CN115005809A

CN115005809A - Fall detection method, device, equipment and storage medium

Info

Publication number: CN115005809A
Application number: CN202210569888.5A
Authority: CN
Inventors: 任兆亭; 慕安臻; 何嘉乐; 丁从张; 张佳舒; 贾勇
Original assignee: Qingdao Hisense Hitachi Air Conditioning System Co Ltd
Current assignee: Qingdao Hisense Hitachi Air Conditioning System Co Ltd
Priority date: 2022-05-24
Filing date: 2022-05-24
Publication date: 2022-09-06

Abstract

The application provides a method, a device, equipment and a storage medium for fall detection, which can perform fall detection without contact on the premise of not relating to user privacy. The method comprises the following steps: the motion characteristics of the target object in each unit time length of the continuous unit time lengths are obtained. The motion characteristics include at least one of distance data, velocity data, doppler signal data, and angle data. Determining a first state of the target object in each unit time length based on the first judgment rule and the motion characteristics of the target object in each unit time length to obtain a first state sequence of the target object in a plurality of unit time lengths; the first state comprises a fall state, a motion state or a rest state, and the first sequence of states comprises a chronologically ordered first state. And determining that the target object falls when the first state sequence meets a preset first falling rule.

Description

Fall detection method, device, equipment and storage medium

Technical Field

The present application relates to the field of radar detection technologies, and in particular, to a fall detection method, apparatus, device, and storage medium.

Background

Currently, falls affect millions of people each year and cause a great deal of injury, particularly among the elderly. Therefore, in order to protect the physical health of a human body, the human body falling real-time detection technology has positive practical significance.

The existing fall identification method generally acquires image information of a user based on a shooting device, so that behavior identification can be performed on the user according to the image information. However, this method has a hidden danger of privacy disclosure, and may cause information security problems.

Disclosure of Invention

The embodiment of the application provides a method, a device, equipment and a storage medium for fall detection, which can perform fall detection in a non-contact manner on the premise of not relating to user privacy.

In a first aspect, there is provided a fall detection method, the method comprising:

acquiring the motion characteristics of a target object in each unit time length of a plurality of continuous unit time lengths; the motion characteristic comprises at least one of distance data, velocity data, doppler signal data and angle data, the distance data being indicative of a maximum change value of the motion distance; the speed data is used for indicating the maximum value of the movement speed and a speed area change value, the speed area change value is used for indicating the ratio of a target movement speed to a plurality of movement speeds in the plurality of movement speeds, and the target movement speed is larger than a first threshold value; the Doppler signal data is used for indicating the maximum value of the Doppler signal intensity; the angle data is used to indicate a maximum variation value of the movement angle. Determining a first state of the target object in each unit time length based on the first judgment rule and the motion characteristics of the target object in each unit time length to obtain a first state sequence of the target object in a plurality of unit time lengths; the first state comprises a fall state, a motion state or a rest state, and the first state sequence comprises first states ordered in time. And determining that the target object falls when the first state sequence meets a preset first falling rule.

The technical scheme provided by the embodiment of the application is applied to radar equipment, and can realize contactless body movement detection on the premise of not relating to user privacy, so that the use experience of a user is effectively improved. Moreover, the radar equipment is not influenced by the environment, so that the problem that the accuracy of the identification result is reduced due to environmental factors such as illumination, smoke dust and shielding is avoided. In addition, according to the technical scheme provided by the embodiment of the application, the state sequence of the target object in the continuous unit time lengths is judged according to the motion characteristics of the target object in each unit time length in the continuous unit time lengths. And then judging whether the state sequence meets a preset falling rule or not, and determining that the target object falls under the condition that the state sequence meets the preset falling rule. That is to say, the embodiment of the application adopts logic judgment to realize human body fall detection, and the algorithm complexity is low, and the hardware computing capability requirement is low, so that the development cost is saved under the condition that the detected target object falls.

As a possible implementation manner, each unit duration includes a plurality of frames, and in the case that the motion feature includes distance data, velocity data, doppler signal data, and angle data, the "acquiring the motion feature of the target object in each of the consecutive unit durations" includes:

acquiring echo signals corresponding to each frame in a plurality of frames through radar equipment to obtain echo signals corresponding to the frames; the echo signal corresponding to each frame comprises a signal reflected by the target object after the radar device sends a plurality of detection signals each frame. And respectively determining the maximum value and the minimum value of the movement distance of the target object in the plurality of frames according to the echo signals corresponding to the plurality of frames, and determining the difference between the maximum value and the minimum value of the movement distance as the distance data of the target object in each unit time length. And respectively determining the maximum value of the movement speed and the change value of the speed area of the target object in the plurality of frames according to the echo signals corresponding to the plurality of frames, and determining the maximum value of the movement speed and the change value of the speed area as the speed data of the target object in each unit time length. And determining the maximum Doppler signal intensity value of the target object in the multiple frames according to the echo signals corresponding to the multiple frames, and determining the maximum Doppler signal intensity value as the Doppler signal data of the target object in each unit time length. And respectively determining the maximum value and the minimum value of the motion angle of the target object in the plurality of frames according to the echo signals corresponding to the plurality of frames, and determining the difference between the maximum value and the minimum value of the motion angle as the angle data of the target object in each unit time length.

Therefore, the radar equipment respectively determines to obtain distance data, speed data, Doppler signal data and angle data based on the processing of the echo signals corresponding to each frame, and based on the characteristic data, the body movement detection can be carried out in a non-contact mode on the premise that the privacy of a user is not involved, so that the use experience of the user is effectively improved.

In one possible implementation, the first determination rule includes a first movement rule, a first stationary rule and a first fall rule; determining a first state of the target object in each unit time length based on the first judgment rule and the motion characteristic of the target object in each unit time length, comprising: under the condition that the motion characteristics of the target object in each unit time length meet a first motion rule, determining that the first state is a motion state; or, under the condition that the motion characteristics of the target object in each unit time length meet the first static rule, determining that the first state is a static state; alternatively, in a case where the motion characteristic of the target object in each unit time length satisfies the first fall rule, the first state is determined to be a fall state. In this way, the state for each unit time length can be determined based on the first determination rule.

In a possible implementation, the method further includes: under the condition that the first state sequence does not meet the first falling rule, determining a second state of the target object in each unit time length on the basis of a second judgment rule and the motion characteristics of the target object in each unit time length to obtain a second state sequence of the target object in a plurality of unit time lengths; the second state comprises a fall state, a movement state or a rest state, and the second state sequence comprises second states ordered in time. And determining that the target object falls under the condition that the second state sequence meets a preset second falling rule. In this way, in the case where it is determined that the target object does not fall based on the first determination rule, the radar apparatus further determines whether the target object falls based on the second determination rule. And determining that the target object falls in the case where it is determined that the second state of the target object in each unit duration satisfies a preset second fall rule based on the second determination rule. Thereby avoiding the situation that the target object falls and is not detected.

In a possible implementation, the method further includes: within a preset time after the target object is determined to fall down, if the target object is continuously in a static state within a preset time length, generating alarm information; the alarm information is used to indicate that the target object has fallen. Therefore, after the target object is determined to fall for the first time, the target object is subjected to fall detection for the second time, and the situation of false alarm is avoided.

In a second aspect, there is provided a fall detection apparatus, the apparatus comprising: an acquisition unit and a determination unit. The device comprises an acquisition unit, a processing unit and a display unit, wherein the acquisition unit is used for acquiring the motion characteristics of a target object in each unit time length of a plurality of continuous unit time lengths; the motion characteristic comprises at least one of distance data, velocity data, doppler signal data and angle data, the distance data being indicative of a maximum change value of the motion distance; the speed data is used for indicating the maximum value of the movement speed and a speed area change value, the speed area change value is used for indicating the ratio of a target movement speed to a plurality of movement speeds in the plurality of movement speeds, and the target movement speed is greater than a first threshold value; the Doppler signal data is used for indicating the maximum value of the Doppler signal intensity; the angle data is used to indicate a maximum variation value of the movement angle. The determining unit is used for determining a first state of the target object in each unit time length based on the first judging rule and the motion characteristics of the target object in each unit time length to obtain a first state sequence of the target object in a plurality of unit time lengths; the first state comprises a fall state, a motion state or a rest state, and the first sequence of states comprises a chronologically ordered first state. And the determining unit is also used for determining that the target object falls when the first state sequence meets a preset first falling rule.

