terminal 22 to achieve the purpose of controlling the ultra-wideband radar 10 to intermittently transmit pulse period signals. Optionally, the maintainer terminal 22 and the ultra-wideband radar 10 are arranged in the same space to facilitate the user's control of the ultra-wideband radar 10. The number of maintainer terminals 22 is not limited in the embodiments of the present application. Optionally, the number of maintainer terminals 22 is the same as the number of ultra-wideband radars 10; or, the number of maintainer terminals 22 is one. Exemplarily, in the case where the ambient assisted living system includes a home environment and the home environment includes multiple spaces, assuming that an ultra-wideband radar 10 is set in each space, the number of maintainer terminals 22 can be the same as the number of ultra-wideband radars 10, that is, a maintainer terminal 22 is set in each space; the number of maintainer terminals 22 can also be one, that is, only one maintainer terminal 22 is included in the home environment, and the maintainer terminal 22 controls the ultra-wideband radars 10 in each space.

[0041] The user terminal 26 refers to the terminal device that uses the target tracking result in the ambient assisted living system, and it has the capabilities of data viewing, acquisition, and analysis processing. In the embodiments of the present application, the user terminal 26 can obtain the target tracking result from the server 24 to display the target tracking result on the user interface for the user to view and further analyze and process. Optionally, the user terminal 26 and the ultra-wideband radar 10 are arranged in different spaces, and the position of the user terminal 26 can be moved, so as to achieve the purpose of viewing the target tracking result anytime and anywhere. Exemplarily, in the case where the ambient assisted living system includes a home environment, the user terminal 26 can be located outside the home environment to facilitate the user to pay attention to the target object 30 in the home environment outside the home environment. For example, in the case where the target object 30 is an empty-nester, the user terminal 26 held by the children of the empty-nester is located outside the home environment where the empty-nester lives, which can facilitate the children living in other places to pay attention to the activity status of the empty-nester. The number of user terminals 26 is not limited in the embodiments of the present application. In practical applications, the number of user terminals 26 can be determined in combination with the number of users associated with the target object 30. For example, in the case where the ambient assisted living system includes a home environment, assuming that the target object 30 is two empty-nesters, the number of user terminals 26 can be the number of children of the empty-nesters.

[0042] Server 24 refers to the device that actually processes the radar frames sampled by the ultra-wideband radar 10. In the embodiments of the present application, the server 24 can receive the radar frames sent by the maintainer terminal 22. Optionally, when there is a need for data analysis, the server 24 receives the radar frames from the maintainer terminal 22; or, the server 24 obtains the radar frames from the maintainer terminal 22 at preset intervals. By obtaining the radar frames at preset intervals, the server 24 can analyze and process the radar frames in a timely manner to detect abnormal situations of the target object 30 in a timely manner. In the embodiments of the present application, in addition to obtaining the radar frames from the maintainer terminal 22, the server 24 can also obtain the relevant parameters of the ultra-wideband radar 10 from the maintainer terminal 22, such as the period of the transmitted signal, the range resolution, etc. The embodiments of the present application do not limit the location setting of the server 24. Optionally, the server 24 and the ultra-wideband radar 10 are set in the same space; or, the server 24 and the ultra-wideband radar 10 are set in different spaces. For example, when the environment-assisted living system is a home environment, the server 24 can be set outside the home environment. Since the volume of the server 24 is usually large, setting it outside the home environment can avoid occupying the space of the home environment. In the embodiments of the present application, the server 24 can receive data from multiple maintainer terminals 10. Exemplarily, when the environment-assisted living system includes multiple home environments, the server 24 can receive data from the maintainer terminals 10 set in multiple home environments.

[0043] In the embodiments of the present application, the server 24 processes the radar frames to obtain the position information of the target object 30, and further determines the movement trajectory of the target object 30 based on this position information. Through the movement trajectory of the target object 30, the activity level and disability degree of the target object 30 can be further obtained. Exemplarily, using the movement trajectory of the target object 30, the frequency of the target object entering and leaving the environment-assisted living system, the walking speed, the time in bed, and the time staying in a certain space (such as the bathroom) in the environment-assisted living system can be further obtained. Furthermore, the change in the activity of the target object 30 can be judged, and the abnormality in the activity of the target object 30 can be detected in a timely manner and a warning can be issued (such as sending an abnormal signal to the user terminal 26), etc.

[0044] In the embodiments of the present application, communication can be carried out between the maintainer terminal 22 and the ultra-wideband radar 10, between the server 24 and the maintainer terminal 22, and between the user terminal 26 and the server 24 through the network. Optionally, the network can be a wired network or a wireless network.

[0045] It should be noted that Figure 1For example, the ambient assisted living system includes a home environment, and the home environment only includes one space. However, this does not limit the technical solution of the present application. After understanding the technical solution of the present application, those skilled in the art will easily think of other system architectures. For example, the technical solution of the present application can be applied to other environments, such as office environments, etc. In the case where the ambient assisted living system is a home environment, the home environment can also include multiple spaces, and these should all fall within the protection scope of the present application.

[0046] According to the above description, it can be seen that the ultra-wideband radar plays a significant role in the target tracking process. However, when the ultra-wideband radar is applied to the ambient assisted living system, since the scale of the target objects that need to be concerned in the ambient assisted living system is usually large, during the processing, the number of scattering points corresponding to the target objects extracted is relatively large. In the subsequent processing, each range cell where the scattering point is located is used as a measurement, and thus the number of measurements that the computer device needs to process is also relatively large. The excessive measurements bring great pressure to both the spatial storage and processing overhead of the computer device. In addition, in the ambient assisted living system, in addition to the target objects, there are usually other objects, and these objects are usually in a stationary state. For example, as Figure 1 shown, in the case where the ambient assisted living system is a home environment, the home environment also includes furniture 40 (such as refrigerators, air conditioners, wardrobes, etc.). These stationary objects will cause significant clutter interference to the echo signal of the ultra-wideband radar, affecting the detection of the target objects. In addition, the ambient assisted living usually includes multiple target objects, and there may be intersections between the movement trajectories of these multiple target objects. In this case, it poses a challenge to the computer device to associate the processed measurements with the target objects.

[0047] Based on this, the embodiments of the present application provide a target tracking method based on ultra-wideband radar, which can be used to solve the above technical problems. Next, the technical solution of the present application will be introduced through several exemplary embodiments.

[0048] Please refer to Figure 2 , which shows a flowchart of a target tracking method based on ultra-wideband radar provided by an embodiment of the present application. This method can be applied to the Figure 1 system architecture shown, for example, applied to the Figure 1 server 24 shown. This method can include the following steps (210-240):

[0049] Step 210, obtain a radar frame obtained by sampling the echo signal by the ultra-wideband radar.

[0050] In the embodiments of the present application, the user can use a terminal device (such as the above Figure 1The maintainer terminal 22 shown in the figure controls the ultra-wideband radar to transmit a signal. Optionally, the ultra-wideband radar is a pulse system, and the transmission signal can be a periodic pulse signal. The embodiment of the present application adopts an ultra-wideband radar with a pulse system to avoid the leakage of the transmission signal from interfering with the receiver's receiving echo signal. For the working principle of the ultra-wideband radar with a pulse system, please refer to the above embodiment, which will not be described in detail here. The expression of the transmission signal provided by an embodiment of the present application is shown below:

[0051]

[0052] Wherein, h(t) refers to the Gaussian pulse signal, and h(t) is the baseband signal; f c refers to the carrier frequency, and 2πf c =ω c ; τ refers to the pulse width factor; f(t) is the transmitting signal in the form of radio frequency; t is the transmitting time of the transmitting signal.

