Fall detection method and radar device

Abstract

The embodiment of the application provides a fall detection method and a radar device, relates to the technical field of signal processing, and can perform fall detection under the premise of protecting the privacy and safety of a user and can guarantee the accuracy of fall detection. The method comprises the following steps: collecting radar data in a target space; obtaining first posture feature information of a target human body at a first moment and second posture feature information of the target human body at a second moment according to the radar data, wherein the time interval between the first moment and the second moment is less than or equal to a preset time interval; determining whether the target human body falls in a first direction according to the first posture feature information and the second posture feature information, wherein the first direction is the direction from a radar device to the target human body in a horizontal plane; and / or determining whether the target human body falls in a second direction according to the first posture feature information and the second posture feature information, wherein the second direction is perpendicular to the first direction in the horizontal plane.

Description

Technical Field

[0001] This application relates to the field of signal processing technology, and in particular to a fall detection method and radar device. Background Technology

[0002] Falls are a common occurrence in daily life, and due to individual differences in physical condition, they can cause varying degrees of injury. For the elderly, because falls are unpredictable and unforeseen, if they do not receive timely and effective treatment for an extended period, it can lead to long-term paralysis or even endanger their lives. Therefore, fall detection is essential to ensure that the elderly receive timely treatment after a fall.

[0003] Existing contact-based fall detection technologies typically rely on wearable devices, using accelerometers to detect motion patterns and determine the state of a fall. However, the accuracy of these methods is affected by how the wearable device is worn; for example, incorrect placement can lead to significant errors. Existing non-contact fall detection technologies are usually based on image and video detection methods. However, these methods can infringe on privacy and cannot be applied to sensitive monitoring areas such as bathrooms and bedrooms. Summary of the Invention

[0004] This application provides a fall detection method and radar device to improve the accuracy of fall detection while protecting user privacy and security.

[0005] In a first aspect, embodiments of this application provide a fall detection method, the method comprising: collecting radar data in a target space; acquiring, based on the radar data, first posture feature information of a target human body at a first moment and second posture feature information at a second moment, wherein the time interval between the first moment and the second moment is less than or equal to a preset time interval; determining, based on the first posture feature information and the second posture feature information, whether the target human body has fallen in a first direction, wherein the first direction is the direction from the radar device to the target human body in a horizontal plane; and / or, determining, based on the first posture feature information and the second posture feature information, whether the target human body has fallen in a second direction, wherein the second direction is perpendicular to the first direction in a horizontal plane.

[0006] Based on the above technical solution, fall detection is performed by collecting radar data without requiring the acquisition of user image or video information, thus protecting user privacy and making it suitable for private areas such as bedrooms and bathrooms. Furthermore, posture feature information at different times (i.e., first posture feature information at the first moment and second posture feature information at the second moment) is extracted from the radar data. Since the time interval between the first and second moments is less than a preset time interval, combining the first and second posture feature information allows for the understanding of the target human's movement within a short period. This enables the determination of whether the target human has fallen in the first and / or second direction, achieving clearer and more accurate fall detection.

[0007] In a second aspect, a radar device is provided, comprising an acquisition unit and a processing unit. The acquisition unit is used to collect radar data within a target space. The processing unit is used to acquire, based on the radar data, first posture feature information of a target human body at a first moment and second posture feature information at a second moment, wherein the time interval between the first moment and the second moment is less than or equal to a preset time interval. The processing unit is further used to determine, based on the first posture feature information and the second posture feature information, whether the target human body has fallen in a first direction, wherein the first direction is the direction from the radar device to the target human body in a horizontal plane; and / or, based on the first posture feature information and the second posture feature information, whether the target human body has fallen in a second direction, wherein the second direction is perpendicular to the first direction in a horizontal plane.

[0008] Thirdly, a radar device is provided, comprising: at least one processor and at least one memory; at least one memory stores computer instructions that, when executed by the radar device, cause the radar device to perform any of the methods described in the first aspect.

[0009] Fourthly, a computer-readable storage medium is provided, the computer-readable storage medium including computer instructions that, when executed on a computer, cause the computer to perform any of the methods described in the first aspect.

[0010] Fifthly, a computer program product comprising computer instructions is provided, which, when executed on a computer, causes the computer to perform any of the methods provided in the first aspect above.