In a possible implementation manner, each unit duration includes a plurality of frames, and in a case that the motion feature includes distance data, velocity data, doppler signal data, and angle data, the obtaining unit is specifically configured to: acquiring echo signals corresponding to each frame in a plurality of frames through radar equipment to obtain echo signals corresponding to the frames; the echo signal corresponding to each frame comprises a signal reflected by a target object after the radar equipment sends a plurality of detection signals each frame; respectively determining the maximum value and the minimum value of the movement distance of the target object in a plurality of frames according to the echo signals corresponding to the frames, and determining the difference between the maximum value and the minimum value of the movement distance as the distance data of the target object in each unit time length; and respectively determining the maximum value of the movement speed and the change value of the speed area of the target object in the plurality of frames according to the echo signals corresponding to the plurality of frames, and determining the maximum value of the movement speed and the change value of the speed area as the speed data of the target object in each unit time length. And determining the maximum Doppler signal intensity of the target object in the multiple frames according to the echo signals corresponding to the multiple frames, and determining the maximum Doppler signal intensity as the Doppler signal data of the target object in each unit time length. And respectively determining the motion angle maximum value and the motion angle minimum value of the target object in the plurality of frames according to the echo signals corresponding to the plurality of frames, and determining the difference between the motion angle maximum value and the motion angle minimum value as angle data of the target object in each unit time length.

In one possible implementation manner, the first determination rule includes a first movement rule, a first stationary rule and a first falling rule; based on the first determination rule and the motion characteristic of the target object in each unit time length, the determining unit is specifically configured to: under the condition that the motion characteristics of the target object in each unit time length meet a first motion rule, determining that the first state is a motion state; or, under the condition that the motion characteristics of the target object in each unit time length meet the first static rule, determining that the first state is a static state; alternatively, in a case where the motion characteristic of the target object in each unit time length satisfies the first fall rule, the first state is determined to be a fall state.

In one possible implementation, the determining unit: the first state sequence is used for determining the first state of the target object in each unit time length according to the first judgment rule and the motion characteristics of the target object in each unit time length under the condition that the first state sequence does not meet the first falling rule, and obtaining a first state sequence of the target object in a plurality of unit time lengths; the second state comprises a fall state, a movement state or a rest state, and the second state sequence comprises second states ordered in time. A determination unit: and the controller is further used for determining that the target object falls if the second state sequence meets a preset second fall rule.

In a possible implementation, the apparatus further includes a generating unit. The generating unit is used for generating alarm information if the target object is continuously in a static state within a preset time length after the target object falls down within the preset time length; the alarm information is used to indicate that the target object has fallen.

In a third aspect, there is provided a radar apparatus comprising: one or more processors; one or more memories; wherein the one or more memories are for storing computer program code comprising computer instructions which, when executed by the one or more processors, cause the radar apparatus to perform the fall detection method of the first aspect.

In a fourth aspect, there is provided a computer-readable storage medium comprising computer-executable instructions that, when executed on a computer, cause the computer to perform the fall detection method of the first aspect.

Drawings

Fig. 1 is a schematic diagram of an antenna of a radar apparatus according to an embodiment of the present disclosure;

fig. 2 is a schematic diagram illustrating a radar apparatus detecting a target object according to an embodiment of the present application;

fig. 3 is a schematic diagram of a fall detection system according to an embodiment of the present application;

fig. 4 is a flowchart of a fall detection method according to an embodiment of the present application;

fig. 5 is a schematic diagram of a first determination rule provided in an embodiment of the present application;

fig. 6 is a second flowchart of a fall detection method according to an embodiment of the present application;

fig. 7 is a schematic diagram of a target object angle message according to an embodiment of the present disclosure;

fig. 8 is a flowchart of processing an echo signal according to an embodiment of the present application;

fig. 9 is a schematic diagram illustrating obtaining a motion characteristic of a target object according to an embodiment of the present application;

fig. 10 is a schematic diagram illustrating obtaining distance information of a target object according to an embodiment of the present disclosure;

fig. 11 is a schematic diagram illustrating obtaining speed information of a target object according to an embodiment of the present application;

fig. 12 is a schematic diagram illustrating obtaining angle information of a target object according to an embodiment of the present disclosure;

fig. 13 is a third flowchart of a fall detection method according to an embodiment of the present application;

fig. 14 is a fourth flowchart of a fall detection method according to an embodiment of the present application;

FIG. 15 is a diagram illustrating a second determination rule provided by an embodiment of the present application;

fig. 16 is a flowchart of a first fall determination provided in an embodiment of the present application;

fig. 17 is a flowchart of a second fall determination provided in the embodiment of the present application;

fig. 18 is a flowchart of a secondary fall confirmation determination provided in the embodiment of the present application;

fig. 19 is a schematic structural diagram of a fall detection apparatus according to an embodiment of the present application;

fig. 20 is a schematic structural diagram of a radar apparatus according to an embodiment of the present application.

Detailed Description

A method and an apparatus for detecting body motion provided by the present application will be described in detail below with reference to the accompanying drawings.

The term "and/or" herein is merely an association describing an associated object, meaning that three relationships may exist, e.g., a and/or B, may mean: a exists alone, A and B exist simultaneously, and B exists alone.

The terms "first" and "second" and the like in the specification and drawings of the present application are used for distinguishing different objects or for distinguishing different processes for the same object, and are not used for describing a specific order of the objects.

Furthermore, the terms "including" and "having," and any variations thereof, as referred to in the description of the present application, are intended to cover non-exclusive inclusions. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those steps or elements listed, but may alternatively include other steps or elements not listed, or inherent to such process, method, article, or apparatus.

It should be noted that in the embodiments of the present application, words such as "exemplary" or "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described herein as "exemplary" or "e.g.," is not necessarily to be construed as preferred or advantageous over other embodiments or designs. Rather, use of the word "exemplary" or "such as" is intended to present concepts related in a concrete fashion.

In the description of the present application, the meaning of "a plurality" means two or more unless otherwise specified.

As mentioned in the background, falls currently affect millions of people each year and cause a great deal of injury, particularly among the elderly. Therefore, in order to protect the physical health of a human body, the human body falling real-time detection technology has positive practical significance.

The existing fall identification method generally acquires image information of a user based on a shooting device, so that behavior identification can be performed on the user according to the image information. However, this method has a hidden risk of privacy disclosure, which may cause information security problems. Moreover, the shooting device is greatly influenced by the environment, and the accuracy of the identification result is reduced due to environmental factors such as illumination, smoke, shielding and the like.

In view of the above technical problems, an embodiment of the present application provides a fall detection method, which obtains a motion characteristic of a target object in each unit duration of a plurality of continuous unit durations; the motion characteristic comprises at least one of distance data, velocity data, doppler signal data and angle data, the distance data being indicative of a maximum change value of the motion distance; the speed data is used for indicating the maximum value of the movement speed and a speed area change value, the speed area change value is used for indicating the ratio of a target movement speed to a plurality of movement speeds in the plurality of movement speeds, and the target movement speed is larger than a first threshold value; the Doppler signal data is used for indicating the maximum value of the Doppler signal intensity; the angle data is used to indicate a maximum variation value of the motion angle. Determining the state of the target object in each unit time length based on a preset state judgment rule and the motion characteristics of the target object in each unit time length to obtain a state sequence of the target object in a plurality of continuous unit time lengths; states include fall, movement, or rest, and the sequence of states includes states ordered in time. And under the condition that the state sequence meets a preset falling rule, determining that the target object falls.

In the embodiment of the present application, the radar apparatus is an electronic apparatus that performs target detection using electromagnetic waves, for example: millimeter wave radar, microwave radar, ultra wide band radar, and the like.

Wherein, the millimeter wave refers to electromagnetic wave in the frequency domain of 30-300 GHz (with the wavelength of 1-10 mm). The wavelength of the millimeter wave is between centimeter wave and light wave, so the millimeter wave has the advantages of microwave guidance and photoelectric guidance. The millimeter wave has extremely wide bandwidth, so that the problem of frequency domain resource shortage can be relieved; the millimeter wave has narrow beam, and the details of the target object can be observed more clearly. Therefore, some embodiments of the application adopt millimeter waves for fall detection, and effectively improve the anti-interference capacity, the resolution capacity and the measurement precision of the radar equipment.

Illustratively, a radar device may be comprised of a radar transmitter, a radar receiver, and an antenna. The radar device may be a Frequency Modulated Continuous Wave (FMCW) millimeter wave radar device.

A radar transmitter is a radio device that provides a high-power radio frequency signal for radar equipment, and can generate a high-power radio frequency signal, i.e., an electromagnetic wave, whose carrier is modulated. The transmitter can be classified into a continuous wave transmitter and a pulse transmitter according to a modulation scheme. The transmitter consists of a primary radio frequency oscillator and a pulse modulator.

The radar receiver is a device for frequency conversion, filtering, amplification and demodulation in radar equipment. The weak high frequency signals received by the antenna are selected from accompanying noise and interference through proper filtering, and are amplified and detected for target detection, display or other radar signal processing.

An antenna is a device used in radar equipment to transmit or receive electromagnetic waves and determine the detection direction thereof. When in emission, the energy is intensively radiated to the direction needing to be irradiated; during reception, echoes in the detection direction are received, and the azimuth and/or the angle of the target are distinguished.

For example, as shown in fig. 1, T1, T2, T3 and T4 are transmitting antennas of an array antenna for transmitting microwave signals, R1, R2 and R3 are receiving antennas of the array antenna for receiving echo signals, and the millimeter wave radar can determine the position information of the target object according to the echo signals received by the receiving antennas. Wherein, the distance between the transmitting antennas is d, and the distance between the receiving antennas is 2 d.

