State monitoring device and state monitoring method

Abstract

This state monitoring device comprises: a distance profile acquisition unit (11) for acquiring a distance profile, the distance profile being information indicating motion in a target region including motion resulting from shaking of each part of an object that is within the target region and that generates motion, from a relationship between a distance from a radio wave sensor (2) to the object, generated on the basis of a detection result of the object detected by the radio wave sensor (2), and a power value corresponding to the distance, the radio wave sensor (2) detecting the object on the basis of a reflected wave resulting from a radio wave radiated toward the target region being reflected by the object; and a living body determination unit (12) that determines whether the object is a living body or a non-living body on the basis of a time-series distance profile acquired by the distance profile acquisition unit (11).

Description

Condition monitoring device and condition monitoring method

[0001] The present disclosure relates to a state monitoring device and a state monitoring method for an area to be monitored (hereinafter referred to as a "target area").

[0002] Conventionally, there is known a technique for determining whether an object is a living being such as a person or a non-living being such as luggage, based on a detection level when a radio wave sensor detects the object. For example, Patent Document 1 discloses an interior monitoring device that includes a sensor that outputs millimeter-wave radio waves toward a vehicle interior and detects the millimeter-wave waves reflected by an object inside the vehicle interior, such as an occupant or luggage, and a determination unit that determines the type of object inside the vehicle interior based on the detection level of the millimeter-wave reflected by the sensor, and the determination unit determines whether the object inside the vehicle is a child or luggage based on a trend in changes in the detection level of the millimeter-wave reflected by the sensor.

[0003] JP 2022-182340 A

[0004] The detection level of a radio wave sensor, such as a millimeter wave, for reflected waves depends on the size of the object reflecting the radio waves. Furthermore, the detection level of reflected waves from an object may vary depending on which part of the object the reflected waves are from. For example, when an object with a certain volume, such as a coat, is shaken and moves, the radio wave sensor will detect the object. However, depending on the part of the object, the change in the detection level of the reflected waves is expected to be small, just like with a living body. Conventional technologies such as those disclosed in Patent Document 1 do not take this into consideration, and therefore have the problem of potentially misjudging whether an object detected by the radio wave sensor is a living or non-living object.

[0005] The present disclosure has been made to solve the above-mentioned problems, and aims to provide a condition monitoring device that reduces erroneous determinations of whether an object in a target area detected by a radio wave sensor is living or non-living.

[0006] The condition monitoring device of the present disclosure includes a radio wave sensor that detects objects that are moving based on reflected waves from objects within the target area when radio waves emitted toward the target area are reflected, a distance profile acquisition unit that acquires a distance profile, which is information indicating movement in the target area, including movement due to shaking of each part of the object, based on the relationship between the distance from the radio wave sensor to the object and the power value corresponding to that distance, generated based on the detection results of the object detected by the radio wave sensor, and a living body determination unit that determines whether the object is living or non-living based on the time-series distance profile acquired by the distance profile acquisition unit.

[0007] According to the present disclosure, a condition monitoring device can reduce erroneous determinations of whether an object in a target area detected by a radio wave sensor is a living or non-living object.

[0008] 11 is a diagram illustrating an example of the configuration of a state monitoring device according to embodiment 1. FIG. 12 is a diagram illustrating the concept of a distance profile according to embodiment 1. FIG. 13 is a diagram illustrating the fluctuations in power values ​​when the target is a person and when the target is an object, as shown in the distance profile. FIGS. 4A, 4B, and 4C are diagrams illustrating an example of a determination method for determining object sway by the biometric determination unit according to embodiment 1. FIGS. 5A and 5B are diagrams illustrating distance profiles when an object having a portion that is difficult to stop swaying is detected. FIG. 13 is a flowchart illustrating the operation of the state monitoring device according to embodiment 1. FIG. 14 is a flowchart illustrating details of an example of object sway determination processing by the biometric determination unit in step ST2 of FIG. 6. FIG. 14 is a flowchart illustrating the operation of the abandonment alarm device according to embodiment 1. FIGS. 9A and 9B are diagrams illustrating an example of the hardware configuration of a state monitoring device according to embodiment 1. FIG. 15 is a diagram illustrating an example of the configuration of a state monitoring device according to embodiment 2. FIG. 16 is a flowchart illustrating the operation of the state monitoring device according to embodiment 2. FIG. 17 is a flowchart illustrating details of an example of object sway determination processing by the biometric determination unit in step ST2a of FIG. 16. FIG. 17 is a diagram showing an example of the configuration of a state monitoring device according to embodiment 3. FIG. 18 is a diagram for explaining the concept of a Doppler signal in embodiment 3. FIG. 19 is a diagram showing an example of a steep peak that appears in a Doppler signal in embodiment 3. FIG. 19 is a flowchart for explaining the operation of a state monitoring device according to embodiment 3. FIG. 19 is a flowchart for explaining details of an example of the object sway determination process by the living body determination unit in step ST2b of FIG. 16. FIG. 19 is a diagram showing an example of the configuration of a state monitoring device when it is determined whether an object detected by a radio wave sensor is a living body or a non-living body based on a distance profile, frequency information, and Doppler signal. FIG. 19 is a flowchart for explaining the operation of a state monitoring device when it is determined whether an object detected by a radio wave sensor is a living body or a non-living body based on a distance profile, frequency information, and Doppler signal.Fig. 20 is a flowchart for explaining details of an example of object sway determination processing by the biometric determination unit in step ST2c of Fig. 19. Fig. 21 is a diagram showing an example configuration in which a status monitoring device is connected to an intrusion alarm device and a seat control device in addition to an abandonment alarm device, and the biometric determination result is output to the intrusion alarm device and the seat control device in addition to the abandonment alarm device. Fig. 22 is a flowchart for explaining an example of operation of the intrusion alarm device. Fig. 23 is a flowchart for explaining an example of operation of the seat control device.

[0009] In the present disclosure, a condition monitoring device monitors the condition of an area to be monitored (hereinafter referred to as a "target area"). In the present disclosure, the condition of the target area refers to the state of whether or not a "living body" such as a person is present in the target area. The condition monitoring device monitors the target area as described above by determining whether an object in the target area (hereinafter referred to as an "object") detected by a radio wave sensor is a "living body" such as a person or a "non-living body" such as luggage.

[0010] In this disclosure, the radio wave sensor is assumed to be a millimeter-wave radar. Millimeter-wave radar excels at detecting extremely minute movements and is expected to be useful for non-contact vital signs sensing (respiration or heart rate detection). It is useful to determine whether an object is "living" or "non-living" based on the detection results of the object by the millimeter-wave radar. However, millimeter-wave radar detects moving objects as targets, i.e., objects. For example, even if a "non-living" object in the target area is shaken due to a shaking factor (hereinafter referred to as a "shaking factor"), such as a door in the target area being closed or other external factors, the millimeter-wave radar can still detect the object. When determining whether an object is "living" or "non-living" based on the detection results of the object by the millimeter-wave radar, there is a possibility that an object that has moved (shaken) due to a shaking factor may be erroneously determined to be "living" even though it is actually "non-living." In particular, for example, when a movement occurs in an object having a certain volume, the movement is difficult to stop depending on the part of the object. If the movement of this part that is difficult to stop is used to determine whether the object is a "living body" or a "non-living body," the movement may be erroneously determined as a "living body" movement, and as a result, the object may be erroneously determined as a "living body."

[0011] On the other hand, there is a big difference between a "living object" and a "non-living object" in terms of whether or not the object moves spontaneously and steadily. The status monitoring device focuses on this point and determines whether the object is a "living object" or a "non-living object" by observing time-series fluctuations in the movement in the target area. In the following first embodiment, as an example, the target area is the interior of a vehicle. That is, as an example, the status monitoring device determines whether an object detected by a radio wave sensor in the vehicle interior is a "living object" or a "non-living object."

[0012] 1 is a diagram showing an example of the configuration of a status monitoring device 1 according to embodiment 1. The status monitoring device 1 is mounted on, for example, a vehicle (not shown) and connected to a radio wave sensor 2 and an abandoned vehicle alarm device 3.

[0013] The radio wave sensor 2 detects objects, i.e., targets, within the vehicle cabin. The radio wave sensor 2 acquires reflected waves that are generated when radio waves are emitted toward the vehicle cabin and reflected by targets within the vehicle cabin. The radio wave sensor 2 is equipped with, for example, an antenna with wide-angle directivity, and is installed within the vehicle cabin so that radio waves are irradiated onto targets that may be present within the vehicle cabin.

[0014] The radio wave sensor 2 is a general radio wave sensor that detects objects. An example of a method for detecting an object using the radio wave sensor 2 will be described. While various modulation methods are available for the sensing signal of the radio wave sensor 2, the following describes an example in which the FM-CW (Frequency Modulation - Continuous Wave) method, which is commonly used in automotive applications, is used as the modulation method. The radio wave transmitter / receiver (not shown) included in the radio wave sensor 2 periodically generates an FM signal (called a chirp wave) whose frequency increases and decreases. The radio wave transmitter / receiver amplifies the signal power to obtain the power required for radio wave emission, and emits radio waves into the space within the vehicle cabin via a transmitting antenna (not shown). When the radio waves radiated into the space within the vehicle cabin reach an object within the radio wave emission range of the radio wave transmitter / receiver, a portion of the waves is reflected by the surface of the object and returns to the radio wave transmitter / receiver. Here, the object is an object that reflects radio waves, such as an occupant in the vehicle cabin, luggage placed in the vehicle cabin, or a vehicle structure.

[0015] The radio wave transmitting / receiving unit receives radio waves (reflected waves) reflected from the surface of the object via a receiving antenna (not shown). A signal similar to the FM transmitted wave is input as a received signal to the radio wave transmitting / receiving unit as an FM received wave. The received signal is input to the radio wave transmitting / receiving unit with a time lag corresponding to the time it takes for the radio waves to reach the object and return. The radio wave transmitting / receiving unit extracts the frequency difference between the frequency of the generated FM signal and the frequency of the received signal, and generates an intermediate frequency (IF) signal having the frequency difference. An A / D conversion unit (not shown) included in the radio wave sensor 2 converts the intermediate frequency signal from an analog signal to a digital signal.

[0016] A signal processing unit (not shown) of the radio wave sensor 2 extracts moving objects based on the digital signal. The technology by which the signal processing unit extracts moving objects is well-known, and therefore detailed description thereof will be omitted. The signal processing unit extracts signal components corresponding to the movement of the object from the digital signal using a well-known method. The movements detected by the signal processing unit include body movements such as chest movements due to breathing and movements due to shaking within the vehicle cabin. The signal processing unit performs frequency analysis on the digital signal to extract information such as the position, velocity, and signal strength of the moving object (hereinafter referred to as "sensor information"). The signal processing unit can extract the sensor information based on various well-known methods or procedures, such as Fourier transform (FFT), integration processing, peak extraction, and beamforming. The signal processing unit also generates a distance profile using a well-known method of applying FFT to the digital signal (so-called distance FFT processing).

[0017] Here, we will explain the distance profile generated by the radio wave sensor 2. In the first embodiment, the distance profile is information that indicates movement in a target area based on the relationship between the distance from the radio wave sensor 2 to the target and the power value corresponding to that distance, and is generated based on the detection result of the target detected by the radio wave sensor 2. The movement in the target area includes movement due to shaking of each part of the target.

[0018] FIG. 2 is a diagram illustrating the concept of a distance profile in the first embodiment. In FIG. 2, the distance profile is indicated by "P." As shown in FIG. 2, the distance profile can be represented by a graph with the horizontal axis representing the distance from the radio wave sensor 2 to a moving object detected by the radio wave sensor 2 and the vertical axis representing the power value corresponding to that distance. In FIG. 2, the interior of the vehicle corresponding to the distance in the distance profile, as viewed from the left side in the direction of vehicle travel, is illustrated above the distance profile, with the distance from the radio wave sensor 2 coinciding with the distance in the distance profile. Here, as an example, the radio wave sensor 2 is mounted on an overhead console (not shown) in the vehicle interior, and radio waves are emitted from the overhead console toward the interior of the vehicle. It is also assumed that the vehicle interior has three rows of seats, and an object (a shaking object or a person) is present on the second-row seat.

[0019] A distance profile is generated for each cycle in which the radio wave sensor 2 emits radio waves toward the vehicle interior and receives reflected waves from objects. That is, a distance profile is generated based on the detection results of all objects detected within the vehicle interior. For convenience, FIG. 2 illustrates three distance profiles (shown as PV1, PV2, and PV3 from the oldest to the newest) superimposed in time series. Note that the distance profile shown in FIG. 2 is a distance profile in which the power values ​​corresponding to the distance from the radio wave sensor 2 are used to roughly indicate the overall trend of the power values. Because the distance from the radio wave sensor 2 to the object changes depending on the movement of the object, strictly speaking, the overall waveform of the power values ​​on the distance profile may change for each distance profile.

[0020] For example, if an object or person is present on a seat in the vehicle cabin and the object or person moves, the radio wave sensor 2 detects this. Note that, for example, if shaking occurs in the vehicle cabin, the object moves with the shaking. The person also moves with the shaking. However, even if no shaking occurs, the person moves spontaneously and steadily due to breathing, etc. The radio wave sensor 2 receives reflected waves from the object, and the power value of the reflected waves fluctuates with the movement of the object. The distance profile can represent the power value that fluctuates with the movement of the object.