[0011] The technical effects of any of the possible solutions in the second to fifth aspects mentioned above can be referred to the corresponding beneficial effects analysis in the first aspect, and will not be repeated here. Attached Figure Description

[0012] Figure 1 A flowchart of a fall detection method provided in an embodiment of this application;

[0013] Figure 2 This is a schematic diagram of an application scenario provided by an embodiment of this application;

[0014] Figure 3 A flowchart of another fall detection method provided in this application embodiment;

[0015] Figure 4 A flowchart of another fall detection method provided in this application embodiment;

[0016] Figure 5 This is a schematic diagram of the composition of a radar device provided in an embodiment of this application;

[0017] Figure 6 This is a schematic diagram of the hardware structure of a radar device provided in an embodiment of this application. Detailed Implementation

[0018] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0019] The terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this application, unless otherwise stated, "a plurality of" means two or more.

[0020] In the description of this application, it should be noted that, unless otherwise expressly specified and limited, the terms "connected" and "linked" should be interpreted broadly, for example, as a fixed connection, a detachable connection, or an integral connection. Those skilled in the art can understand the specific meaning of the above terms in this application based on the specific circumstances. Furthermore, when describing pipelines, the terms "connected" and "linked" as used in this application have the meaning of establishing electrical connection. The specific meaning needs to be understood in conjunction with the context.

[0021] In the embodiments of this application, the terms "exemplary" or "for example" are used to indicate that something is an example, illustration, or description. Any embodiment or design that is described as "exemplary" or "for example" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or design. Specifically, the use of the terms "exemplary" or "for example" is intended to present the relevant concepts in a specific manner.

[0022] As described in the background section, existing contact-based fall detection methods using wearable devices can produce significant errors if the devices are not worn correctly. Furthermore, existing image / video-based fall detection methods raise concerns about infringing on user privacy.

[0023] In view of this, embodiments of this application provide a fall detection method and a radar device. The method includes: collecting radar data within a target space; acquiring first posture feature information of a target human body at a first moment and second posture feature information at a second moment based on the radar data, wherein the time interval between the first moment and the second moment is less than or equal to a preset time interval; determining whether the target human body has fallen in a first direction based on the first posture feature information and the second posture feature information, wherein the first direction is the direction from the radar device to the target human body in a horizontal plane; and / or determining whether the target human body has fallen in a second direction based on the first posture feature information and the second posture feature information, wherein the second direction is perpendicular to the first direction in a horizontal plane.

[0024] Compared to existing fall detection methods that do not distinguish between directions, this application analyzes changes in posture features based on different posture characteristics to perform fall detection in different directions, thus improving the accuracy of fall detection. Furthermore, by collecting radar data for fall detection, it eliminates the need to obtain the user's image or video information, protecting the user's privacy.

[0025] The specific scheme of this application will be described in detail below with reference to the accompanying drawings.

[0026] like Figure 1 As shown in the figure, a fall detection method is provided in this application embodiment. The method includes the following steps:

[0027] S101. The radar equipment collects radar data within the target space.

[0028] The target space refers to the space that is pre-defined for radar monitoring, such as a bathroom or bedroom, where falls are likely to occur.

[0029] Radar is an electronic device that uses electromagnetic waves to detect targets. Radar emits electromagnetic waves to illuminate a target and receives its echo signal (i.e., radar data), thereby obtaining information such as the distance from the target to the electromagnetic wave emission point, the rate of change of distance (radial velocity), azimuth, and altitude.

[0030] Optionally, the radar equipment can be positioned above the target space, at a height higher than the height of a person within the target space, to facilitate the collection of radar data on the person's position within the target space. For example, the radar can be installed 2m or 3m above the ground within the target space. For example,... Figure 2As shown, radar 1 can be placed on air conditioner 2 at a height of 2m within the target space. Optionally, radar 1 can establish a communication connection with air conditioner 2, thereby enabling information exchange between radar 1 and air conditioner 2.

[0031] Optionally, the radar installed in the aforementioned target space can be a millimeter-wave radar.

[0032] Millimeter-wave radar operates in the millimeter-wave band, emitting signals with wavelengths of 1-10 mm and frequencies of 30 GHz-300 GHz. In the electromagnetic spectrum, this wavelength is considered short, implying high accuracy. Millimeter-wave systems operating at 76–81 GHz (corresponding to a wavelength of approximately 4 mm) will be able to detect movements as small as a few tenths of a millimeter.

[0033] Optionally, after acquiring radar data within the target space, the radar equipment can process the acquired radar data to remove clutter signals.

[0034] Optionally, the acquired radar data can be processed using moving target indication technology.

[0035] Moving target indication (MTI) technology utilizes the difference in the frequency spectrum between moving targets and clutter due to the Doppler effect. It employs stopband filtering to suppress the clutter spectrum and extract target information. It is a type of radar technology.