The principle of the radar device for measuring the distance is that the radar device can obtain the distance of the target object by measuring the time difference between the transmission of the electromagnetic wave and the reception of the electromagnetic wave.

The principle of the radar apparatus measuring the velocity is a doppler shift phenomenon generated according to a relative motion between the radar apparatus and a target object. When the electromagnetic wave contacts a static target object, the reflected electromagnetic wave reflects from the target object according to the original frequency; when an electromagnetic wave contacts a moving target object, the frequency of the electromagnetic wave reflected from the target object is increased or decreased due to the modulation effect of the target velocity on the electromagnetic wave, so that a doppler shift phenomenon occurs. By using the doppler shift phenomenon, the doppler frequency associated with the moving target object can be extracted. The fluctuation range of the doppler frequency is proportional to the moving speed of the target object, that is, when the moving speed of the target object is slow, the fluctuation range of the doppler frequency is small, and when the moving speed of the target object is fast, the fluctuation range of the doppler frequency is large. Therefore, the velocity of the target object can be determined from the fluctuation amplitude of the doppler frequency.

The principle of the radar equipment for measuring the azimuth is that the radar equipment measures the distance and the elevation angle according to the azimuth beam and the elevation beam of the antenna, and then the angle of the target object is obtained.

In some embodiments, the radar device is installed at an indoor ceiling, and is turned on to perform fall detection on an indoor target object upon receiving an on instruction transmitted from the electronic device.

The radar equipment can be applied to a human body falling detection scene. As shown in fig. 2, when a target object falls, the radar apparatus transmits an electromagnetic wave to a space where the target object is located through a transmitting antenna, receives an electromagnetic wave reflected by the target object, that is, an echo signal, through a receiving antenna, and sends the echo signal to a receiver for signal processing. After frequency conversion, filtering, amplification, demodulation, or the like, the receiver extracts relevant information of the target object (for example, a distance between the target object and the radar, an angle of the target object, a speed of the target object, or the like), and analyzes the relevant information of the target object, so that whether the target object falls can be determined.

Fig. 3 is a schematic diagram of a fall detection system 10 according to an embodiment of the present disclosure. The system may include: a radar device 101 and an electronic device 102. The radar apparatus 101 and the electronic apparatus 102 may be connected in a wired or wireless manner. For example, the radar apparatus 101 and the electronic apparatus 102 are connected by a wireless local area network.

The electronic device 102 is configured to issue a manipulation instruction to the radar device 101 and receive a fall detection result of the radar device 101. For example, the electronic device in the embodiment of the present application may be a mobile phone, a tablet computer, a desktop computer, a laptop computer, a handheld computer, a notebook computer, an ultra-mobile personal computer (UMPC), a netbook, a cellular phone, a Personal Digital Assistant (PDA), an Augmented Reality (AR) \ Virtual Reality (VR) device, and the like. The present application does not specifically limit the specific form of the electronic device. The system can be used for man-machine interaction with a user through one or more modes of a keyboard, a touch pad, a touch screen, a remote controller, voice interaction or handwriting equipment and the like.

After detecting that the target falls, the radar device 101 may also synchronously upload the falling time and the falling motion characteristics of the target object to the server. Therefore, the server can acquire relevant falling data of the target object, data loss of the target object is avoided, and follow-up statistics and analysis on falling analysis are facilitated. The server may be a cloud server.

The scheme provided by the application is specifically explained in the following with the attached drawings of the specification.

The embodiment of the application provides a fall detection method, which is applied to the radar equipment. As shown in fig. 4, the method comprises the steps of: S201-S204.

S201, the radar equipment acquires the motion characteristics of the target object in each unit time length of a plurality of continuous unit time lengths.

Wherein the motion characteristic comprises at least one of distance data, velocity data, doppler signal data and angle data, the distance data being indicative of a maximum change in the distance of motion; the speed data is used for indicating the maximum value of the movement speed and a speed area change value, the speed area change value is used for indicating the ratio of a target movement speed to a plurality of movement speeds in the plurality of movement speeds, and the target movement speed is greater than a first threshold value; the Doppler signal data is used for indicating the maximum value of the Doppler signal intensity; the angle data is used to indicate a maximum variation value of the movement angle.

As a possible implementation manner, the radar device processes the echo signal reflected by the target object, so as to acquire the motion characteristics of the target object in each of the continuous unit time lengths.

In some embodiments, the radar device processes echo signals reflected by the target object to obtain distance data and/or velocity data for the target object for each of a plurality of consecutive unit durations.

Illustratively, the unit time length is 1 second(s), and the plurality of unit time lengths are 4 s. The radar device acquires the maximum change value of the moving distance per second and the maximum value of the moving speed of the target object for 4 consecutive seconds.

In some embodiments, the radar device processes echo signals reflected by the target object to obtain velocity data and/or doppler signal data of the target object for each of a plurality of consecutive unit durations.

Illustratively, the unit time length is 1 second(s), and the plurality of unit time lengths are 4 s. The radar device acquires the maximum value of the moving speed per second and the maximum value of the doppler signal intensity in 4 consecutive seconds of the target object.

In some embodiments, the radar apparatus processes echo signals reflected by the target object to acquire distance data, velocity data, doppler signal data, and angle data of the target object in each of a plurality of consecutive unit durations.

Illustratively, the unit time length is 1 second(s), and the plurality of unit time lengths are 4 s. The radar device acquires the maximum value of the moving speed, the speed area change value and the maximum value of the Doppler signal intensity of the target object per second in 4 consecutive seconds.

It should be noted that, in the embodiment of the present application, no specific limitation is made on a plurality of continuous unit time lengths and a unit time length. The unit time length may be seconds or other time units, and the continuous unit time lengths may be 4s, 6s or other time lengths.

S202, the radar equipment determines the first state of the target object in each unit time length based on the first state judgment rule and the motion characteristics of the target object in each unit time length, and obtains a first state sequence of the target object in continuous multiple unit time lengths.

Wherein the first state comprises falling, moving or stationary and the first sequence of states comprises states ordered in time.

As a possible implementation manner, in a case where the first determination rule includes a first movement rule, a first stationary rule, and a first fall rule, the radar apparatus determines whether the movement characteristic in the first unit time length satisfies the first movement rule, the first stationary rule, or the first fall rule. If the motion characteristics in the first unit time length meet the first falling rule, the radar equipment determines that the first state of the target object in the first unit time length is a falling state. If the motion characteristic in the first unit time length does not meet the first falling rule, the radar equipment judges whether the motion characteristic in the first unit time length meets the first motion rule or not. The first unit period is any one of a plurality of unit periods in succession.

Further, if the motion characteristic in the first unit time length meets the first motion rule, the radar device determines that the first state of the target object in the first unit time length is a motion state. Subsequently, if the motion characteristic in the first unit time length does not meet the first motion rule, the radar device determines that the first state of the target object in the first unit time length is a static state. And finally, the radar equipment acquires a plurality of first states, and the first states are sequentially sequenced according to the time sequence to obtain a first state sequence of the target object in continuous unit time lengths.

Specifically, as shown in fig. 5, the radar apparatus determines whether or not the motion characteristic of the target object within the first unit time length satisfies the first fall rule. If the first fall rule is met, the radar equipment determines that the target object is in a fall state in the first unit time length, and sets the flag bit of the state in the first unit time length to be 1. If the first fall rule is not met, the radar equipment judges whether the motion characteristics in the first unit duration meet the first motion rule or not. If the first motion rule is met, the radar equipment determines that the target object is in a motion state in the first unit time length, and marks the position of a state in the first unit time length to be 0. And if the first motion rule is not met, determining that the first static rule is met, further determining that the target object is in a static state in the first unit time length by the radar equipment, and marking the mark position 2 of the state in the first unit time length. Finally, the radar equipment acquires the zone bits of the target object in multiple states in multiple unit time lengths, and sequentially sorts the zone bits of the multiple states according to the time sequence to obtain a first state sequence of the target object in continuous multiple unit time lengths.

Illustratively, the unit time length is 1 second, and the plurality of unit time lengths are 4 s. Based on the first judgment rule, the radar device sequentially determines the state of the target object within 4 s: fall, movement, rest, and acquire a first sequence of states of the target object within 4 s: 1. 0, 0 and 2.

Illustratively, the unit time length is 1 second, and the plurality of unit time lengths are 5 s. Based on the first judgment rule, the radar device sequentially determines the state of the target object within 5 s: fall, move, rest, move, and acquire a first state sequence of the target object within 4 s: 1. 0, 2, 0.

It should be noted that the radar device may further determine, first, whether the motion characteristic of the target object in the first unit time length satisfies the first stationary rule, or first, whether the motion characteristic of the target object in the first unit time length satisfies the first moving rule, or simultaneously determine which rule of the first stationary rule, the first moving rule, and the first falling rule the motion characteristic of the target object in the first unit time length satisfies. The value of the flag bit representing the first state may also be other values, and this is not limited in this embodiment of the present application.