[0021] Here, the fluctuations in power values ​​appearing in the distance profile will be explained separately for the cases where the target is a person and the case where the target is an object. Fig. 3 is a diagram for explaining the fluctuations in power values ​​appearing in the distance profile when the target is a person and the fluctuations in power values ​​when the target is an object. Fig. 3 shows the power values ​​of the reflected waves that fluctuate with the movement of the person and the power values ​​of the reflected waves that fluctuate with the movement of the object, which appear in a time-series distance profile from when shaking occurs in the vehicle cabin and when the object also moves until the shaking stops. Note that for convenience of explanation, Fig. 3 shows the fluctuations in power values ​​for the person and the object separately, but as described above, the power values ​​based on the movement of the person and the movement of the object are expressed together in the distance profile.

[0022] In FIG. 3 , the dotted line indicates the fluctuation in power value due to human movement, i.e., the fluctuation in power value due to the movement of the person when the object is a person, and the dashed-dotted line indicates the fluctuation in power value due to the movement of an object, i.e., the fluctuation in power value due to the movement of the object when the object is an object. As shown in FIG. 3 , when the object is an object, a certain level of power value is detected immediately after the occurrence of shaking, but the power value based on the movement of the object (object) that appears in the distance profile subsequently decreases. This is because the amount of shaking of the object attenuates over time. More specifically, in the time-series distance profile, the power value waveform attenuates overall over time. Note that in the first embodiment, "the power value waveform attenuates overall over time" means that the power value waveform tends to attenuate overall over time. For example, even if a power value corresponding to a certain distance in a distance profile momentarily increases more than a power value corresponding to that distance in the previous distance profile, if the power value waveform can be said to attenuate overall, it is considered that the power value waveform tends to attenuate overall over time.

[0023] In contrast, if the object is a person, the power value based on the object (person)'s (person's) movement, which appears in the distance profile, fluctuates steadily over time due to spontaneous, steady movements such as body movement or breathing. The overall waveform of the power value does not decrease over time, as it would if the object were an object. For convenience, FIG. 3 does not show the minute fluctuations in the power value based on the person's body movement, breathing, or other movements. In this way, it is possible to distinguish whether the object whose power value is observed is a person or an object based on the time series fluctuations in the power value in the distance profile. In other words, it is possible to distinguish whether the power value is due to the movement of a person or the movement (sway) of an object based on the time series fluctuations in the power value in the distance profile. In the following first embodiment, the movement of an object due to shaking is also referred to as "object shaking."

[0024] The radio wave sensor 2 generates the distance profile as described above and outputs it to the condition monitoring device 1. The condition monitoring device 1 according to the first embodiment uses the distance profile acquired from the radio wave sensor 2 to determine whether the object detected by the radio wave sensor 2 is a living organism or a non-living organism.

[0025] An example of the configuration of a state monitoring device 1 according to embodiment 1 will be described below. As shown in FIG.

[0026] The distance profile acquisition unit 11 acquires the distance profile output from the radio wave sensor 2. The distance profile acquisition unit 11 outputs the acquired distance profile to the biometric determination unit 12.

[0027] The liveness determination unit 12 determines whether the object detected by the radio wave sensor 2 is a living body or a non-living body based on the time-series distance profile acquired by the distance profile acquisition unit 11. In the first embodiment, the determination by the liveness determination unit 12 of whether the object is a living body or a non-living body based on the distance profile is also referred to as "object shaking determination." In the object shaking determination, the liveness determination unit 12 determines whether the object detected by the radio wave sensor 2 is a living body or a non-living body, in other words, whether the movement of the object detected by the radio wave sensor 2 is a body movement or a respiratory movement caused by a person, or a movement caused by shaking of an object that is not supposed to move itself, i.e., object shaking.

[0028] The biometric determination unit 12 stores, for example, the distance profiles acquired from the distance profile acquisition unit 11 in a time series in a storage unit (not shown). For example, the distance profile acquisition unit 11 may store the distance profiles acquired from the radio wave sensor 2 in a time series in the storage unit. The biometric determination unit 12 acquires the time series distance profiles from the storage unit. The biometric determination unit 12 performs object sway determination based on the time series distance profiles for a predetermined period (hereinafter referred to as the "first determination period"). The first determination period is set by an administrator, for example, to 5 to 6 seconds. The respiratory rate of an adult is generally considered to be 12 to 20 bpm, and observation for 5 to 6 seconds can capture at least one cycle of respiratory movement. That is, in the distance profile, it is assumed that the power value waveform fluctuates between 5 and 6 seconds in accordance with movements such as a person's breathing. Conversely, if the power value waveform does not fluctuate between 5 and 6 seconds, it is assumed that the power value is not associated with movements such as a person's breathing; in other words, it is assumed that the power value is due to object sway. In this way, by performing an object shaking determination based on a time-series distance profile of, for example, 5 to 6 seconds, the liveness determination unit 12 can accurately determine whether the target object is a living body or a non-living body. Note that this is merely an example, and the length of the time-series distance profile over which the liveness determination unit 12 performs object shaking determination can be set as appropriate. In other words, the length of the first determination period can be set as appropriate.

[0029] The details of the object shaking determination by the biometric determination unit 12 will be described with an example.

[0030] <Object Shake Determination Example (1)> For example, the liveness determination unit 12 determines whether an object is alive or non-live based on whether a power value corresponding to at least one distance in a time-series distance profile attenuates over time during the first determination period, more specifically, whether the power value only attenuates. If a power value corresponding to at least one distance in a time-series distance profile attenuates over time during the first determination period, the liveness determination unit 12 determines that the object is alive. Note that if a power value corresponding to a certain distance attenuates over time, the liveness determination unit 12 considers the waveform of the power value in the distance profile to attenuate overall over time. On the other hand, if the power value of the reflected wave corresponding to at least one distance in a time-series distance profile fluctuates up and down, i.e., rises and attenuates, during the first determination period, the liveness determination unit 12 determines that the object is alive.

[0031] 4A is a diagram for explaining the above-mentioned "Object shaking determination example (1)", which is an example of a determination method for object shaking determination by the biometric determination unit 12 in the first embodiment. For convenience, FIG. 4A shows a time-series distance profile (time t １ , t ２ , ...) are shown superimposed on each other. The biometric determination unit 12 performs object shaking determination from the power value in each distance profile corresponding to the distance "R", for example.

[0032] For example, in each distance profile in the time series for the first determination period, the power value corresponding to the distance "R" decays over time. In this way, when the power value corresponding to at least one distance in the distance profile in the time series decays simply over time within the first determination period, the liveness determination unit 12 determines that the object is non-living. FIG. 4A shows an example in which the liveness determination unit 12 determines whether the object is living or non-living from the power value corresponding to one distance "R". The liveness determination unit 12 calculates one distance "R" from, for example, the oldest time (i.e., t １) is the distance at which the largest power value is detected in the distance profile. If the object for which a power value is detected is an object, focusing on the power value of the largest reflected wave, it is assumed that the amount of attenuation of the power value increases over time, in other words, as the shaking subsides. By focusing on the distance at which the largest power value is detected and observing the power value of the reflected wave at that distance, the living body determination unit 12 can more accurately determine whether the object is a living body or a non-living body.

[0033] <Object Vibration Determination Example (2)> For example, the biometric determination unit 12 may determine whether an object is a living or non-living object based on whether the gradient of attenuation of power values ​​corresponding to at least one distance in a time-series distance profile satisfies a preset condition (hereinafter referred to as the "attenuation determination condition"). The attenuation determination condition may be set, for example, as the following condition (1) or condition (2). The attenuation determination condition is set in advance by, for example, an administrator, and stored in a location that can be referenced by the biometric determination unit 12, such as a buffer (not shown) of the biometric determination unit 12. Condition (1): The gradient of attenuation of power values ​​corresponding to at least one distance in distance profiles adjacent in time series is equal to or less than a preset threshold (hereinafter referred to as the "gradient determination threshold"). Condition (2): The gradient of attenuation of power values ​​corresponding to at least one distance in a plurality of distance profiles spaced a preset interval (hereinafter referred to as the "gradient determination interval") is equal to or less than the gradient determination threshold.

[0034] The living body determination unit 12 determines that the object is a non-living body if the attenuation determination condition is satisfied, whereas the living body determination unit 12 determines that the object is a living body if the attenuation determination condition is not satisfied.

[0035] 4B and 4C are diagrams for explaining the above-mentioned "Object sway determination example (2)," which is an example of a determination method for object sway determination by the biometric determination unit 12 in embodiment 1. Fig. 4B is a diagram for explaining an example of object sway determination by the biometric determination unit 12 when the attenuation determination condition is the above-mentioned condition (1), and Fig. 4C is a diagram for explaining an example of object sway determination by the biometric determination unit 12 when the attenuation determination condition is the above-mentioned condition (2).

[0036] For example, when the attenuation determination condition is the above-mentioned condition (1), the living body determination unit 12 calculates a plurality of time-series distance profiles (time t １ , t ２ , ...) corresponding to a certain distance. Then, the liveness determination unit 12 generates a graph with the extracted power value on the vertical axis and time on the horizontal axis (see FIG. 4B). １ The power value corresponding to a certain distance in the distance profile is Pt １ , t ２ The power value corresponding to a certain distance in the distance profile is Pt ２ , t ３ The power value corresponding to a certain distance in the distance profile is Pt ３ is shown.

[0037] The living body determination unit 12 compares the gradient of the attenuation of the power value corresponding to a certain distance in the adjacent distance profile with the gradient determination threshold value from the generated graph. In the example of FIG. 4B, the living body determination unit 12 compares, for example, Pt １ From Pt ２ the slope of the decay to １ and Pt ２ The living body determination unit 12 compares the gradient of the line connecting Pt １ From Pt ２If the gradient of the attenuation up to Pt is equal to or less than the gradient judgment threshold, the attenuation judgment condition is satisfied, and the object is judged to be non-living. Note that if the gradient of the attenuation of the power value corresponding to a certain distance is equal to or less than the gradient judgment threshold, the living body judgment unit 12 considers that the waveform of the power value in the distance profile is attenuating overall over time. １ From Pt ２ If the gradient of attenuation up to Pt is greater than the gradient determination threshold, the attenuation determination condition is not satisfied, and the object is determined to be a living body. ２ From Pt ３ the slope of the decay to ２ and Pt ３ The living body determination unit 12 may compare the gradient of the line connecting Pt ２ From Pt ３ If the gradient of attenuation up to Pt is equal to or less than the gradient determination threshold, the attenuation determination condition is satisfied, and the object is determined to be a non-living body. ２ From Pt ３ If the gradient of attenuation up to is greater than the gradient determination threshold, it is determined that the attenuation determination condition is not satisfied, and the object is determined to be a living body.

[0038] For example, when the attenuation determination condition is the above-mentioned condition (2), similarly to when the attenuation determination condition is the above-mentioned condition (1), the living body determination unit 12 calculates a plurality of time-series distance profiles (time t １ , t ２ , ...) corresponding to a certain distance. Then, the liveness determination unit 12 generates a graph with the vertical axis representing the extracted power value of the reflected wave and the horizontal axis representing time (see FIG. 4C). １ The power value corresponding to a certain distance in the distance profile is Pt １ , t ２ The power value corresponding to a certain distance in the distance profile is Pt ２ , t ３ The power value corresponding to a certain distance in the distance profile is Pt ３However, when the attenuation determination condition is the above condition (2), the biometric determination unit 12 compares the gradient of attenuation of the power value corresponding to at least one distance in a plurality of distance profiles spaced apart by the gradient determination interval from the generated graph with the gradient determination threshold. Here, it is assumed that the gradient determination interval is set to an interval equal to or longer than the time required to acquire at least three time-series distance profiles.

[0039] In the example of FIG. 4C, the biometric determination unit 12, for example, １ From Pt ３ the slope of the decay to １ and Pt ３ The living body determination unit 12 compares the gradient of the line connecting Pt １ From Pt ３ If the gradient of the attenuation up to Pt is equal to or less than the gradient judgment threshold, the attenuation judgment condition is satisfied, and the object is judged to be non-living. Note that if the gradient of the attenuation of the power value corresponding to a certain distance is equal to or less than the gradient judgment threshold, the living body judgment unit 12 considers that the waveform of the power value in the distance profile is attenuating overall over time. １ From Pt ３ If the gradient of attenuation up to is greater than the gradient judgment threshold, the attenuation judgment condition is not satisfied, and the object is judged to be a living body. If the attenuation judgment condition is the above-mentioned condition (2), the living body judgment unit 12 will make an object shaking judgment based on power values ​​corresponding to a certain distance in the distance profile at regular time intervals. Therefore, when the living body judgment unit 12 makes an object shaking judgment based on the above-mentioned condition (2), robustness against slight movements can be expected in the object shaking judgment.

[0040] The biometric determination unit 12 may perform the object shaking determination by combining the above condition (1) or the above condition (2). For example, the biometric determination unit 12 may perform the object shaking determination by combining the above condition (1) or the above condition (2). １ From Pt ２ The gradient of the attenuation up to Pt is equal to or less than the gradient judgment threshold value. １ From Pt ３If the gradient of attenuation up to is equal to or less than the gradient determination threshold, the attenuation determination condition may be satisfied, and the object may be determined to be a non-living body.

[0041] In the above example, the biometric determination unit 12 determines whether an object is shaking based on a power value corresponding to one distance, but this is merely an example, and the biometric determination unit 12 may determine whether an object is shaking based on power values ​​corresponding to multiple distances in each distance profile. For example, the biometric determination unit 12 may determine whether an object is a living object or a non-living object based on whether or not all of the power values ​​corresponding to multiple distances in each distance profile attenuate over time within the first determination period.