[0036] The processing formula using the moving target display technology can be shown in formula (1):

[0037] S BMTI (t)=S B (t)-S B (tT r (1)

[0038] Among them, S B (t) represents all radar data acquired by the radar equipment; S BM1I (t) represents the echo signal of the target human body in the radar data; S B (tT r ) indicates clutter signals in radar data.

[0039] It should be noted that, due to the specific environment of the target space, the radar data acquired by the radar equipment may include a large amount of clutter signals generated by indoor furnishings such as beds, wardrobes, and sofas. These clutter signals are mixed with the echo signals generated by the target human body, which will interfere with the subsequent analysis of the echo signals generated by the target human body. Therefore, the radar equipment can first preprocess the radar data collected from the target space to remove the acquired background clutter signals, and then perform the following step S102 based on the processed radar data.

[0040] S102. The radar equipment acquires the first posture feature information of the target human body at the first moment and the second posture feature information at the second moment based on the radar data.

[0041] The time interval between the first moment and the second moment is less than or equal to the preset time interval.

[0042] The preset time interval can be the maximum possible time for a human body to transition from a normal state to a fall state, such as 0.5 milliseconds or 1 second.

[0043] Therefore, the first and second moments can be any two moments in the fall detection process, with a time interval less than or equal to a preset time interval. Thus, both the first and second moments can occur at any point during the target human's fall. Furthermore, the target human's first and second posture features can also be posture information during the fall process. Therefore, the radar device can acquire the first and second posture features to perform fall detection on the target human.

[0044] Optionally, the attitude feature information may include one or more of the following: the relative distance between the target human body and the radar, the movement speed of the target human body, the angle or horizontal point cloud data between the target human body and the radar.

[0045] The following is a brief introduction to how the parameters in the attitude feature information are determined.

[0046] (1) Distance

[0047] Radar equipment can determine the relative distance between a user and the radar based on radar ranging principles. Specifically, the radar equipment can determine the delay t in receiving the reflected signal by using the time T1 when the radar transmits the electromagnetic wave signal and the time T2 when the radar receives the reflected signal. The delay t is the difference between the time T2 when the radar receives the reflected signal and the time T1 when the radar transmits the electromagnetic wave signal (T2-T1). Furthermore, since electromagnetic waves propagate at the speed of light, based on t, the radar equipment can determine the relative distance between the user and the radar within the target space.

[0048] For example, the radar device can determine the one-dimensional range image between the target human body and the radar device according to the following formula (1):

[0049]

[0050] TR (m，k) W represents the amplitude of the m-th pulse signal at point k. u S is a preset window function. (n-u，m) This represents the data at the null-th sampling point of the m-th pulse signal.

[0051] (2) Speed

[0052] Based on real-life situations, we know that under the influence of gravity, a human body in a falling state will experience a significant acceleration, which will cause a change in the target body's speed. Therefore, radar equipment can determine whether a target body is in a falling state by calculating the target body's speed within the target space.

[0053] For example, by combining Doppler shift, the motion speed of the target human body can be determined based on the wave properties of the echo reflected from the target human body.

[0054] The difference between the transmitted and received frequencies caused by the Doppler effect is called the Doppler shift. It reveals the law that the properties of a wave change during motion.

[0055] The Doppler effect refers to the change in the wavelength of radiation emitted by an object due to the relative motion between the wave source and the observer. In front of a moving wave source, the wave is compressed, resulting in a shorter wavelength and a higher frequency, known as a blue shift. Behind a moving wave source, the opposite effect occurs: the wavelength becomes longer and the frequency lower, known as a red shift. The higher the speed of the wave source, the greater the effect. Therefore, the speed of the wave source along the observation direction can be calculated based on the degree of blue or red shift.

[0056] In this embodiment, the echo reflected from the target human body also exhibits a Doppler frequency shift. Therefore, the velocity of the target human body can be determined according to the following formula (2):

[0057]

[0058] Where ω is the phase difference between the two echoes, λ is the wavelength, and T c V represents the transmission duration of the echo, and V represents the speed of the target human body.

[0059] (3) Angle

[0060] The angle between the target human body and the radar changes depending on whether the target human body is in a falling, walking, or standing state. Therefore, the angle information between the target human body and the radar can be obtained to more accurately determine whether the target human body is in a falling state.

[0061] For example, for example, the radar device can determine the speed of the target human body's movement according to formula (2), and determine the angle between the target human body and the radar according to the following formula (3):

[0062]

[0063] Where w2 is the phase difference caused by the change in the distance to the target human body, l is the wavelength, d is the distance between the two antennas, and q is the angle between the target human body and the radar.