The specific implementation of this step may refer to the above step, which is not described herein again.

S203, the radar equipment judges whether the first state sequence meets a preset first falling rule.

As a possible implementation manner, the radar device obtains each sequence state parameter in the first state sequence, and sequentially determines whether each state sequence parameter satisfies a preset first falling rule.

In some embodiments, the radar device determines in turn whether each state sequence parameter satisfies a preset first fall rule.

Illustratively, in a first state sequence: 1. 0, 2 are examples. The radar device acquires a first state sequence: 1. 0, 0 and 2, and judging whether the first parameter of the first state sequence is 1 or not based on a preset first falling rule. In the case where it is confirmed that the first parameter of the first state sequence is 1, the radar apparatus sequentially determines whether the second parameter and the third parameter of the first state sequence are not 1, and determines whether the fourth parameter of the first state sequence is 2.

As another possible implementation manner, the radar device obtains a plurality of preset state sequences in a preset first fall rule, and determines whether the first state sequence is consistent with any one of the preset state sequences.

And acquiring state parameters of each sequence in the first state sequence, and sequentially judging whether the state parameters of each state sequence meet a first falling rule.

Illustratively, in a first state sequence: 1. 0, 2, the preset first fall rule comprises 4 preset state sequences: [1, 0, 2], [1, 2, 0, 2], [1, 0, 2], [1, 2] are exemplified. The radar device judges whether the first state sequence is consistent with any one of the 4 preset state sequences.

It should be noted that the preset first fall rule is stored in the radar device by the operation and maintenance personnel in advance.

And S204, determining that the target object falls under the condition that the first state sequence meets a preset first falling rule by the radar equipment.

As a possible implementation manner, the radar device determines that the target object falls when determining that each state sequence parameter satisfies a preset first falling rule.

In another case, the radar device acquires a state in a first unit duration of the continuous unit durations, and determines whether the state in the first unit duration satisfies a first fall rule based on the state in the first unit duration and the first fall rule. If the first falling rule is not met, the radar equipment determines that the target object is not fallen, and does not continue to judge. If the first fall rule is satisfied, the radar device judges whether the state in the second unit duration of the continuous multiple unit durations satisfies the first fall rule. In this way, the radar apparatus sequentially determines whether the state in each of the continuous plurality of unit time lengths satisfies the first fall rule.

Illustratively, the unit time length is 1 second, and the plurality of unit time lengths are 4 s. The radar equipment acquires the state of the target object in the 1 st s, and judges whether the state of the 1 st s meets a first falling rule. If the state of the 1 st s does not meet the first falling rule, the radar equipment determines that the target object is not fallen, and does not judge the state of the target object in the 2 nd s based on the first judgment rule. If the state of the 1 st s meets the first falling rule, the radar device judges the state of the target object in the 2 nd s based on the first judgment rule pair, and judges whether the state of the 2 nd s meets the first falling rule. In this way, the radar device judges whether the state of the target object within 4s satisfies the first fall state one by one, and determines that the target object is not fallen under the condition that the state within any one second does not satisfy the first fall rule, and does not continue to judge the state within the next second.

Subsequently, in some embodiments, the radar device sends the fall time, the motion characteristics, the state sequence, and the fall result of the target object to the electronic device and the server.

The technical effect brought by the technical scheme provided by the embodiment of the application is as follows: under the premise that the privacy of the user is not involved, the user can carry out non-contact falling detection, and the use experience of the user is effectively improved. Moreover, the radar equipment is not influenced by the environment, so that the problem that the accuracy of the identification result is reduced due to environmental factors such as illumination, smoke dust and shielding is avoided. In addition, according to the technical scheme provided by the embodiment of the application, the state sequence of the target object in the continuous unit time lengths is judged according to the motion characteristics of the target object in each unit time length in the continuous unit time lengths. And then judging whether the state sequence meets a preset falling rule or not, and determining that the target object falls under the condition that the state sequence meets the preset falling rule. That is to say, the embodiment of the application adopts logic judgment to realize human body fall detection, and the algorithm complexity is low, and the hardware computing capability requirement is low, so that the development cost is saved under the condition that the detected target object falls.

In one design, each unit duration includes a plurality of frames, and in a case that the motion feature includes distance data, velocity data, doppler signal data, and angle data, in order to obtain the motion feature of the target object in each of the consecutive unit durations, as shown in fig. 6, S201 provided in this embodiment of the present application specifically includes the following S2011-S2019.

And S2011, the radar equipment acquires the echo signals corresponding to each frame in a plurality of frames to obtain the echo signals corresponding to the frames.

The echo signal corresponding to each frame comprises a signal which is reflected by a target object after the radar equipment sends a plurality of detection signals each frame.

As a possible implementation manner, a receiving antenna of the radar device obtains an echo signal corresponding to each frame in a plurality of frames, and obtains echo signals corresponding to the plurality of frames.

Specifically, the transmitting antenna of the radar device alternately transmits chirp (chirp) signals of a plurality of frames in a specific sequence, thereby forming an effective virtual antenna array. Wherein a single transmit antenna transmits a plurality of chirp signals within a frame. Subsequently, a receiving antenna of the radar device acquires chirp signals of a plurality of frames reflected by the target object.

Further, the radar device processes the echo signal received in the first frame of the plurality of frames. Wherein the first frame is any one of a plurality of frames. The specific processing steps include steps 11-14.

And step 11, the radar equipment performs pulse compression on the echo signal of the received first frame to obtain a target range profile.

The pulse compression refers to performing pulse compression and sidelobe suppression on a linear frequency modulation signal or a phase coding signal echo, compressing a wide pulse into a narrow pulse, enabling an output signal to have a peak value at a range gate of a target, and meanwhile improving the signal-to-noise ratio. The radar equipment transmits a large-time-width and bandwidth signal at a transmitting antenna end so as to improve the speed measurement accuracy and speed resolution of the signal. At the receiving antenna end, the wide pulse signal is compressed into the narrow pulse signal through pulse compression, and the distance resolution precision and the distance resolution of the radar equipment to the target object can be improved.

In some embodiments, the above-described process of the pulse compression process may satisfy the following formula (1):

wherein, TR _(m,k) Representing the amplitude value of the mth chirp signal (chirp signal) at frequency k. The frequency k may represent a distance unit. The frequency k is proportional to the distance. The frequency k may satisfy the following formula (2):

wherein s is the slope of the frequency modulation signal of the radar device, D represents the distance between the radar device and the target object, and c represents the speed of light.

W in the above formula (1) _u Is a predetermined window function, S _(n-u,m) Data representing the nth-u sample point of the mth chirp signal. It should be understood that the pulse compression may be performed in units of frames, and after performing the calculation as formula (1) on one frame of data, the target range image of the first frame of data may be obtained.

It should be understood that pulse compression of a chirp signal over all range bins yields the target range image ri (t).

And step 12, the radar equipment performs pulse compression processing on the time range image of the first frame to obtain a target speed image.

Since the human body may have a large acceleration during a fall, the radar device will balance the maximum detection speed and speed resolution when acquiring data. The velocity of the target object acquired by the radar is the range rate of the target, so that the velocity information of the target is included in the phase shift of the time range image, and in order to extract range-doppler (RD) information of the target, the time range image of each frame is subjected to pulse compression processing to obtain a target velocity image.

In some embodiments, the time-distance image may be subjected to a pulse compression process according to the following formula (3):

wherein the content of the first and second substances,

representing the velocity distance amplitude, W, at point d1 obtained on the kth line time distance image _u For a predetermined window function, TR _(k,m-u) Indicating the first on the framek rows, m-u columns of range image data.

Subsequently, the target velocity image VR is used to calculate the doppler signal intensity of the target object corresponding to the frame.

In some embodiments, the doppler signal strength may satisfy the following equation (4):

dooppler _ mean VR/FFT _ num equation (4)

Here, doopper _ mean represents doppler signal intensity, and FFT _ num represents a length of a Fast Fourier Transform (FFT) when fourier transform is performed.

And step 13, the radar equipment acquires the angle image of the first frame.

The angle of the target object in the falling state or the moving state can be changed, so that the angle information is added into the feature space, and the falling action is accurately judged.

For the change of the target object angle, the embodiment of the present application may adopt a direction of arrival (DOA) -based estimation method. Due to the antenna arrangement mode of the radar device, the distances from the echo signals to different receiving antennas are different, so that the echo signals obtained by different receiving antennas have phase differences, the angle information of the target object is obtained by using the principle, and a schematic diagram of estimating the angle information of the target object by using the DOA is shown in fig. 7.

In some embodiments, the signal reception echo of a single antenna is xn, and the signal composed of all the reception antennas is formula (5):

xn equation (5) X ═ X1, X2, x3.

Where x1 is the first received signal and n is the total number of received signals.