[0042] As described above, in the first embodiment, the biometric determination unit 12 determines whether an object is living or non-living based on the time-series distance profile. One advantage of using the distance profile when the biometric determination unit 12 determines whether an object detected by the radio wave sensor 2 is living or non-living is that it can accurately capture the attenuation of movement (shaking) for an object having a certain volume. An object having a certain volume is assumed to be an object that is about two to three times larger than the person requiring care, such as a coat.

[0043] For example, suppose a vehicle door is closed and shaking occurs while a coat is hanging from a hanger attached to an assist grip. In this case, a difference appears in the distance profile between the attenuation rate of the power value corresponding to the distance from the radio wave sensor 2 to the area around the coat hanger (such as the contact point with the hanger hook) and the attenuation rate of the power value corresponding to the distance from the radio wave sensor 2 to the bottom of the coat. This is because, even for the same coat, the area around the hanger tends to settle down, while the bottom of the coat tends to settle down. The distance profile shows the movement in the vehicle cabin based on the relationship between the power value and the distance from the radio wave sensor 2 to the coat, including the movement caused by the shaking of each part of the coat. In other words, the distance profile shows the relationship between the distance and power value corresponding to the area around the coat hanger and the relationship between the distance and power value corresponding to the bottom of the coat. In other words, by using the distance profile, even if there are parts of the object that are difficult to settle over time and are difficult to distinguish from human movement, the biometric determination unit 12 can determine that the coat is a non-biometric object based on the attenuation of the power value in the parts that are easy to settle over time. The biometric determination unit 12 can reduce the chance of mistakenly determining that the coat is a biometric object.

[0044] 5A and 5B are diagrams illustrating distance profiles when an object having a portion that is difficult to settle is detected. FIG. 5A is a diagram illustrating an example of a distance profile showing the relationship between the distance from the radio wave sensor 2 to each portion of a coat hanging on a hanger attached to an assist grip in the vehicle cabin as described above and the power value. For ease of understanding, FIG. 5A also illustrates the coat. For convenience, FIG. 5A also shows time-series distance profiles (shown as PV1a, PV2a, and PV3a in order of the oldest in time) superimposed. For example, as shown in FIG. 5A , the power value corresponding to the distance corresponding to the portion of the coat around the hanger, which tends to settle over time, significantly attenuates over time. Meanwhile, the power value of the reflected wave corresponding to the distance corresponding to the bottom of the coat, which tends to settle over time, attenuates less over time than the power value of the reflected wave corresponding to the portion of the coat around the hanger.

[0045] In the prior art described above, if the coat is located at any position on the hem of a coat and the detection level of the reflected waves from the radio wave sensor at that hem is used to determine whether the object is a living or non-living object, the low attenuation may result in an erroneous determination that the object is a steadily moving living object. In contrast, in the condition monitoring device 1 according to embodiment 1, as described above, the living or non-living object determination unit 12 determines whether the object is a living or non-living object based on a time-series distance profile. If at least a portion of the distance profile shows attenuation of the power value corresponding to the distance of the object from the radio wave sensor 2 over time, the living or non-living object determination unit 12 can determine that the object's movement is a swaying object, i.e., that the object is a non-living object. This allows the condition monitoring device 1 to reduce erroneous determinations of whether an object detected by the radio wave sensor is a living or non-living object.

[0046] In addition, with a living body, each part from the head to the feet moves. Therefore, in the distance profile, the power values ​​corresponding to the distance corresponding to each part of the living body do not simply attenuate. In the distance profile, it is estimated that the waveforms of the power values ​​corresponding to the distance corresponding to each part of the living body fluctuate up and down in at least a part of the distance profile. Thus, in the distance profile, there is a difference between living and non-living objects in whether the waveforms of the power values ​​corresponding to the distance from the radio wave sensor 2 simply attenuate or not. By using the distance profile to determine object shaking, the living body determination unit 12 can reduce erroneous determinations of whether an object is living or non-living.

[0047] While the above example illustrates a case in which the object is a court, this is merely an example. The same principle can be applied to an object such as a golf bag containing golf clubs. FIG. 5B illustrates a golf bag containing golf clubs placed on the seat surface of a vehicle interior. In a golf bag such as that shown in FIG. 5B , the portion opposite the seat surface is less likely to settle. On the other hand, the portion adjacent to the seat surface is more likely to settle. In this case, the power value corresponding to the distance corresponding to the portion of the golf bag opposite the seat surface, which tends to settle over time, attenuates significantly over time. Meanwhile, the attenuation over time of the power value of the reflected wave corresponding to the portion adjacent to the seat surface is smaller than the attenuation over time of the power value of the reflected wave corresponding to the portion adjacent to the seat surface. By using the distance profile to determine object sway, the living body determination unit 12 can reduce the likelihood of erroneously determining that the object is a living body, even when the object is a golf bag such as that shown in FIG. 5B .

[0048] Returning to the explanation of Fig. 1, when the living body determination unit 12 determines whether the object detected by the radio wave sensor 2 is a living body or a non-living body, it outputs the determination result (hereinafter referred to as the "status determination result") to the abandonment alarm device 3.

[0049] As shown in FIG. 1 , the abandonment alarm device 3 includes an abandonment detection unit 31 and an output control unit 32. When the status monitoring device 1 determines that a living object is present in the vehicle cabin, the abandonment detection unit 31 detects whether a person requiring assistance has been abandoned in the vehicle cabin. The abandonment detection unit 31 can determine whether the status monitoring device 1 has determined that a living object is present in the vehicle cabin based on the status determination result output from the status monitoring device 1. When the status monitoring device 1 outputs a status determination result indicating that the object is a living object, the abandonment detection unit 31 determines that the status monitoring device 1 has determined that a living object is present in the vehicle cabin. When the status monitoring device 1 outputs a status determination result indicating that the object is a non-living object, or when the status monitoring device 1 does not output a status determination result, the abandonment detection unit 31 determines that the status monitoring device 1 did not determine that a living object is present in the vehicle cabin. In the first embodiment, the term "person requiring assistance" refers to a living body, such as an infant, that has a physique that makes it difficult for it to leave the target area, which is the vehicle interior in this case, by itself if it is left there. Note that in the first embodiment, living bodies such as pets are also included in the term "person requiring assistance."

[0050] The abandonment detection unit 31 detects whether a person requiring assistance has been abandoned in the vehicle cabin based on, for example, the reflected power value, position, vibration frequency, or speed of the object and preset conditions (hereinafter referred to as "abandonment determination conditions"). For example, the abandonment detection unit 31 acquires sensor information from the radio wave sensor 2 and extracts the reflected power value, position, vibration frequency, or speed of the object based on the sensor information. The radio wave sensor 2 can also calculate the vibration frequency of the object based on the reflected waves. Note that the arrow from the radio wave sensor 2 to the abandonment detection unit 31 is omitted in FIG. 1 . For example, the abandonment detection unit 31 may extract the reflected power value and position of the object based on a distance profile. In this case, in the condition monitoring device 1, the biometric determination unit 12 outputs the distance profile along with the state determination result to the abandonment alarm device 3.

[0051] The abandonment determination conditions are set in advance by an administrator or the like and stored in a buffer (not shown) or the like of the abandonment detection unit 31. The abandonment determination conditions include, for example, the following conditions (1a) to (4a): Condition (1a): "If the reflected power value is equal to or less than a preset threshold, the person requires assistance." Condition (2a): "If the position is in the driver's seat, the person is an adult (not requiring assistance)." Condition (3a): "If the vibration frequency is equal to or greater than a preset threshold, the person requires assistance." Condition (4a): "If the speed is equal to or less than a preset threshold, the person requires assistance." Regarding condition (1a), a person requiring assistance generally has a smaller reflected power value than an adult. Regarding condition (2a), it is not normally expected that a person requiring assistance is seated in the driver's seat. Regarding condition (3a), a person requiring assistance generally moves less than an adult. Regarding condition (4a), a person requiring assistance generally moves more slowly than an adult. The abandonment detection unit 31 may detect whether a person requiring assistance has been left behind in the vehicle cabin by combining the above-mentioned conditions (1a) to (4a).

[0052] The abandonment detection unit 31 may detect whether a person requiring assistance has been left behind in the vehicle cabin using other methods. For example, the abandonment detection unit 31 may detect whether a person requiring assistance has been left behind in the vehicle cabin based on information on the reflected power value, position, vibration frequency, or speed of an object and a trained model (hereinafter referred to as a "machine learning model"). The machine learning model is a model that receives information on the reflected power value, position, vibration frequency, or speed of an object as input and outputs information indicating whether a person requiring assistance has been left behind in the vehicle cabin, and is stored in advance in a buffer or the like of the abandonment detection unit 31. The abandonment detection unit 31 may detect whether a person requiring assistance has been left behind in the vehicle cabin using a known method for detecting whether a person has been left behind in a target area based on sensor information.

[0053] In the first embodiment, when the state monitoring device 1 determines that a living body is present in the vehicle cabin, the abandonment detection unit 31 detects whether the living body is a person requiring assistance. As described above, the state monitoring device 1 reduces the likelihood of erroneously determining that a non-living body having a portion that is difficult to stop shaking is a living body. In other words, the abandonment detection unit 31 can obtain a state determination result indicating that a living body is present in the vehicle cabin as highly accurate information. As a result, the abandonment detection unit 31 can accurately detect whether an abandoned body has occurred in the vehicle cabin. Conversely, the state monitoring device 1 can reduce the likelihood of erroneously determining that an object is shaking in the vehicle cabin as a living body, for example, and as a result, the abandonment detection unit 31 can reduce the likelihood of erroneously detecting that an object is abandoned in the vehicle cabin when an object is shaking.

[0054] The abandonment detection unit 31 outputs the detection result of whether or not a person requiring assistance has been left behind in the vehicle compartment (hereinafter referred to as the “abandonment detection result”) to the output control unit 32 .

[0055] The output control unit 32 controls the output of an alarm to an output device (not shown) based on the abandonment detection result output from the abandonment detection unit 31. Specifically, for example, when the abandonment detection unit 31 outputs an abandonment detection result indicating that a person requiring assistance has been abandoned in the vehicle cabin, the output control unit 32 outputs alarm output control information to cause the output device to output an alarm. The output device is, for example, a mobile terminal carried by the vehicle owner, an audio output device such as a speaker provided in a navigation device (not shown) installed in the vehicle, or a display device such as a display. When the output device is an audio output device, the output control unit 32 outputs, for example, alarm output control information to cause the audio output device to output an alarm sound. For example, by outputting an alarm from the audio output device installed in the vehicle, the abandonment alarm device 3 can notify people around the vehicle that a person has been abandoned in the vehicle cabin. When the output device is a display device, the output control unit 32 outputs, for example, alarm output control information to cause the display device to display an alarm message. For example, by displaying a warning message on a display device provided on a mobile terminal carried by the vehicle owner, the abandonment warning device 3 can notify the vehicle owner that an abandoned vehicle has occurred in the vehicle cabin.

[0056] The operation of the state monitoring device 1 according to the first embodiment will now be described. Fig. 6 is a flowchart for explaining the operation of the state monitoring device 1 according to the first embodiment. The state monitoring device 1 starts the operation shown in the flowchart of Fig. 6 when power is supplied to the state monitoring device 1, for example, when the vehicle power is turned on. The state monitoring device 1 repeats the operation shown in the flowchart of Fig. 6 until power is no longer supplied.

[0057] The distance profile acquisition unit 11 acquires the distance profile output from the radio wave sensor 2 (step ST1). The distance profile acquisition unit 11 outputs the acquired distance profile to the biometric determination unit 12.

[0058] The living body determination unit 12 performs an object shaking determination to determine whether the object detected by the radio wave sensor 2 is a living body or a non-living body based on the time-series distance profile acquired by the distance profile acquisition unit 11 in step ST1 (step ST2). The living body determination unit 12 outputs the state determination result to the abandonment alarm device 3.

[0059] FIG. 7 is a flowchart illustrating an example of the object shaking determination process performed by the biometric determination unit 12 in step ST2 of FIG. 6 . The biometric determination unit 12 determines whether the power value corresponding to at least one distance in the time-series distance profile decays over time during the first determination period (step ST21). If the power value corresponding to at least one distance in the time-series distance profile decays over time during the first determination period (step ST21: YES), the biometric determination unit 12 determines that the object is non-biometric (step ST22). The biometric determination unit 12 outputs the status determination result to the abandonment alarm device 3. On the other hand, if the power value corresponding to at least one distance in the time-series distance profile does not simply decay (step ST21: NO), in other words, if the power value corresponding to at least one distance in the time-series distance profile fluctuates during the first determination period, the biometric determination unit 12 determines that the object is biometric (step ST23). The biometric determination unit 12 outputs the state determination result to the abandonment alarm device 3 .

[0060] In step ST21, the biometric determination unit 12 may determine whether the gradient of the attenuation of the power value corresponding to at least one distance in the time-series distance profile satisfies the attenuation determination condition. In this case, if the biometric determination unit 12 determines in step ST21 that the gradient of the attenuation of the power value corresponding to at least one distance satisfies the attenuation determination condition (YES in step ST21), the biometric determination unit 12 determines that the object is a non-biometric object (step ST22) and outputs the status determination result to the abandonment alarm device 3. If the biometric determination unit 12 determines in step ST21 that the gradient of the attenuation of the power value corresponding to at least one distance does not satisfy the attenuation determination condition (NO in step ST21), the biometric determination unit 12 determines that the object is a biometric object (step ST23) and outputs the status determination result to the abandonment alarm device 3.