[0064] (4) Horizontal point cloud

[0065] Point cloud refers to a massive set of points representing the surface characteristics of a target. Horizontal point cloud is obtained by calculating the distance and angle between the radar and the target using the radar's horizontal aperture, thus extracting a massive set of points representing the target's surface scattering characteristics in the horizontal direction.

[0066] Specifically, the radar equipment obtains the distance information between the target human body and the radar by performing range-dimensional pulse compression on the collected radar data. Then, it uses the range image data from multiple antennas of the radar equipment's virtual antenna array to perform horizontal Capon beamforming. Finally, constant false alarm rate (CFAR) detection technology is used to detect the range and azimuth angle of the target, thus obtaining the target's horizontal point cloud data.

[0067] Capon beamforming involves weighted summation of the outputs of each array element to "guide" the antenna array beam in one direction within a given time. The guiding position that yields the maximum output power for the desired signal provides a DOA estimate. Although the radiation pattern of the radar array antenna is omnidirectional, the array outputs, after weighted summation, can be adjusted so that the directional gain of the array reception is concentrated in one direction, effectively forming a "beam." In this embodiment, the radar device can form a horizontal Capon beam.

[0068] DOA estimation, also known as angle spectrum estimation or angle of arrival estimation, utilizes the principle of rectilinear propagation of electromagnetic waves. By processing the received reflected signal through radar, the direction of arrival of the reflected signal can be estimated, thereby obtaining the user's azimuth information.

[0069] Constant False Alarm Rate (CFAR) is a radar system technique that distinguishes between the receiver's output signal and noise to determine the presence of a target signal while maintaining a constant false alarm probability. The principle is to first process the input noise and determine a threshold. This threshold is then compared to the input signal. If the input signal exceeds the threshold, a target is detected; otherwise, no target is detected. Generally, the signal is emitted by the signal source, encounters various interferences during propagation, and after reaching the receiver, it is processed and output to the detector. The detector then makes a decision on the input signal based on appropriate criteria. It should be understood that the above methods for determining the various parameters in the attitude characteristic information are exemplary and do not constitute specific limitations; other methods can be used in practical applications.

[0070] Optionally, after step S102, the radar device may perform the following steps S103 and / or S104.

[0071] S103. The radar equipment determines whether the target human body has fallen in the first direction based on the first attitude feature information and the second attitude feature information.

[0072] The first direction is the direction from the radar equipment to the target human body in the horizontal plane.

[0073] It should be noted that if the target person falls in the first direction, and the direction between the target person and the radar equipment remains unchanged during the fall, then the distance between the target person and the radar will change significantly during the fall, with the distance between the target person and the radar suddenly decreasing or increasing. Therefore, the change in distance between the target person and the radar equipment can be used to determine whether the target person has fallen in the first direction.

[0074] Furthermore, since the speed of a person's movement suddenly increases under the influence of gravity when they fall, radar equipment can use the speed of the target person's movement as a basis for determining whether the target person has fallen in the first direction.

[0075] Therefore, in order to determine whether the target human body has fallen in the first direction, the first attitude feature information includes a first distance between the target human body and the radar device, the second attitude feature information includes a second distance between the target human body and the radar device, and a second velocity of the target human body. Based on this, step S103 can be specifically implemented as follows: if the first preset condition is met, the radar device can determine that the target human body has fallen in the first direction. If the first preset condition is not met, the radar device determines that the target human body has not fallen in the first direction.

[0076] The first preset condition includes that the difference between the second distance and the first distance is greater than or equal to a first threshold, and the second speed is greater than or equal to the second threshold. The first threshold can be the possible distance change value within a preset time interval when the target human body falls in the first direction. The second threshold can be the possible minimum movement speed of the target human body when it is in a falling state.

[0077] S104. The radar equipment determines whether the target human body has fallen in the second direction based on the first attitude characteristic information and the second attitude characteristic information.

[0078] The second direction is perpendicular to the first direction in the horizontal plane.

[0079] It should be noted that analysis of existing data on human movement speed reveals that the rate of change of speed is greater when a person falls in a secondary direction than during other movements. Therefore, radar equipment can determine whether a target person has fallen in a secondary direction based on changes in their movement speed.

[0080] Furthermore, compared to other human movements, the horizontal point cloud increases significantly during a fall in the second direction. Therefore, radar equipment can further combine this horizontal point cloud data to determine whether a target person has fallen in the second direction, improving the accuracy and stability of fall detection in this direction.