In some embodiments, the range of a single chirp signal is like X, and its autocorrelation matrix is of formula (6):

R _xx ＝E[XX ^H ]formula (6)

The steering vector of the signal angle is formula (7):

a(θ)＝[1,e ^{-j2πdsinθ/c} ,e ^{-j2π2dsinθ/c} ......,e ^{-j2π(n-1)dsinθ/c} ]formula (7)

Where a (θ) is the signal angle and d is the distance between the transmitting antennas of the radar apparatus.

Thus, the signal strength CBF of the target echo of the x < th > chirp at the angle theta _(θ,x) As in equation (8):

CBF _(θ,x) ＝a(θ)R _xx a (θ) equation (8)

Meanwhile, a normalized angle image CBF can be obtained _nor Is of formula (9):

at the same time, using the angle image CBF _nor The target object angle spectrogram feature information DOA _ mean of the frame can be calculated as formula (10):

DOA_mean＝CBF _nor formula/angle _ num (10)

Where angle _ num is 181, which represents a change in angle from 0 degree to 180 degrees.

The range image, velocity image, and angle image of the target object are acquired as shown in fig. 8.

In addition, because the static object is completely in a static state, and the detected target object has small fluctuation, the radar apparatus may adopt a Moving Target Indication (MTI) technology, that is, two-pulse cancellation is performed on the received data, so as to cancel the electromagnetic wave reflected by the static object, thereby realizing static target cancellation. The above-described process of static target elimination may satisfy the following formula (11):

RI _MTI (t-T _r )＝RI(t-T _r ) RI (t) formula (11)

Wherein ri (t) is a target range profile at the current time, i.e., ri (t). t is the time corresponding to the mth chirp signal. RI (T-T) _r ) Indicating a distance T before the current time _r Target range image of time. RI (Ri) _MTI (t-T _r ) Representing the range image of the target after static target elimination.

In some embodiments, it is considered that the radar device may lose a target object or track a static target in an actual detection process. In order to avoid this problem, the radar device in the embodiment of the present application determines whether the doppler signal strength doopper _ mean of the current frame is greater than a second strength threshold.

And when the Doppler signal intensity Dooppler _ mean of the first frame is smaller than the second intensity threshold, marking the position 0 by the state information of the target object corresponding to the first frame.

When the doppler signal strength Dooppler _ mean of the first frame is equal to or higher than the second strength threshold value, the following step 14 is performed.

In some embodiments, since the static object is completely in a static state, and the detected target object has small fluctuation, the radar apparatus may employ a Moving Target Indication (MTI) technique, that is, two-pulse cancellation is performed on the received data to cancel the electromagnetic wave reflected by the static object, so as to implement static target cancellation. The above-described process of static target elimination may satisfy the following formula (11):

RI _MTI (t-T _r )＝RI(t-T _r ) -RI (t) formula (11)

And 14, the radar equipment respectively determines the distance, the speed and the angle of the target object corresponding to the first frame based on the distance image, the target image and the angle image of the first frame.

1) And the radar equipment acquires a Range unit Range _ wave corresponding to the maximum amplitude position in the Range image of the first frame and calculates to obtain the distance of the target object corresponding to the current frame.

In some embodiments, the motion distance of the target object corresponding to the first frame is calculated as formula (12):

range _ wave ═ Location _ num × Range _ resolution formula (12)

Where Range _ wave denotes a moving distance of the target object, and Range _ resolution denotes a Range resolution of the radar apparatus.

2) And the radar equipment acquires a velocity unit Location _ cel corresponding to the maximum amplitude in the velocity image of the first frame, and calculates to obtain the velocity of the target object corresponding to the first frame.

In some embodiments, the velocity of the target object corresponding to the first frame is calculated as formula (13):

velocity _ wave ═ (Location _ cel-128) × Vel _ resolution equation (13)

Where, Velocity _ wave represents the Velocity of the target object, and Vel _ resolution represents the Velocity resolution of the radar apparatus.

3) The radar equipment acquires the angle unit Location _ doa corresponding to the maximum amplitude in the angle image of the first frame, and calculates to obtain the angle of the target object corresponding to the first frame.

In some embodiments, the angle of the target object corresponding to the first frame is calculated as formula (14):

angle _ wave ═ Location _ doa formula (14)

Where Angle _ wave represents the Angle of the target object.

Fig. 9 is a schematic diagram of a radar device acquiring distance information, speed information, and angle information of a first frame according to echo signals corresponding to a plurality of frames.

S2012, the radar device determines the maximum value and the minimum value of the movement distance of the target object in the multiple frames respectively according to the echo signals corresponding to the multiple frames.

As a possible implementation manner, the radar device processes the echo signals corresponding to multiple frames, and obtains the moving distances of the target objects corresponding to the multiple frames. Further, the radar apparatus acquires a moving distance maximum value and a moving distance minimum value from moving distances of a plurality of target objects.

Wherein, obtaining the maximum range _ max of the movement distance is formula (15):

range_max＝[Range_wave[0],Range_wave[1]...Range_wave[n]] _max formula (15)

Obtaining the minimum movement distance range _ min as formula (16):

range_min＝[Range_wave[0],Range_wave[1]...Range_wave[n]] _min formula (16)

S2013, the radar equipment determines the difference between the maximum value of the movement distance and the minimum value of the movement distance as distance data of the target object in each unit time length.

Obtaining the distance data range _ change is expressed by formula (17):

range _ change is range _ max-range _ min equation (17)

Fig. 10 is a schematic diagram of the radar apparatus acquiring the maximum moving distance, the minimum moving distance, and the distance data.

S2014, the radar device respectively determines the maximum motion speed value and the speed area change value of the target object in the frames according to the echo signals corresponding to the frames.

As a possible implementation manner, the radar device processes echo signals corresponding to multiple frames, and obtains the motion speed of the target object corresponding to the multiple frames. Further, the radar apparatus acquires a maximum value of the moving speed from moving speeds of a plurality of target objects. In addition, the radar apparatus acquires a first number of moving speeds greater than an eleventh speed threshold value and a second number of moving speeds different from zero from moving speed values of the plurality of target objects, and determines a ratio of the first number to the second number as a speed area change value.

Wherein, obtaining the maximum value of the motion speed velocity _ max is expressed by the formula (18):

velocity_max＝[Velocity_wave[0],Velocity_wave[1]...Velocity_wave[n]] _max formula (18)

Obtaining a first quantity vel _above Max is equation (19):

vel _above _max＝[Velocity_wave[0],Velocity_wave[1]...Velocity_wave[n]] _>p formula (19)

For example, p may be 0.5, or may be other values, and the embodiments of the present application are not limited.

Obtaining a second quantity vel _exist Max is equation (20):

vel _exist _num＝[Velocity_wave[0],Velocity_wave[1]...Velocity_wave[n]] _≠0 formula (20)

It should be noted that, in the embodiment of the present application, the second number is a number whose motion speed is not zero, and the second number may also be another number, for example, the second number is a number whose motion speed is greater than 0.1.

Obtaining a velocity area change value velocity _ count formula (21):

for example, q may be 10, or may be other values, and the embodiments of the present application are not limited.

Fig. 11 is a diagram illustrating that the radar apparatus acquires the maximum value of the movement speed and the area change value of the speed.

S2015, determining the maximum motion speed value and the speed area change value as speed data of the target object in each unit time length by the radar device.

And S2016, determining the maximum Doppler signal intensity value of the target object in a plurality of frames by the radar equipment according to the echo signals corresponding to the plurality of frames.

As a possible implementation manner, the radar device processes echo signals corresponding to multiple frames, and obtains doppler signal intensities corresponding to the multiple frames. Further, the radar apparatus acquires a doppler signal strength maximum value from the plurality of doppler signal strengths.

Wherein, the maximum doppler _ max of the obtained doppler signal intensity is the following formula (22):

doppler_max＝[Doppler_wave[0],Doppler_wave[1]...Doppler_wave[n]] _max

s2017, the radar equipment determines the maximum Doppler signal intensity value as the Doppler signal data of the target object in each unit time length.

S2018, the radar equipment respectively determines the motion angle maximum value and the motion angle minimum value of the target object in the multiple frames according to the echo signals corresponding to the multiple frames.

As a possible implementation manner, the radar device processes echo signals corresponding to multiple frames to obtain motion angles corresponding to the multiple frames. Further, the radar device respectively obtains the maximum value and the minimum value of the motion angle from the motion angle.

Wherein, obtaining the maximum value of the motion angle _ max is formula (23):

angle_max＝[Angle_wave[0],Angle_wave[1]...Angle_wave[n]] _max formula (23)

Obtaining the minimum angle _ min of the motion angle as formula (24):

angle_min＝[Angle_wave[0],Angle_wave[1]...Angle_wave[n]] _min formula (24)

S2019, the radar equipment determines the difference between the maximum value of the motion angle and the minimum value of the motion angle as angle data of the target object in each unit time length.

The acquisition angle data angle _ change is formula (25):

angle _ change ═ angle _ max-angle _ min equation (25)

In some embodiments, in this embodiment, an average value of motion angles corresponding to a plurality of frames may also be obtained.

Fig. 12 is a schematic diagram of the radar apparatus acquiring the maximum value of the motion angle, the minimum value of the motion angle, and the angle data.

Obtaining an average value doa _ mean of motion angles corresponding to a plurality of frames as formula (26):

DOA _ mean ═ DOA _ mean [0] + DOA _ mean [1] +

As can be understood, in the embodiment of the present application, the radar device acquires the distance data, the velocity data, the doppler signal data, and the angle data of the target object in each unit time length.

In one design, the first determination rule includes a first movement rule, a first stationary rule, and a first fall rule. In order to determine the state of the target object in each unit duration, as shown in fig. 13, S202 provided in the embodiment of the present application specifically includes the following S2021 to S2026.

S2021, the radar equipment judges whether the motion characteristics of the target object in each unit time length meet a first falling rule or not.

S2022, in a case where the motion feature of the target object in each unit time length satisfies the first motion rule, the radar apparatus determines that the state of the target object in each unit time length is a falling state.

Specifically, in the case where the distance data in the first unit duration is greater than the first distance threshold and the maximum value of the speed of the target object in the first unit duration is greater than the first speed threshold, the state of the target object in the first unit duration is determined to be fallen. Or, in the case that the angle data value of the target object in the first unit duration is greater than the first angle threshold and the maximum value of the speed of the target object in the first unit duration is greater than the second speed threshold, determining that the movement of the target object in the first unit duration is a fall.

Or under the conditions that the angle data of the target object in the first unit duration is greater than the second angle threshold, the maximum speed value of the target object in the first unit duration is greater than the third speed threshold, each angle value of the target object in the first unit duration is greater than the ninth angle threshold, and each distance of the target object in the first unit duration is greater than the ninth distance threshold, determining that the state of the target object in the first unit duration is fallen. Or determining that the state of the target object in the first unit duration is fallen under the condition that the maximum speed value of the target object in the first unit duration is greater than the fourth speed threshold and the speed area change value of the target object in the first unit duration is greater than the first change threshold.

Or, in the case that the maximum value of the velocity of the target object in the first unit duration is greater than the fourth velocity threshold, and the maximum value of the doppler signal intensity of the target object in the first unit duration is greater than the first doppler signal intensity threshold, determining that the state of the target object in the first unit duration is a falling state.

S2023, the radar device judges whether the motion characteristics of the target object in each unit time length meet a first motion rule.

S2024, under the condition that the motion characteristics of the target object in each unit time length meet the first motion rule, the radar device determines that the state of the target object in each unit time length is a motion state.

Specifically, the state of the target object in the first unit time length is determined to be a motion state under the condition that the distance data of the target object in the first unit time length is greater than or equal to a third distance threshold, the maximum speed value of the target object in the first unit time length is greater than or equal to a fifth speed threshold, or the angle data of the target object in the first unit time length is greater than or equal to a third angle threshold.

S2025, the radar device judges whether the motion characteristics of the target object in each unit time length meet a first static rule.

S2026, under the condition that the motion characteristics of the target object in each unit time length meet the first static rule, the radar device determines that the state of the target object in each unit time length is a static state.

Specifically, the state of the target object in the first unit duration is determined to be static when the distance variation value of the target object in the first unit duration is smaller than the third distance threshold, the maximum speed value of the target object in the first unit duration is smaller than the fifth speed threshold, or the angle data of the target object in the first unit duration is smaller than the third angle threshold.

It should be noted that, in some embodiments, the radar apparatus first determines whether the motion characteristic of the target object in each unit time length satisfies the first fall rule, and determines whether the motion characteristic in the first unit time length satisfies the first motion rule in a case where the motion characteristic in the first unit time length does not satisfy the first fall rule. And finally, under the condition that the motion characteristics in the first unit time length do not meet the first motion rule, judging whether the motion characteristics in the first unit time length meet the first static rule or not.

In some embodiments, the radar apparatus determines whether the current distance to the target object is equal to or less than a tenth distance threshold before determining the state per unit time. And under the condition that whether the current distance of the target object is greater than a tenth distance threshold value or not, the radar equipment judges that the maximum speed value of the target object in the first unit time length is smaller than a sixth speed threshold value or the maximum Doppler signal intensity value of the target object in the first unit time length is smaller than a second Doppler signal intensity threshold value, and determines that the state of the target object in each unit time length is a motion state. And otherwise, determining that the state of the target object in the first unit duration is a static state.

The first distance threshold, the third distance threshold, the tenth distance threshold, the first speed threshold, the second speed threshold, the third speed threshold, the fourth speed threshold, the fifth speed threshold, the sixth speed threshold, the first angle threshold, the second angle threshold, the third angle threshold, the second doppler signal strength threshold, and the first doppler signal strength threshold are stored in the radar device by the operation and maintenance personnel in advance.

The first unit period is any one of a plurality of unit periods in succession.

In the embodiment of the present application, the order of executing S2021, S2023, and S2025 may not be limited, S2021 may be performed first, S2025 may be performed first, or S2021, S2023, and S2025 may be performed simultaneously.

When the state of the target object is a motion state in the first unit duration, the state flag of the target object in the first unit duration may be set to 0. In the first unit duration, when the state of the target object is the traumatic state, the state flag of the target object may be set to 1. In the first unit duration, when the state of the target object is a static state, the state flag of the target object may be set to 1.

In one design, to avoid the problem of false alarm, as shown in fig. 14, following S204 provided in the embodiment of the present application, the following S205-S207 are also included.

S205, under the condition that the first state sequence does not meet the first falling rule, the radar equipment determines the second state of the target object in each unit time length based on the second judgment rule and the motion characteristics of the target object in each unit time length to obtain a second state sequence of the target object in a plurality of unit time lengths.

Wherein the second state comprises a fall state, a movement state or a rest state, and the sequence of second states comprises the second states in chronological order.

Specifically, the second determination rule includes a second movement rule, a second stationary rule, and a second fall rule. In order to determine the state of the target object per unit time length under the second determination rule, the embodiment of the present application includes steps 21 to 23.

And step 21, the radar equipment judges whether the motion characteristics of the target object in each unit time length meet a second falling rule or not, and determines that the state of the target object in each unit time length is a falling state under the condition that the motion characteristics of the target object in each unit time length meet the second falling rule.

Specifically, the radar device determines that the target object in the first unit duration falls down when the radar device determines that the distance data in the first unit duration is greater than the fourth distance threshold and smaller than the fifth distance threshold, and the maximum speed of the target object in the first unit duration is greater than the seventh speed threshold. Or, in the case that the angle data value of the target object in the first unit duration is greater than or equal to the fourth angle threshold and less than or equal to the fifth angle threshold, and the maximum speed value of the target object in the first unit duration is greater than the eighth speed threshold, determining that the state of the target object in the first unit duration is falling.

Or, determining that the state of the target object in the first unit time length is fallen under the condition that the distance data in the first unit time length is larger than a sixth distance threshold, the angle data value of the target object in the first unit time length is larger than or equal to a sixth angle threshold, and the maximum speed value of the target object in the first unit time length is larger than a ninth speed threshold.

Or, determining that the state of the target object in the first unit duration is falling under the conditions that the distance data in the first unit duration is smaller than a seventh distance threshold, the angle data value of the target object in the first unit duration is smaller than or equal to a seventh angle threshold, and the maximum speed value of the target object in the first unit duration is greater than a tenth speed threshold.

And step 22, the radar equipment judges whether the motion characteristics of the target object in each unit time length meet the second motion rule or not, and determines that the state of the target object in each unit time length is a motion state under the condition that the motion characteristics of the target object in each unit time length meet the second motion rule.

Specifically, the radar device determines that the state of the target object in the first unit duration is motion under the condition that the distance data in the first unit duration is greater than or equal to an eighth distance threshold, the angle data value of the target object in the first unit duration is greater than or equal to an eighth angle threshold, and the maximum speed value of the target object in the first unit duration is greater than an eleventh speed threshold.

And 21, judging whether the motion characteristics of the target object in each unit time length meet a second stationary rule or not by the radar equipment, and determining that the state of the target object in each unit time length is a stationary state under the condition that the motion characteristics of the target object in each unit time length meet the second stationary rule.

Specifically, the radar device determines that the state of the target object in the first unit duration is motion when the distance data in the first unit duration is smaller than an eighth distance threshold, the angle data value of the target object in the first unit duration is smaller than an eighth angle threshold, or the maximum speed value of the target object in the first unit duration is smaller than or equal to an eleventh speed threshold.

The state of acquiring the target object in the first unit time length is shown in fig. 15.

Note that the first unit time length is any one of a plurality of continuous unit time lengths.

In the embodiment of the present application, the order of step 21, step 22, and step 23 may not be limited, step 21 may be performed first, step 22 may be performed first, or step 21, step 22, and step 23 may be performed simultaneously.