[0061] In the above description, the state monitoring device 1 is assumed to start the operation shown in the flowchart of FIG. 6 when power is turned on. However, this is merely an example, and the state monitoring device 1 may start the operation shown in the flowchart of FIG. 6 when a shaking-causing factor occurs in the vehicle cabin, such as when a vehicle door is opened or closed, when a vehicle door is locked, or when the vehicle engine is turned on. For example, the control unit (not shown) of the state monitoring device 1 acquires information indicating that a vehicle door has been opened or closed or when a vehicle door has been locked from a door sensor provided on the vehicle door, and when the door has been opened or closed or when the door is locked, outputs an operation start instruction to the distance profile acquisition unit 11 and the biometric determination unit 12. As a result, the distance profile acquisition unit 11 and the biometric determination unit 12 of the state monitoring device 1 start the operation shown in the flowchart of FIG. 6. For example, in the flowchart of FIG. 6, a step (step ST0) in which the control unit determines that a shaking-causing factor has occurred may be added before step ST1. If the control unit determines in step ST0 that a cause of shaking has occurred ("YES" in step ST0), the operation of the status monitoring device 1 proceeds to step ST1, whereas if the control unit determines that a cause of shaking has not occurred ("NO" in step ST0), the operation of the status monitoring device 1 ends the processing. In this case, the trigger for starting the flowchart of Figure 6 may be the power being turned on to the status monitoring device 1.

[0062] By having the distance profile acquisition unit 11 and the biometric determination unit 12 operate when a shaking factor occurs, the state monitoring device 1 operates in a situation where shaking is likely to occur in the vehicle cabin. This makes it easier for the state monitoring device 1 to improve the accuracy of shaking determination. That is, the state monitoring device 1 can further reduce erroneous determinations of whether an object detected by the radio wave sensor 2 is a living or non-living object. Note that, regardless of whether a shaking factor has occurred, the state monitoring device 1 can also reduce erroneous determinations of whether an object detected by the radio wave sensor 2 is a living or non-living object by starting operation of the distance profile acquisition unit 11 and the biometric determination unit 12 in response to power-on. This also allows the state monitoring device 1 to improve the accuracy of determining whether an object detected by the radio wave sensor 2 is a living or non-living object.

[0063] The operation of the abandonment alarm device 3 according to the first embodiment will now be described. Fig. 8 is a flowchart for explaining the operation of the abandonment alarm device 3 according to the first embodiment. The abandonment alarm device 3 starts the operation shown in the flowchart of Fig. 8 when it is triggered by powering on the abandonment alarm device 3, for example, when the power of the vehicle is turned on. The abandonment alarm device 3 repeats the operation shown in the flowchart of Fig. 8 until it is no longer powered on.

[0064] The abandonment detection unit 31 determines whether the state monitoring device 1 has determined that a living body is present in the vehicle compartment based on the state determination result output from the state monitoring device 1 (step ST31).

[0065] If the state monitoring device 1 determines in step ST31 that a living body is present in the vehicle compartment (YES in step ST31), the abandonment detection unit 31 detects whether a person requiring assistance has been left behind in the vehicle compartment (step ST32). The abandonment detection unit 31 outputs the abandonment detection result to the output control unit 32.

[0066] The output control unit 32 controls the output of an alarm to the output device based on the abandonment detection result output from the abandonment detection unit 31 in step ST32 (step ST33).

[0067] If, in step ST31, the status monitoring device 1 determines that there is no living organism in the vehicle cabin (if "NO" in step ST31), in other words, if the status monitoring device 1 determines that there is no living organism in the vehicle cabin, or if the status monitoring device 1 does not output a status determination result, the abandonment alarm device 3 terminates the operation shown in the flowchart of Figure 8.

[0068] 9A and 9B are diagrams showing an example of the hardware configuration of the condition monitoring device 1 according to the first embodiment. In the first embodiment, the functions of the distance profile acquisition unit 11, the living body determination unit 12, and a control unit (not shown) are realized by a processing circuit 1001. That is, the condition monitoring device 1 includes the processing circuit 1001 for performing control to determine whether an object detected by the radio wave sensor 2 is living or non-living. The processing circuit 1001 may be dedicated hardware as shown in FIG. 9A, or may be a processor 1004 that executes a program stored in memory as shown in FIG. 9B.

[0069] If the processing circuit 1001 is dedicated hardware, the processing circuit 1001 may be, for example, a single circuit, a composite circuit, a programmed processor, a parallel programmed processor, an ASIC (Application Specific Integrated Circuit), an FPGA (Field-Programmable Gate Array), or a combination thereof.

[0070] When the processing circuit is the processor 1004, the functions of the distance profile acquisition unit 11, the biometric determination unit 12, and the control unit (not shown) are realized by software, firmware, or a combination of software and firmware. The software or firmware is written as a program and stored in the memory 1005. The processor 1004 executes the functions of the distance profile acquisition unit 11, the biometric determination unit 12, and the control unit (not shown) by reading and executing the program stored in the memory 1005. In other words, the condition monitoring device 1 includes the memory 1005 for storing a program that, when executed by the processor 1004, results in the execution of the processes of steps ST1 and ST2 in FIG. 6 described above. It can also be said that the program stored in the memory 1005 causes a computer to execute the procedures or methods of the distance profile acquisition unit 11, the biometric determination unit 12, and the control unit (not shown). Here, the memory 1005 may be, for example, a non-volatile or volatile semiconductor memory such as a RAM, a ROM (Read Only Memory), a flash memory, an EPROM (Erasable Programmable Read Only Memory), or an EEPROM (Electrically Erasable Programmable Read-Only Memory), a magnetic disk, a flexible disk, an optical disk, a compact disk, a mini disk, or a DVD (Digital Versatile Disc).

[0071] Note that the functions of the distance profile acquisition unit 11, the biometric determination unit 12, and the control unit (not shown) may be partially implemented by dedicated hardware and partially implemented by software or firmware. For example, the distance profile acquisition unit 11 may be implemented by a processing circuit 1001 as dedicated hardware, and the biometric determination unit 12 and the control unit (not shown) may be implemented by a processor 1004 reading and executing a program stored in a memory 1005. The storage unit (not shown) may be configured, for example, with a memory. The status monitoring device 1 also includes an input interface device 1002 and an output interface device 1003 that communicate with devices such as the radio wave sensor 2 or the abandoned object alarm device 3 via wired or wireless communication.

[0072] The hardware configuration of the abandonment alarm device 3 according to the first embodiment is the same as the hardware configuration of the status monitoring device 1 described using Figures 9A and 9B, and therefore is not shown in the drawings. In the first embodiment, the functions of the abandonment detection unit 31 and the output control unit 32 are realized by a processing circuit 1001. That is, the abandonment alarm device 3 includes a processing circuit 1001 for detecting that a person requiring assistance has been abandoned in the vehicle cabin and for controlling the output of an alarm. The processing circuit 1001 may be dedicated hardware as shown in Figure 9A, or may be a processor 1004 that executes a program stored in a memory 1005 as shown in Figure 9B.

[0073] The processing circuit 1001 executes the functions of the abandonment detection unit 31 and the output control unit 32 by reading and executing a program stored in the memory 1005. That is, the abandonment alarm device 3 includes the memory 1005 for storing a program that, when executed by the processing circuit 1001, results in the execution of steps ST31 to ST33 in FIG. 8 described above. It can also be said that the program stored in the memory 1005 causes a computer to execute the processing procedures or methods of the abandonment detection unit 31 and the output control unit 32. The abandonment alarm device 3 includes an input interface device 1002 and an output interface device 1003 that perform wired or wireless communication with the status monitoring device 1 or a device such as an output device (not shown).

[0074] In the first embodiment, the abandonment alarm device 3 includes the abandonment detection unit 31. However, this is merely an example. For example, the status monitoring device 1 may include the abandonment detection unit 31.

[0075] In the first embodiment, the status monitoring device 1 is an on-board device mounted on a vehicle, but this is merely an example. For example, part or all of the distance profile acquisition unit 11 or the biometric determination unit 12 may be provided in a server (not shown), and the on-board device and the server may form a system. In the first embodiment, the abandonment warning device 3 is an on-board device mounted on a vehicle, but this is merely an example. For example, part or all of the abandonment detection unit 31 or the output control unit 32 may be provided in a server (not shown), and the on-board device and the server may form a system.

[0076] In the first embodiment, the target area is the interior of a vehicle, but this is merely an example. The target area is not limited to the interior of a vehicle, and may be, for example, the interior of an airplane, a train, or any other interior of a moving object other than a vehicle. Furthermore, the target area is not limited to the interior of a moving object, and may be, for example, the interior of a room. When the target area is the interior of a room, factors that cause shaking include the room door being closed or the air conditioner being turned on. For example, when the air conditioner is turned on, clothes hanging on hangers in the room will shake due to the wind from the air conditioner. The state monitoring device 1 uses the distance profile to determine whether the object detected by the radio wave sensor 2 is a living or non-living object. For example, when there is no one in the room but the curtains are shaking, the state monitoring device 1 can reduce the likelihood of incorrectly determining that the shaking curtains detected by the radio wave sensor 2 are a living object. In other words, the state monitoring device 1 can reduce the likelihood of incorrectly determining that the shaking curtains represent human movement and that a living object is present in the room.

[0077] As described above, according to the first embodiment, the condition monitoring device 1 is configured to include: a radio wave sensor 2 that detects moving objects based on waves emitted toward a target area and reflected by the objects (targets) within the target area; a distance profile acquisition unit 11 that acquires a distance profile, which is information indicating movement in the target area, including movement due to shaking of each part of the object, based on the relationship between the distance from the radio wave sensor 2 to the object and the power value corresponding to the distance, generated based on the detection result of the object detected by the radio wave sensor 2; and a living body determination unit 12 that determines whether the object is living or non-living based on the time-series distance profile acquired by the distance profile acquisition unit 11. Therefore, the condition monitoring device 1 can reduce erroneous determinations of whether an object in the target area detected by the radio wave sensor 2 is living or non-living.

[0078] Furthermore, according to the first embodiment, the abandonment detection unit 31 detects whether a person requiring assistance has been left behind in the target area based on the result of the determination by the living body determination unit 12 as to whether an object (target) is a living or non-living body. Specifically, when the status monitoring device 1 determines that a living body is present in the vehicle cabin, the abandonment detection unit 31 detects whether the living body is a person requiring assistance. This allows the abandonment detection unit 31 to accurately detect whether a person has been left behind in the vehicle cabin. The status monitoring device 1 can reduce the number of times that an object swaying in the vehicle cabin is mistakenly determined to be a living body. As a result, the abandonment detection unit 31 can reduce the number of times that an object swaying in the vehicle cabin is mistakenly detected as being abandoned. In particular, in the field of abandonment detection, suppressing over-alarms is an important factor from the perspective of usability. For example, it is easy to imagine that an object swaying due to the impact of closing a door can easily occur. If the radio wave sensor 2 detects the movement of a non-living body due to the object swaying, this could lead to an over-alarm for an object being left behind in the vehicle cabin. In contrast to this, in the first embodiment, as described above, when the state monitoring device 1 determines that a living body is present in the vehicle compartment, the abandonment detection unit 31 detects whether the living body is a person requiring assistance or not. This allows the state monitoring device 1 to contribute to reducing excessive alarms.

[0079] Embodiment 2. In embodiment 1, the status monitoring device uses a distance profile to determine whether an object detected by a radio wave sensor is a living or non-living object. In embodiment 2, an embodiment will be described in which the status monitoring device uses information on the vibration frequency of the object in addition to the distance profile to determine whether an object detected by a radio wave sensor is a living or non-living object.

[0080] 10 is a diagram showing a configuration example of a status monitoring device 1a according to embodiment 2. In embodiment 2, the status monitoring device 1a is connected to a radio wave sensor 2 and an abandonment alarm device 3. In embodiment 2, the status monitoring device 1a, the radio wave sensor 2, and the abandonment alarm device 3 are mounted on, for example, a vehicle (not shown).

[0081] 10, components similar to those of the condition monitoring device 1 described in embodiment 1 using FIG. 1 are denoted by the same reference numerals, and redundant description will be omitted. The condition monitoring device 1a according to embodiment 2 differs from the condition monitoring device 1 according to embodiment 1 in that it includes a vibration frequency information acquisition unit 13. Furthermore, in the condition monitoring device 1a according to embodiment 2, the specific operation of the biometric determination unit 12a differs from the specific operation of the biometric determination unit 12 in the condition monitoring device 1 according to embodiment 1.

[0082] The radio wave sensor 2 has a function of calculating a frequency in addition to a distance profile. Specifically, in the radio wave sensor 2, the signal processing unit has a function of generating a distance profile and calculating the frequency of the detected object as a detection result of the detected object. The signal processing unit calculates the frequency of the object, for example, using a known breathing detection method. Known breathing detection methods can observe distance fluctuations between the radio wave sensor 2 and the body surface caused by movements of the human body surface associated with breathing. The distance fluctuations appear as a phase difference between multiple received signals. Using a similar method, the signal processing unit can observe the vibration of the object and calculate the frequency. The signal processing unit generates information regarding the calculated frequency of the object (hereinafter referred to as "frequency information"). The frequency information includes information regarding the position of the detected object (the distance from the radio wave sensor 2 to the object) and frequency information. In the second embodiment, the radio wave sensor 2 outputs the distance profile and frequency information to the condition monitoring device 1a. The status monitoring device 1a then acquires frequency information in addition to the distance profile, and determines whether the object detected by the radio wave sensor 2 is a living organism or a non-living organism.

[0083] The vibration frequency information acquisition unit 13 acquires vibration frequency information from the radio wave sensor 2. The vibration frequency information acquisition unit 13 outputs the acquired vibration frequency information to the living body determination unit 12a.