[0081] Therefore, in order to determine whether the target human body has fallen in the second direction, the first posture feature information may include first horizontal point cloud data, and the second posture feature information may include the second velocity and second horizontal point cloud data of the target human body. Based on this, step S104 can be specifically implemented as follows: if the second preset condition is met, the radar device determines that the target human body has fallen in the second direction. If the second preset condition is not met, the radar device determines that the target human body has not fallen in the second direction.

[0082] The second preset condition includes a second speed greater than or equal to a third threshold, and the difference between the number of point data contained in the second horizontal point cloud data and the number of point data contained in the first horizontal point cloud data is greater than or equal to a fourth threshold.

[0083] It should be understood that the radar equipment can preset a reasonable speed change value as a third threshold and a reasonable number of point data as a fourth threshold based on the changes in the existing motion speed and horizontal point cloud data when falling in the second direction.

[0084] based on Figure 1The described embodiment performs fall detection by collecting radar data, without requiring the acquisition of the user's image or video information, thus protecting the user's privacy and making it suitable for private areas such as bedrooms and bathrooms. Furthermore, compared to existing fall detection methods that do not distinguish between directions, this application analyzes changes in posture features based on different posture characteristics to perform fall detection in different directions, thereby improving the accuracy of fall detection.

[0085] Optional, based on Figure 1 The illustrated embodiments, such as Figure 3 As shown, after step S104 above, the fall detection method may further include the following steps:

[0086] S105. When the target human body falls, the radar equipment obtains the distance between the target human body and the radar equipment, as well as the horizontal angle between the target human body and the radar equipment.

[0087] For example, the radar device can determine the distance between the target human body and the radar device according to the above formula (1).

[0088] The radar equipment can construct a two-dimensional coordinate system in the horizontal plane, with itself as the origin, any direction in the horizontal plane as the X-axis, and the direction perpendicular to the X-axis in the horizontal plane as the Y-axis. Therefore, the horizontal angle between the target human body and the radar equipment is the angle between the direction from the radar equipment to the target human body in the horizontal plane and the X-axis.

[0089] S106. The radar equipment determines the position of the target human body when it falls based on the distance between the target human body and the radar equipment, as well as the horizontal angle between the target human body and the radar equipment.

[0090] Specifically, the radar equipment can determine the position of the target person in the target space when they fall, based on its own position on the horizontal plane, the distance between the target person and the radar equipment when they fall, and the horizontal angle between the target person and the radar equipment.

[0091] For example, the coordinates of the target human body's fall position in the above two-dimensional coordinate system can be determined according to the following formula (4):

[0092]

[0093] Where d represents the distance between the target human body and the radar equipment, θ is the horizontal angle, x is the x-coordinate of the fall position, and y is the y-coordinate of the fall position.

[0094] Based on the above embodiments, the radar device can further determine the user's location information when the user falls, so that rescuers can quickly find the user based on this location information and provide timely help and treatment.

[0095] Optional, based on Figure 1 The illustrated embodiments, such as Figure 4 As shown, after step S104 above, the fall detection method may further include the following step S107:

[0096] S107. After the target person falls, the radar equipment issues an alarm.

[0097] In one possible implementation, when the radar device detects that a target human body is in a fall, it can send an alarm message to the terminal device.

[0098] The alarm information may include the time of the fall, the posture characteristics of the fall, and the location of the fall.

[0099] In addition, the radar device can establish a connection with a terminal device in advance. This terminal device can be a mobile phone, smartwatch, smart bracelet, or other portable terminal device of the emergency contact person corresponding to the target person, so that the emergency contact person corresponding to the target person can receive the alarm information sent by the radar device in a timely manner.

[0100] In another possible implementation, when the radar device detects that the target human body is in a fall, it can also control the alarm device to issue an alarm message.

[0101] The alarm information may also include preset alarm sounds, alarm indicator lights, and other alarm signals. The alarm device may be a device with indicator lights and / or sound playback functionality.

[0102] Optionally, the alarm device can be integrated into the radar equipment.

[0103] In another possible implementation, the radar device can be connected to other smart home devices such as air conditioners and refrigerators, or it can be integrated into the smart home system. Upon detecting a person falling, the radar device can send an alarm message to the smart home system, prompting it to issue an alarm signal to alert others in the vicinity to assist the fallen person.

[0104] In some embodiments, after a target human body falls, the radar device can send a fall record to the server.