And setting the state identification bit of the target object to be 0 in the first unit duration when the state of the target object is the motion state in the first unit duration. And setting the state identification bit of the target object in the first unit duration as 1 when the state of the target object is the traumatic state in the first unit duration. And setting the state identification bit of the target object in the first unit duration as 1 when the state of the target object is in a static state in the first unit duration.

In some embodiments, the radar apparatus first determines whether or not the motion characteristic of the target object within each unit duration satisfies the second fall rule, and determines whether or not the motion characteristic within the first unit duration satisfies the second motion rule in a case where the motion characteristic within the first unit duration does not satisfy the second fall rule. And finally, under the condition that the motion characteristic in the first unit time length does not meet the second motion rule, judging whether the motion characteristic in the first unit time length meets the second static rule or not.

The fourth distance threshold, the fifth distance threshold, the sixth distance threshold, the seventh distance threshold, the eighth distance threshold, the fourth angle threshold, the fifth angle threshold, the sixth angle threshold, the seventh angle threshold, the eighth angle threshold, the seventh speed threshold, the eighth speed threshold, the ninth speed threshold, the tenth speed threshold, and the eleventh speed threshold are stored in the radar device by the operation and maintenance personnel in advance.

And subsequently, the radar equipment obtains a second state sequence of the target object in a plurality of unit time lengths according to the second state of the target object in each unit time length.

Illustratively, the plurality of unit time lengths are 6 s. The radar apparatus acquires the states of the target object in 6 consecutive seconds as follows: fall, motion, rest, still, and the second state sequence of the target object within the plurality of unit durations is 1, 0, 2.

And S206, the radar equipment judges whether the second state sequence meets a preset second falling rule.

As a possible implementation, the radar device determines whether the second sequence of states is consistent with the sequence of states in the second fall rule.

It should be noted that S206 is similar to S203 described above, and can be understood with reference to S203 described above, which is not described herein again.

And S207, determining that the target object falls under the condition that the second state sequence meets a preset second falling rule by the radar equipment.

As can be understood, the first judgment rule has a higher threshold for judging the falling of the target object, and in order to avoid the situation that the target object falls and the radar device is not detected, the second judgment rule is adopted in the embodiment of the present application to perform secondary judgment on the target object.

In one design, to avoid the false alarm problem, following S207 provided in this embodiment of the present application, the following S208 is further included.

And S208, generating alarm information if the target object is continuously in a static state within a preset time after the radar equipment determines that the target object falls down.

Wherein the alarm information is used for indicating that the target object falls.

As a possible implementation manner, the radar device determines the state of the target object again within a preset time after determining that the target object falls down, so as to obtain the state of the target object within the preset time. And if the state of the target object is continuously in a static state within the preset time length, giving an alarm.

Specifically, after the radar device determines that the target object falls down, the radar device determines the state of the target object in the preset time length based on the first determination rule or the second determination rule and the state of the target object in each unit time length in the preset time length to obtain a third state sequence.

For example, the unit time length is 1s, and the preset time length may be 3 minutes. After the radar equipment determines that the target object falls down, the obtained states of the target object per second are all static states, and a third state sequence with 180 state identification bits being 2 is obtained. Subsequently, the radar equipment judges that the third state sequences are all 2, and generates alarm information.

For example, the preset time period may be 3 minutes or 5 minutes, and the application is not limited thereto.

As can be understood, after determining that the target object falls, the radar device verifies the first fall result based on the third fall rule, and generates alarm information to notify the user when the state of the target object in the preset time period meets the third fall rule. Thereby avoiding the false alarm problem.

For a better understanding of the embodiments of the present application. Fig. 16 is a diagram illustrating first fall determination. Fig. 17 is a diagram illustrating a second fall determination. Fig. 18 is a schematic diagram of the first fall determination, the second fall determination, and the second fall confirmation determination. Here, fig. 16 exemplifies a state in which the target object is within 4 consecutive seconds. Fig. 17 exemplifies a state in which the target object is within 6 consecutive seconds.

The above embodiments mainly describe the solutions provided in the embodiments of the present application from the perspective of apparatuses (devices). It is understood that, in order to implement the method, the device or apparatus includes hardware structures and/or software modules corresponding to the execution of the respective method flows, and the hardware structures and/or software modules corresponding to the execution of the respective method flows may constitute a material information determination device. Those of skill in the art will readily appreciate that the present application is capable of hardware or a combination of hardware and computer software implementing the various illustrative algorithm steps described in connection with the embodiments disclosed herein. Whether a function is performed as hardware or computer software drives hardware depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.

In the embodiment of the present application, the device or the apparatus may be divided into the functional modules according to the method example, for example, the device or the apparatus may divide each functional module corresponding to each function, or may integrate two or more functions into one processing module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode. It should be noted that, in the embodiment of the present application, the division of the module is schematic, and is only one logic function division, and there may be another division manner in actual implementation.

Fig. 19 shows a schematic diagram of a possible configuration of a radar apparatus, with functional modules being divided for each function. As shown in fig. 19, the fall detection apparatus 30 provided in the embodiment of the present application includes an acquisition unit 301 and a determination unit 302.

An obtaining unit 301, configured to obtain a motion characteristic of a target object in each of a plurality of continuous unit durations; the motion characteristic comprises at least one of distance data, velocity data, doppler signal data and angle data, the distance data being indicative of a maximum change value of the motion distance; the speed data is used for indicating the maximum value of the movement speed and a speed area change value, the speed area change value is used for indicating the ratio of a target movement speed to a plurality of movement speeds in the plurality of movement speeds, and the target movement speed is greater than a first threshold value; the Doppler signal data is used for indicating the maximum value of the Doppler signal intensity; the angle data is used to indicate a maximum variation value of the movement angle.

A determining unit 302, configured to determine, based on the first determination rule and the motion characteristic of the target object in each unit duration, a first state of the target object in each unit duration, to obtain a first state sequence of the target object in multiple unit durations; the first state comprises a fall state, a motion state or a rest state, and the first state sequence comprises first states ordered in time.

The determining unit 302 is further configured to determine that the target object falls if the first state sequence satisfies a preset first fall rule.

Optionally, each unit duration includes a plurality of frames, and in the case that the motion feature includes distance data, velocity data, doppler signal data, and angle data, the obtaining unit 301 is specifically configured to: acquiring echo signals corresponding to each frame in a plurality of frames through radar equipment to obtain echo signals corresponding to the frames; the echo signal corresponding to each frame comprises a signal reflected by a target object after the radar equipment sends a plurality of detection signals each frame; respectively determining the maximum value and the minimum value of the movement distance of the target object in a plurality of frames according to the echo signals corresponding to the frames, and determining the difference between the maximum value and the minimum value of the movement distance as the distance data of the target object in each unit time length; and respectively determining the maximum value of the movement speed and the change value of the speed area of the target object in the plurality of frames according to the echo signals corresponding to the plurality of frames, and determining the maximum value of the movement speed and the change value of the speed area as the speed data of the target object in each unit time length. And determining the maximum Doppler signal intensity value of the target object in the multiple frames according to the echo signals corresponding to the multiple frames, and determining the maximum Doppler signal intensity value as the Doppler signal data of the target object in each unit time length. And respectively determining the motion angle maximum value and the motion angle minimum value of the target object in the plurality of frames according to the echo signals corresponding to the plurality of frames, and determining the difference between the motion angle maximum value and the motion angle minimum value as angle data of the target object in each unit time length.

Optionally, the first determination rule includes a first movement rule, a first stationary rule and a first fall rule; based on the first determination rule and the motion characteristic of the target object in each unit time length, the determining unit 302 is specifically configured to: under the condition that the motion characteristics of the target object in each unit time length meet a first motion rule, determining that the first state is a motion state; or, under the condition that the motion characteristics of the target object in each unit time length meet the first static rule, determining that the first state is a static state; alternatively, in a case where the motion characteristic of the target object in each unit time length satisfies the first fall rule, the first state is determined to be a fall state.

Optionally, the determining unit 302: the first state sequence is used for determining the first state of the target object in each unit time length according to the first judgment rule and the motion characteristics of the target object in each unit time length under the condition that the first state sequence does not meet the first falling rule, and obtaining a first state sequence of the target object in a plurality of unit time lengths; the second state comprises a fall state, a movement state or a rest state, and the second state sequence comprises the second states in a chronological order. A determination unit: and the controller is further used for determining that the target object falls if the second state sequence meets a preset second fall rule.

Optionally, the fall detection apparatus further comprises a generation unit 303. The generating unit 303 is configured to generate alarm information if the target object is continuously in a static state within a preset time after the target object falls down; the alarm information is used to indicate that the target object has fallen.

In the case of implementing the functions of the integrated modules in the form of hardware, the embodiments of the present application provide a schematic diagram of a possible structure of the radar apparatus in the embodiments. As shown in fig. 20, a radar apparatus 40. The radar apparatus 40 includes a processor 401, a memory 402, and a bus 403. The processor 401 and the memory 402 may be connected by a bus 403.