[0084] The living body determination unit 12a performs object shaking determination to determine whether the object is a living body or a non-living body based on the time-series distance profile acquired by the distance profile acquisition unit 11 and the frequency information acquired by the frequency information acquisition unit 13. Specifically, the living body determination unit 12a determines whether or not a power value corresponding to at least one distance in the time-series distance profile acquired by the distance profile acquisition unit 11 attenuates over time within a first determination period, and whether or not the frequency of the object during the first determination period based on the frequency information acquired by the frequency information acquisition unit 13 satisfies a predetermined condition (hereinafter referred to as a "first shaking condition"). Whether or not the frequency of the object during the first determination period satisfies the first shaking condition specifically means whether or not the frequency of the object at any time point within the first determination period satisfies the first shaking condition. The first vibration condition is set as follows: "The vibration frequency of the object during the first determination period is equal to or greater than a predetermined threshold (hereinafter referred to as the "breathing determination threshold"), or is less than a predetermined threshold (hereinafter referred to as the "lower threshold for breathing determination"). The liveness determination unit 12a determines that the object detected by the radio wave sensor 2 is non-living if the power value corresponding to at least one distance in the time-series distance profile attenuates over time during the first determination period. On the other hand, the liveness determination unit 12a determines that the object detected by the radio wave sensor 2 is living if the power value corresponding to at least one distance in the time-series distance profile does not simply attenuate over time during the first determination period. However, if the vibration frequency of the object satisfies the first vibration condition at any point during the first determination period—in other words, if the vibration frequency of the object is equal to or greater than the breathing determination threshold or is less than the lower threshold for breathing determination—the liveness determination unit 12a determines that the object is non-living without waiting until the end of the first determination period.For example, if the vibration frequency of the object is equal to or greater than the breathing detection threshold at any point in time during the first determination period, the living body determination unit 12a may subsequently determine whether the vibration frequency of the object is less than the breathing detection threshold, and if the vibration frequency of the object is less than the breathing detection threshold, determine that the object is a living body without waiting for the end of the first determination period.Furthermore, for example, if the vibration frequency of the object is less than the breathing detection lower-limit threshold at any point in time during the first determination period, the living body determination unit 12a may subsequently determine whether the vibration frequency of the object is equal to or greater than the breathing detection lower-limit threshold, and if the vibration frequency of the object is equal to or greater than the breathing detection lower-limit threshold, determine that the object is a living body without waiting for the end of the first determination period.

[0085] The breathing detection threshold and the lower breathing detection threshold are set in advance by an administrator or the like and stored in a buffer (not shown) or the like of the biometric determination unit 12a. The breathing detection threshold is set, for example, to the upper limit of an estimated human breathing rate. Generally, a human breathing rate is considered to be approximately 15 bpm (adult) to 40 bpm (newborn). Therefore, the administrator or the like sets the breathing detection threshold to, for example, 40 bpm. While object swaying is a periodic movement like breathing, its period is clearly faster than breathing. For example, suppose there is an object hanging by a string (hereinafter referred to as a "hanging object") in a vehicle cabin, such as a hanging air freshener, a hanging toy, or the slider of a zipper. In this case, if the swinging of the hanging object is considered to be a pendulum motion, the vibration frequency of the hanging object is likely to easily exceed 40 bpm. For example, even if the string is 0.4 m long, the vibration frequency of the hanging object will be 47 bpm. Based on the vibration frequency information, the biometric determination unit 12a determines whether the vibration frequency of the object detected by the radio wave sensor 2 is equal to or greater than the breathing detection threshold. If the vibration frequency of the object is equal to or greater than the breathing detection threshold, i.e., if the vibration frequency of the object is clearly greater than a person's breathing rate, it can be determined that the object's movement is due to object swaying. The lower limit threshold for breathing detection is set to, for example, the lower limit of a value expected for a person's breathing rate. The administrator, for example, sets the lower limit threshold for breathing detection to a frequency value indicating a movement too slow for a human breathing rate. For example, if a large object such as a coat is hanging and swinging, the vibration frequency of the coat is likely to be slower than a person's breathing rate.

[0086] The details of the method by which the biometric determination unit 12a determines whether or not a power value corresponding to at least one distance in a time-series distance profile has decayed over time within the first determination period are the same as the method by which the biometric determination unit 12 determines whether or not a power value corresponding to at least one distance in a time-series distance profile has decayed over time within the first determination period, as already explained in embodiment 1, and therefore will not be explained again.

[0087] Instead of the above determination method, the living body determination unit 12a may determine that the object detected by the radio wave sensor 2 is non-living body if, for example, in the time-series distance profile acquired by the distance profile acquisition unit 11, the gradient of the attenuation of the power value corresponding to at least one distance satisfies the attenuation determination condition, or if the vibration frequency of the object during a first determination period based on the vibration frequency information satisfies a first vibration condition. Details of the method by which the living body determination unit 12a determines whether or not the gradient of the attenuation of the power value corresponding to at least one distance in the time-series distance profile satisfies the attenuation determination condition are the same as the method by the living body determination unit 12 described in embodiment 1 for determining whether or not the gradient of the attenuation of the power value corresponding to at least one distance in the time-series distance profile satisfies the attenuation determination condition, and therefore redundant description will be omitted.

[0088] Thus, in the second embodiment, the biometric determination unit 12a determines whether an object is alive or non-living based on the time-series distance profile and frequency information. The advantage of using frequency information in addition to the distance profile when determining whether an object detected by the radio wave sensor 2 is alive or non-living is that the biometric determination unit 12a can more accurately determine whether the movement (shaking) of a relatively small object, such as a plastic bottle or plastic water container, is due to a person's bodily movement or breathing, or whether the movement is due to the shaking of an object that is not supposed to move, i.e., object swaying, for relatively small objects that are the same size as or smaller than a small child. The vibration frequency of relatively small objects is expected to be faster. For example, when water in a typical 40 cm square plastic container is shaking, it is expected to shake at 100 bpm or more. The biometric determination unit 12a uses frequency information together with the distance profile to determine whether an object detected by the radio wave sensor 2 is biometric or non-bimetric, thereby improving the accuracy of determining whether an object is biometric or non-bimetric, especially for relatively small objects, compared to when only the distance profile is used.

[0089] In order to capture fast vibrations, a certain sampling period is required. In the radio wave sensor 2, the signal transmission interval (for example, in the case of an FM-CW system, the transmission interval of an FM signal (chirp wave)) corresponds to this sampling period. Therefore, it is effective for the biometric determination unit 12a to use the vibration frequency information if the signal transmission interval by the radio wave sensor 2 is determined after determining in advance how much vibration to capture. Therefore, for example, in the condition monitoring device 1a, the biometric determination unit 12a may be able to control the interval at which the radio wave sensor 2 transmits a signal, in other words, the interval at which the radio wave sensor 2 emits radio waves.

[0090] The configuration example of the abandonment alarm device 3 according to the second embodiment is the same as the configuration example of the abandonment alarm device 3 according to the first embodiment, so a duplicated description will be omitted. Note that in the second embodiment, the abandonment detection unit 31 of the abandonment alarm device 3 may, for example, extract the vibration frequency of the target object from the vibration frequency information. In this case, the living body determination unit 12a in the status monitoring device 1a outputs the vibration frequency information together with the status determination result to the abandonment alarm device 3.

[0091] The operation of the state monitoring device 1a according to the second embodiment will now be described. Fig. 11 is a flowchart for describing the operation of the state monitoring device 1a according to the second embodiment. The trigger for starting the operation of the state monitoring device 1a may be the same as the trigger for starting the operation of the state monitoring device 1 according to the first embodiment, and therefore a duplicated description will be omitted. With regard to the processing shown in the flowchart of Fig. 11 , processing whose specific content is the same as the processing already explained using the flowchart of Fig. 6 in the first embodiment will be assigned the same step numbers as in the flowchart of Fig. 6 and a duplicated description will be omitted.

[0092] The vibration frequency information acquisition unit 13 acquires vibration frequency information from the radio wave sensor 2 (step ST1a) and outputs the acquired vibration frequency information to the living body determination unit 12a.

[0093] The living body determination unit 12a performs an object sway determination to determine whether the object is a living body or a non-living body based on the time-series distance profile acquired by the distance profile acquisition unit 11 in step ST1 and the frequency information acquired by the frequency information acquisition unit 13 in step ST1a (step ST2a). The living body determination unit 12a outputs the state determination result to the abandonment alarm device 3.

[0094] FIG. 12 is a flowchart for explaining details of an example of the object shaking determination process by the biometric determination unit 12a in step ST2a of FIG.

[0095] The biometric determination unit 12a determines whether the power value corresponding to at least one distance in the time-series distance profile decays over time during the first determination period or satisfies the first vibration condition (step ST21a). If the power value corresponding to at least one distance in the time-series distance profile decays over time during the first determination period (if "YES" in step ST21a), the biometric determination unit 12a determines that the object is non-biometric (step ST22). If the vibration frequency of the object during the first determination period satisfies the first vibration condition (if "YES" in step ST21a), the biometric determination unit 12a determines that the object is non-biometric without waiting for the end of the first determination period (step ST22). The biometric determination unit 12a outputs the status determination result to the abandonment alarm device 3.

[0096] On the other hand, in step ST21a, if the time-series distance profile shows that the power value corresponding to at least one distance does not simply attenuate, in other words, if the power value corresponding to at least one distance fluctuates within the first determination period, and the vibration frequency of the object during the first determination period based on the vibration frequency information does not satisfy the first vibration condition (if "NO" in step ST21a), the living body determination unit 12a determines that the object is a living body (step ST23). The living body determination unit 12a outputs the state determination result to the abandonment alarm device 3. For example, if the vibration frequency of the object during the first determination period is equal to or greater than the breathing determination threshold and then becomes less than the breathing determination threshold, the living body determination unit 12a may determine "NO" in step ST21a and determine that the object is a living body without waiting for the end of the first determination period. Furthermore, for example, if the vibration frequency of the object during the first determination period becomes less than the lower threshold for respiration determination, and then the vibration frequency of the object becomes equal to or greater than the lower threshold for respiration determination, the living body determination unit 12a may determine that the object is a living body, judging step ST21a as “NO,” without waiting until the end of the first determination period.

[0097] In step ST21a, the living body determination unit 12a may determine whether the gradient of the attenuation of the power value corresponding to at least one distance in the time-series distance profile satisfies the attenuation determination condition. In this case, if the living body determination unit 12a determines in step ST21a that the gradient of the attenuation of the power value corresponding to at least one distance satisfies the attenuation determination condition or that the vibration frequency of the object during the first determination period based on the vibration frequency information satisfies the first vibration condition (if "YES" in step ST21a), the living body determination unit 12a determines that the object is non-living (step ST22) and outputs the status determination result to the abandonment alarm device 3. In step ST21a, if it is determined that the gradient of the attenuation of the power value of the reflected wave corresponding to at least one distance does not satisfy the attenuation judgment condition, and if it is determined that the vibration frequency of the object during the first judgment period based on the vibration frequency information does not satisfy the first shaking condition (if "NO" in step ST21a), if the vibration frequency of the object during the first judgment period becomes greater than or equal to the breathing judgment threshold and then becomes less than the breathing judgment threshold, or if the vibration frequency of the object during the first judgment period becomes less than the breathing judgment lower limit threshold and then becomes greater than or equal to the breathing judgment lower limit threshold, the living body judgment unit 12a judges that the object is a living body (step ST23) and outputs the status judgment result to the abandonment alarm device 3.

[0098] In the above description, in the operation shown in the flowchart of Fig. 11, the processing of step ST1 and the processing of step ST1a are performed in parallel, but this is merely an example. For example, the processing of step ST1a may be performed after the processing of step ST1, or the processing of step ST1 may be performed after the processing of step ST1a. It is sufficient that the processing of step ST1 and the processing of step ST1a are performed before the processing of step ST2a is performed.

[0099] The hardware configuration of the condition monitoring device 1a according to the second embodiment is the same as that shown in Figures 9A and 9B in the first embodiment, and is therefore not shown in the drawings. In the second embodiment, the functions of the distance profile acquisition unit 11, the vibration frequency information acquisition unit 13, the living body determination unit 12a, and a control unit (not shown) are realized by a processing circuit 1001. That is, the condition monitoring device 1a includes the processing circuit 1001 for performing control to determine whether an object detected by the radio wave sensor 2 is living or non-living. The processing circuit 1001 may be dedicated hardware as shown in Figure 9A, or may be a processor 1004 that executes a program stored in memory as shown in Figure 9B.

[0100] The processing circuit 1001 reads and executes a program stored in the memory 1005, thereby executing the functions of the distance profile acquisition unit 11, the vibration frequency information acquisition unit 13, the biometric determination unit 12a, and a control unit (not shown). That is, the status monitoring device 1a includes a memory 1005 for storing a program that, when executed by the processing circuit 1001, results in the execution of step ST1 and steps ST1a to ST2a of FIG. 11 . The program stored in the memory 1005 can also be said to cause a computer to execute the processing procedures or methods of the distance profile acquisition unit 11, the vibration frequency information acquisition unit 13, the biometric determination unit 12a, and the control unit (not shown). The status monitoring device 1a includes an input interface device 1002 and an output interface device 1003 that perform wired or wireless communication with devices such as the radio wave sensor 2 or the abandonment alarm device 3.

[0101] In the second embodiment, the abandonment alarm device 3 includes the abandonment detection unit 31. However, this is merely an example. For example, the status monitoring device 1a may include the abandonment detection unit 31.