[0053] The ultra-wideband radar can collect echo signals during the intervals between transmitting signals. The echo signal is the signal reflected back after the transmitting signal of the ultra-wideband radar encounters a reflecting object. In the embodiment of the present application, corresponding to the transmitting signal in the form of periodic pulses, the ultra-wideband radar also periodically collects echo signals. After the ultra-wideband radar receives the echo signal, the echo signal can be further digitally sampled to obtain at least one radar frame. Among them, the frame number of the radar frame represents the slow time, and each radar frame is used to indicate the strength of the reflected signal at different radial distance units in the slow time space corresponding to the radar frame, that is, the sampling result of the entire fast time.

[0054] In the embodiment of the present application, the terminal device (such as the above-mentioned Figure 1 The maintainer terminal 22 shown) or the server (as described above Figure 1 The server 24 shown in the figure can store radar frames. Optionally, the radar frame is stored in the form of a radio frequency signal; or, the radar frame is stored in the form of a baseband signal, which is not limited in the embodiment of the present application. Among them, since the center frequency of the radio frequency signal is in the high frequency band and is a real signal, the spectrum utilization rate is low, and the baseband signal is obtained by reducing the frequency of the radio frequency signal. The center frequency of the baseband signal is at zero frequency and is a complex signal, and the spectrum utilization rate is high. Therefore, the embodiment of the present application can store the radar frame in the form of a baseband signal to reduce the storage overhead of the data while ensuring the target detection performance requirements.

[0055] In addition, the above-mentioned reflection object refers to an object that can obstruct the propagation of a signal and reflect the signal. In the embodiments of the present application, the reflection object obstructs the propagation of the transmitted signal of the ultra-wideband radar and reflects an echo signal for the transmitted signal. The embodiments of the present application do not limit the type of the reflection object. In practical applications, for different ambient assisted living systems, there may be different types of reflection objects. For example, in the case where the ambient assisted living system includes a home indoor environment, the reflection object includes at least one of the following: animals, robots, household appliances, furniture, as Figure 1 shown, the household appliance 40 in this ambient assisted living system is the reflection object; in the case where the ambient assisted living system includes a home outdoor environment, the reflection object includes at least one of the following: animals, vehicles, plants.

[0056] The server for analyzing and processing the radar frame can obtain the radar frame sampled by the ultra-wideband radar. Optionally, the server directly obtains the radar frame sampled by the ultra-wideband radar from the ultra-wideband radar; or, the server obtains the radar frame sampled by the ultra-wideband radar from a terminal device connected to the ultra-wideband radar. The embodiments of the present application do not limit this. In practical applications, the method for the server to obtain the radar frame can be determined in combination with the system architecture design of the ambient assisted living system.

[0057] Step 220: Extract scatter points based on the radar frame to obtain a measurement corresponding to the radar frame. The measurement refers to the range cell where the scatter point is located, and the measurement corresponds to the scatter point one by one.

[0058] After obtaining the radar frame, the server can extract scatter points based on the radar frame. Optionally, in order to improve the accuracy of target detection, the server can, after obtaining the radar frame, further perform filtering processing on the radar frame, and then extract scatter points based on the filtered radar frame. For the introduction and description of the process of the server performing filtering processing on the radar frame, please refer to the following embodiments, and details are not elaborated here.

[0059] The embodiments of the present application do not limit the method for the server to extract scatter points. Optionally, the server can use the CLEAN algorithm to extract scatter points. In one example, the above-mentioned step 220 includes: obtaining a waveform template, where the signal form of the waveform template is the same as that of the radar frame, and the range resolution of the waveform template is the same as that of the radar frame; using the waveform template to extract scatter points from the radar frame. That is, the server can use a waveform template having the same signal form and range resolution as the radar frame to extract scatter points from the radar frame. As Figure 3 shown, it shows a flowchart of the scatter point extraction process provided by an embodiment of the present application. The signal form of the waveform template in this flowchart is the same as that of the radar frame, and the range resolution of the waveform template is also the same as the waveform resolution of the radar frame. The server extracts scatter points by executing Figure 3The scattering point extraction process shown can extract the scattering points corresponding to the radar frame.

[0060] To facilitate the description of the target tracking process, in the embodiments of the present application, the range bin where the scattering point is located is called a measurement. After the server extracts the scattering points corresponding to the radar frame, it can obtain the measurements corresponding to the radar frame. Since the measurement is the range bin where the scattering point is located, there is a one-to-one correspondence between the scattering point and the measurement.

[0061] Step 230: Aggregate the measurements corresponding to the radar frame to obtain the aggregated measurement corresponding to the radar frame.

[0062] For each radar frame, the number of extracted scattering points may be different. However, usually, for each radar frame, the number of extracted scattering points corresponding to the radar frame is concentrated between 1 and 3. Consequently, for each radar frame, the number of measurements corresponding to the radar frame is also concentrated between 1 and 3. To further reduce the number of measurements corresponding to the radar frame, the embodiments of the present application propose to perform an aggregation process after obtaining the measurements corresponding to the radar frame to obtain the aggregated measurement corresponding to the radar frame. The following describes the aggregation process.

[0063] In a possible implementation manner, the measurements corresponding to the radar frame are arranged in ascending or descending order, and the number of measurements corresponding to the radar frame is n, where n is a positive integer. The above step 230 includes: for the i-th measurement among the n measurements, determine whether there are other measurements within the search range corresponding to the i-th measurement, where the other measurements are greater than the i-th measurement, and i is a positive integer less than n; in the case where there are other measurements within the search range, perform an averaging process on the i-th measurement and the other measurements to obtain an average measurement, and the aggregated measurement corresponding to the radar frame includes the average measurement.

[0064] Before the aggregation process, the server can sort the measurements corresponding to the radar frame so that the measurements corresponding to the radar frame are arranged in ascending or descending order, facilitating the subsequent aggregation process. The embodiments of the present application do not limit the sorting method. Optionally, the server sorts the measurements corresponding to the radar frame in descending order; or sorts the measurements corresponding to the radar frame in ascending order.

[0065] During the aggregation process, the server determines whether to perform aggregation processing in sequence according to the order of the measurements corresponding to the radar frames. For example, when the measurements corresponding to the radar frames are sorted in ascending order, the server starts from the smallest measurement and determines whether to perform aggregation processing in sequence; when the measurements corresponding to the radar frames are arranged in descending order, the server starts from the largest measurement and determines whether to perform aggregation processing in sequence. Exemplarily, for the i-th measurement, the server can determine the search range corresponding to the i-th measurement, and further determine whether other measurements are included in this search range. If other measurements are included, the server determines that aggregation processing is required.

[0066] Among them, the above search range includes a front boundary and a rear boundary. The front boundary is the i-th measurement, the rear boundary is greater than the front boundary, and there are r distance units between the rear boundary and the front boundary, where r is a positive integer. The embodiments of the present application do not limit the specific value of r. In practical applications, the value of r can be determined in combination with the requirements for the degree of aggregation. For example, when the requirement for the degree of aggregation is relatively high, that is, when fewer measurements are required, the value of r can be set to be relatively large.