[0105] The fall record may include one or more of the following: the time the target fell, the location of the target when they fell, and radar data of the fall.

[0106] In addition, radar equipment can be pre-connected to a server, which can be a device with data processing and data storage capabilities.

[0107] based on Figure 4 The illustrated embodiment can promptly issue a fall alarm when a user is in a fall, to alert relevant personnel that the user has fallen and to ensure that the user receives timely medical attention after the fall.

[0108] It should be understood that the above Figure 3 and Figure 4 The embodiments shown can be used in combination with each other.

[0109] The foregoing primarily describes the solution provided in this application from a methodological perspective. It is understood that, in order to achieve the aforementioned functions, the radar device includes corresponding hardware structures and / or software modules for executing each function. Those skilled in the art should readily recognize that, based on the algorithmic steps of the examples described in conjunction with the embodiments disclosed herein, the present invention can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed in hardware or by computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present invention.

[0110] This application can divide radar equipment into functional modules based on the above method examples. For example, each function can be divided into its own functional module, or two or more functions can be integrated into one processing module. The integrated modules can be implemented in hardware or as software functional modules. It should be noted that the module division in this application is illustrative and only represents one logical functional division; other division methods may be used in actual implementation.

[0111] Figure 5 This diagram illustrates the composition of a radar device according to an embodiment of this application. Figure 5 As shown, the radar device 1000 includes an acquisition unit 1001 and a processing unit 1002. Optionally, the radar device 1000 also includes an alarm unit 1003.

[0112] Acquisition unit 1001 is used to collect radar data within the target space.

[0113] The processing unit 1002 is used to acquire, based on radar data, the first posture feature information of the target human body at a first moment and the second posture feature information at a second moment, wherein the time interval between the first moment and the second moment is less than or equal to a preset time interval.

[0114] The processing unit 1002 is further configured to determine, based on the first attitude feature information and the second attitude feature information, whether the target human body has fallen in a first direction, wherein the first direction is the direction from the radar device to the target human body in the horizontal plane; and / or, based on the first attitude feature information and the second attitude feature information, whether the target human body has fallen in a second direction, wherein the second direction is perpendicular to the first direction in the horizontal plane.

[0115] In some embodiments, the first posture feature information includes a first distance between the target human body and the radar device, the second posture feature information includes a second distance between the target human body and the radar device, and a second velocity of the target human body; then the processing unit 1002 is specifically used to determine that the target human body has fallen in the first direction if a first preset condition is met, the first preset condition includes that the difference between the second distance and the first distance is greater than or equal to a first threshold, and the second velocity is greater than or equal to the second threshold; or, if the first preset condition is not met, determine that the target human body has not fallen in the first direction.

[0116] In some embodiments, the first posture feature information includes first horizontal point cloud data, and the second posture feature information includes the second velocity of the target human body and the second horizontal point cloud data; then the processing unit 1002 is specifically configured to determine that the target human body has fallen in the second direction if a second preset condition is met, the second preset condition including the second velocity being greater than or equal to a third threshold, and the difference between the number of point data contained in the second horizontal point cloud data and the number of point data contained in the first horizontal point cloud data being greater than or equal to a fourth threshold; if the second preset condition is not met, determine that the target human body has not fallen in the second direction.

[0117] In some embodiments, the acquisition unit 1001 is further configured to acquire the distance between the target human body and the radar device, and the horizontal angle of the target human body relative to the radar device, when the target human body falls. The processing unit 1002 is further configured to determine the position of the target human body when it falls based on the distance between the target human body and the radar device, and the horizontal angle of the target human body relative to the radar device.

[0118] In some embodiments, the alarm unit 1003 is used to issue an alarm message after the target human body falls.

[0119] Figure 5 The units within can also be called modules; for example, a processing unit can be called a processing module. Additionally, in... Figure 5 In the embodiments shown, the names of the various units may not be the same as those shown in the figures. For example, the transceiver unit may also be called the communication unit.

[0120] Figure 5If the various units in the process are implemented as software functional modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solutions of the embodiments of this application, in essence, or the parts that contribute to the prior art, or all or part of the technical solutions, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) or processor to execute all or part of the steps of the methods described in the various embodiments of this application. Storage media for storing computer software products include: USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, optical disks, and other media capable of storing program code.

[0121] This application also provides a schematic diagram of the hardware structure of a radar device, such as... Figure 6 As shown, the radar device 2000 includes a processor 2001, and optionally, may also include a memory 2002 and a transceiver 2003 connected to the processor 2001. The processor 2001, memory 2002, and transceiver 2003 are connected via a bus 2004.

[0122] Processor 2001 may be a central processing unit (CPU), a general-purpose processor, a network processor (NP), a digital signal processor (DSP), a microprocessor, a microcontroller, a programmable logic device (PLD), or any combination thereof. Processor 2001 may also be any other device with processing capabilities, such as a circuit, device, or software module. Processor 2001 may also include multiple CPUs, and processor 2001 may be a single-core processor or a multi-core processor. Here, "processor" may refer to one or more devices, circuits, or processing cores used to process data (e.g., computer program instructions).

[0123] The memory 2002 may be a read-only memory (ROM) or other type of static storage device capable of storing static information and instructions, random access memory (RAM) or other type of dynamic storage device capable of storing information and instructions, or it may be an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer. This application embodiment does not impose any limitations on this. The memory 2002 may exist independently or may be integrated with the processor 2001. The memory 2002 may contain computer program code. The processor 2001 is used to execute the computer program code stored in the memory 2002, thereby implementing the method provided in this application embodiment.

[0124] The transceiver 2003 can be used to communicate with other devices or communication networks (such as Ethernet, radioaccess network (RAN), wireless local area networks (WLAN), etc.). The transceiver 2003 can be a module, circuit, transceiver, or any device capable of enabling communication.

[0125] Bus 2004 can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. Bus 2005 can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 6 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0126] This application also provides a computer-readable storage medium including computer-executable instructions that, when run on a computer, cause the computer to perform any of the methods provided in the above embodiments.

[0127] This application also provides a computer program product containing computer execution instructions, which, when run on a computer, causes the computer to perform any of the methods provided in the above embodiments.

[0128] This application also provides a chip, including a processor and an interface. The processor is coupled to a memory through the interface. When the processor executes a computer program in the memory or computer execution instructions, any of the methods provided in the above embodiments are executed.

[0129] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented using software programs, implementation can be, in whole or in part, in the form of a computer program product. This computer program product includes one or more computer-executable instructions. When these computer-executable instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer-executable instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, computer-executable instructions can be transmitted from one website, computer, server, or data center to another via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium accessible to a computer or a data storage device containing one or more servers, data centers, etc., that can be integrated with the medium. The available media can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., DVDs), or semiconductor media (e.g., solid-state disks, SSDs).

[0130] Although this application has been described herein in conjunction with various embodiments, those skilled in the art, by reviewing the accompanying drawings, the disclosure, and the appended claims, will understand and implement other variations of the disclosed embodiments in carrying out the claimed application. In the claims, the word "comprising" does not exclude other components or steps, and "a" or "an" does not exclude multiple instances. A single processor or other unit can implement several functions listed in the claims. While different dependent claims may recite certain measures, this does not mean that these measures cannot be combined to produce good results.

[0131] Although this application has been described in conjunction with specific features and embodiments, it is obvious that various modifications and combinations can be made thereto without departing from the spirit and scope of this application. Accordingly, this specification and drawings are merely exemplary illustrations of this application as defined by the appended claims, and are considered to cover any and all modifications, variations, combinations, or equivalents within the scope of this application. Clearly, those skilled in the art can make various alterations and modifications to this application without departing from the spirit and scope of this application. Thus, if such modifications and modifications of this application fall within the scope of the claims of this application and their equivalents, this application is also intended to include such modifications and modifications.

[0132] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any changes or substitutions within the technical scope disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A fall detection method, characterized in that, Applied to radar equipment, the method includes: Collect radar data within the target space; Based on the radar data, the first posture feature information of the target human body at the first moment and the second posture feature information at the second moment are obtained, and the time interval between the first moment and the second moment is less than or equal to a preset time interval. Based on the first posture feature information and the second posture feature information, it is determined whether the target human body has fallen in a first direction, where the first direction is the horizontal direction from the radar device to the target human body; and / or, Based on the first posture feature information and the second posture feature information, it is determined whether the target human body has fallen in the second direction, which is perpendicular to the first direction in the horizontal plane; The step of determining whether the target human body has fallen in the second direction includes: If the second velocity in the second attitude feature information is greater than or equal to the third threshold, and the difference between the number of point data contained in the second horizontal point cloud data in the second attitude feature information and the number of point data contained in the first horizontal point cloud data in the first attitude feature is greater than or equal to the fourth threshold, then it is determined that the target human body has fallen in the second direction; the second horizontal point cloud data is obtained by performing range dimension pulse compression on the radar data, using the range image data of multiple antennas of the virtual antenna array of the radar device to perform horizontal Capon beamforming, and then using constant false alarm rate detection technology to detect the target's range azimuth angle.

2. The method according to claim 1, characterized in that, The first attitude feature information includes a first distance between the target human body and the radar device, and the second attitude feature information includes a second distance between the target human body and the radar device, as well as a second velocity of the target human body; The step of determining whether the target human body has fallen in a first direction based on the first posture feature information and the second posture feature information includes: Under the condition that a first preset condition is met, it is determined that the target human body has fallen in the first direction. The first preset condition includes that the difference between the second distance and the first distance is greater than or equal to a first threshold, and that the second speed is greater than or equal to a second threshold; or, If the first preset condition is not met, it is determined that the target human body did not fall in the first direction.

3. The method according to claim 1, characterized in that, The first posture feature information includes first horizontal point cloud data, and the second posture feature information includes the second velocity and second horizontal point cloud data of the target human body; The step of determining whether the target human body has fallen in the second direction based on the first posture feature information and the second posture feature information includes: If the second preset condition is not met, it is determined that the target human body has not fallen in the second direction; the second preset condition includes that the second speed is greater than or equal to a third threshold, and the difference between the number of point data contained in the second horizontal point cloud data and the number of point data contained in the first horizontal point cloud data is greater than or equal to a fourth threshold.

4. The method according to any one of claims 1 to 3, characterized in that, The method includes: When the target human body falls, the distance between the target human body and the radar device, as well as the horizontal angle of the target human body relative to the radar device, are obtained; The position of the target human body when it fell is determined based on the distance between the target human body and the radar device, and the horizontal angle between the target human body and the radar device.

5. The method according to any one of claims 1 to 3, characterized in that, The method includes: An alarm is triggered after the target person falls.

6. A radar device, characterized in that, The radar equipment includes: Acquisition unit, used to collect radar data within the target space; The processing unit is used to acquire, based on the radar data, the first posture feature information of the target human body at a first moment and the second posture feature information at a second moment, wherein the time interval between the first moment and the second moment is less than or equal to a preset time interval. The processing unit is further configured to determine, based on the first attitude feature information and the second attitude feature information, whether the target human body has fallen in a first direction, wherein the first direction is the horizontal direction from the radar device to the target human body; and / or, Based on the first posture feature information and the second posture feature information, it is determined whether the target human body has fallen in the second direction, which is perpendicular to the first direction in the horizontal plane; The step of determining whether the target human body has fallen in the second direction includes: If the second velocity in the second attitude feature information is greater than or equal to the third threshold, and the difference between the number of point data contained in the second horizontal point cloud data in the second attitude feature information and the number of point data contained in the first horizontal point cloud data in the first attitude feature is greater than or equal to the fourth threshold, then it is determined that the target human body has fallen in the second direction; the second horizontal point cloud data is obtained by performing range dimension pulse compression on the radar data, using the range image data of multiple antennas of the virtual antenna array of the radar device to perform horizontal Capon beamforming, and then using constant false alarm rate detection technology to detect the target's range azimuth angle.

7. The radar device according to claim 6, characterized in that, The first attitude feature information includes a first distance between the target human body and the radar device, and the second attitude feature information includes a second distance between the target human body and the radar device, as well as a second velocity of the target human body; The processing unit is specifically used to determine that the target human body has fallen in the first direction when a first preset condition is met. The first preset condition includes that the difference between the second distance and the first distance is greater than or equal to a first threshold, and the second speed is greater than or equal to a second threshold. or, If the first preset condition is not met, it is determined that the target human body did not fall in the first direction.

8. The radar device according to claim 6, characterized in that, The first posture feature information includes first horizontal point cloud data, and the second posture feature information includes the second velocity and second horizontal point cloud data of the target human body; The processing unit is specifically used to determine that the target human body has not fallen in the second direction if the second preset condition is not met; the second preset condition includes that the second speed is greater than or equal to a third threshold, and the difference between the number of point data contained in the second horizontal point cloud data and the number of point data contained in the first horizontal point cloud data is greater than or equal to a fourth threshold.

9. The radar device according to any one of claims 6 to 7, characterized in that, The acquisition unit is also used to acquire the distance between the target human body and the radar device, and the horizontal angle of the target human body relative to the radar device when the target human body falls. The processing unit is further configured to determine the position of the target human body when it falls based on the distance between the target human body and the radar device, and the horizontal angle between the target human body and the radar device.

10. The radar device according to claim 6, characterized in that, The radar equipment also includes: An alarm unit is used to issue an alarm message after the target human body falls.

Images