[0102] In the second embodiment, the state monitoring device 1a is an in-vehicle device mounted on a vehicle, but this is merely an example. For example, the distance profile acquisition unit 11, the vibration frequency information acquisition unit 13, the biometric determination unit 12a, and some or all of the control unit (not shown) may be provided in a server (not shown), and the in-vehicle device and the server may form a system.

[0103] In the second embodiment, the target area is the interior of a vehicle, but this is merely an example. The target area is not limited to the interior of a vehicle, and may be, for example, the interior of an airplane, a train, or any other interior of a moving object other than a vehicle. Furthermore, the target area is not limited to the interior of a moving object, and may be, for example, the interior of a room.

[0104] As described above, according to the second embodiment, the condition monitoring device 1a includes the distance profile acquisition unit 11 that acquires a distance profile, and the frequency information acquisition unit 13 that acquires frequency information related to the vibration frequency of an object generated based on the detection result of the object detected by the radio wave sensor 2, and the living body determination unit 12a is configured to determine whether an object is a living body or a non-living body based on the time-series distance profile acquired by the distance profile acquisition unit 11 and the frequency information acquired by the frequency information acquisition unit 13. Therefore, the condition monitoring device 1a can reduce erroneous determinations as to whether an object in a target area detected by the radio wave sensor is a living body or a non-living body.

[0105] Third Embodiment In a third embodiment, a description will be given of an embodiment in which a status monitoring device uses a Doppler signal in addition to a distance profile to determine whether an object detected by a radio wave sensor is a living body or a non-living body.

[0106] 13 is a diagram showing a configuration example of a status monitoring device 1b according to embodiment 3. In embodiment 3, the status monitoring device 1b is connected to a radio wave sensor 2 and an abandonment alarm device 3. In embodiment 3, the status monitoring device 1b, the radio wave sensor 2, and the abandonment alarm device 3 are mounted on, for example, a vehicle (not shown).

[0107] The radio wave sensor 2 has the function of generating a Doppler signal in addition to a distance profile. Specifically, the signal processing unit in the radio wave sensor 2 has the function of generating a distance profile and a Doppler signal as a detection result of a detected object. The signal processing unit can generate a Doppler signal by compressing the distance direction of a range-Doppler map (a two-dimensional graph with distance on the horizontal axis and velocity on the vertical axis) obtained by applying an FFT (so-called Doppler FFT) in the hit direction to multiple distance profiles generated by so-called distance FFT processing. Compression in the distance direction refers to reducing the information of the range-Doppler map to only information in the velocity direction through processing such as averaging in the distance direction or adding in the distance direction.

[0108] Here, we will explain the Doppler signal generated by the radio wave sensor 2. In the third embodiment, the Doppler signal is information that indicates movement in a target area based on the relationship between the speed and power value of an object, i.e., a target object, detected by the radio wave sensor 2, as described above. The movement in the target area includes movement due to the shaking of each part of the object. The Doppler signal is a signal whose power value tends to fluctuate according to the magnitude of the movement of the target object.

[0109] Fig. 14 is a diagram for explaining the concept of Doppler signals in embodiment 3. Fig. 14 explains the velocity of an object's movement and the corresponding fluctuations in power value that appear in the Doppler signal, separately for the case where the object is a person and the case where the object is an object. Fig. 14 shows the velocity of the person's movement and the corresponding fluctuations in power value, and the velocity of the object's movement and the corresponding fluctuations in power value that appear in the time-series Doppler signal from when shaking occurs in the vehicle cabin and the object also moves until the shaking stops. Note that for convenience of explanation, Fig. 14 shows the fluctuations in power value for each of the person and the object separately, but in the Doppler signal, the power value based on the velocity of the person's movement and the power value based on the velocity of the object's movement are expressed together.

[0110] In Figure 14, the dotted line indicates the fluctuation in power value due to human movement, i.e., the fluctuation in power value corresponding to the speed of human movement when the object is a person, and the dashed-dotted line indicates the fluctuation in power value due to object movement, i.e., the fluctuation in power value corresponding to the speed of object movement when the object is an object. As shown in Figure 14, when the object is an object, a certain level of power value is detected immediately after the occurrence of shaking, but thereafter, the power value based on the speed of the object's (object's) movement, as seen in the Doppler signal, decreases overall. This is because the amount of shaking of the object attenuates over time. As the amplitude of the object's vibration decreases, the power value in the Doppler signal decreases. More specifically, in the time-series Doppler signal, the waveform of the power value attenuates overall over time. In the third embodiment, the phrase "the waveform of the power values ​​attenuates overall over time" means that the waveform of the power values ​​tends to attenuate overall over time. For example, even if there is a momentary increase in the power value corresponding to a certain speed on a certain Doppler signal compared to the power value corresponding to the same speed on the previous Doppler signal, if it can be said that the waveform of the power values ​​is attenuating overall, then it is considered that the waveform of the power values ​​tends to attenuate overall over time.

[0111] In contrast, when the object is a person, the power value based on the speed of the object's (person's) movement, which appears in the Doppler signal, fluctuates steadily with the passage of time after the occurrence of shaking, due to spontaneous and steady movements such as body movement or breathing, and the waveform of the power value does not generally decrease over time as it does when the object is an object. Note that, for convenience, Figure 14 does not show the minute fluctuations in the power value based on the person's body movement, breathing, etc.

[0112] In this way, it is possible to distinguish whether the object for which the power value is observed is a person or an object from the time-series fluctuation of the power value in the Doppler signal.

[0113] Furthermore, as shown in FIG. 14 , in the case of object sway, a characteristic peak, specifically a steep peak (indicated by a ▼ in FIG. 14 ) and its harmonics (components that are integer multiples of the fundamental wave), appear in the Doppler signal at a location corresponding to the period of the sway. FIG. 15 shows an example of a steep peak that appears in a Doppler signal in embodiment 3. In embodiment 3, a peak whose half-width is equal to or less than a predetermined value is defined as a steep peak. As shown in FIG. 14 , when the target object is an object, the power value at the speed where the steep peak appears decays over time. Note that a similar peak also appears when respiratory movement is observed, but because respiratory movement is a steady, continuous movement, the power value at the speed where the peak appears does not simply decay over time. In this way, when a steep peak appears in the Doppler signal, object sway can also be determined by tracking the power change at that location over time.

[0114] The radio wave sensor 2 generates the Doppler signal as described above and outputs it together with the distance profile to the condition monitoring device 1b. The condition monitoring device 1b according to the third embodiment uses the Doppler signal in addition to the distance profile acquired from the radio wave sensor 2 to determine whether the object detected by the radio wave sensor 2 is a living organism or a non-living organism.

[0115] An example configuration of a condition monitoring device 1b will be described. In Fig. 13, components similar to those of the condition monitoring device 1 described in embodiment 1 using Fig. 1 are denoted by the same reference numerals, and duplicated description will be omitted. The condition monitoring device 1b according to embodiment 3 differs from the condition monitoring device 1 according to embodiment 1 in that it includes a Doppler signal acquisition unit 14. Furthermore, in the condition monitoring device 1b according to embodiment 3, the specific operation of the living body determination unit 12b differs from the specific operation of the living body determination unit 12 in the condition monitoring device 1 according to embodiment 1.

[0116] The Doppler signal acquisition unit 14 acquires a Doppler signal from the radio wave sensor 2. The Doppler signal acquisition unit 14 outputs the acquired Doppler signal to the living body determination unit 12b.

[0117] The living body determination unit 12b performs object sway determination to determine whether the object is a living body or a non-living body based on the time-series distance profile acquired by the distance profile acquisition unit 11 and the time-series Doppler signals acquired by the Doppler signal acquisition unit 14. Note that the living body determination unit 12b stores the Doppler signals acquired from the Doppler signal acquisition unit 14 in a time-series manner in a storage unit, for example. For example, the Doppler signal acquisition unit 14 may store the Doppler signals acquired from the radio wave sensor 2 in a time-series manner in the storage unit. The living body determination unit 12b acquires the time-series Doppler signals from the storage unit.

[0118] The details of the object shaking determination by the living body determination unit 12b will be described with an example. For example, the living body determination unit 12b determines whether the object is a living body or a non-living body based on whether or not a power value corresponding to at least one distance in the time-series distance profile attenuates over time within the first determination period, and whether or not a power value corresponding to the speed of the object in the time-series Doppler signal during the first determination period satisfies a preset condition (hereinafter referred to as a "second shaking condition").

[0119] The second vibration condition is set to a condition such as the following second vibration condition (1) or second vibration condition (2). The second vibration condition is set in advance by, for example, an administrator or the like, and is stored in a location that can be referenced by the living body determination unit 12b, such as a buffer (not shown) of the living body determination unit 12b. Second vibration condition (1): In the time-series Doppler signal, the overall tendency of the power value corresponding to the speed of the object in the first determination period attenuates over time. Second vibration condition (2): In the time-series Doppler signal, peaks in the power value corresponding to the speed of the object in the first determination period appear periodically, and the power value of the peaks gradually decreases.

[0120] The living body determination unit 12b determines that the object is non-living if the power value corresponding to at least one distance in the time-series distance profile attenuates over time within the first determination period, or if the power value corresponding to the object's speed in the time-series Doppler signal satisfies the second fluctuation condition.On the other hand, the living body determination unit 12b determines that the object is non-living if the power value corresponding to at least one distance in the time-series distance profile does not simply attenuate over time within the first determination period, or if the power value corresponding to the object's speed in the time-series Doppler signal satisfies the second fluctuation condition.

[0121] In addition, the method used by the biometric determination unit 12b to determine whether a power value corresponding to at least one distance in a time-series distance profile is attenuating over time within the first determination period is the same as the method used by the biometric determination unit 12 to determine whether a power value corresponding to at least one distance in a time-series distance profile is attenuating over time within the first determination period, as described in embodiment 1, so duplicate explanations will be omitted.

[0122] As described above, in the third embodiment, the living body determination unit 12b determines whether an object is a living body or a non-living body based on the time-series distance profile and the time-series Doppler signal. As with the advantage of using frequency information, the living body determination unit 12b uses the Doppler signal in addition to the distance profile to determine whether an object detected by the radio wave sensor 2 is a living body or a non-living body, and this advantage is that, for relatively small objects, it is possible to more accurately determine whether the movement (vibration) of the object is due to bodily movement or respiratory movement by a person or movement due to the vibration of an object that is not supposed to move, i.e., object sway.

[0123] The configuration example of the abandonment alarm device 3 according to the third embodiment is the same as the configuration example of the abandonment alarm device 3 according to the first embodiment, so a duplicated description will be omitted. In the third embodiment, the abandonment detection unit 31 of the abandonment alarm device 3 may extract, for example, the speed of the target object from the Doppler signal. In this case, the living body determination unit 12b in the status monitoring device 1b outputs the Doppler signal together with the status determination result to the abandonment alarm device 3.

[0124] The operation of the state monitoring device 1b according to the third embodiment will now be described. Fig. 16 is a flowchart for describing the operation of the state monitoring device 1b according to the third embodiment. The trigger for starting the operation of the state monitoring device 1b may be the same as the trigger for starting the operation of the state monitoring device 1 according to the first embodiment, and therefore a duplicated description will be omitted. With regard to the processing shown in the flowchart of Fig. 16, processing whose specific content is the same as the processing already explained using the flowchart of Fig. 6 in the first embodiment will be assigned the same step numbers as in the flowchart of Fig. 6, and duplicated description will be omitted.

[0125] The Doppler signal acquisition unit 14 acquires a Doppler signal from the radio wave sensor 2 (step ST1b) and outputs the acquired Doppler signal to the living body determination unit 12b.

[0126] The living body determination unit 12b performs an object sway determination to determine whether the object is a living body or a non-living body based on the time-series distance profile acquired by the distance profile acquisition unit 11 in step ST1 and the time-series vibration frequency information acquired by the vibration frequency information acquisition unit 13 in step ST1b (step ST2b). The living body determination unit 12b outputs the state determination result to the abandonment alarm device 3.

[0127] FIG. 17 is a flowchart for explaining details of an example of the object shaking determination process by the living body determination unit 12b in step ST2b of FIG.

[0128] The living body determination unit 12b determines whether the power value corresponding to at least one distance in the time-series distance profile decays over time during the first determination period, or whether the power value corresponding to the object's velocity during the first determination period in the time-series Doppler signal satisfies the second fluctuation condition (step ST21b). If the power value corresponding to at least one distance in the time-series distance profile decays over time during the first determination period, or if the power value corresponding to the object's velocity during the first determination period in the time-series Doppler signal satisfies the second fluctuation condition ("YES" in step ST21b), the living body determination unit 12b determines that the object is non-living (step ST22). The living body determination unit 12b outputs the status determination result to the abandonment alarm device 3. On the other hand, in step ST21b, if the power value corresponding to at least one distance in the time-series distance profile does not simply attenuate, in other words, if the power value corresponding to at least one distance within the first determination period fluctuates, and the power value corresponding to the speed of the object during the first determination period in the time-series Doppler signal does not satisfy the second shaking condition (if "NO" in step ST21b), the living body determination unit 12b determines that the object is a living body (step ST23). The living body determination unit 12b outputs the status determination result to the abandonment alarm device 3.

[0129] In step ST21b, the biometric determination unit 12b may determine whether the gradient of the attenuation of the power value corresponding to at least one distance in the time-series distance profile satisfies the attenuation determination condition. In this case, if the gradient of the attenuation of the power value corresponding to at least one distance in the time-series distance profile satisfies the attenuation determination condition or if the power value corresponding to the velocity of the object during the first determination period in the time-series Doppler signal satisfies the second sway condition (if "YES" in step ST21b), the biometric determination unit 12b determines that the object is non-biological (step ST22) and outputs the status determination result to the abandonment alarm device 3. If the gradient of the attenuation of the power value corresponding to at least one distance does not satisfy the attenuation determination condition and if the power value corresponding to the velocity of the object during the first determination period in the time-series Doppler signal does not satisfy the second sway condition (if "NO" in step ST21b), the biometric determination unit 12b determines that the object is biometric (step ST23) and outputs the status determination result to the abandonment alarm device 3.