[0067] When it is determined that aggregation processing is required, the server performs an averaging process on the i-th measurement and other measurements included in its corresponding search range to obtain an average measurement, and the aggregated measurement corresponding to the radar frame includes this average measurement. It should be noted that after those skilled in the art understand the technical solution of the present application, they will easily think of other aggregation processing methods. For example, performing a weighted averaging process on the i-th measurement and other measurements included in its corresponding search range, etc. These should all fall within the protection scope of the present application.

[0068] The above is for the case where aggregation processing is required. In practical applications, there may be no other measurements included in the search range corresponding to the i-th measurement. For the case where no other measurements are included in the search range, the embodiments of the present application also propose corresponding processing methods. In one example, the above step 230 includes: when no other measurements are included in the search range, retaining the i-th measurement, and the aggregated measurement corresponding to the radar frame includes the i-th measurement.

[0069] For example, as Figure 4 shown, it shows a comparison diagram before and after the aggregation of the measurements corresponding to the radar frame provided by an embodiment of the present application. Figure 4 (a) represents the radar frame in the form of a baseband signal; Figure 4 (b) represents the Figure 4 measurements corresponding to the radar frame obtained by extracting scatter points based on the radar frame shown in (a); Figure 4 (c) represents the Figure 4The aggregated measurement corresponding to the radar frame obtained by aggregating the measurements shown in (b).

[0070] Step 240: Determine the position information of at least one target object according to the aggregated measurement corresponding to the radar frame.

[0071] The server can determine the position information of at least one target object in the environment assisted living system based on the aggregated measurement corresponding to the radar frame obtained in step 230. In the embodiments of the present application, the type of the target object is not limited. In practical applications, the type of the target object is determined in combination with the objects concerned by the environment assisted living system. For example, when the environment assisted living system is concerned about empty nesters, the target object is an empty nester; when the environment assisted living system is concerned about the pets raised, the target object is a pet. In the embodiments of the present application, the form of expression of the position information is not limited. Optionally, the position information is expressed in the form of two-dimensional coordinates. Usually, the number of target objects corresponding to the radar frame obtained by the server is equal to the number of target objects corresponding to the position information. For the specific determination process of the position information, please refer to the following embodiments and will not be elaborated here.

[0072] In one example, the above method further includes: for the j-th object among the target objects, concatenate the position information of the j-th object in the chronological order of x radar frames in the time domain to obtain the motion trajectory of the j-th object, where x is an integer greater than 1 and j is a positive integer.

[0073] After obtaining the position information of the target object in each radar frame, the server can further determine the motion trajectory of the target object according to the position information of the target object in each radar frame, so as to analyze the activity amount and / or disability degree of the target object. When there are multiple target objects in the environment assisted living system, for the j-th object among the multiple target objects, the position information determined by the server through these x radar frames can be concatenated in the chronological order of x radar frames in the time domain, and then the motion trajectory of the j-th object can be obtained. In the embodiments of the present application, the specific value of x is not limited. In practical applications, the value of x can be determined in combination with the analysis requirements of the user. For example, when the user needs to analyze the motion trajectory of the target object in a day, the value of x can be set to be equal to the number of radar frames obtained by the server in a day.

[0074] In summary, the technical solution provided by the embodiments of the present application obtains a radar frame obtained by sampling an echo signal by an ultra-wideband radar, extracts scatter points based on the radar frame, and uses the range cell where the scatter points are located as a measurement to obtain the measurement corresponding to the radar frame. Then, the measurements are aggregated to obtain aggregated measurements, so as to reduce the number of measurements and improve the processing speed of the computer device. After that, the position information of the target object is further determined according to the aggregated measurements. In the technical solution provided by the embodiments of the present application, since the measurements are aggregated, the number of measurements is reduced, thereby effectively alleviating the storage pressure of the computer device and reducing the computing overhead of the computer device, and avoiding resource waste. In addition, since no images and videos need to be captured during the process of the ultra-wideband radar collecting echo signals, and the ultra-wideband radar has the characteristic of non-invasiveness, the embodiments of the present application apply the ultra-wideband radar to the detection and tracking of target objects, fully considering the user's usage habits and helping to protect the user's privacy.

[0075] Moreover, in the technical solution provided by the embodiments of the present application, both the storage and processing processes of the radar frame adopt the radar frame in the form of a baseband signal. Since the radar frame in the form of a baseband signal is obtained by reducing the frequency of the radar frame in the form of a radio frequency signal and is a complex signal, the spectrum utilization rate is relatively high, which can ensure the target detection performance while reducing the storage overhead of the computer device.

[0076] In addition, in the technical solution provided by the embodiments of the present application, after obtaining the position information of the target object, the position information of the target object is further concatenated in the chronological order of the radar frames in the time domain to obtain the motion trajectory of the target object. Since this motion trajectory can be used for subsequent analysis and processing of the activity amount and disability degree of the target object, etc., the technical solution provided by the embodiments of the present application expands the application scenario of the target tracking method and improves the application potential of the target tracking method.

[0077] Since the echo signal collected by the ultra-wideband radar may include echo signals corresponding to other reflection objects in addition to the echo signal corresponding to the target object, in order to improve the accuracy of the server in detecting the target object, the embodiments of the present application propose to filter out the clutter signals in the radar frame before processing the radar frame corresponding to the echo signal, as follows.

[0078] In a possible implementation manner, before the above step 220, the following steps are further included:

[0079] (1) Obtain m radar frames that are continuous in the time domain.

[0080] In the embodiments of the present application, since the ultra-wideband radar periodically transmits pulse signals and collects echo signals at intervals of transmitting pulse signals, the ultra-wideband radar periodically collects echo signals. Optionally, when the terminal device controlling the ultra-wideband radar obtains a radar frame, it can record the timestamp of the radar frame. Furthermore, each radar frame obtained by the server from the terminal device also includes a timestamp. In the subsequent analysis and processing, the server can distinguish the chronological order of each radar frame in the time domain, etc.

[0081] After the server obtains the radar frames, it can further obtain m radar frames that are continuous in the time domain, and these m radar frames correspond to different echo signals. The embodiments of the present application do not limit the value of m. Optionally, when using an ultra-wideband radar for target detection, the transceiver frame rate of the ultra-wideband radar is usually set to more than 100 frames. To maintain uniformity in hardware, the target tracking is also set to the same frame rate, that is, more than 100 frames. However, in practical applications, a hardware frame rate of 5 to 10 can meet the requirements of target tracking. Therefore, in the embodiments of the present application, the value range of m can be 10 to 20.

[0082] (2) Obtain a two-dimensional data matrix based on the m radar frames.

[0083] After the server determines the m radar frames, it can form a two-dimensional data matrix according to these m radar frames. Among them, the number of rows of the two-dimensional data matrix is used to indicate the total number of range cells included in each radar frame; the number of columns of the two-dimensional data matrix is used to indicate the number of m radar frames, that is, the number of columns is m; the element in the x-th row and y-th column of the two-dimensional data matrix is used to indicate the echo intensity of the y-th radar frame at the x-th range cell, where y is a positive integer less than or equal to m, x is a positive integer, and x is less than or equal to the total number of range cells included in each radar frame. Optionally, the size of this element is related to the power of the periodic pulse transmitted by the ultra-wideband radar, the target azimuth angle, the control loss, and the sampling settings of the receiving end, etc.

[0084] (3) Set the largest k singular values among the singular vectors obtained by decomposing the two-dimensional data matrix to zero to obtain a processed two-dimensional data matrix, where k is a positive integer.

[0085] After forming the two-dimensional data matrix, the server can further decompose the two-dimensional data matrix to extract singular values and singular vectors. Optionally, the server can use the SVD (Singular Value Decomposition) algorithm to extract the singular values and singular vectors corresponding to the two-dimensional data matrix. Assume that the total number of range cells included in each radar frame is z, then the size of the two-dimensional data matrix R is (m×z). Furthermore, for this two-dimensional data matrix R, the server decomposes it to obtain:

[0086]

[0087] Among them, U and V are unitary matrices (also known as unitary matrices) with dimensions (m×m) and (z×z) respectively; S = diag(σ1, σ2, …, σ r ) are the singular vectors, and σ1, σ2, …, σ r in the singular vectors are the singular values, and the singular values satisfy σ1 ≥ σ2 ≥ … ≥ σ r ≥ 0; u i and v i are the column vectors of matrices U and V respectively.

[0088] After decomposing to obtain the singular vectors, the server can determine the magnitudes of the singular values in the singular vectors. Optionally, the server can sort the singular values by magnitude to facilitate subsequent selection of singular values according to their magnitudes. Since in the ambient assisted living system, in addition to the moving target object, there are other reflecting objects, and these reflecting objects are usually stationary. Exemplarily, in the case where the ambient assisted living system includes a home environment, in addition to the target object, the home environment also includes stationary reflecting objects such as furniture and household appliances. In the embodiments of the present application, the signal reflected by the reflecting object other than the target object is called clutter signal. Since the energy of the clutter signal is usually higher than that of the signal reflected by the target object, the clutter signal also has relatively large singular values. To achieve the purpose of filtering out clutter, after determining the singular vectors, the server can set the largest k singular values in the singular vectors to zero. The embodiments of the present application do not limit the specific value of k. In practical applications, the value of k can be determined in combination with the singular values corresponding to the clutter signal, the singular values corresponding to the target object, and the number of other reflecting objects. Optionally, k is 1 or 2, so that while filtering out clutter, the signal reflected by the target object is not filtered out, ensuring the accuracy of target detection.

[0089] (4) Based on the processed two-dimensional data matrix, obtain a filtered radar frame, and the filtered radar frame is used to extract scatter points to obtain the measurement corresponding to the radar frame.

[0090] After the server sets the largest k singular values to zero, it can obtain a processed two-dimensional data matrix. Based on this processed two-dimensional data matrix, the server can further obtain a filtered radar frame, and this filtered radar frame is used for subsequent extraction of scatter points to obtain the measurement corresponding to the radar frame.

[0091] Please refer to Figure 5 , which shows the waveform diagrams of different forms of radar frames provided by an embodiment of the present application. Among them, Figure 5 (a) refers to the radar frame in the form of a radio frequency signal; Figure 5 (b) refers to the radar frame in the form of a baseband signal; Figure 5(c) refers to the radar frame in the form of a baseband signal after clutter filtering. As can be seen from Figure 5 , compared with the radar frame in the form of a radio frequency signal, the radar frame in the form of a baseband signal has a lower center frequency and higher spectrum utilization rate. As can also be seen from Figure 5 , in the radar frame after clutter filtering processing, the useful signals are more prominent.

[0092] In summary, for the technical solution provided in the embodiments of the present application, by forming a two-dimensional data matrix from multiple consecutive radar frames in the time domain and setting to zero several of the largest singular values among the singular vectors obtained by decomposing the two-dimensional data matrix. Since in an ambient assisted living system, static reflection objects often have relatively high energy and thus have relatively large singular values, the embodiments of the present application can achieve the purpose of filtering the clutter signals reflected by static reflection objects by setting to zero several of the largest singular values, thereby improving the accuracy of target detection. In addition, the embodiments of the present application further propose to set to zero one or two of the largest singular values, so as to avoid filtering the signals reflected by the target objects and avoid affecting the accuracy of target detection.

[0093] The process of determining the position information of the target object will be described below.

[0094] In one example, step 240 described above includes the following steps:

[0095] (1) Filter the aggregated measurement corresponding to the radar frame to obtain the filtered measurement.

[0096] The server can filter the aggregated measurement corresponding to the radar frame to obtain the filtered measurement, and further determine the position information of the target object based on the filtered measurement. The embodiments of the present application do not limit the specific filtering method. Optionally, the filtering method is Kalman filtering, or Wiener filtering, or particle filtering.

[0097] (2) Select valid measurements from the filtered measurements.

[0098] Based on the filtered measurement, the server can further select valid measurements from it to improve the accuracy of the target detection result. Since in the process of the server filtering the aggregated measurement corresponding to the radar frame to obtain the filtered measurement, the number of target objects and the filtered measurements corresponding to each target object can be determined. Therefore, in the embodiments of the present application, the process of the server selecting valid measurements is carried out for each target object and the filtered measurement corresponding to the target object. The process of selecting valid measurements will be described below.

[0099] In one example, step (2) above includes: for the j-th object in the target objects, obtaining the maximum movement speed of the j-th object and the distance resolution of the ultra-wideband radar; setting the distance gate corresponding to the j-th object according to the maximum movement speed and the distance resolution of the i-th object; and determining the measurements within the distance gate corresponding to the j-th object in the filtered measurements as valid measurements.

[0100] Since the target objects in the ambient assisted living system usually have characteristics such as slow walking and stable walking process, for each target object, a corresponding distance gate can be set, and the distance gate is a constant. Optionally, the distance gate of the j-th object is determined according to the maximum movement speed of the j-th object and the distance resolution of the ultra-wideband radar. For example, assume that the maximum movement speed of the j-th object is 1.5 m / s, the distance resolution of the ultra-wideband radar is 0.05 m, and the time interval between two adjacent frames is 0.1 s. Then the theoretical value of the distance gate corresponding to the j-th object is 1.5 * 0.1 / 0.05, that is, 3. It should be noted that considering the case where the target object is a human body, the human body has the characteristic of multi-point scattering. Therefore, in order to improve the robustness, the distance gate can be set larger than the theoretical value.

[0101] After the server determines the distance gate corresponding to the j-th object, it can select the valid measurements corresponding to the j-th object according to the distance gate. Exemplarily, the server compares the measurements corresponding to the j-th object in the filtered measurements with the distance gate of the j-th object, and the measurements within the distance gate of the j-th object are determined as valid measurements.

[0102] For the case where the filtered measurements do not include the measurements within the distance gate corresponding to the j-th object, the embodiments of the present application also propose corresponding processing methods. Optionally, the above method further includes: in the case where there are no measurements within the distance gate corresponding to the j-th object in the filtered measurements, determining the filtered measurements as the position information of the j-th object. That is, in the process of the server comparing the measurements corresponding to the j-th object in the filtered measurements of a certain radar frame with the distance gate corresponding to the j-th object, if no measurement within the distance gate corresponding to the j-th object is determined, the filtered measurements of this radar frame are directly determined as the position information of the j-th object corresponding to this radar frame.

[0103] (3) Construct a confirmation matrix based on the valid measurements.

[0104] In the case where the server determines valid measurements from the filtered measurements, the server may further construct a confirmation matrix based on the valid measurements, and determine measurement values based on the confirmation matrix to further determine the position information of the target object. In the embodiments of the present application, the value of the element in the p-th row and q-th column of the confirmation matrix is 0 or 1. When the value is 0, the element is used to indicate that the p-th valid measurement is not located within the range gate corresponding to the q-th target object; when the value is 1, the element is used to indicate that the p-th valid measurement is located within the range gate corresponding to the q-th target object.

[0105] (4) Split the confirmation matrix according to the target criterion to obtain at least one joint event, where the joint event is used to indicate the correspondence between the valid measurement and the target object.

[0106] Considering that the ambient assisted living system is usually applied to a home environment, and there are usually two empty-nest elderly people in the home environment. Therefore, in such a sparse target object environment, joint probabilistic data association (JPDA) can be used to allocate and associate the measurements. That is, after constructing the determination matrix, the server can split the confirmation matrix according to the target criterion to obtain at least one joint event. Wherein, the joint event is used to indicate the correspondence between the valid measurement and the target object. For example, assume that there are two target objects, namely target 1 and target 2, and assume that there are three valid measurements, namely measurement 1, measurement 2, and measurement 3. Then measurement 1 can be discarded, measurement 2 can be assigned to target 1, and measurement 3 can be assigned to target 2. The above is a possible situation of allocating these three valid measurements to these two target objects, that is, the above is a joint event.

[0107] The embodiments of the present application do not limit the specific content of the target criterion. Optionally, the target criterion includes a single-source criterion and a single-measurement criterion. Among them, the single-source criterion means that the object corresponding to any valid measurement is unique, that is, within a certain radar frame, one valid measurement belongs to only one target object, so there is only one "1" in each row of the confirmation matrix; the single-measurement criterion means that the valid measurement corresponding to any object in the radar frame is unique, that is, within a certain radar frame, one target object can only correspond to one valid measurement, so there is at most one "1" in each column of the confirmation matrix.

[0108] (5) For the j-th object among the target objects, determine the weighted measurement of the j-th object based on the association probability of the joint event, where j is a positive integer.

[0109] After splitting the confirmation matrix to obtain the joint event, the server can further calculate the association probability of the joint event. The following shows the joint event θ iExpression for the interconnection probability of (k):

[0110]

[0111] where c represents the normalization constant; V represents the volume of the associated gate; P d represents the detection probability, m k represents the number of valid measurements, T represents the number of target objects; N jt [z i (k)] is given by ; δ t (θ i (k)) and τ j (θ i (k)) both represent binary indicator variables; φ(θ i (k)) is given by ; v j (k) is given by ; z j (k) is called a valid measurement, represents the predicted position of target t in the current frame, which is obtained by the server filtering based on the aggregated measurement corresponding to the radar frame, S t (k) represents the actual error covariance matrix of the t-th target object.

[0112] Through the above formula, the interconnection probability between the valid measurement j and the target object t can be obtained as follows:

[0113]

[0114] According to this interconnection probability, the actual state of the t-th target object is updated to obtain:

[0115]

[0116] The error covariance of the t-th target object is updated to obtain:

[0117]

[0118] Thus, the weighted measurement of the target object t can be further obtained:

[0119]

[0120] It should be noted that the above takes the target object t as an example to illustrate the calculation process of the weighted measurement. For the j-th target object, the calculation of the weighted measurement of the j-th target object can refer to the calculation of the weighted measurement of the target object t, which will not be elaborated here.

[0121] (6) Determine the position information of the j-th object according to the weighted measurement of the j-th object.

[0122] After the server determines the weighted measurements of the j-th object for each valid measurement within a certain radar frame, it can further determine the position information of the j-th object based on the weighted measurements of the j-th object.

[0123] In summary, for the technical solution provided by the embodiments of the present application, by filtering the aggregated measurements, and then selecting valid measurements based on the filtered measurements. For a certain radar frame, when there are no valid measurements in this radar frame, directly use the filtered measurements as the position information of the target object. Since the filtered measurements further reduce the error of the aggregated measurements, therefore, determining the filtered measurements as the position information can improve the accuracy of target tracking; when there are valid measurements in this radar frame, further determine the weighted measurements based on the valid measurements, and determine the position information of the target object according to the weighted measurements. By further determining the valid measurements on the basis of the filtered measurements and determining the position information based on the weighted measurements, the accuracy of the position information can be further improved, and the performance of target tracking can be enhanced.

[0124] Next, a complete technical solution of the present application will be introduced and described by means of an exemplary embodiment.

[0125] Suppose there are two target objects in an ambient assisted living system, namely object 1 and object 2. Suppose both of these two target objects are human bodies. Among them, object 1 starts from the target position and takes the ultra-wideband radar as the end point, and walks straight in the direction close to the ultra-wideband radar; object 2 starts from the ultra-wideband radar and takes the target position as the end point, and walks straight in the direction away from the ultra-wideband radar. And during the walking process of object 1 and object 2, the starting point and the end point are continuously exchanged to achieve the purpose of making multiple round trips between the target position and the ultra-wideband radar. Among them, the target position refers to a position directly in front of the ultra-wideband radar and separated from the ultra-wideband radar by a certain distance. Suppose the walking speeds of object 1 and object 2 are both 0.5 m / s, and the acquisition duration is set to 20 seconds. In order to keep the software and hardware consistent with application scenarios such as action recognition and gait recognition that require a large amount of training data, the frame rate of the ultra-wideband radar is set to 150 frames, that is, the time interval between adjacent radar frames is 1 / 150 second.

[0126] As Figure 6As shown, the server first obtains radar frames according to the above settings, and stores these radar frames in the form of baseband signals. Since the walking speed of the target object is slow, there is no need to use too high a frame rate for the process of filtering out clutter signals. Therefore, the server arranges every 15 radar frames in a two-dimensional data matrix according to time sequence, and uses the SVD algorithm to filter out clutter, and takes the average as one frame. Through this operation, the frame rate is equivalent to being reduced to 10 frames per second. Then, for each radar frame, the server uses the CLEAN algorithm to extract measurements. Table 1 below shows the detection comparison when the input of the CLEAN algorithm is a radar frame in the form of a radio frequency signal and a radar frame in the form of a baseband signal respectively.

[0127] Table 1 Comparison of the processing performance of radar frames in different signal forms

[0128] Radar frame in the form of radio frequency signal Radar frame in the form of baseband signal Processing time per frame on average / s 0.038 0.023 Measurements of real targets / number 3-10 1-3

[0129] From Table 1 above, it can be seen that for the radar frame in the form of a baseband signal compared with the radar frame in the form of a radio frequency signal, the average processing time per frame is shortened by 39.7%, and there is a significant improvement in the processing speed. Moreover, for the radar frame in the form of a baseband signal, the measurements of real targets extracted are also significantly reduced. After the scatter point aggregation algorithm, the range extended target further tends to be a point target. In this way, the dimension of the confirmation matrix in the subsequent processing is reduced, and at the intersection of the trajectories of the target objects, the number of intersecting wave gates is also reduced, preventing the occurrence of combinatorial explosion. In addition, since in the embodiment of the present application, the range resolution of the radar frame in the form of a baseband signal is set to eight times that of the radar frame in the form of a radio frequency signal, the storage space of the radar frame in the form of a baseband signal is reduced by one-eighth compared with the radar frame in the form of a radio frequency signal.

[0130] Figure 7 Shows the tracking and filtering results of the target object obtained through the above settings and calculation process. To illustrate that the technical solution provided by the embodiment of the present application has good performance, it is calculated through the following formula Figure 7 The root mean square error of the shown tracking and filtering results:

[0131]

[0132] Among them, z(i) represents the true value of the position of the target object; Represents the tracking and filtering result of the target object

[0133] As shown in Table 2 below, it shows the root mean square errors of Object 1 and Object 2.

[0134] Table 2 Root mean square errors of target tracking results

[0135] Target object Root mean square error (meter) Object 1 0.1750 Object 2 0.2650

[0136] As can be seen from Table II above, the tracking error of the target object is controlled within 0.3 meters. Although in the above example, the trajectories of Object 1 and Object 2 cross, the association between the measurement and the object is accurate, and the trajectory of each target object is correctly updated. Therefore, the technical solution provided by the embodiments of the present application has good performance and application prospects.

[0137] It should be noted that, in the embodiments of the present application, only the steps of the above method executed by the server are taken as examples for illustration. In actual applications, all steps of the above method may be executed entirely by the server, or part of them may be executed by the server and the other part by the terminal device. For example, the step of aggregating the measurements corresponding to the radar frames in the above method steps may be executed by the terminal device (such as Figure 1 the Maintainer Terminal 22 in the system architecture shown), and the other steps are executed by the server. How to specifically implement each step of the above method can be determined in combination with application requirements, system architecture design, etc. The embodiments of the present application do not limit this, but these methods should all fall within the protection scope of the present application.

[0138] The following are the device embodiments of the present application, which can be used to execute the method embodiments of the present application. For details not disclosed in the device embodiments of the present application, please refer to the method embodiments of the present application.

[0139] Please refer to Figure 8 , which shows a block diagram of a target tracking device based on ultra-wideband radar provided by an embodiment of the present application. The device has the functions of implementing the above method example, and the functions can be implemented by hardware or by hardware executing corresponding software. The device can be Figure 1 the Server 24 in the system architecture shown, or can be set in Figure 1 the Server 24 in the system architecture shown. As Figure 8 shown, the device 800 may include: an information acquisition module 810, a measurement determination module 820, an aggregation processing module 830, and a position determination module 840.

[0140] The information acquisition module 810 is configured to acquire radar frames obtained by sampling echo signals by an ultra-wideband radar.

[0141] The measurement determination module 820 is configured to extract scatter points based on the radar frames to obtain the measurements corresponding to the radar frames, where the measurement refers to the range cell where the scatter point is located, and the measurement corresponds to the scatter point one by one.

[0142] The aggregation processing module 830 is configured to perform aggregation processing on the measurements corresponding to the radar frames to obtain the aggregated measurements corresponding to the radar frames.

[0143] A position determination module 840, configured to determine position information of at least one target object according to the aggregated measurements corresponding to the radar frame.

[0144] In one example, the measurements corresponding to the radar frame are arranged in order according to size, and the number of measurements corresponding to the radar frame is n, where n is a positive integer; the aggregation processing module 830 is configured to: for the i-th measurement among the n measurements, determine whether other measurements are included in the search range corresponding to the i-th measurement, where the other measurements are greater than the i-th measurement, and i is a positive integer less than n; in the case where the other measurements are included in the search range, perform an averaging process on the i-th measurement and the other measurements to obtain an average measurement, and the aggregated measurements corresponding to the radar frame include the average measurement.

[0145] In one example, the aggregation processing module 830 is further configured to: in the case where the other measurements are not included in the search range, retain the i-th measurement, and the aggregated measurements corresponding to the radar frame include the i-th measurement.

[0146] In one example, the search range includes a front boundary and a rear boundary, the front boundary is the i-th measurement, the rear boundary is greater than the front boundary, and there are r distance units between the rear boundary and the front boundary, where r is a positive integer.

[0147] In one example, as Figure 9 shown, the apparatus 800 further includes: a radar frame acquisition module 850, configured to acquire m radar frames that are continuous in the time domain; a matrix determination module 860, configured to obtain a two-dimensional data matrix according to the m radar frames; a matrix processing module 870, configured to set to zero the k largest singular values among the singular vectors obtained by decomposing the two-dimensional data matrix to obtain a processed two-dimensional data matrix, where k is a positive integer; a radar frame determination module 880, configured to obtain a filtered radar frame based on the processed two-dimensional data matrix, and the filtered radar frame is used to extract scatter points to obtain the measurements corresponding to the radar frame; where the element at the x-th row and the y-th column in the two-dimensional data matrix is used to indicate the echo intensity of the y-th radar frame at the x-th distance unit, y is a positive integer less than or equal to m, x is a positive integer, and x is less than or equal to the total number of distance units included in each radar frame.

[0148] In one example, k is 1 or 2.

[0149] In one example, the value range of m is from 10 to 20.

[0150] In one example, the measurement determination module 820 is configured to: obtain a waveform template, where the signal form of the waveform template is the same as that of the radar frame, and the range resolution of the waveform template is the same as that of the radar frame; and extract scatter points in the radar frame by using the waveform template.

[0151] In one example, as Figure 9 shown, the position determination module 840 includes: a filtering processing unit 841 configured to perform filtering processing on the aggregated measurement corresponding to the radar frame to obtain a filtered measurement; a measurement selection unit 842 configured to select valid measurements from the filtered measurements; a matrix construction unit 843 configured to construct a confirmation matrix based on the valid measurements; an event determination unit 844 configured to split the confirmation matrix according to a target criterion to obtain at least one joint event, where the joint event is used to indicate the correspondence between the valid measurement and the target object; a measurement weighting unit 845 configured to, for the j-th object in the target object, determine a weighted measurement of the j-th object based on the interconnection probability of the joint event, where j is a positive integer; and an information determination unit 846 configured to determine the position information of the j-th object according to the weighted measurement of the j-th object; where the value of the element in the p-th row and q-th column of the confirmation matrix is 0 or 1. When the value is 0, the element is used to indicate that the p-th valid measurement is not within the range gate corresponding to the q-th target object; when the value is 1, the element is used to indicate that the p-th valid measurement is within the range gate corresponding to the q-th target object.

[0152] In one example, the target criterion includes a single-source criterion and a single-measurement criterion. The single-source criterion means that the object corresponding to any valid measurement is unique, and the single-measurement criterion means that the valid measurement corresponding to any object in the radar frame is unique.

[0153] In one example, as Figure 9 shown, the measurement selection unit 842 is configured to: for the j-th object in the target object, obtain the maximum movement speed of the j-th object and the range resolution of the ultra-wideband radar; set a range gate corresponding to the j-th object according to the maximum movement speed of the j-th object and the range resolution; and determine the measurements within the range gate corresponding to the j-th object in the filtered measurements as the valid measurements.

[0154] In one example, as Figure 9 shown, the information determination unit 846 is further configured to: when there is no measurement in the filtered measurements within the range gate corresponding to the j-th object, determine the filtered measurements as the position information of the j-th object.

[0155] In one example, the signal form of the radar frame is a baseband signal form.

[0156] In one example, the system of the ultra-wideband radar is a pulse system.

[0157] In one example, as Figure 9 shown, the device 800 further includes: a trajectory determination module 890, configured to, for the j-th object in the target object, concatenate the position information of the j-th object according to the chronological order of x radar frames in the time domain to obtain the motion trajectory of the j-th object, where x is an integer greater than 1 and j is a positive integer.

[0158] In summary, the technical solution provided by the embodiments of the present application obtains a radar frame obtained by sampling an echo signal by an ultra-wideband radar, extracts scatter points based on the radar frame, and uses the range cell where the scatter points are located as a measurement to obtain the measurement corresponding to the radar frame. Then, the measurements are aggregated to obtain aggregated measurements to reduce the number of measurements and improve the processing speed of the server. After that, the position information of the target object is further determined according to the aggregated measurements. The technical solution provided by the embodiments of the present application effectively alleviates the storage pressure of the server and reduces the computing overhead of the server by aggregating the measurements, thereby avoiding resource waste. In addition, since the ultra-wideband radar does not need to capture images and videos during the process of collecting echo signals, and the ultra-wideband radar has the characteristic of non-invasiveness, the embodiments of the present application apply the ultra-wideband radar to the detection and tracking of target objects, fully considering the user's usage habits and helping to protect the user's privacy.

[0159] It should be noted that when the device provided in the above embodiments implements its functions, only the above-mentioned division of each functional module is used for illustration. In actual applications, the above functions can be allocated to different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the device provided in the above embodiments and the method embodiments belong to the same concept, and the specific implementation process can be found in the method embodiments and will not be elaborated here.

[0160] Please refer to Figure 10 , which shows a structural block diagram of a computer device provided by an embodiment of the present application.

[0161] The computer device in the embodiments of the present application may include one or more of the following components: a processor 1010 and a memory 1020.

[0162] The processor 1010 may include one or more processing cores. The processor 1010 connects various parts within the entire computer device using various interfaces and lines, and executes various functions of the computer device and processes data by running or executing instructions, programs, code sets, or instruction sets stored in the memory 1020, and by invoking the data stored in the memory 1020. Optionally, the processor 1010 may be implemented in at least one hardware form of digital signal processing (DSP), field-programmable gate array (FPGA), or programmable logic array (PLA). The processor 1010 may integrate a combination of one or more of a central processing unit (CPU) and a modem, etc. Among them, the CPU mainly processes the operating system, application programs, etc.; the modem is used for processing wireless communication. It can be understood that the above-mentioned modem may not be integrated into the processor 1010 and may be implemented separately by a single chip.

[0163] Optionally, when the processor 1010 executes the program instructions in the memory 1020, it implements the methods provided by the above-mentioned various method embodiments.

[0164] The memory 1020 may include random access memory (RAM) and may also include read-only memory (ROM). Optionally, the memory 1020 includes a non-transitory computer-readable storage medium. The memory 1020 can be used to store instructions, programs, code, code sets, or instruction sets. The memory 1020 may include a program storage area and a data storage area. Among them, the program storage area may store instructions for implementing the operating system, instructions for at least one function, instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area may store data created according to the use of the computer device, etc.

[0165] The structure of the above-mentioned computer device is only illustrative. In actual implementation, the computer device may include more or fewer components, such as: a display screen, etc. This embodiment does not make any limitations in this regard.

[0166] Those skilled in the art can understand that Figure 10 the structure shown in

[0167] An embodiment of the present application also provides a computer-readable storage medium, in which a computer program is stored, and the computer program is used to be executed by a processor of a computer device to implement the above-mentioned target tracking method based on ultra-wideband radar.

[0168] An embodiment of the present application also provides a chip, which includes a programmable logic circuit and / or program instructions, and when the chip runs on a computer device, it is used to implement the target tracking method based on ultra-wideband radar as described above.

[0169] An embodiment of the present application also provides a computer program product, which when running on a computer device, causes the computer device to execute the above-mentioned target tracking method based on ultra-wideband radar.

[0170] Those skilled in the art should be able to realize that in the above one or more examples, the functions described in the embodiments of the present application can be implemented by hardware, software, firmware, or any combination thereof. When implemented using software, these functions can be stored in a computer-readable medium or transmitted as one or more instructions or codes on a computer-readable medium. A computer-readable medium includes a computer storage medium and a communication medium, where the communication medium includes any medium that facilitates the transmission of a computer program from one place to another. The storage medium can be any available medium accessible by a general-purpose or special-purpose computer.

[0171] The above are only exemplary embodiments of the present application and are not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A target tracking method based on ultra-wideband radar, characterized in that, The method includes: Obtaining a radar frame obtained by sampling an echo signal by an ultra-wideband radar; Extracting scatter points based on the radar frame to obtain a measurement corresponding to the radar frame, where the measurement refers to the range cell where the scatter point is located, and the measurement corresponds one-to-one to the scatter point. The measurements corresponding to the radar frame are arranged in order of magnitude, and the number of measurements corresponding to the radar frame is n, and n is a positive integer; For the i-th measurement among the n measurements, determining whether other measurements are included in the search range corresponding to the i-th measurement, where the other measurements are greater than the i-th measurement, and i is a positive integer less than n; In the case where the other measurements are included in the search range, performing an averaging process on the i-th measurement and the other measurements to obtain an average measurement, and the aggregated measurement corresponding to the radar frame includes the average measurement; Determining the position information of at least one target object according to the aggregated measurement corresponding to the radar frame.

2. The method according to claim 1, wherein The method further includes: In the case where the other measurements are not included in the search range, retaining the i-th measurement, and the aggregated measurement corresponding to the radar frame includes the i-th measurement.

3. The method according to claim 1, characterized in that, The search range includes a front boundary and a rear boundary. The front boundary is the i-th measurement, the rear boundary is greater than the front boundary, and the rear boundary is separated from the front boundary by r range cells, where r is a positive integer.

4. The method according to claim 1, characterized in that, Before extracting the scatter points based on the radar frame, it further includes: Obtaining m radar frames that are continuous in the time domain; Obtaining a two-dimensional data matrix according to the m radar frames; Setting the k largest singular values among the singular vectors obtained by decomposing the two-dimensional data matrix to zero to obtain a processed two-dimensional data matrix, where k is a positive integer; Based on the processed two-dimensional data matrix, obtaining a filtered radar frame, and the filtered radar frame is used to extract scatter points to obtain the measurement corresponding to the radar frame; Wherein, the element in the x-th row and y-th column of the two-dimensional data matrix is used to indicate the echo intensity of the y-th radar frame at the x-th range cell, y is a positive integer less than or equal to m, x is a positive integer, and x is less than or equal to the total number of range cells included in each radar frame.

5. The method according to claim 4, wherein k is 1 or 2.

6. The method according to claim 4, wherein The value range of m is from 10 to 20.

7. The method according to claim 1, wherein The extracting scatter points based on the radar frame includes: Obtaining a waveform template, where the signal form of the waveform template is the same as that of the radar frame, and the range resolution of the waveform template is the same as that of the radar frame; Using the waveform template to extract scatter points in the radar frame.

8. The method according to claim 1, wherein The determining the position information of at least one target object according to the aggregated measurement corresponding to the radar frame includes: Performing a filtering process on the aggregated measurement corresponding to the radar frame to obtain a filtered measurement; Selecting valid measurements from the filtered measurements; Constructing a confirmation matrix based on the valid measurements; Splitting the confirmation matrix according to a target criterion to obtain at least one joint event, and the joint event is used to indicate the correspondence between the valid measurement and the target object; For the j-th object in the target objects, based on the interconnection probability of the joint event, determine the weighted measurement of the j-th object, where j is a positive integer; Determine the position information of the j-th object according to the weighted measurement of the j-th object; Wherein, the value of the element in the p-th row and q-th column of the confirmation matrix is 0 or 1. When the value is 0, the element is used to indicate that the p-th effective measurement is not within the range gate corresponding to the q-th target object; when the value is 1, the element is used to indicate that the p-th effective measurement is within the range gate corresponding to the q-th target object.

9. The method according to claim 8, wherein The target criteria include a single-source criterion and a single-measurement criterion. The single-source criterion means that the object corresponding to any effective measurement is unique, and the single-measurement criterion means that the effective measurement corresponding to any object in the radar frame is unique.

10. The method according to claim 8, wherein The selection of effective measurements from the filtered measurements includes: For the j-th object in the target objects, obtain the maximum movement speed of the j-th object and the range resolution of the ultra-wideband radar; Set the range gate corresponding to the j-th object according to the maximum movement speed of the j-th object and the range resolution; Determine the measurements within the range gate corresponding to the j-th object in the filtered measurements as the effective measurements.

11. The method according to claim 10, wherein The method further includes: In the case where there is no measurement in the filtered measurements that is within the range gate corresponding to the j-th object, determine the filtered measurements as the position information of the j-th object.

12. The method according to claim 1, wherein The signal form of the radar frame is a baseband signal form.

13. The method according to claim 1, wherein The system of the ultra-wideband radar is a pulse system.

14. The method according to any one of claims 1 to 13, characterized in that, The method further includes: For the j-th object in the target objects, concatenate the position information of the j-th object in the order of m radar frames in the time domain to obtain the movement trajectory of the j-th object, where m is an integer greater than 1 and j is a positive integer.

15. A target tracking device based on ultra-wideband radar, characterized in that, The device includes: An information acquisition module, configured to acquire a radar frame obtained by sampling an echo signal by an ultra-wideband radar; A measurement determination module, configured to extract scatter points based on the radar frame to obtain the measurements corresponding to the radar frame. The measurement refers to the range cell where the scatter point is located, and the measurement corresponds to the scatter point one by one. The measurements corresponding to the radar frame are arranged in order of magnitude, and the number of measurements corresponding to the radar frame is n, where n is a positive integer; An aggregation processing module, configured to, for the i-th measurement among the n measurements, determine whether there are other measurements within the search range corresponding to the i-th measurement, where the other measurements are greater than the i-th measurement, and i is a positive integer less than n; in the case where there are other measurements within the search range, perform an averaging process on the i-th measurement and the other measurements to obtain an average measurement, and the aggregated measurements corresponding to the radar frame include the average measurement; A position determination module, configured to determine the position information of at least one target object according to the aggregated measurements corresponding to the radar frame.

16. The device according to claim 15, characterized in that, The aggregation processing module is further configured to: When the other measurements are not included within the search range, the i-th measurement is retained, and the aggregated measurement corresponding to the radar frame includes the i-th measurement.

17. The device according to claim 15, characterized in that, The search range includes a front boundary and a rear boundary. The front boundary is the i-th measurement. The rear boundary is greater than the front boundary, and there are r distance units between the rear boundary and the front boundary, where r is a positive integer.

18. The device according to claim 15, characterized in that, The apparatus further includes: a radar frame acquisition module configured to acquire m consecutive radar frames in the time domain; a matrix determination module configured to obtain a two-dimensional data matrix based on the m radar frames; a matrix processing module configured to set to zero the k largest singular values in the singular vectors obtained by decomposing the two-dimensional data matrix, thereby obtaining a processed two-dimensional data matrix, where k is a positive integer; a radar frame determination module configured to obtain a filtered radar frame based on the processed two-dimensional data matrix, and the filtered radar frame is used to extract scatter points to obtain the measurement corresponding to the radar frame; wherein the element at the x-th row and y-th column in the two-dimensional data matrix is used to indicate the echo intensity of the y-th radar frame at the x-th distance unit, y is a positive integer less than or equal to m, x is a positive integer, and x is less than or equal to the total number of distance units included in each radar frame.

19. The device according to claim 18, wherein The k is 1 or 2.

20. The device according to claim 18, characterized in that, The value range of m is from 10 to 20.

21. The device according to claim 15, characterized in that, The measurement determination module is configured to: acquire a waveform template, where the signal form of the waveform template is the same as that of the radar frame, and the range resolution of the waveform template is the same as that of the radar frame; extract scatter points in the radar frame using the waveform template.

22. The device according to claim 15, characterized in that, The position determination module includes: a filtering processing unit configured to perform filtering processing on the aggregated measurement corresponding to the radar frame to obtain a filtered measurement; a measurement selection unit configured to select valid measurements from the filtered measurements; a matrix construction unit configured to construct a confirmation matrix based on the valid measurements; an event determination unit configured to split the confirmation matrix according to a target criterion to obtain at least one joint event, and the joint event is used to indicate the correspondence between the valid measurement and the target object; a measurement weighting unit configured to, for the j-th object in the target object, determine a weighted measurement of the j-th object based on the interconnection probability of the joint event, where j is a positive integer; an information determination unit configured to determine the position information of the j-th object according to the weighted measurement of the j-th object; wherein the value of the element at the p-th row and q-th column in the confirmation matrix is 0 or 1. When the value is 0, the element is used to indicate that the p-th valid measurement is not located within the range gate corresponding to the q-th target object; when the value is 1, the element is used to indicate that the p-th valid measurement is located within the range gate corresponding to the q-th target object.

23. The device according to claim 22, characterized in that, The target criterion includes a single-source criterion and a single-measurement criterion. The single-source criterion means that the object corresponding to any valid measurement is unique, and the single-measurement criterion means that the valid measurement corresponding to any object in the radar frame is unique.

24. The device according to claim 22, wherein The measurement selection unit is configured to: For the j-th object in the target objects, obtain the maximum movement speed of the j-th object and the range resolution of the ultra-wideband radar; Set the range gate corresponding to the j-th object according to the maximum movement speed of the j-th object and the range resolution; Determine the measurements within the range gate corresponding to the j-th object in the filtered measurements as the valid measurements.

25. The device according to claim 24, characterized in that, The information determination unit is further configured to: In the case that there are no measurements within the range gate corresponding to the j-th object in the filtered measurements, determine the filtered measurements as the position information of the j-th object.

26. The device according to claim 15, characterized in that, The signal form of the radar frame is a baseband signal form.

27. The device according to claim 15, characterized in that, The system of the ultra-wideband radar is a pulse system.

28. The device according to any one of claims 15 to 27, characterized in that, The device further includes: A trajectory determination module, configured to, for the j-th object in the target objects, concatenate the position information of the j-th object in the chronological order of m radar frames in the time domain to obtain the movement trajectory of the j-th object, where m is an integer greater than 1 and j is a positive integer.

29. A computer device, characterized in that, The computer device includes a processor and a memory, and the memory stores a computer program, and the computer program is loaded and executed by the processor to implement the ultra-wideband radar-based target tracking method according to any one of claims 1 to 14.

30. A computer-readable storage medium, characterized in that, A computer program is stored in the storage medium, and the computer program is used to be executed by the processor of the computer device to implement the ultra-wideband radar-based target tracking method according to any one of claims 1 to 14.

31. A chip, characterized in that, The chip includes programmable logic circuits and / or program instructions, and when the chip runs on the computer device, it is used to implement the ultra-wideband radar-based target tracking method according to any one of claims 1 to 14.

32. A computer program product, characterized in that, When the computer program product runs on the computer device, the computer device is caused to execute the ultra-wideband radar-based target tracking method according to any one of claims 1 to 14.

Images