The processor 401 is a control center of the user equipment, and may be a single processor or a collective term for a plurality of processing elements. For example, the processor 401 may be a general-purpose central processing unit 402 (CPU), or may be another general-purpose processor. Wherein a general purpose processor may be a microprocessor or any conventional processor or the like.

For one embodiment, processor 401 may include one or more CPUs, such as CPU 0 and CPU 1 shown in FIG. 20.

The memory 402 may be, but is not limited to, a read-only memory (ROM) or other type of static storage device that may store static information and instructions, a Random Access Memory (RAM) or other type of dynamic storage device that may store information and instructions, an electrically erasable programmable read-only memory (EEPROM), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer.

As a possible implementation, the memory 402 may be present separately from the processor 401, and the memory 402 may be connected to the processor 401 via a bus 403 for storing instructions or program code. The map plotting method provided by the embodiments of the present application can be implemented when the processor 401 calls and executes instructions or program codes stored in the memory 402.

In another possible implementation, the memory 402 may be integrated with the processor 401.

The bus 403 may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, an Extended ISA (EISA) bus, or the like. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is shown in FIG. 20, but this is not intended to represent only one bus or type of bus.

Note that the structure shown in fig. 20 does not constitute a limitation of the radar apparatus 40. In addition to the components shown in fig. 20, the radar apparatus 40 may include more or fewer components than shown, or combine certain components, or a different arrangement of components.

As an example, in conjunction with fig. 20, the functions implemented by the acquisition unit 301, the processing unit 302, and the generation unit 303 in the fall detection apparatus 30 are the same as those of the processor 401 in fig. 20.

Optionally, as shown in fig. 20, the radar device 40 provided in the embodiment of the present application may further include a communication interface 404.

A communication interface 404 for connecting with other devices through a communication network. The communication network may be an ethernet network, a radio access network, a Wireless Local Area Network (WLAN), etc.

In one design, in the radar device provided in the embodiment of the present application, the communication interface may be further integrated in the processor.

Through the above description of the embodiments, it is clear for a person skilled in the art that, for convenience and simplicity of description, only the division of the above functional units is illustrated. In practical applications, the above function allocation can be performed by different functional units according to needs, that is, the internal structure of the device is divided into different functional units to perform all or part of the above described functions. For the specific working processes of the system, the apparatus and the unit described above, reference may be made to the corresponding processes in the foregoing method embodiments, and details are not described here again.

The embodiment of the present application further provides a computer-readable storage medium, where instructions are stored in the computer-readable storage medium, and when the instructions are executed by a computer, the computer executes each step in the method flow shown in the above method embodiment.

Embodiments of the present application provide a computer program product comprising instructions which, when run on a computer, cause the computer to perform the fall detection method of the above-described method embodiments.

The computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: an electrical connection having one or more wires, a portable computer diskette, and a hard disk. Random Access Memory (RAM), Read-Only Memory (ROM), Erasable Programmable Read-Only Memory (EPROM), registers, a hard disk, an optical fiber, a portable Compact disk Read-Only Memory (CD-ROM), an optical storage device, a magnetic storage device, or any other form of computer-readable storage medium, in any suitable combination, or as appropriate in the art. An exemplary storage medium is coupled to the processor such the processor can read information from, and write information to, the storage medium. Of course, the storage medium may also be integral to the processor. The processor and the storage medium may reside in an Application Specific Integrated Circuit (ASIC). In embodiments of the present application, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.

The above description is only an embodiment of the present application, but the scope of the present application is not limited thereto, and any changes or substitutions within the technical scope disclosed in the present application should be covered within the scope of the present application.

Claims

1. A fall detection method, characterized in that the method comprises:

acquiring the motion characteristics of a target object in each unit time length of a plurality of continuous unit time lengths; the motion characteristics include at least one of distance data, velocity data, doppler signal data, and angle data, the distance data indicating a maximum change value of a motion distance; the speed data is used for indicating the maximum value of the movement speed and a speed area change value, the speed area change value is used for indicating the ratio of a target movement speed to the plurality of movement speeds, and the target movement speed is larger than a first threshold value; the Doppler signal data is used for indicating the maximum value of the Doppler signal intensity; the angle data is used for indicating the maximum change value of the motion angle;

determining a first state of the target object in each unit time length based on a first judgment rule and the motion characteristics of the target object in each unit time length, and obtaining a first state sequence of the target object in the unit time lengths; the first state comprises a fall state, a motion state, or a rest state, the first sequence of states comprising the first states in chronological order;

determining that the target object falls if the first state sequence satisfies a preset first fall rule.

2. The method of claim 1, wherein each of the unit durations includes a plurality of frames, and wherein the obtaining the motion characteristic of the target object for each of the consecutive unit durations, in the case that the motion characteristic includes distance data, velocity data, doppler signal data, and angle data, comprises:

acquiring echo signals corresponding to each frame in the multiple frames through radar equipment to obtain the echo signals corresponding to the multiple frames; the echo signal corresponding to each frame comprises a signal reflected by the target object after the radar equipment sends a plurality of detection signals in each frame;

respectively determining the maximum value and the minimum value of the movement distance of the target object in the plurality of frames according to the echo signals corresponding to the plurality of frames, and determining the difference between the maximum value and the minimum value of the movement distance as the distance data of the target object in each unit time length;

respectively determining the maximum value of the movement speed and the change value of the speed area of the target object in the plurality of frames according to the echo signals corresponding to the plurality of frames, and determining the maximum value of the movement speed and the change value of the speed area as the speed data of the target object in each unit time length;

determining the maximum Doppler signal intensity of the target object in the multiple frames according to the echo signals corresponding to the multiple frames, and determining the maximum Doppler signal intensity as the Doppler signal data of the target object in each unit time length;

according to the echo signals corresponding to the frames, respectively determining the motion angle maximum value and the motion angle minimum value of the target object in the frames, and determining the difference between the motion angle maximum value and the motion angle minimum value as the angle data of the target object in each unit time length.

3. The method according to claim 2, wherein the first determination rule comprises a first movement rule, a first stationary rule and a first fall rule; the determining a first state of the target object in the each unit time length based on the first determination rule and the motion characteristic of the target object in the each unit time length includes:

determining that the first state is a motion state if the motion characteristic of the target object in each unit time length meets the first motion rule; alternatively, the first and second electrodes may be,

determining that the first state is a stationary state if the motion characteristic of the target object within the each unit duration satisfies the first stationary rule; alternatively, the first and second electrodes may be,

determining that the first state is a fall state if the motion characteristic of the target object within the each unit time length satisfies the first fall rule.

4. The method of claim 3, further comprising:

determining a second state of the target object in each unit time length on the basis of a second judgment rule and the motion characteristics of the target object in each unit time length under the condition that the first state sequence does not meet the first falling rule, so as to obtain a second state sequence of the target object in the unit time lengths; the second state comprises a fall state, a motion state, or a rest state, the second sequence of states comprising the second states in chronological order;

determining that the target object falls when the second state sequence meets a preset second falling rule.

5. The method according to any one of claims 1-4, further comprising:

within a preset time after the target object is determined to fall down, if the target object is continuously in a static state within the preset time, generating alarm information; the alarm information is used for indicating that the target object falls.

6. A fall detection apparatus, characterized in that the apparatus comprises: an acquisition unit and a determination unit;

the acquisition unit is used for acquiring the motion characteristics of the target object in each unit time length of a plurality of continuous unit time lengths; the motion characteristics include at least one of distance data, velocity data, doppler signal data, and angle data, the distance data indicating a maximum change value of a motion distance; the speed data is used for indicating the maximum value of the movement speed and a speed area change value, the speed area change value is used for indicating the ratio of a target movement speed to the plurality of movement speeds, and the target movement speed is larger than a first threshold value; the Doppler signal data is used for indicating the maximum value of the Doppler signal intensity; the angle data is used for indicating the maximum change value of the motion angle;

the determining unit is configured to determine, based on a first determination rule and the motion feature of the target object in each unit duration, a first state of the target object in each unit duration, and obtain a first state sequence of the target object in the unit durations; the first state comprises a fall state, a motion state, or a rest state, the first sequence of states comprising the first states in chronological order;

the determining unit is further configured to determine that the target object falls if the first state sequence satisfies a preset first fall rule.

7. The apparatus according to claim 6, wherein each unit duration comprises a plurality of frames, and in the case that the motion feature comprises distance data, velocity data, doppler signal data, and angle data, the obtaining unit is specifically configured to:

8. The apparatus according to claim 7, wherein the first determination rule includes a first movement rule, a first stationary rule, and a first fall rule; the determining unit, based on the first determination rule and the motion feature of the target object in each unit duration, is specifically configured to:

9. A radar apparatus, comprising:

one or more processors;

one or more memories;

wherein the one or more memories are for storing computer program code comprising computer instructions which, when executed by the one or more processors, cause the radar apparatus to perform the fall detection method of any of claims 1 to 5.

10. A computer-readable storage medium comprising computer-executable instructions which, when run on a computer, cause the computer to perform a fall detection method as claimed in any one of claims 1 to 5.