[0130] In the above description, in the operation shown in the flowchart of Fig. 16, the processing of step ST1 and the processing of step ST1b are performed in parallel, but this is merely an example. For example, the processing of step ST1b may be performed after the processing of step ST1, or the processing of step ST1 may be performed after the processing of step ST1b. It is sufficient that the processing of step ST1 and the processing of step ST1b are performed before the processing of step ST2b is performed.

[0131] The hardware configuration of the condition monitoring device 1b according to the third embodiment is the same as that shown in Figures 9A and 9B in the first embodiment, and is therefore not shown in the drawings. In the third embodiment, the functions of the distance profile acquisition unit 11, the Doppler signal acquisition unit 14, the living body determination unit 12b, and a control unit (not shown) are realized by a processing circuit 1001. That is, the condition monitoring device 1b includes the processing circuit 1001 for performing control to determine whether an object detected by the radio wave sensor 2 is living or non-living. The processing circuit 1001 may be dedicated hardware as shown in Figure 9A, or a processor 1004 that executes a program stored in memory as shown in Figure 9B.

[0132] The processing circuit 1001 reads and executes a program stored in the memory 1005, thereby performing the functions of the distance profile acquisition unit 11, the Doppler signal acquisition unit 14, the biometric determination unit 12b, and a control unit (not shown). That is, the status monitoring device 1b includes a memory 1005 for storing a program that, when executed by the processing circuit 1001, results in the execution of step ST1 and steps ST1b to ST2b of FIG. 16 . The program stored in the memory 1005 can also be said to cause a computer to execute the processing procedures or methods of the distance profile acquisition unit 11, the Doppler signal acquisition unit 14, the biometric determination unit 12b, and the control unit (not shown). The status monitoring device 1b includes an input interface device 1002 and an output interface device 1003 that perform wired or wireless communication with devices such as the radio wave sensor 2 or the abandonment alarm device 3.

[0133] In the third embodiment, the abandonment alarm device 3 includes the abandonment detection unit 31. However, this is merely an example. For example, the status monitoring device 1b may include the abandonment detection unit 31.

[0134] In the third embodiment, the condition monitoring device 1b is an in-vehicle device mounted on a vehicle, but this is merely an example. For example, the distance profile acquisition unit 11, the Doppler signal acquisition unit 14, the biometric determination unit 12b, and some or all of the control unit (not shown) may be provided in a server (not shown), and the in-vehicle device and the server may form a system.

[0135] In addition, in the third embodiment described above, the target area is the interior of a vehicle, but this is merely an example. The target area is not limited to the interior of a vehicle, and may be, for example, the interior of an airplane, the interior of a train, or any other interior of a moving object other than a vehicle. Furthermore, the target area is not limited to the interior of a moving object, and may be, for example, the interior of a room.

[0136] As described above, according to the third embodiment, the condition monitoring device 1b includes the distance profile acquisition unit 11 that acquires a distance profile, and the Doppler signal acquisition unit 14 that acquires a Doppler signal, which is information indicating movement in a target area, including movement due to shaking of each part of the object, based on the relationship between the object's speed and power value, generated based on the detection result of the object (target object) detected by the radio wave sensor 2, and the living body determination unit 12b is configured to determine whether the object is a living body or a non-living body, based on the time-series distance profile acquired by the distance profile acquisition unit 11 and the time-series Doppler signal acquired by the Doppler signal acquisition unit 14. Therefore, the condition monitoring device 1b can reduce erroneous determinations of whether an object in a target area detected by the radio wave sensor is a living body or a non-living body.

[0137] The configuration of the condition monitoring device 1 according to embodiment 1 may be applied to the configuration of the condition monitoring device 1a according to embodiment 2 and the configuration of the condition monitoring device 1b according to embodiment 3. That is, the condition monitoring device may determine whether the object detected by the radio wave sensor 2 is a living or non-living object based on the distance profile, frequency information, and Doppler signal.

[0138] Fig. 18 is a diagram showing an example configuration of a condition monitoring device 1c when determining whether an object detected by a radio wave sensor 2 is a living organism or a non-living organism based on a distance profile, frequency information, and Doppler signal. In the example configuration of the condition monitoring device 1c shown in Fig. 18, components similar to those of the condition monitoring devices 1, 1a, and 1b already explained using Fig. 1, Fig. 10, or Fig. 13 in the first to third embodiments are assigned the same reference numerals and redundant explanations will be omitted.

[0139] In the condition monitoring device 1c, the living body determination unit 12c determines whether the object is a living body or a non-living body based on the time-series distance profile acquired by the distance profile acquisition unit 11, the frequency information acquired by the frequency information acquisition unit 13, and the time-series Doppler signals acquired by the Doppler signal acquisition unit 14. In detail, the living body determination unit 12c determines that the object is a non-living body if, in the time-series distance profile acquired by the distance profile acquisition unit 11, a power value corresponding to at least one distance attenuates over time within a first determination period, if the frequency of the object during the first determination period based on the frequency information acquired by the frequency information acquisition unit 13 satisfies a first vibration condition, or if, in the time-series Doppler signals acquired by the Doppler signal acquisition unit 14, a power value corresponding to the speed of the object during the first determination period satisfies a second vibration condition. The living body determination unit 12c determines that the object is a living body if, in the time-series distance profile acquired by the distance profile acquisition unit 11, a power value corresponding to at least one distance does not simply attenuate over time within the first determination period, if the vibration frequency of the object during the first determination period based on the vibration frequency information acquired by the vibration frequency information acquisition unit 13 does not satisfy a first vibration condition, and if, in the time-series Doppler signals acquired by the Doppler signal acquisition unit 14, a power value corresponding to the object's velocity during the first determination period does not satisfy a second vibration condition. The living body determination unit 12c may determine that the object is a living body if, for example, the vibration frequency of the object during the first determination period is equal to or greater than a breathing determination threshold and then falls below the breathing determination threshold, or if the vibration frequency of the object during the first determination period is less than a breathing determination lower-limit threshold and then falls to or greater than the breathing determination lower-limit threshold, and if, in the time-series Doppler signals acquired by the Doppler signal acquisition unit 14, a power value corresponding to the object's velocity during the first determination period does not satisfy the second vibration condition.

[0140] 19 is a flowchart for explaining the operation of the condition monitoring device 1c when determining whether an object detected by the radio wave sensor 2 is a living organism or a non-living organism based on the distance profile, frequency information, and Doppler signal. The trigger for starting operation of the condition monitoring device 1c may be the same as the trigger for starting operation of the condition monitoring devices 1, 1a, and 1b according to embodiments 1 to 3, and therefore a duplicated explanation will be omitted.

[0141] Regarding the processing shown in the flowchart of Figure 19, processing that has the same specific content as the processing already explained in embodiment 1 using the flowchart of Figure 6, the processing already explained in embodiment 2 using the flowchart of Figure 11, or the processing already explained in embodiment 3 using the flowchart of Figure 16 will be assigned the same step numbers as in the flowchart of Figure 6, the flowchart of Figure 11, or the flowchart of Figure 16, and duplicate explanations will be omitted.

[0142] The living body determination unit 12c determines whether the object is a living body or a non-living body based on the time-series distance profile acquired by the distance profile acquisition unit 11 in step ST1, the frequency information acquired by the frequency information acquisition unit 13 in step ST1a, and the time-series Doppler signal acquired by the Doppler signal acquisition unit 14 in step ST1b (step ST2c).

[0143] FIG. 20 is a flowchart for explaining details of an example of the object shaking determination process by the living body determination unit 12c in step ST2c of FIG.

[0144] The living body determination unit 12c determines whether the power value corresponding to at least one distance in the time-series distance profile decays over time during the first determination period, whether the vibration frequency of the object during the first determination period based on the vibration frequency information satisfies a first vibration condition, or whether the power value corresponding to the object's velocity during the first determination period in the time-series Doppler signal satisfies a second vibration condition (step ST21c). In step ST21c, if the power value corresponding to at least one distance in the time-series distance profile decays over time during the first determination period, if the vibration frequency of the object during the first determination period based on the vibration frequency information satisfies the first vibration condition, or if the power value corresponding to the object's velocity during the first determination period in the time-series Doppler signal satisfies the second vibration condition ("YES" in step ST21c), the living body determination unit 12c determines that the object is non-living (step ST22). The living body determination unit 12c outputs the status determination result to the abandonment alarm device 3.

[0145] On the other hand, in step ST21a, if the time-series distance profile shows that the power value corresponding to at least one distance does not simply attenuate, in other words, the power value corresponding to at least one distance fluctuates within the first determination period, the vibration frequency of the object during the first determination period based on the vibration frequency information does not satisfy the first vibration condition, and the time-series Doppler signal shows that the power value corresponding to the object's speed during the first determination period does not satisfy the second vibration condition ("NO" in step ST21c), the living body determination unit 12c determines that the object is a living body (step ST23). The living body determination unit 12c outputs the status determination result to the abandonment alarm device 3. In step ST21c, the living body determination unit 12c may determine that the object is a living body, for example, if the vibration frequency of the object during the first determination period is equal to or greater than the breathing determination threshold and then becomes less than the breathing determination threshold, or if the vibration frequency of the object during the first determination period is less than the breathing determination lower limit threshold and then becomes equal to or greater than the breathing determination lower limit threshold, and if the power value corresponding to the speed of the object during the first determination period in the time-series Doppler signal acquired by the Doppler signal acquisition unit 14 does not satisfy the second shaking condition.

[0146] As described above, even if the condition monitoring device 1c is configured to include a distance profile acquisition unit 11, a frequency information acquisition unit 13, and a Doppler signal acquisition unit 14, and the living body determination unit 12c determines whether an object is living or non-living based on the time-series distance profile acquired by the distance profile acquisition unit 11, the frequency information acquired by the frequency information acquisition unit 13, and the time-series Doppler signal acquired by the Doppler signal acquisition unit 14, the condition monitoring device 1c can reduce erroneous determinations of whether an object in the target area detected by the radio wave sensor is living or non-living.

[0147] Furthermore, in the above-described first to third embodiments, the status monitoring devices 1, 1a, 1b, and 1c are configured to output the biometric determination results to the abandonment alarm device 3, but the output destination of the biometric determination results by the status monitoring devices 1, 1a, 1b, and 1c is not limited to the abandonment alarm device 3. For example, as shown in FIG. 21 , the status monitoring device 1 may be connected to an intrusion alarm device 4 and a seat control device 5 in addition to the abandonment alarm device 3, and the biometric determination results may be output to the intrusion alarm device 4 and the seat control device 5 in addition to the abandonment alarm device 3. As shown in FIG. 21 , the intrusion alarm device 4 includes, for example, an intrusion detection unit 41 and an output control unit 42. The seat control device 5 includes, for example, a seating position detection unit 51 and an output control unit 52.

[0148] In the intrusion alarm device 4, the intrusion detection unit 41 detects whether or not an intrusion has occurred into the target area based on the living body determination result and sensor information output from the status monitoring device 1. When the status monitoring device 1 determines that a living body is present in the target area, the intrusion detection unit 41 detects whether or not an intrusion has occurred into the target area based on the sensor information. The intrusion detection unit 41 may detect whether or not an intrusion has occurred into the target area using a known intrusion detection technology based on the object detection result by the radio wave sensor 2. For example, when the intrusion detection unit 41 detects that an intrusion has occurred into the target area, the output control unit 52 controls the output device to output an alarm.

[0149] In the seat control device 5, the seating position detection unit 51 detects the seating position of a person in the target area based on the living body determination result and sensor information output from the status monitoring device 1. When the status monitoring device 1 determines that a living body is present in the target area, the seating position detection unit 51 detects the seating position of the person in the target area based on the sensor information. The seating position detection unit 51 may detect the seating position of the person in the target area using a known seating position detection technology based on the object detection result by the radio wave sensor 2. The output control unit 52 controls the seat belt, for example, based on the seating position of the person in the target area detected by the seating position detection unit 51. Specifically, the output control unit 52 outputs control information for controlling the seat belt to a seat belt sensor (not shown).

[0150] When detecting whether or not a person has entered the target area or when detecting a seating position in the target area, if a shaking factor occurs, such as the recoil of a door closing or the influence of wind, a non-living object may sway within the target area, potentially resulting in the object shaking being mistakenly detected as the movement of a living body. As a result, for example, a false alarm may occur. The intrusion alarm device 4 and the seat control device 5 perform intrusion detection processing or seating position detection processing when a living body is determined to be present within the target area based on the living body determination result output from the status monitoring device 1, 1a, 1b, or 1c, thereby reducing the false detection of object shaking as the movement of a living body, as described above. For example, in the field of intrusion detection, reducing over-alarms is an important factor from the perspective of usability. In the first to third embodiments, the abandoned object detection unit 31 detects whether or not a person has entered the target area when the status monitoring device 1, 1a, 1b, or 1c determines that a living body is present within the target area, thereby allowing the status monitoring device 1, 1a, 1b, or 1c to contribute to reducing over-alarms. Furthermore, when the intrusion warning device 4 and the seat control device 5 determine that a living body is present within the target area based on the living body determination result output from the status monitoring device 1, 1a, 1b, 1c, they detect the seating position and perform seat belt control processing, thereby allowing the status monitoring device 1, 1a, 1b, 1c to contribute to reducing unnecessary seat belt control.

