Method, apparatus and computer readable storage medium for tracking human motion

Abstract

The application discloses a human motion tracking method, device and computer readable storage medium. The human motion tracking method comprises the following steps: acquiring a motion feature of a human body; predicting a motion trend of the human body according to the motion feature; and controlling a radar device to emit a first radar signal to the human body according to the motion trend. The application predicts the motion trend of the human body, determines the chest and abdomen position of the human body based on the motion trend, realizes real-time tracking of the chest and abdomen position of the human body, and then improves the accuracy of the detection result of the physiological parameter of the human body.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of signal processing, in particular to a human motion tracking method and device and computer readable storage medium. BACKGROUND

[0002] In the process of human motion, real-time monitoring of breathing and heart rate can reflect the motion condition (such as aerobic, anaerobic, etc.) to guide the motion, and can also provide early warning in case of abnormal physical condition. However, the existing gymnasium exercise equipment usually does not have the function of tracking human motion, that is, it cannot detect the physiological parameters of the human body in real time. Therefore, users usually monitor the physiological parameters in the process of motion by wearing smart watches. However, such contact type detection devices need to be close to the user's skin, causing discomfort, and in some cases, may cause inflammation. In addition, such contact type detection devices are easily disturbed by vibration and sweat, thereby causing the detection result to deviate and reducing the accuracy of the detection result. SUMMARY

[0003] The embodiments of the present application provide a human motion tracking method, device and computer readable storage medium, aiming to solve the problems of low accuracy of physiological parameter detection result caused by sweat interference and discomfort of traditional contact type.

[0004] To achieve the above-mentioned purpose, one aspect of the present application provides a human motion tracking method, which comprises:

[0005] obtaining the motion characteristics of the human body;

[0006] predicting the motion trend of the human body according to the motion characteristics;

[0007] controlling the radar device to emit a first radar signal to the human body according to the motion trend.

[0008] Optionally, the step of predicting the motion trend of the human body according to the motion characteristics comprises:

[0009] obtaining a preset motion model;

[0010] predicting the motion trend of the human body at the next moment according to the preset motion model and the motion characteristics.

[0011] Optionally, the step of controlling the radar device to emit a first radar signal to the human body according to the motion trend comprises:

[0012] determining the emission parameters of the first radar signal according to the motion trend;

[0013] controlling the radar device to emit the first radar signal to the human body according to the emission parameter, and adjusting the measurement precision of the physiological parameter of the human body.

[0014] Optionally, the step of acquiring the motion feature of the human body comprises:

[0015] controlling the radar emission device to emit a second radar signal to the human body;

[0016] receiving a second echo signal reflected by the human body, and detecting the motion feature of the human body according to the second echo signal.

[0017] Optionally, the step of controlling the radar emission device to emit a second radar signal to the human body comprises:

[0018] acquiring a three-dimensional image of the chest and abdomen of the human body and skeleton information of the human body;

[0019] determining the chest position and the abdomen position of the human body according to the three-dimensional image of the chest and abdomen and / or the skeleton information;

[0020] controlling the radar emission device to emit the second radar signal to the chest position and the abdomen position.

[0021] Optionally, the step of acquiring the motion feature of the human body according to the second echo signal comprises:

[0022] reconstructing a three-dimensional image of the chest and abdomen of the human body and skeleton information of the human body according to the second echo signal;

[0023] acquiring the motion feature of the human body according to the reconstructed three-dimensional image of the chest and abdomen and / or skeleton information.

[0024] Optionally, the method further comprises:

[0025] receiving an echo signal reflected by the human body;

[0026] acquiring a physiological parameter of the human body according to the echo signal.

[0027] Optionally, the physiological parameter comprises a breathing frequency and a heartbeat frequency, and the step of acquiring the physiological parameter of the human body according to the echo signal comprises:

[0028] performing data processing on the echo signal to acquire a vibration signal of the chest and abdomen of the human body;

[0029] extracting a breathing signal and a heartbeat signal of the human body according to the vibration signal;

[0030] determining a breathing frequency of the human body according to the breathing signal, and determining a heartbeat frequency of the human body based on the heartbeat signal.

[0031] In addition, to achieve the above object, another aspect of the present application provides a human motion tracking device, which comprises a memory, a processor, and a human motion tracking program stored in the memory and running on the processor, and the processor implements the steps of the human motion tracking method as described above when executing the human motion tracking program.

[0032] In addition, to achieve the above object, another aspect of the present application provides a computer readable storage medium, which stores a human motion tracking program, and the human motion tracking program implements the steps of the human motion tracking method as described above when executed by a processor.

[0033] The present application provides a human motion tracking method, which comprises the following steps: acquiring a motion feature of a human body; predicting a motion trend of the human body according to the motion feature; and controlling a radar device to emit a first radar signal to the human body according to the motion trend. The present application predicts the motion trend of the human body, determines the chest and abdomen position of the human body based on the motion trend, realizes real-time tracking of the chest and abdomen position of the human body, and improves the accuracy of the detection result of the physiological parameter of the human body. BRIEF DESCRIPTION OF DRAWINGS

[0034] Figure 1 The terminal structure schematic diagram of the hardware running environment involved in the embodiment of the present application;

[0035] Figure 2 The flowchart of the first embodiment of the human motion tracking method of the present application;

[0036] Figure 3 The flowchart before step S10 in the second embodiment of the human motion tracking method of the present application;

[0037] Figure 4 The flowchart of the third embodiment of the human motion tracking method of the present application;

[0038] Figure 5 The schematic diagram of each functional module in the human motion tracking device of the present application.

[0039] The implementation, functional features and advantages of the present application will be further described with reference to the embodiments and the accompanying drawings. DETAILED DESCRIPTION

[0040] It should be understood that the specific embodiments described herein are merely intended to explain the present application, and are not intended to limit the present application.

[0041] The main solution of the embodiment of the application is: acquiring a motion feature of a human body; predicting a motion trend of the human body according to the motion feature; and controlling a radar device to emit a first radar signal to the human body according to the motion trend.

[0042] Since the existing gymnasium fitness equipment generally does not have the function of tracking human motion, that is, cannot detect the physiological parameters of the human body in real time, based on this, the user generally monitors the physiological parameters in the motion process by wearing a smart watch, but such a contact type detection device needs to be close to the skin of the user, causing discomfort, and in some cases, may cause inflammation, in addition, such a contact type detection device is easily disturbed by vibration and sweat, thereby causing the detection result to deviate and reducing the accuracy of the detection result.

[0043] The application acquires the motion feature of the human body, predicts the motion trend of the human body according to the motion feature, and controls the radar device to emit the first radar signal to the human body according to the motion trend. The application predicts the motion trend of the human body, determines the chest and abdomen position of the human body based on the motion trend, realizes real-time tracking of the chest and abdomen position of the human body, and then improves the accuracy of the detection result of the physiological parameters of the human body.

[0044] As shown in Figure 1 , a terminal device structure schematic diagram of a hardware running environment related to the embodiment of the application is shown. Figure 1 As shown in

[0045] As shown in Figure 1 , the terminal device can include: a processor 1001 such as a CPU, a network interface 1004, a user interface 1003, a memory 1005, and a communication bus 1002. The communication bus 1002 is used to realize the connection and communication between the components. The user interface 1003 can include a display screen (Display), an input unit such as a keyboard (Keyboard), and an optional user interface 1003 can also include a standard wired interface, a wireless interface. The network interface 1004 can optionally include a standard wired interface, a wireless interface (such as a WI-FI interface). The memory 1005 can be a high-speed RAM memory, or a stable memory (non-volatile memory) such as a magnetic disk memory. The memory 1005 can also be an independent storage device from the aforementioned processor 1001.

[0046] Those skilled in the art can understand that Figure 1 the terminal device structure shown in the embodiment of the application does not constitute a limitation on the terminal device, and can include more or fewer components than the diagram, or combine certain components, or different component arrangements.

[0047] As shown in Figure 1As shown, the memory 1005 as a computer readable storage medium can include a human motion tracking program.

[0048] In Figure 1 In the terminal device shown, the network interface 1004 is mainly used for data communication with the background server; the user interface 1003 is mainly used for data communication with the client (user end); the processor 1001 can be used to call the human motion tracking program in the memory 1005 and perform the following operations:

[0049] Obtain the motion characteristics of the human body;

[0050] Predict the motion trend of the human body according to the motion characteristics;

[0051] Control the radar device to emit a first radar signal to the human body according to the motion trend.

[0052] Reference Figure 2 , Figure 2 The flowchart of the first embodiment of the human motion tracking method of the present application.

[0053] The embodiment of the present application provides a human motion tracking method, and it should be noted that although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that here.

[0054] The human motion tracking method of the present embodiment includes the following steps:

[0055] Step S10, obtaining the motion characteristics of the human body;

[0056] It should be noted that due to different types of movements, the corresponding exercise equipment is also different, and at the same time, the placement position of the detection device (such as a sensor) is also different. In the process of human motion, a visual camera, a structured light camera or a TOF camera and a millimeter wave radar can be used to position and identify the chest and abdomen of the human body, and to track and measure the overall movement of the chest and abdomen. Among them, before tracking and measuring the overall movement of the chest and abdomen of the human body, the camera module (including visual camera, structured light camera or TOF camera) and millimeter wave radar module need to be calibrated, and the mapping relationship between the world coordinate system, camera coordinate system, millimeter wave radar coordinate system, radar data space coordinate system and image coordinate system is established.

[0057] In this embodiment, during the movement of the human body, the camera in the human body movement tracking system captures the image of the human body, and then the movement characteristics of the human body are obtained according to the captured image. For example, when the human body movement tracking system detects that the user is moving on the fitness equipment, the image of the human body is captured by the camera module, and then the human body posture is recognized and calculated based on the image deep learning model to obtain the movement characteristics of the human body, such as body posture, movement trajectory, movement time, movement speed, movement rate and the like. The body posture refers to the state of the body and each part of the body in different movement stages. The movement trajectory refers to the spatial characteristics of the action of the part of the body from the starting position to the end. The movement trajectory is represented by the movement trajectory direction, the movement trajectory form and the movement amplitude. The movement time refers to the time required for the human body to complete the movement action. The movement speed refers to the displacement distance of the body or a part of the body in a unit of time. The movement rate refers to the number of repetitions of the movement action in a unit of time.

[0058] Step S20, predicting the movement trend of the human body according to the movement characteristics;

[0059] It should be noted that most of the movement actions are periodic, that is, the same movement action is repeated in a period of time, such as running, pull-ups, sit-ups and the like. Based on this, the movement action of the human body at the next moment can be preset, so as to realize the tracking of the human body movement.

[0060] In this embodiment, the movement trend of the human body at the next moment is preset based on the movement characteristics. Specifically, a preset movement model is obtained, and then the movement trend of the human body at the next moment is preset based on the preset movement model and the movement characteristics.

[0061] Optionally, the movement action of the human body and the frequency of the movement action are obtained according to the movement characteristics, and then the movement trend of the human body is determined according to the frequency of the movement action. For example, it is assumed that the user does pull-ups on the equipment in the gym. At this time, the image in a period of time is captured by the camera module, the movement action of the human body in this period of time is extracted based on the captured image, and then the frequency of each movement action is counted. The movement trend of the human body at the next moment, that is, the movement action at the next moment, is predicted based on the frequency of each movement action.

[0062] Step S30, controlling the radar device to emit a first radar signal to the human body according to the movement trend;

[0063] After determining the motion trend of the human body at the next moment, the radar device is controlled to emit a first radar signal to the human body according to the motion trend. In an embodiment, the emission parameters of the radar emission device are determined according to the motion trend, which mainly include but are not limited to: emission direction, emission distance, emission power, etc. Then, the radar emission device is controlled to emit the first radar signal to the human body according to the emission parameters, and the measurement accuracy of the physiological parameters of the human body is further adjusted. For example, it is assumed that the chest and abdomen of the human body are tracked. Then, the position information of the chest and abdomen of the human body at the next moment is determined according to the motion trend. Then, the radar emission device is controlled to emit the first radar signal to the chest and abdomen of the human body based on the position information.

[0064] The embodiment of the present application can obtain the motion characteristics of the human body, predict the motion trend of the human body according to the motion characteristics, and control the radar device to emit a first radar signal to the human body according to the motion trend. The present application can predict the motion trend of the human body, determine the chest and abdomen positions of the human body based on the motion trend, realize real-time tracking of the chest and abdomen positions of the human body, and improve the accuracy of the detection results of the physiological parameters of the human body.

[0065] Further, with reference to Figure 3 , based on the first embodiment, the present application proposes a second example of the tracking method of the human body motion.

[0066] The second example of the tracking method of the human body motion of the present application is different from the first embodiment in that the step of obtaining the motion characteristics of the human body includes:

[0067] Step S11, controlling the radar emission device to emit a second radar signal to the human body;

[0068] When detecting that the user is exercising on the exercise machine, the three-dimensional imaging of the chest and abdomen of the human body and the skeleton information of the human body are acquired through the camera module. In an embodiment, the field of view of the camera module and the millimeter wave radar module can cover the whole human body, or at least the range of the chest and abdomen. For the case that the whole body can be covered, the human skeleton can be extracted from the collected images, and the three-dimensional posture information of the human body is acquired by using the structured light or TOF camera. For the case that the whole body cannot be covered, but at least the range of the chest and abdomen can be covered, the three-dimensional imaging of the chest and abdomen can be performed by using the structured light camera or the TOF camera. For example, by using the TOF or multi-transmit multi-receive radar technology, the point cloud information in the field of view of the sensor (TOF or radar) can be generated, that is, the three-dimensional coordinates of the object surface in space. Then, the acquired point cloud information is subjected to point cloud filtering processing, which specifically includes: since the relative position of the target object (human body) and the sensor is relatively fixed, the position information of the human body and the sensor can be known in advance, and based on the position information, the points falling outside the range can be removed to exclude the interference of the background or surrounding objects. Then, the point cloud is subjected to CFAR (Constant False-Alarm Rate) to exclude the interference of noise points (such as radar). Further, DBSCAN (Density-Based Spatial Clustering of Applications with Noise) is used for clustering analysis to obtain relatively "clean" point cloud. The point cloud after the processing is the surface space coordinates of the human body facing the sensor. The point cloud after the above filtering processing is input into the pre-trained human body model to obtain the state parameters representing the current human body posture, and the three-dimensional imaging of the chest and abdomen of the human body is acquired based on the state parameters.

[0069] Optionally, according to different imaging tissues and imaging methods, radar waves of various wave bands such as UWB and millimeter wave can be used, and then the received signals are acquired by using reflection, scattering and transmission, wherein the acquired information mainly includes time interval between signal transmission and reception, signal strength, phase and other information, and further information of the interface between the surface and internal tissues of the human body. Further, the radar can form spatial resolution by mechanical scanning, radar antenna cascade and multiple transmission and reception, that is, the spatial position source of the received signal can be confirmed, so as to form a radar data image with spatial resolution. The continuous scanning can be performed, that is, on the basis of the spatial resolution, a certain time resolution is provided, and dynamic information can be processed. Then, the acquired radar information can be reconstructed in various ways to form an image expression of density or related physical quantity corresponding to the spatial position of the human tissue, for example, imaging the shape of the human surface, imaging the tomographic information of the human body, and imaging the chest and abdomen of the human body, wherein the imaging physical quantity can be tissue density, tissue elasticity, absorption rate of a specific wave band radar wave and the like.

[0070] In an embodiment, after the skeleton information of the human body and the three-dimensional imaging of the chest and abdomen are acquired, the chest position and the abdomen position of the human body are determined according to the three-dimensional imaging of the chest and abdomen and / or the skeleton information, and then the radar emission device is controlled to emit the second radar signal to the chest position and the abdomen position. For example, after the three-dimensional imaging of the chest and abdomen of the human body is determined, the chest position and the abdomen position of the human body are determined, and then the radar emission device is directed to emit the second radar signal to the chest and the abdomen of the human body. Alternatively, after the skeleton information of the human body is determined, the chest position and the abdomen position of the human body are determined according to the arrangement information of the skeleton, and then the radar emission device is directed to emit the second radar signal to the chest and the abdomen of the human body. Alternatively, after the chest position and the abdomen position of the human body are determined by the three-dimensional imaging of the chest and abdomen, the skeleton information of the human body is used to verify whether the positions are correct again, so as to improve the accuracy of the positions. Assuming that the positions determined twice match, the radar emission device is directed to emit the second radar signal to the chest and the abdomen of the human body.

[0071] In step S12, the second echo signal reflected by the human body is received, and the motion feature of the human body is detected according to the second echo signal.

[0072] In the embodiment, after the radar transmitting device transmits the radar signal (i.e., electromagnetic wave signal) to the chest and abdomen of the human body, the electromagnetic wave signal is reflected after encountering the human body in space, then the reflected second echo signal is received by the radar receiving device, the three-dimensional imaging of the chest and abdomen of the human body is reconstructed according to the second echo signal, and the skeleton information of the human body is obtained, and then the motion characteristics of the human body are obtained according to the reconstructed three-dimensional imaging of the chest and abdomen and / or the skeleton information, including body posture, motion trajectory, motion time, motion speed, motion rate and the like.

[0073] In the embodiment, the radar transmitting device is controlled to emit the second radar signal to the human body in a directional manner, the second echo signal reflected by the human body is received, and then the motion characteristics of the human body are obtained based on the second echo signal, so that the accuracy of the motion characteristics is improved.

[0074] Further, with reference to Figure 4 , based on the first and second embodiments, the third example of the human motion tracking method is proposed.

[0075] The third example of the human motion tracking method of the present application is different from the first and second embodiments in that after the step of controlling the radar device to emit the first radar signal to the human body according to the motion trend, the step comprises:

[0076] Step S40, receiving the echo signal reflected by the human body;

[0077] In the embodiment, after the radar transmitting device transmits the radar signal (i.e., electromagnetic wave signal) to the chest and abdomen of the human body, the electromagnetic wave signal is reflected after encountering the human body in space, then the reflected second echo signal is received by the radar receiving device, the three-dimensional imaging of the chest and abdomen of the human body is reconstructed according to the second echo signal, and the skeleton information of the human body is obtained, and then the motion characteristics of the human body are obtained according to the reconstructed three-dimensional imaging of the chest and abdomen and / or the skeleton information, including body posture, motion trajectory, motion time, motion speed, motion rate and the like.

[0078] Step S50, obtaining the physiological parameters of the human body according to the echo signal.

[0079] It should be noted that when a contact type device (such as a smart watch, a smart phone, etc.) is used to detect physiological parameters of a human body, the following shortcomings exist: low endurance, since the contact type device is mostly a device that needs to be charged, when the power is too low, the device cannot work; low accuracy of detection results, since the contact type device needs to be close to the skin of the user for detection, once deviating from the skin of the user, the detection result may be deviated; for users with sensitive skin, long-term wearing of the contact type device may cause skin diseases. Based on this, the present application uses a non-contact type device to monitor physiological indicators of a human body, wherein the non-contact human motion tracking system of the present application is mainly composed of a visual camera, a structured light camera or a TOF (Time of Flight) camera, a millimeter wave radar and the like, can be adapted to different fitness equipment, and realizes real-time monitoring of physiological indicators such as heart rate and respiration of a human body in motion. The principle of radar measuring human respiration and heartbeat is that respiration and heartbeat and the like will cause the fluctuation of the chest cavity, and then cause the change of the radial distance between the radar and the measured human body, and by measuring the change of the radial distance, the human respiration and heartbeat signals can be extracted.

[0080] When the radar receiving device receives the reflected echo signal, the echo signal is sent to the data processor, and the physiological parameters of the human body are obtained by the data processor processing the echo signal. In an embodiment, the echo signal is processed to obtain the vibration signals of the chest and abdomen of the human body, wherein the data processing process usually includes: fast time dimension processing (Range-FFT) and slow time dimension processing (Doppler-FFT), CFAR algorithm filtering false objects, extracting phase signals from Range bin, direct current elimination, extracting phase signals of specified range bin, phase unwrapping, applying appropriate band-pass filtering, and obtaining vibration signals related to chest, abdomen, respiration and heart rate. Then, the respiration information and heartbeat information of the human body are extracted according to the vibration signals, the respiration frequency of the human body is determined according to the respiration information, and the heartbeat frequency of the human body is determined based on the heartbeat information. For example, the distance dimension information of the echo signal is subjected to Fourier transform, then maximum value search is performed, and the echo sequence of the human body is obtained by extracting data near the maximum value. The waveform analysis module obtains the vibration signals of the chest and abdomen of the human body from the echo sequence by filtering and screening, extracts the respiration signal and the heart rate signal of the human body based on the vibration signals, and respectively performs noise reduction and fast Fourier transform on the two characteristic signals, restores the respiration frequency and the heartbeat frequency of the human body in the motion process, and completes the measurement of the heart rate and the respiration.

[0081] The embodiment detects physiological parameters of a human body through a millimeter wave radar, and has the following advantages: strong endurance, since the detection device is not a battery charging device, the device can work for a long time; high accuracy of detection results, since the detection method is non-contact, the problem of inaccurate detection results caused by deviation of the device from the skin is avoided; and improved user experience.

[0082] In addition, the application further provides a human motion tracking device, which comprises a memory, a processor, and a human motion tracking program stored in the memory and running on the processor. The device obtains the motion characteristics of the human body, predicts the motion trend of the human body according to the motion characteristics, and controls the radar device to emit a first radar signal to the human body according to the motion trend. The embodiment predicts the motion trend of the human body, determines the chest and abdomen position of the human body based on the motion trend, realizes real-time tracking of the chest and abdomen position of the human body, and improves the accuracy of the detection results of the physiological parameters of the human body.

[0083] Further, with reference to Figure 5 , the human motion tracking device 100 comprises an acquisition module 10, a prediction module 20, and an emission module 30, wherein:

[0084] The acquisition module 10 is configured to obtain the motion characteristics of the human body.

[0085] The prediction module 20 is configured to predict the motion trend of the human body according to the motion characteristics.

[0086] The emission module 30 is configured to control the radar device to emit a first radar signal to the human body according to the motion trend.

[0087] Further, the prediction module 20 comprises a first acquisition unit and a prediction unit.

[0088] The first acquisition unit is configured to acquire a preset motion model.

[0089] The prediction unit is configured to predict the motion trend of the human body at the next moment according to the preset motion model and the motion characteristics.

[0090] Further, the emission module 30 comprises a determination unit and a first emission unit.

[0091] The determination unit is configured to determine emission parameters of the first radar signal according to the motion trend.

[0092] The first emission unit is configured to control the radar device to emit the first radar signal to the human body according to the emission parameters, and adjust the measurement accuracy of the physiological parameters of the human body.

[0093] Further, the acquisition module 10 comprises a second transmitting unit and a first receiving unit;

[0094] The second transmitting unit is configured to control the radar transmitting device to transmit a second radar signal to the human body.

[0095] The first receiving unit is configured to receive a second echo signal reflected by the human body, and detect a motion feature of the human body according to the second echo signal.

[0096] Further, the second transmitting unit comprises a first acquisition subunit, a first determination subunit and a second transmitting subunit.

[0097] The first acquisition subunit is configured to acquire three-dimensional imaging of a chest and an abdomen of the human body and skeleton information of the human body.

[0098] The first determination subunit is configured to determine a chest position and an abdomen position of the human body according to the three-dimensional imaging of the chest and the abdomen and / or the skeleton information.

[0099] The second transmitting subunit is configured to control the radar transmitting device to transmit the second radar signal to the chest position and the abdomen position.

[0100] Further, the receiving unit comprises a construction subunit and a second acquisition subunit.

[0101] The construction subunit is configured to reconstruct three-dimensional imaging of a chest and an abdomen of the human body and skeleton information of the human body according to the second echo signal.

[0102] The second acquisition subunit is configured to acquire a motion feature of the human body according to the reconstructed three-dimensional imaging of the chest and the abdomen and / or skeleton information.

[0103] Further, the human body motion tracking device 100 further comprises a receiving module.

[0104] The receiving module is configured to receive an echo signal reflected by the human body.

[0105] The acquisition module 10 is further configured to acquire a physiological parameter of the human body according to the echo signal.

[0106] Further, the acquisition module 10 comprises a third acquisition unit, an extraction unit and a second determination unit.

[0107] The third acquisition unit is configured to perform data processing on the echo signal to acquire a vibration signal of a chest and an abdomen of the human body.

[0108] The extraction unit is configured to extract a breathing signal and a heartbeat signal of the human body according to the vibration signal.

[0109] The second determination unit is configured to determine a breathing frequency of the human body according to the breathing signal, and determine a heartbeat frequency of the human body based on the heartbeat signal.

[0110] The implementation of the functions of each module of the human motion tracking device is similar to the processes in the method embodiments, and will not be described again.

[0111] In addition, the present application also provides a computer readable storage medium, and the computer readable storage medium stores a human motion tracking method program. The human motion tracking method program is executed by a processor to implement the steps of the human motion tracking method.

[0112] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can be in the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can be in the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0113] The present application is described with reference to flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and the combination of the flows and / or blocks in the flowcharts and / or block diagrams can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing apparatus to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing apparatus produce a device implemented in the flowcharts and / or block diagrams. Figure 1 The device that implements the functions specified in one flow or multiple flows and / or blocks. Figure 1 The device that implements the functions specified in one block or multiple blocks.

[0114] These computer program instructions can also be stored in a computer readable storage medium that can guide the computer or other programmable data processing apparatus to work in a specific manner, so that the instructions stored in the computer readable storage medium produce a manufactured product including instruction devices that implement the flowcharts and / or block diagrams. Figure 1 The device that implements the functions specified in one flow or multiple flows and / or blocks. Figure 1 The device that implements the functions specified in one block or multiple blocks.

[0115] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0116] It should be noted that any reference signs placed between parentheses in the claims should not be construed as limiting the claims. The word "comprising" does not exclude the presence of components or steps not listed in the claims. The word "a" or "an" preceding a component does not exclude the presence of a plurality of such components. This application can be implemented by means of hardware comprising several different components and by means of a suitably programmed computer. In a unit claim enumerating several means, several of these means may be embodied by the same item of hardware. The use of the words first, second, and third, etc., does not indicate any order. These words can be interpreted as names.

[0117] Although alternative embodiments of this application have been described, those skilled in the art, upon learning the basic inventive concept, can make further changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the alternative embodiments as well as all changes and modifications falling within the scope of this application.

[0118] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of the claims of this application and their equivalents, this application also intends to include such modifications and variations.

Claims

1. A method for tracking human motion, characterized in that, The method includes: When a user is detected moving on exercise equipment and the information collection cannot cover the entire human body, point cloud information within the radar range is obtained, which is the three-dimensional coordinates of the object's surface in space. The point cloud information is processed by point cloud filtering and cluster analysis is performed to obtain filtered point cloud information. The filtered point cloud information is input into a pre-trained human body model to obtain state parameters representing the current human body posture. Based on the state parameters, obtain three-dimensional images of the human chest and abdomen, as well as obtain the skeletal information of the human body; The chest and abdomen positions of the human body are determined based on the three-dimensional imaging of the chest and abdomen and the skeletal information. The location of the chest and abdomen is verified to be correct using the skeletal information of the human body. If a position match is determined, the radar transmitter is controlled to transmit a second radar signal to the chest position and the abdomen position; Receive the second echo signal reflected by the human body, and reconstruct a three-dimensional image of the chest and abdomen of the human body, as well as the skeletal information of the human body, based on the second echo signal; The motion characteristics of the human body are obtained based on the reconstructed three-dimensional imaging and skeletal information of the chest and abdomen. The motion characteristics include body posture, motion trajectory, motion time, motion speed, and motion rate. The body posture refers to the state of the body and its various parts at different stages of motion. The motion trajectory refers to the spatial characteristics of the movement formed by the route taken by a part of the body from the starting position to the end position. The motion trajectory is represented by the direction of the motion trajectory, the form of the motion trajectory, and the amplitude of the motion. Obtain the preset motion model; Predict the human body's movement trend at the next moment based on the preset motion model and the motion characteristics; The radar device is controlled to transmit a first radar signal to the human body based on the movement trend.

2. The human motion tracking method as described in claim 1, characterized in that, The step of controlling the radar device to transmit a first radar signal to the human body based on the motion trend includes: The transmission parameters of the first radar signal are determined based on the motion trend; The radar device is controlled to transmit the first radar signal to the human body according to the transmission parameters, and the measurement accuracy of the human body's physiological parameters is adjusted.

3. The human motion tracking method as described in claim 1, characterized in that, The method further includes: Receive the echo signal reflected by the human body; Physiological parameters of the human body are obtained based on the echo signal.

4. The human motion tracking method as described in claim 3, characterized in that, The physiological parameters include respiratory rate and heart rate, and the step of obtaining the physiological parameters of the human body based on the echo signal includes: The echo signal is processed to obtain the vibration signals of the chest and abdomen of the human body; The human body's respiratory and heartbeat signals are extracted based on the vibration signals. The respiratory rate of the human body is determined based on the respiratory signal, and the heart rate of the human body is determined based on the heartbeat signal.

5. A human motion tracking device, characterized in that, The human motion tracking device includes a memory, a processor, and a human motion tracking program stored in the memory and running on the processor. When the processor executes the human motion tracking program, it implements the steps of the method as described in any one of claims 1 to 4.

6. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a human motion tracking program, which, when executed by a processor, implements the steps of the method as described in any one of claims 1 to 4.

Images