[0151] 22 is a flowchart illustrating an example of the operation of the intrusion alarm device 4. When the status monitoring device 1 determines that a living organism is present in the target area ("YES" in step ST41), the intrusion detection unit 41 detects whether an intrusion into the target area has occurred (step ST42). The intrusion detection unit 41 outputs the detection result indicating whether an intrusion into the target area has occurred to the output control unit 42, and the output control unit 42 controls the output of an alarm to the output device (step ST43). When the status monitoring device 1 determines that a living organism is not present in the target area ("NO" in step ST41), the intrusion alarm device 4 ends the operation shown in the flowchart of FIG. 22.

[0152] 23 is a flowchart illustrating an example of the operation of the seat control device 5. When the state monitoring device 1 determines that a living body is present in the target area ("YES" in step ST51), the seating position detection unit 51 detects the seating position of the person in the target area (step ST52). The seating position detection unit 51 outputs the detection result of the seating position of the person in the target area to the output control unit 52, and the output control unit 52 outputs control information for controlling the seat belt (step ST53). When the state monitoring device 1 determines that a living body is not present in the vehicle cabin ("NO" in step ST51), the seat control device 5 ends the operation shown in the flowchart of FIG. 23.

[0153] 21 illustrates a configuration example in which the abandonment alarm device 3, the intrusion alarm device 4, and the seat control device 5 are connected to the status monitoring device 1 according to the first embodiment, but this is merely an example. In FIG. 21 , the configuration example of the status monitoring device 1 may be the configuration example of the status monitoring device 1a according to the second embodiment (see FIG. 10 ), the configuration example of the status monitoring device 1b according to the third embodiment (see FIG. 13 ), or the configuration example of the status monitoring device 1c shown in FIG. 18 . Also, in the configuration example shown in FIG. 21 , the abandonment alarm device 3, the intrusion alarm device 4, and the seat control device 5 are connected to the status monitoring device 1, but this is merely an example. For example, the status monitoring device 1 may be connected to any one or two of the abandonment alarm device 3, the intrusion alarm device 4, and the seat control device 5.

[0154] The hardware configurations of the intrusion alarm device 4 and the seat control device 5 are similar to those shown in Figures 9A and 9B and are therefore not shown. In the intrusion alarm device 4, the functions of the intrusion detection unit 41 and the output control unit 42 are realized by a processing circuit 1001. That is, the intrusion alarm device 4 includes a processing circuit 1001 for detecting an intrusion into a target area and controlling the output of an alarm. In the seat control device 5, the functions of the seating position detection unit 51 and the output control unit 52 are realized by the processing circuit 1001. That is, the seat control device 5 includes a processing circuit 1001 for detecting a person's seating position in the target area and controlling the seat belt. The processing circuit 1001 may be dedicated hardware as shown in Figure 9A, or a processor 1004 that executes a program stored in a memory 1005 as shown in Figure 9B.

[0155] In the intrusion alarm device 4, the processing circuit 1001 reads out and executes a program stored in the memory 1005, thereby performing the functions of the intrusion detection unit 41 and the output control unit 42. That is, the intrusion alarm device 4 includes the memory 1005 for storing a program that, when executed by the processing circuit 1001, results in the execution of steps ST41 to ST43 of FIG. 22 described above. It can also be said that the program stored in the memory 1005 causes a computer to execute the processing procedures or methods of the intrusion detection unit 41 and the output control unit 42. In the seat control device 5, the processing circuit 1001 reads out and executes a program stored in the memory 1005, thereby performing the functions of the seating position detection unit 51 and the output control unit 52. That is, the seat control device 5 includes the memory 1005 for storing a program that, when executed by the processing circuit 1001, results in the execution of steps ST51 to ST53 of FIG. 23 described above. In addition, it can be said that the program stored in the memory 1005 causes the computer to execute the processing procedures or methods of the seating position detection unit 51 and the output control unit 52.

[0156] In the above first to third embodiments, the condition monitoring devices 1, 1a, and 1b may have the function of acquiring sensor information including a digital signal from the radio wave sensor 2 and generating a distance profile. Also, in the above second embodiment, the condition monitoring device 1a may have the function of acquiring sensor information including a digital signal from the radio wave sensor 2 and generating frequency information. Also, in the above third embodiment, the condition monitoring device 1b may have the function of acquiring sensor information including a digital signal from the radio wave sensor 2 and generating a Doppler signal.

[0157] Furthermore, in the above-described first to third embodiments, the state monitoring devices 1, 1a, and 1b can determine whether a living object is present among multiple objects in a target area by determining whether the movements of the multiple objects include living body movements. Even when the multiple objects include both living and non-living objects, the state monitoring devices 1, 1a, and 1b can determine whether a living object is present among the multiple objects. For example, when an infant or the like is awake and moving its arms or legs, it is assumed that the body movements of the infant or the like are greater than the movements caused by the swaying of objects. In this case, the state monitoring devices 1, 1a, and 1b can determine, using the method described in the above-described first to third embodiments, that the power value of the reflected wave corresponding to at least one distance in the time-series distance profile rises and falls, i.e., increases and attenuates, within the first determination period, and can determine that the target object is a living object. For example, when an infant or the like is asleep and only the chest and abdomen are moving, the movements caused by the swaying of objects may be greater than the movements of the infant or the like. However, even in this case, after a certain period of time has passed, the movement caused by the shaking of the object will attenuate and eventually stop. For example, if an administrator or the like sets the first determination period to a length that is expected to be long enough for the shaking of the object to subside even if the shaking occurs, the status monitoring device 1, 1a, 1b can determine that the target object contains a living organism even in such a situation.

[0158] It should be noted that the embodiments may be freely combined, or any of the components in each embodiment may be modified, or any of the components in each embodiment may be omitted.

[0159] The condition monitoring device according to the present disclosure reduces erroneous determinations as to whether an object in a target area detected by a radio wave sensor is a living or non-living object.

[0160] 1, 1a, 1b, 1c Status monitoring device, 11 Distance profile acquisition unit, 12, 12a, 12b, 12c Biometric determination unit, 13 Vibration frequency information acquisition unit, 14 Doppler signal acquisition unit, 2 Radio wave sensor, 3 Abandonment alarm device, 31 Abandonment detection unit, 32 Output control unit, 4 Intrusion alarm device, 41 Intrusion detection unit, 42 Output control unit, 5 Seat control device, 51 Seating position detection unit, 52 Output control unit, 1001 Processing circuit, 1002 Input interface device, 1003 Output interface device, 1004 Processor, 1005 Memory.

Claims

1. a distance profile acquisition unit that acquires a distance profile, which is information indicating a movement in a target area, including a movement due to a sway of each part of the object, based on a relationship between a distance from the radio wave sensor to the object and a power value corresponding to the distance, generated based on a detection result of the object detected by the radio wave sensor, the distance profile being information indicating a movement in the target area, including a movement due to a sway of each part of the object; a liveness determining unit that determines whether the object is a live body or a non-live body based on the time-series distance profile acquired by the distance profile acquiring unit; A condition monitoring device comprising:

2. The biometric determination unit is When the power value corresponding to at least one of the distances in the time-series distance profile acquired by the distance profile acquisition unit attenuates over time within a first determination period, the object is determined to be the non-living body.

2. The condition monitoring device according to claim 1.

3. The biometric determination unit is When a gradient of attenuation of the power value corresponding to at least one of the distances in the time-series distance profile acquired by the distance profile acquisition unit satisfies an attenuation determination condition, the object is determined to be the non-living body.

3. The condition monitoring device according to claim 2.

4. The biometric determination unit is When a gradient of attenuation of the power value corresponding to at least one of the distances in the distance profiles adjacent in time series is equal to or less than a gradient determination threshold, it is determined that the attenuation determination condition is satisfied.

4. The condition monitoring device according to claim 3.

5. The biometric determination unit is When a gradient of attenuation of the power value corresponding to at least one of the distances in a plurality of distance profiles spaced apart by a gradient judgment interval is equal to or less than a gradient judgment threshold, it is determined that the attenuation judgment condition is satisfied.

4. The condition monitoring device according to claim 3.

6. The biometric determination unit is When the power value corresponding to at least one of the distances in the time-series distance profile acquired by the distance profile acquisition unit fluctuates within a first determination period, the object is determined to be the living body.

6. The condition monitoring device according to claim 1, wherein the first and second electrodes are connected to the first and second electrodes.

7. a frequency information acquisition unit that acquires frequency information related to a frequency of the object, the frequency information being generated based on a detection result of the object detected by the radio wave sensor; The living body determination unit determines whether the object is a living body or a non-living body based on the time-series distance profile acquired by the distance profile acquisition unit and the vibration frequency information acquired by the vibration frequency information acquisition unit.

2. The condition monitoring device according to claim 1.

8. The biometric determination unit is When the power value corresponding to at least one of the distances in the time-series distance profile acquired by the distance profile acquisition unit attenuates over time within a first determination period, or when the vibration frequency of the object during the first determination period based on the vibration frequency information acquired by the vibration frequency information acquisition unit satisfies a first vibration condition, the object is determined to be the non-living body.

8. The condition monitoring device according to claim 7.

9. The biometric determination unit is When the vibration frequency of the object during the first determination period is equal to or greater than a breathing determination threshold, or when the vibration frequency of the object during the first determination period is less than a breathing determination lower limit threshold, it is determined that the first shaking condition is satisfied.

9. The condition monitoring device according to claim 8.

10. a Doppler signal acquisition unit that acquires a Doppler signal, which is information indicating a movement in the target area including a movement due to a sway of each part of the object, based on a relationship between a speed of the object and the power value, the Doppler signal being generated based on a detection result of the object detected by the radio wave sensor; The living body determination unit determines whether the object is a living body or a non-living body based on the time-series distance profile acquired by the distance profile acquisition unit and the time-series Doppler signal acquired by the Doppler signal acquisition unit.

2. The condition monitoring device according to claim 1.

11. The biometric determination unit is If the power value corresponding to at least one of the distances in the time-series distance profile acquired by the distance profile acquisition unit attenuates over time within a first determination period, or if the power value corresponding to the velocity of the object in the first determination period in the time-series Doppler signal acquired by the Doppler signal acquisition unit satisfies a second shaking condition, the object is determined to be the non-living object.

11. The condition monitoring device according to claim 10.

12. The biometric determination unit is When the power value corresponding to the velocity of the object during the first determination period attenuates over time in the time-series Doppler signal, it is determined that the second shaking condition is satisfied.

12. The condition monitoring device according to claim 11.

13. The biometric determination unit is When a peak in the power value corresponding to the velocity of the object during the first determination period appears periodically in the time series of the Doppler signal and the power value of the peak gradually decreases, it is determined that the second shaking condition is satisfied.

12. The condition monitoring device according to claim 11.

14. a frequency information acquisition unit that acquires frequency information regarding a frequency of the object, the frequency information being generated based on a detection result of the object detected by the radio wave sensor; a Doppler signal acquisition unit that acquires a Doppler signal, which is information indicating a movement in the target area including a movement due to a sway of each part of the object, based on a relationship between the speed of the object and the power value, generated based on a detection result of the object detected by the radio wave sensor; The living body determination unit determines whether the object is a living body or a non-living body based on the time-series distance profile acquired by the distance profile acquisition unit, the vibration frequency information acquired by the vibration frequency information acquisition unit, and the time-series Doppler signal acquired by the Doppler signal acquisition unit.

2. The condition monitoring device according to claim 1.

15. The biometric determination unit is If, in the time-series distance profile acquired by the distance profile acquisition unit, the power value corresponding to at least one of the distances attenuates over time within a first determination period, if the vibration frequency of the object in the first determination period based on the vibration frequency information acquired by the vibration frequency information acquisition unit satisfies a first vibration condition, or if, in the time-series Doppler signal acquired by the Doppler signal acquisition unit, the power value corresponding to the speed of the object in the first determination period satisfies a second vibration condition, the object is determined to be a non-living body.

15. The condition monitoring device according to claim 14.

16. The biometric determination unit is The radio wave sensor controls the interval at which the radio wave is emitted.

15. The condition monitoring device according to claim 7 or 14.

17. and an abandonment detection unit that detects whether a person requiring assistance has been abandoned in the target area based on a result of the determination by the living body determination unit as to whether the object is the living body or the non-living body and on sensor information regarding the object detected by the radio wave sensor.

15. The condition monitoring device according to claim 1, 7, 10, or 14.

18. and an intrusion detection unit that detects whether an intrusion into the target area has occurred based on a result of the determination by the living body determination unit as to whether the object is the living body or the non-living body and on sensor information regarding the object detected by the radio wave sensor.

15. The condition monitoring device according to claim 1, 7, 10, or 14.

19. and a seating position detection unit that detects a seating position of a person in the target area based on a result of the determination by the biometric determination unit as to whether the object is the biometric or non-bimetric object and on sensor information related to the object detected by the radio wave sensor.

15. The condition monitoring device according to claim 1, 7, 10, or 14.

20. A distance profile acquisition unit acquires a distance profile, which is information indicating movements in the target area, including movements due to shaking of each part of the object, based on a relationship between a distance from the radio wave sensor to the object and a power value corresponding to the distance, generated based on a detection result of the object detected by a radio wave sensor that detects an object that is moving based on a reflected wave of radio waves emitted toward the target area and reflected by the object in the target area; a step in which a living body determination unit determines whether the object is a living body or a non-living body based on the time-series distance profile acquired by the distance profile acquisition unit; A condition monitoring method comprising: