Seating detection device, seating detection method, and program recording medium

Abstract

A seated person detection device (10) includes: one or more receivers (12) disposed in a space having a plurality of seats to receive sound occurring in or outside the space; a sound characteristic analysis section (13) configured to calculate a time characteristic or a frequency characteristic of the sound in the space based on signals received by the one or more receivers (12); and a detection section (14) configured to detect the presence or absence of a person in the space or the presence or absence of a seated person based on the time characteristic or the frequency characteristic calculated by the sound characteristic analysis section (13) and output a detection result.

Description

Technical Field

[0001] This disclosure relates to the technology of the presence or absence of testing personnel or their seating. Background Technology

[0002] Previously, techniques for detecting the presence or absence of personnel or their seating arrangements were known (for example, see Patent Documents 1-4).

[0003] Existing technical documents

[0004] Patent documents

[0005] Patent Document 1: Japanese Patent Application Publication No. 2006-69454

[0006] Patent Document 2: Japanese Patent Application Publication No. 11-151970

[0007] Patent Document 3: Japanese Patent Application Publication No. 2000-16233

[0008] Patent Document 4: Japanese Patent Application Publication No. 2019-138671 Summary of the Invention

[0009] The problem that the invention aims to solve

[0010] The technologies described in Patent Documents 1 and 2 suffer from the problem of needing to embed sensors in each seat to be detected. Furthermore, the technology described in Patent Document 3 suffers from the problem that only one seat can be detected using a single set of sensors. Additionally, the technology described in Patent Document 4 suffers from a high memory load due to the need for image processing using a camera.

[0011] Therefore, this disclosure is made in view of the above-mentioned problems, and the object is to provide a seating detection device that can detect the presence or absence of people in two or more seats by a single set of sensors without embedding sensors in each seat as the detection object, and without requiring image processing using a camera.

[0012] Methods used to solve problems

[0013] A seating detection device according to a technical solution disclosed herein includes: one or more receivers disposed in a space having multiple seats to receive sound generated in or outside the space; a sound characteristic analysis unit that calculates the time characteristics or frequency characteristics of the sound in the space based on the signals received by the one or more receivers; and a detection unit that detects the presence or absence of persons in the space or the presence or absence of persons seated based on the time characteristics or frequency characteristics calculated by the sound characteristic analysis unit, and outputs the detection result.

[0014] The seating detection method disclosed herein is a seating detection method performed by a seating detection device comprising one transmitter, one or more receivers, a sound characteristic analysis unit, and a detection unit. The transmitter sequentially transmits a predetermined sound into a space; the one or more receivers sequentially receive reflected waves of the predetermined sound transmitted by the transmitter; the sound characteristic analysis unit sequentially calculates the time or frequency characteristics of the sound inside the vehicle interior space based on the predetermined sound, according to at least one of the transmitted signal and one or more received signals. The transmitted signal represents the sound transmitted by the transmitter. The waveform of the specified sound transmitted by the transmitter, and one or more received signals respectively represent the waveform of the reflected wave of the specified sound received by the one or more receivers; the detection unit detects the presence or absence of a person in the space based on the time characteristic or frequency characteristic of the sound in the vehicle interior space based on the specified sound transmitted by the transmitter at the first time interval, calculated by the sound characteristic analysis unit, and the difference between the time characteristic or frequency characteristic of the sound in the vehicle interior space based on the specified sound transmitted by the transmitter at the second time interval, calculated by the sound characteristic analysis unit, and outputs the detection result.

[0015] A program recording medium related to a technical solution disclosed herein records a program for causing a seating detection device comprising one transmitter, one or more receivers, a sound characteristic analysis unit, and a detection unit to perform a seating detection process. The seating detection process includes the following steps: the transmitter sequentially transmits a predetermined sound into a space; the one or more receivers sequentially receive reflected waves of the predetermined sound transmitted by the transmitter; and the sound characteristic analysis unit sequentially calculates, based on at least one of the transmitted signal and one or more received signals, the time or frequency characteristics of the sound in the vehicle's interior space according to the predetermined sound. The symbol represents the waveform of the specified sound transmitted by the aforementioned transmitter, and the aforementioned one or more received signals represent the waveforms of the reflected waves of the specified sound received by the aforementioned one or more receivers; the detection unit detects the presence or absence of persons in the space based on the time or frequency characteristics of the sound in the vehicle interior space calculated by the sound characteristic analysis unit based on the specified sound transmitted by the aforementioned transmitter at the first time interval, and the difference between the time or frequency characteristics of the sound in the vehicle interior space calculated by the sound characteristic analysis unit based on the specified sound transmitted by the aforementioned transmitter at the second time interval, and outputs the detection result.

[0016] Invention Effects

[0017] According to the seating detection device, seating detection method and procedure recording medium disclosed herein, a seating detection device is provided that can detect the presence or absence of people in two or more seats by a single set of sensors without embedding sensors in each seat as the detection object, and without requiring image processing using a camera. Attached Figure Description

[0018] Figure 1 This is a block diagram showing the structure of the seating detection device according to Embodiment 1.

[0019] Figure 2 This is a schematic plan view showing the seating detection device of Embodiment 1 installed inside the vehicle.

[0020] Figure 3 This is a waveform diagram showing an example of the transmission signal in Implementation 1.

[0021] Figure 4 This is a waveform diagram showing an example of the impulse response generated by the acoustic characteristic analysis unit in Embodiment 1.

[0022] Figure 5 This is a block diagram showing the structure of the detection unit in Embodiment 1.

[0023] Figure 6 This is a flowchart of the first seating detection process in Implementation Method 1.

[0024] Figure 7 This is a block diagram showing the structure of the seating detection device according to Embodiment 2.

[0025] Figure 8 This is a block diagram showing the structure of the seating detection device according to Embodiment 3.

[0026] Figure 9 This is a block diagram showing the structure of the seating detection device according to Embodiment 4.

[0027] Figure 10 This is a schematic plan view of a vehicle equipped with the seating detection device according to Embodiment 4.

[0028] Figure 11 This is a schematic diagram illustrating an example of the correspondence between the learning model of implementation method 4, the teacher data used in its training, the conditions satisfied by the teacher data, and the correct answer label assigned to the teacher data.

[0029] Figure 12 This is a flowchart of the second seating detection process in Implementation Method 4. Detailed Implementation

[0030] (The process of obtaining the technical solution disclosed herein)

[0031] Through research on a seating detection device for detecting the presence or absence of people in a space with multiple seats, the inventors have realized that when using an ultrasonic transmitter and receiver installed in the space to sequentially calculate the ultrasonic pulse response within the space, differences occur in the calculated pulse responses when human movement is present. More specifically, the inventors have realized that even if human movement occurs between a first timing and a second timing, such as a relatively small movement accompanied by breathing, a difference exists between the first pulse response based on the prescribed ultrasonic wave transmitted by the transmitter at the first timing and the second pulse response based on the prescribed ultrasonic wave transmitted by the transmitter at the second timing. Furthermore, based on the above realization, the inventors have repeatedly conducted research and obtained the following seating detection device, which can detect the presence or absence of people in two or more seats using a single set of sensors without embedding sensors in each seat, and without requiring image processing using a camera.

[0032] A seating detection device according to a technical solution of this disclosure includes: one or more receivers disposed in a space having multiple seats to receive sound occurring in or outside the space; a sound characteristic analysis unit that calculates the time characteristics or frequency characteristics of the sound in the space based on the signals received by the one or more receivers; and a detection unit that detects the presence or absence of a person in the space or the presence or absence of a seat based on the time characteristics or frequency characteristics calculated by the sound characteristic analysis unit, and outputs the detection result.

[0033] In the aforementioned seating detection device, the temporal or frequency characteristics of sound within a space with multiple seats reflect the presence or absence of people in the space, or whether they are seated.

[0034] Therefore, according to the above-mentioned seating detection device, a seating detection device can be provided that can detect the presence or absence of people in two or more seats by a single set of sensors without embedding sensors in each seat as the detection object, and without requiring image processing using a camera.

[0035] Alternatively, it may also include a transmitter that transmits a specified sound into the space; one or more receivers that receive the reflected waves of the specified sound; the sound characteristic analysis unit that calculates the time characteristic or frequency characteristic of the specified sound based on the signal of the specified sound and the signal received by the one or more receivers; and the detection unit that detects the presence or absence of the person or the presence or absence of the seated person based on the difference between the time characteristic or frequency characteristic of the specified sound transmitted by the transmitter at a first time interval calculated by the sound characteristic analysis unit and the time characteristic or frequency characteristic of the specified sound transmitted by the transmitter at a second time interval calculated by the sound characteristic analysis unit.

[0036] In the aforementioned seating detection device, if there is human movement between the first timing and the second timing, even if the movement is a relatively small movement such as the movement of a person accompanied by breathing, a difference will occur between the time characteristics or frequency characteristics calculated by the sound characteristic analysis unit corresponding to the first timing and the time characteristics or frequency characteristics corresponding to the second timing.

[0037] Therefore, the aforementioned seating detection device can more accurately detect the presence or absence of people or whether they are seated.

[0038] Alternatively, the sound transmitted by the aforementioned transmitter could be ultrasonic.

[0039] This can suppress the discomfort that may be caused to people in the space by sound transmitted from a single transmitter.

[0040] Alternatively, the aforementioned transmitter could be located in a position capable of transmitting sound to all seats within the aforementioned space.

[0041] Therefore, it is possible to detect the presence or absence of people or whether they are seated by considering all seats within the space.

[0042] Alternatively, the space may be the interior space of a vehicle; at least one of the transmitters and receivers may be located off-center from the centerline extending in the direction of travel of the vehicle; and the transmitter may not be located in a position symmetrical about the centerline with respect to at least one of the receivers.

[0043] Therefore, in at least one receiver, the timing of receiving the reflected wave from a person seated in one of the two seats, which are located in a position symmetrical about the center line, can be made different from the timing of receiving the reflected wave from a person seated in the other seat. Thus, it is possible to detect the presence or absence of a person seated in one of the two seats separately from the other. Particularly in the case of a vehicle, where the seating arrangement is symmetrical, it is possible to detect the presence or absence of a person in all seats.

[0044] Alternatively, the space described above could be a vehicle; the transmitter and the more than one receiver could be located within the overhead console of the vehicle.

[0045] Therefore, the seating detection device is positioned so that it can have a clear view of all the seats, thus enabling more effective detection of whether people are present or seated.

[0046] Alternatively, the aforementioned one or more receivers may be multiple receivers; the aforementioned sound characteristic analysis unit calculates the aforementioned time characteristics or the aforementioned frequency characteristics by performing directional control, and the aforementioned directional control uses at least two of a plurality of received signals representing the waveforms of the aforementioned reflected waves received by the aforementioned multiple receivers.

[0047] Therefore, for multiple seats, the location of these seats can be distinguished to detect the presence or absence of a person or whether they are seated.

[0048] Alternatively, if a difference of a predetermined value or more occurs between the time characteristic or frequency characteristic of the prescribed sound transmitted by the transmitter at the first timing calculated by the sound characteristic analysis unit and the time characteristic or frequency characteristic of the prescribed sound transmitted by the transmitter at the second timing, the detection unit may calculate the seating position based on the position of the time characteristic or frequency characteristic on the time axis where the difference occurs.

[0049] Therefore, it is possible to detect the seat position.

[0050] Alternatively, the aforementioned transmitter and at least one of the aforementioned receivers may be a speaker and a microphone used in the vehicle emergency notification system.

[0051] This allows for the reduction of the number of speakers and microphones installed in a vehicle.

[0052] Alternatively, the aforementioned detection department may use the communication device used in the vehicle emergency notification system to send the detected information regarding the presence or absence of seats in the aforementioned space to the emergency notification center linked to the vehicle emergency notification system.

[0053] Therefore, in the event of an emergency such as a traffic accident, information regarding the availability of seats can be sent to the emergency notification center, enabling effective emergency rescue and life-saving activities.

[0054] A seating detection method according to the present disclosure is a seating detection device comprising one transmitter, one or more receivers, an acoustic characteristic analysis unit, and a detection unit. The transmitter sequentially transmits a predetermined sound into a space; the receivers sequentially receive reflected waves of the predetermined sound transmitted by the transmitter; the acoustic characteristic analysis unit sequentially calculates the time or frequency characteristics of the sound in the vehicle's interior space based on the predetermined sound, using at least one of a transmission signal representing the waveform of the predetermined sound transmitted by the transmitter and at least one reception signal representing the waveform of the reflected waves of the predetermined sound received by the receivers; the detection unit detects the presence or absence of a person in the space, or whether a person is seated, based on the difference between the time or frequency characteristics of the sound in the vehicle's interior space calculated by the acoustic characteristic analysis unit based on the predetermined sound transmitted by the transmitter at a first time interval and the time or frequency characteristics of the sound in the vehicle's interior space calculated by the acoustic characteristic analysis unit based on the predetermined sound transmitted by the transmitter at a second time interval, and outputs a detection result.

[0055] In the seating detection device that performs the above-mentioned seating detection method, the temporal or frequency characteristics of sound in a space with multiple seats reflect the presence or absence of people in the space or whether they are seated.

[0056] Therefore, based on the above-described seating detection method, a seating detection device can be provided that can detect the presence or absence of people in two or more seats by a single set of sensors without embedding sensors in each seat, and without requiring image processing using a camera.

[0057] A program recording medium relating to a technical solution of this disclosure records a program for causing a seating detection device, comprising one transmitter, one or more receivers, an acoustic characteristic analysis unit, and a detection unit, to perform a seating detection process. The seating detection process includes the following steps: the transmitter sequentially transmits a predetermined sound into space; the one or more receivers sequentially receive reflected waves of the predetermined sound transmitted by the transmitter; and the acoustic characteristic analysis unit transmits a signal representing the waveform of the predetermined sound transmitted by the transmitter, and signals representing the predetermined sound received by the one or more receivers. At least one of the received signals of the waveform of the reflected wave is used to sequentially calculate the time characteristic or frequency characteristic of the sound in the vehicle interior space based on the specified sound; the detection unit detects the presence or absence of a person in the space or whether a person is seated based on the difference between the time characteristic or frequency characteristic of the sound in the vehicle interior space calculated by the sound characteristic analysis unit based on the specified sound transmitted by the transmitter at the first time interval and the time characteristic or frequency characteristic of the sound in the vehicle interior space calculated by the sound characteristic analysis unit based on the specified sound transmitted by the transmitter at the second time interval, and outputs the detection result.

[0058] In a seating detection device that performs seating detection processing through a recording medium as described above, the temporal or frequency characteristics of sound within a space with multiple seats reflect the presence or absence of people in the space, or whether they are seated.

[0059] Therefore, based on the above-mentioned recording medium, a seating detection device can be provided that can detect the presence or absence of people in two or more seats by a single set of sensors without embedding sensors in each seat as the detection object, and without requiring image processing using a camera.

[0060] The following is a reference to the appendix. Figure 1 Specific examples of a seating detection device relating to a technical solution of this disclosure will be described below. The embodiments shown herein are all specific examples of this disclosure. The numerical values, shapes, constituent elements, arrangements and connection patterns of constituent elements, as well as steps (processes) and their order shown in the following embodiments are examples and are not intended to limit this disclosure. Furthermore, the figures are schematic diagrams and are not necessarily rigorous illustrations.

[0061] Furthermore, the inclusive or specific technical solutions disclosed herein can also be implemented by systems, methods, integrated circuits, computer programs, or computer-readable CD-ROMs and other recording media, or by any combination of systems, methods, integrated circuits, computer programs, and recording media.

[0062] (Implementation Method 1)

[0063] The following is a reference to the appendix. Figure 1 The seating detection device according to Embodiment 1 will be described below. This seating detection device is installed in a space with multiple seats to detect the presence or absence of people in the space, or whether they are seated. Spaces with multiple seats include, for example, passenger vehicles, multi-passenger vehicles, buses, trains, airplanes, and indoor spaces. In this embodiment, as an example, it is assumed that the space with multiple seats is a passenger vehicle. However, spaces with multiple seats are not limited to passenger vehicles.

[0064] <Structure>

[0065] Figure 1 This is a block diagram showing the structure of the seating detection device 10 according to Embodiment 1.

[0066] like Figure 1 As shown, the seating detection device 10 includes a transmitter 11, a receiver 12, an acoustic characteristic analysis unit 13, a detection unit 14, an amplifier 15, an amplifier 16, an ADC 17 (ADC: Analog to Digital Converter), a DAC 18 (DAC: Digital to Analog Converter), and a transmission signal generation unit 19.

[0067] When an electrical signal is input, the transmitter 11 converts the input electrical signal into sound and transmits the converted sound into the vehicle equipped with the seating detection device 10. In Embodiment 1, the following description assumes that the sound converted by the transmitter 11, i.e., the sound transmitted by the transmitter 11, is ultrasonic, but the sound transmitted by the transmitter is not necessarily limited to ultrasonic waves. The transmitter 11 is implemented, for example, by a loudspeaker. Furthermore, the transmitter 11 may also be implemented, for example, by a piezoelectric element. The transmitter 11 transmits a specified ultrasonic wave by receiving a transmission signal described later.

[0068] Receiver 12 receives the sound and its reflected waves transmitted by transmitter 11, converts the received sound and its reflected waves into a received signal composed of analog electrical signals, and outputs the converted received signal. In Embodiment 1, the following description assumes that the sound and its reflected waves received by receiver 12 are ultrasonic waves, but the sound and its reflected waves received by receiver 12 are not necessarily limited to ultrasonic waves. Receiver 12 is implemented, for example, by a microphone. Furthermore, receiver 12 may also be implemented, for example, by a piezoelectric element. When transmitter 11 and receiver 12 are implemented by piezoelectric elements, transmitter 11 and receiver 12 may also be implemented by a single piezoelectric element with time-division operation.

[0069] Furthermore, this description assumes that the seating detection device 10 has one receiver 12, but the seating detection device 10 is not limited to having one receiver and may also have multiple receivers.

[0070] Figure 2 This is a plan view schematically showing the seating detection device 10 installed inside the vehicle 30. Figure 2 The diagram illustrates a portion of the structure within the vehicle 30 in a way that is not actually directly recognizable, but appears recognizable.

[0071] like Figure 2 As shown, the seating detection device 10 is disposed within a roof-mounted console 32 located in the roof of the vehicle 30. More specifically, the seating detection device 10 is disposed within the roof-mounted console 32 at a position offset from the centerline extending from the vehicle 30 in the direction of travel.

[0072] By placing the seating detection device 10 in the aforementioned position, the distances from which the ultrasonic waves transmitted from the transmitter 11 are reflected by the seat 31A and reach the receiver 12, the distances from which the ultrasonic waves transmitted from the transmitter 11 are reflected by the seat 31B and reach the receiver 12, the distances from which the ultrasonic waves transmitted from the transmitter 11 are reflected by the seat 31C and reach the receiver 12, and the distances from which the ultrasonic waves transmitted from the transmitter 11 are reflected by the seat 31D and reach the receiver 12 are all different from each other.

[0073] Back to Figure 1 Continue with the explanation of the seated detection device 10.

[0074] The transmission signal generation unit 19 generates a transmission signal representing the waveform of a predetermined ultrasonic wave output by the transmitter 11, and outputs the generated transmission signal to the sound characteristic analysis unit 13 and the DAC 18. Here, it is assumed that the transmission signal generation unit 19 generates a transmission signal composed of a digital signal for explanation. The transmission signal generation unit 19 is implemented, for example, by executing a program stored in a memory (not shown) provided by the seating detection device 10 by a microprocessor (not shown) provided by the seating detection device 10.

[0075] Figure 3 This is a waveform diagram showing an example of the transmitted signal output by the transmitted signal generation unit 19.

[0076] exist Figure 3 In the diagram, the horizontal axis represents time, the vertical axis of the waveform displayed on the upper side represents the amplitude of the transmitted signal, and the vertical axis of the waveform displayed on the lower side represents the frequency of the transmitted signal.

[0077] like Figure 3As shown, the transmitted signal is an 86ms signal consisting of a 43ms signal period and a 43ms no signal period formed by a frequency-sweeping sine wave.

[0078] like Figure 3 As shown, the transmission signal generation unit 19 continuously outputs the transmission signal, which consists of a signal period and a no-signal period.

[0079] Back to Figure 1 Continue with the explanation of the seated detection device 10.

[0080] DAC18 converts the digital signal generated by the transmit signal generation unit 19 into an analog signal, and outputs the transmit signal composed of the converted analog signal to amplifier 16.

[0081] Amplifier 16 amplifies the transmitted signal obtained by DAC 18 converting it into an analog signal, and outputs the amplified transmitted signal to transmitter 11. Transmitter 11 then transmits the specified ultrasonic waves. As described above, the transmitted signal generation unit 19 continuously outputs the transmitted signals sequentially. Therefore, transmitter 11 continuously transmits the specified ultrasonic waves sequentially.

[0082] Amplifier 15 amplifies the received signal, which is composed of the analog signal output from receiver 12, and outputs the amplified received signal to ADC17.

[0083] The ADC17 converts the received signal, which is composed of the amplified analog signal output from the amplifier 16, into a digital signal, and outputs the received signal, which is composed of the converted digital signal, to the sound characteristic analysis unit 13.

[0084] As described above, the transmitter 11 continuously transmits specified ultrasonic waves sequentially. Therefore, the receiver 12 continuously receives the specified ultrasonic waves and their reflected waves sequentially. Consequently, the ADC 17 continuously outputs received signals corresponding to the specified ultrasonic waves transmitted from the transmitter 11 sequentially.

[0085] The sound characteristic analysis unit 13 calculates the time or frequency characteristics of the sound within the space of the vehicle 30, i.e., the space with multiple seats, based on the signal received by the receiver 12. More specifically, the sound characteristic analysis unit 13 is input with each transmitted signal sequentially output from the transmitted signal generation unit 19 and each received signal sequentially output from the ADC 17. For each transmitted signal sequentially input, the unit calculates the impulse response of a specified ultrasonic wave within the vehicle 30 based on the transmitted signal and the corresponding received signal, and outputs the calculated impulse response sequentially to the detection unit 14.

[0086] Here, the impulse response of a specified ultrasonic wave within the vehicle 30 calculated by the sound characteristic analysis unit 13 is an example of the time or frequency characteristics of sound within the space of the vehicle 30. Hereinafter, it will be explained assuming that the time or frequency characteristics of sound within the vehicle 30 calculated by the sound characteristic analysis unit 13 are the impulse response of a specified ultrasonic wave within the vehicle 30; however, the time or frequency characteristics of sound within the vehicle 30 calculated by the sound characteristic analysis unit 13 are not necessarily limited to the impulse response of a specified ultrasonic wave within the vehicle 30. The sound characteristic analysis unit 13 is implemented, for example, by executing a program stored in a memory (not shown) provided by the seating detection device 10 via a microprocessor (not shown) provided by the seating detection device 10.

[0087] Figure 4 This is a waveform diagram representing an example of the impulse response generated by the acoustic characteristic analysis unit 13.

[0088] exist Figure 4 In the diagram, the horizontal axis represents time, and the vertical axis represents the signal level.

[0089] like Figure 4 As shown, the positions of the reflection components based on seat 31A, seat 31B, seat 31C, and seat 31D on the time axis in the impulse response are different from each other. This is because, as mentioned above, the distances from which the ultrasonic waves transmitted from transmitter 11 reach receiver 12 after being reflected by seat 31A, seat 31B, seat 31C, and seat 31D are different from each other.

[0090] In this way, the position on the time axis in the impulse response corresponds to the length of the path from the transmitter to the location where the person's movement occurs to the receiver.

[0091] The sound characteristic analysis unit 13 may, for example, perform Fourier transform on the transmitted signal and the received signal, calculate the ratio of the signal strength per frequency for the Fourier transformed transmitted signal and the received signal, and perform an inverse Fourier transform on the calculated ratio of the signal strength per frequency to calculate the impulse response.

[0092] The detection unit 14 detects the presence or absence of occupants or seated persons in the vehicle 30 based on the time or frequency characteristics of the sound within the vehicle 30 calculated by the sound characteristic analysis unit 13, and outputs the detection result. More specifically, the detection unit 14 is input with pulse responses calculated sequentially by the sound characteristic analysis unit 13, and detects the presence or absence of occupants or seated persons in the vehicle 30 based on the difference between the pulse response of a predetermined ultrasonic wave transmitted by the transmitter 11 at a first timing (hereinafter also referred to as the "first pulse response") and the pulse response of a predetermined ultrasonic wave transmitted by the transmitter at a second timing (hereinafter also referred to as the "second pulse response"), and outputs the detection result. The detection unit 14 is implemented, for example, by executing a program stored in a memory (not shown) provided by the seating detection device 10 via a microprocessor (not shown) provided by the seating detection device 10.

[0093] Figure 5 This is a block diagram showing the structure of the detection unit 14. Figure 5 The diagram above shows schematic waveforms of the signals output from the main components of the detection unit 14. The horizontal axis of each waveform represents time, and the vertical axis represents the signal level.

[0094] like Figure 5 As shown, the detection unit 14 includes a pulse response holding unit 21, a difference calculation unit 22, an absolute value calculation unit 23, and a change position calculation unit 24.

[0095] The impulse response holding unit 21 stores each impulse response calculated sequentially by the acoustic characteristic analysis unit 13.

[0096] When a new pulse response is input from the sound characteristic analysis unit 13, the difference calculation unit 22 takes the newly input pulse response as the first pulse response, takes one of the pulse responses stored by the pulse response holding unit 21 (for example, the pulse response input immediately before the first pulse response) as the second pulse response, calculates the difference between the first pulse response and the second pulse response, and outputs the difference signal representing the calculated difference to the absolute value calculation unit 23.

[0097] like Figure 5As shown, the positions of the reflection components based on seat 31A, seat 31B, seat 31C, and seat 31D in the difference signal on the time axis are different from each other. Therefore, for example, when a person is seated in seat 31A, due to the person's movement (e.g., movement accompanied by breathing), the position of the reflection component based on seat 31A in the difference signal on the time axis will have a difference of more than a predetermined value. The same applies when the person is seated in seat 31B, seat 31C, or seat 31D. Thus, when a person is seated in a seat within the vehicle 30, the position of the seat they are seated in is reflected in the position of the difference signal on the time axis where a difference of more than a predetermined value occurs.

[0098] When a difference signal is input from the difference calculation unit 22, the absolute value calculation unit 23 calculates the absolute value of the input difference signal and outputs the difference absolute value signal, which represents the calculated absolute value of the difference signal, to the change position calculation unit 24.

[0099] When the absolute value difference signal is input from the absolute value calculation unit 23, the position change calculation unit 24 detects seating within the vehicle 30 based on the absolute value difference signal and outputs detection information indicating the detection result. More specifically, if a difference of a predetermined value or higher occurs in the absolute value difference signal, the position change calculation unit 24 detects seating and outputs seating information indicating seating; if no difference of a predetermined value or higher occurs, it detects no seating and outputs seating information indicating no seating.

[0100] The position change calculation unit 24 then calculates the seating position based on the position of the absolute value of the difference signal that has occurred on the time axis when a difference of more than a predetermined value occurs in the absolute value of the difference signal, and includes information representing the calculated seating position in the output seating information.

[0101] Furthermore, the position change calculation unit 24 is not limited to calculating seating information using only a single absolute difference signal; it can also utilize the average or maximum value of multiple past absolute difference signals, the frequency of change, etc. Additionally, this information can be used as feature quantities for machine learning to make judgments.

[0102] When making judgments using machine learning, the following approach can be used.

[0103] During the learning phase, data from multiple absolute difference signals (absolute difference signals) acquired in the past, including the average, maximum, and frequency of change of these signals, are assigned correct labels (whether the person is seated) as teacher data. This data is used to construct a learning model, which outputs the learned model. In the utilization phase, at least one of the absolute difference signals acquired by the seating detection device, the average, maximum, or frequency of change of these signals is input into the generated learned model. The learned model then processes this information internally to determine whether the person is seated. Furthermore, the machine learning algorithm is not particularly limited as long as it achieves the above output result. For example, it could be teacher-learned algorithms such as logistic regression or support vector machines, or deep learning algorithms using neural networks capable of discovering features independently.

[0104] <Action>

[0105] The seating detection device 10 with the above structure performs the first seating detection process in the vehicle 30.

[0106] The first seating detection process performed by the seating detection device 10 will be described below with reference to the accompanying drawings.

[0107] Figure 6 This is the flowchart for the first seating detection process.

[0108] The first seating detection process begins, for example, when the impulse response calculated by the acoustic characteristic analysis unit 13 is stored in the impulse response holding unit 21, by outputting a transmission signal from the transmission signal generation unit 19.

[0109] When the first seating detection process begins, transmitter 11 sends a specified ultrasonic wave into vehicle 30 (step S10).

[0110] When a specified ultrasonic wave is transmitted from the transmitter 11, the receiver 12 receives the ultrasonic wave and its reflected wave, and outputs a received signal (step S20).

[0111] When the received signal is output from the receiver 12, the sound characteristic analysis unit 13 calculates the impulse response within the vehicle 30 based on the transmitted signal output from the transmitted signal generation unit 19 and the received signal output from the receiver 12 (step S30), and outputs the calculated impulse response.

[0112] When an impulse response is output from the sound characteristic analysis unit 13, the difference calculation unit 22 takes this impulse response as the first impulse response, takes the impulse response previously calculated by the sound characteristic analysis unit 13 and stored in the impulse response holding unit 21 as the second impulse response, calculates the difference between these first impulse responses and second impulse responses, and outputs a difference signal representing the calculated difference. Furthermore, the absolute value calculation unit 23 calculates the absolute value of the difference signal output from the difference calculation unit 22 and outputs a difference absolute value signal representing the absolute value of the calculated difference signal (step S40).

[0113] When the absolute value of the difference is output from the absolute value calculation unit 23, the change position calculation unit 24 investigates whether the absolute value of the difference has a difference greater than a predetermined value (step S50).

[0114] If a difference of a predetermined value or greater occurs during the processing in step S50 (step S50: Yes), the position change calculation unit 24 further calculates the seating position based on the position of the absolute value difference signal on the time axis (step S60). Then, the position change calculation unit 24 outputs seating information indicating that a seat has been taken and the seating position is correct (step S70).

[0115] In the process of step S50, if no difference greater than a predetermined value occurs (step S50: No), the position change calculation unit 24 outputs a seating signal indicating that no one has taken a seat (step S80).

[0116] When the processing in step S70 and step S80 is completed, the seating detection device 10 ends the first seating detection process.

[0117] <Inspection>

[0118] The seating detection device 10 with the above structure eliminates the need to embed sensors (transmitter 11 and receiver 12) in each seat (seats 31A to 31D) to be detected. Furthermore, it can detect the presence or absence of people in two or more seats (seats 31A to 31D) using only one set of sensors (transmitter 11 and receiver 12). Moreover, since image processing using a camera is not required, it reduces memory load and computational complexity compared to conventional devices that detect seating by image processing using a camera.

[0119] Furthermore, the seating detection device 10 calculates the impulse response within the vehicle 30 based on ultrasound. Generally, ultrasound is less common than sound waves in relation to noise within a vehicle. Therefore, compared to seating detection devices that calculate the impulse response within a vehicle based on sound waves, the seating detection device 10 can detect the presence or absence of a person or the presence or absence of a seat with higher accuracy.

[0120] As described above, the seating detection device 10 detects the presence or absence of a person or whether they are seated based on the presence or absence of human movement. Therefore, it is possible to detect the presence or absence of a person or whether they are seated regardless of their shape or posture. Furthermore, it is possible to suppress false detections of the presence or absence of a person or whether they are seated due to stationary objects such as luggage placed on the seat.

[0121] As described above, the seating detection device 10 does not require embedding sensors in each seat that is the object of detection. Therefore, it is possible to detect the presence or absence of a person or whether they are seated, regardless of the deformation of the seat (e.g., the shape of the seat deforms from a chair shape to a cushion shape, etc.) or the folded state of a part of the seat.

[0122] Typically, ultrasonic waves can diffract and travel behind an object. Therefore, the seating detection device 10 can detect the presence or absence of a person or whether they are seated even in areas that cannot be directly identified from its location.

[0123] The seating detection device 10 can, for example, output a calculated seating signal to the ECU (Electronic Control Unit) that controls the vehicle 30. In this way, the ECU controlling the vehicle 30 can, for example, prevent unnecessary airbag deployment for unoccupied seats. Furthermore, the ECU controlling the vehicle 30 can, for example, turn off the seat heaters for unoccupied seats to suppress battery consumption. Additionally, the ECU controlling the vehicle 30 can, for example, prevent unnecessary air conditioning ventilation for unoccupied seats.

[0124] (Implementation Method 2)

[0125] The following description pertains to a seating detection device of embodiment 2, which is constructed by modifying a portion of the structure of the seating detection device 10 of embodiment 1. This seating detection device is mounted on a vehicle corresponding to a vehicle emergency notification system (hereinafter also referred to as "the vehicle of embodiment 2"), i.e., a vehicle equipped with a speaker, microphone, and communication device used by the vehicle emergency notification system. The following description of the seating detection device of embodiment 2 focuses on its differences from the seating detection device 10. Furthermore, the vehicle emergency notification system is, for example, e-Call.

[0126] Figure 7 This is a block diagram showing the structure of the seating detection device 10A according to Embodiment 2.

[0127] like Figure 7As shown, the seating detection device 10A is configured by changing the transmitter 11 to the transmitter 51, the receiver 12 to the receiver 52, and the detection unit 14 to the detection unit 14A from the seating detection device 10 of the relevant embodiment 1.

[0128] Transmitter 51 is a loudspeaker used by the emergency notification system and has the same function as transmitter 11. That is, transmitter 51 is shared by both the transmitter of the seating detection device 10A and the loudspeaker used by the emergency notification system.

[0129] Receiver 52 is the microphone used by the emergency notification system and has the same function as receiver 12. That is, receiver 52 is shared as both the receiver of the seating detection device 10A and the microphone used by the emergency notification system.

[0130] In addition to the functions of the detection unit 14, the detection unit 14A also has the following additional functions.

[0131] That is, the so-called additional function is, under certain conditions, the function of sending information about the presence or absence of relevant personnel in the vehicle of Embodiment 2, or whether they are seated, to the emergency notification center using the communication device 50 used by the vehicle emergency notification system. Here, the specified conditions can be, for example, conditions determined by the emergency notification system as indicating that the vehicle of Embodiment 2 has been involved in an accident, or conditions determined by the emergency notification system as indicating that a person riding in the vehicle of Embodiment 2 has fallen seriously ill.

[0132] <Inspection>

[0133] According to the seating detection device 10A with the above-described structure, a speaker and a microphone are shared between the seating detection device 10A and the emergency notification system. Therefore, it is possible to suppress the number of speakers and microphones installed in the vehicle of the relevant embodiment 2.

[0134] Furthermore, according to the seating detection device 10A with the above-described structure, in emergency situations such as an accident involving the vehicle of Embodiment 2 or a passenger in the vehicle of Embodiment 2 falling seriously ill, information regarding the presence or absence of the relevant person or whether they are seated can be sent to the emergency notification center. Therefore, in response to a request from the emergency notification center, emergency medical personnel dispatched to the vehicle of Embodiment 2 can know in advance which seat a person is in and how many people are in the vehicle, thus enabling faster and / or more reliable emergency rescue operations.

[0135] (Implementation Method 3)

[0136] Hereinafter, we will describe the seating detection device of embodiment 3, which is constructed by changing part of the structure of the seating detection device 10 of embodiment 1. Hereinafter, we will focus on the differences between the seating detection device of embodiment 3 and the seating detection device 10.

[0137] Figure 8 This is a block diagram showing the structure of the seating detection device 10B according to Embodiment 2.

[0138] like Figure 8 As shown, the seating detection device 10B is configured by changing the receiver 12 to receivers 12A to 12N, the amplifier 15 to amplifiers 15A to 15N, the ADC 17 to ADC 17A to ADC 17N, and adding a directional control unit 60, which is different from the seating detection device 10 of Embodiment 1.

[0139] Receivers 12A to 12N each have the same function as receiver 12.

[0140] Amplifiers 15A through 15N each have the same function as amplifier 15.

[0141] ADC17A to ADC17N have the same functions as ADC17.

[0142] That is, the seating detection device 10B is configured by changing the number of receivers 12 from 1 to K, the number of amplifiers 15 from 1 to K, and the number of ADCs 17 from 1 to K, compared to the seating detection device 10. Here, in Figure 8 The diagram illustrates that K can be an integer greater than or equal to 3, but K can be any integer greater than or equal to 2; it is not necessarily limited to a specific integer. Figure 8 As shown in the diagram, it is an integer greater than or equal to 3.

[0143] The directional control unit 60 receives K received signals output from ADC17A to ADC17N respectively, performs directional control using at least two of the K received signals, calculates a received signal that emphasizes the reflected wave component from a specific direction, and outputs the calculated received signal that emphasizes the reflected wave component from the specific direction to the transmit signal generation unit 19. The directional control unit 60 is implemented, for example, by executing a program stored in a memory (not shown) provided in the seating detection device 10B via a microprocessor (not shown).

[0144] <Inspection>

[0145] The seating detection device 10B with the above structure can calculate the seating position with better accuracy compared to the seating detection device 10 of Embodiment 1.

[0146] (Implementation Method 4)

[0147] Hereinafter, we will describe the seating detection device of embodiment 4, which is constructed by changing part of the structure of the seating detection device 10 of embodiment 1.

[0148] Hereinafter, the seating detection device of embodiment 4 will be described with a focus on the differences from the seating detection device 10.

[0149] Figure 9 This is a block diagram showing the structure of the seating detection device 10C according to Embodiment 4.

[0150] like Figure 9 As shown, the seating detection device 10C is configured by removing the transmitter 11, amplifier 16, DAC 18 and transmission signal generation unit 19 from the seating detection device 10 of Embodiment 1, adding a door sensor 20 and a conditional learning model storage unit 70, changing the sound characteristic analysis unit 13 to a sound characteristic analysis unit 13C, and changing the detection unit 14 to a detection unit 14C.

[0151] Figure 10 This is a schematic plan view of a vehicle 30C equipped with a seating detection device 10C. In Embodiment 4, it is assumed that the seating detection device 10C is as follows: Figure 10 The following description describes a vehicle 30C equipped with a left front door, a right front door, a left rear door, a right rear door, and a trunk lid. The presence or absence of a person, or whether they are seated, is detected by the sound generated when the left front door, right front door, left rear door, right rear door, or trunk lid (hereinafter simply referred to as "doors") of the vehicle 30C is closed. However, the seating detection device of Embodiment 4 is not necessarily limited to an example of a structure equipped with a vehicle 30C, nor is it limited to an example where the sound used to detect the presence or absence of a person, or whether they are seated, is generated when the doors are closed.

[0152] Furthermore, the following description assumes that the seating detection device 10C is mounted on the vehicle 30C, but it is only necessary that at least the receiver 12 is mounted on the vehicle 30C, and it is not necessary that all the components of the seating detection device 10C are mounted on the vehicle 30C.

[0153] The door sensor 20 detects the opening and closing status of the left front door, right front door, left rear door, right rear door and trunk lid respectively.

[0154] The sound characteristic analysis unit 13C calculates the time or frequency characteristics of the sound within the space of the vehicle 30C, i.e., the space with multiple seats, based on the signal received from the receiver 12. More specifically, the sound characteristic analysis unit 13C is input to the detection result of the door opening / closing state output from the door sensor 20 and the received signal output from the ADC 17. Based on the detection result of the door opening / closing state, it detects a door closing event and obtains the received signals before and after the door closing event. Furthermore, the sound characteristic analysis unit 13C calculates the time or frequency characteristics of the sound within the space of the vehicle 30C based on the obtained received signals.

[0155] Here, a door closing event refers to an event in which at least one of the following doors changes from an open state to a closed state: the left front door, the right front door, the left rear door, the right rear door, and the trunk lid. For example, a door closing event occurs when an occupant of vehicle 30C is boarding or alighting.

[0156] The conditional learning model storage unit 70 stores multiple machine learning models (hereinafter simply referred to as "learning models") trained under different conditions.

[0157] Multiple learning models were pre-trained using data that assigned positive solution labels to the time or frequency characteristics of the sound within the vehicle 30C output from the sound characteristics analysis unit 13C as teacher data.

[0158] Here, among the different conditions, there are at least the conditions that the left front door closing event occurs when all other doors are closed, the right front door closing event occurs when all other doors are closed, the left front door closing event occurs when all other doors are closed, and the trunk lid closing event occurs when all other doors are closed.

[0159] Furthermore, among the multiple learning models stored in the conditional learning model storage unit 70, at least one learning model A71A was trained using teacher data that satisfies the condition that a door closing event of the left front door occurred while all other doors were closed; a learning model B71B was trained using teacher data that satisfies the condition that a door closing event of the right front door occurred while all other doors were closed; a learning model C71C was trained using teacher data that satisfies the condition that a door closing event of the left rear door occurred while all other doors were closed; and a learning model N71N was trained using teacher data that satisfies the condition that a door closing event of the trunk lid occurred while all other doors were closed.

[0160] Figure 11This is a schematic diagram illustrating an example of the correspondence between the teacher data used in training for each of the multiple learning models stored in the conditional learning model storage unit 70, the conditions satisfied by the teacher data, and the correct solution labels assigned to the teacher data.

[0161] The detection unit 14C detects the presence or absence of occupants in the vehicle 30C based on the time or frequency characteristics of the sound within the vehicle 30C calculated by the sound characteristic analysis unit 13C, and outputs the detection result. More specifically, the detection unit 14C includes a recognizer 14C. By inputting the time or frequency characteristics of the sound within the vehicle 30C calculated by the sound characteristic analysis unit 13C, and a door closing event detected by the sound characteristic analysis unit 13C, the recognizer 14C obtains the presence or absence of occupants in the vehicle 30C or their seating status output by the recognizer 14C, and outputs the obtained information on the presence or absence of occupants in the vehicle 30C or their seating status.

[0162] When the recognizer 140 is input with the temporal or frequency characteristics of the sound within the vehicle 30C calculated by the sound characteristic analysis unit 13C, and a door closing event detected by the sound characteristic analysis unit 13C, it retrieves a learning model trained using teacher data that satisfies the conditions corresponding to the input door closing event from the conditional learning model storage unit 70. Furthermore, the recognizer 14C inputs the temporal or frequency characteristics of the sound within the vehicle 30C into the retrieved learning model, obtains the presence or absence of occupants in the vehicle 30, or whether they are seated, output from the learning model, and outputs the obtained information regarding the presence or absence of occupants in the vehicle 30.

[0163] <Action>

[0164] The seating detection device 10C with the above structure performs the second seating detection process in the vehicle 30C.

[0165] The second seating detection process performed by the seating detection device 10C will be described below with reference to the accompanying drawings.

[0166] Figure 12 This is the flowchart for the second seating detection process.

[0167] If the second seating detection process is initiated, the sound characteristic analysis unit 13C begins an attempt to detect the door closing event (step S110).

[0168] In the processing of step S110, when the sound characteristic analysis unit 13C detects a door closing event (after repeatedly being step S110: No, step S110: Yes), it investigates whether all doors other than the door that is the object of the detected door closing event are closed (step S120).

[0169] In the process of step S120, if all doors except the door to which the detected door closing event is located are closed (step S120: Yes), the sound characteristic analysis unit 13C acquires the received signals before and after the detected door closing event (step S130).

[0170] Having acquired the received signals before and after the detected door closing event, the sound characteristic analysis unit 13C calculates the time or frequency characteristics of the sound in the space inside the vehicle 30C based on the acquired received signals (step S140).

[0171] After calculating the temporal or frequency characteristics of the sound in the space inside the vehicle 30C, the detection unit 14C uses a learning model to determine whether there are people in the vehicle 30 or whether they are seated (step S150). The learning model is obtained by training with teacher data that satisfies the conditions corresponding to the door closing event detected by the sound characteristic analysis unit 13C.

[0172] In the process of step S120, if at least one of the doors other than the door to which the detected door closing event is located is not closed (step S120: No), and if the process of step S150 ends, the seating detection device 10C ends the second seating detection process.

[0173] <Inspection>

[0174] The seating detection device 10C with the above structure can detect the presence or absence of a person or whether they are seated by using the sound that occurs when the car door is closed.

[0175] (Replenish)

[0176] The above describes a seating detection device based on embodiments 1 to 3. However, this disclosure is not limited to these embodiments. Any modifications to these embodiments that can be conceived by those skilled in the art, or any combination of the constituent elements of different embodiments, are also included within the scope of one or more technical solutions of this disclosure, as long as they do not depart from the spirit of this disclosure.

[0177] (1) In Embodiment 1, it is assumed that the seating detection device 10 is located in the overhead console 32 at a position deviating from the centerline extending from the vehicle 30 in the direction of travel. However, the seating detection device 10 is only required to be located at a position that allows ultrasonic waves transmitted from the transmitter 11 to at least one of the seats 31A to 31D to be reflected by that seat and reach the receiver 12. It is not necessary to limit it to a specific example of being located in the overhead console 32 at a position deviating from the centerline extending from the vehicle 30 in the direction of travel.

[0178] The position of the seating detection device 10 does not necessarily need to be limited, but it is preferably located at a position where the distance from which the ultrasonic waves transmitted from the transmitter 11 are reflected by the seat 31A to the receiver 12 (hereinafter also referred to as the "first distance"), the distance from which the ultrasonic waves transmitted from the transmitter 11 are reflected by the seat 31B to the receiver 12 (hereinafter also referred to as the "second distance"), the distance from which the ultrasonic waves transmitted from the transmitter 11 are reflected by the seat 31C to the receiver 12 (hereinafter also referred to as the "third distance"), and the distance from which the ultrasonic waves transmitted from the transmitter 11 are reflected by the seat 31D to the receiver 12 (hereinafter also referred to as the "fourth distance") are different from each other. Typically, the seats in the vehicle are located in a position symmetrical about the centerline extending in the direction of travel of the vehicle. Therefore, in vehicle 30, in order to make the first distance, the second distance, the third distance and the fourth distance different from each other, for example, at least one of the transmitter 11 and the receiver 12 is located at a position deviating from the center line extending from the vehicle 30 in the direction of travel, and the transmitter 11 is not located at a position that is linearly symmetrical with respect to the receiver 12 about the aforementioned center line as the axis of symmetry.

[0179] (2) In Embodiment 1, as an example, it is described that the difference calculation unit 22 calculates the difference between the first pulse response and the second pulse response, taking the newly input pulse response as the first pulse response and the pulse response immediately preceding (and immediately before) the first pulse response as the second pulse response. However, the first pulse response and the second pulse response are only required to be pulse responses of ultrasonic waves transmitted by the transmitter 11 at different timings, and are not limited to examples of newly input pulse responses and pulse responses immediately preceding them. For example, the first pulse response and the second pulse response could also be the newly input pulse response as the first pulse response, and the pulse response in the unmanned vehicle 30 pre-calculated by the sound characteristic analysis unit 13 as the second pulse response.

[0180] (3) In Embodiment 1, it is assumed that the transmission signal generated by the transmission signal generation unit 19 is a signal composed of a swept-frequency sine wave. However, the transmission signal is not limited to a signal composed of a swept-frequency sine wave. The transmission signal may also be, for example, a signal composed of white noise, a signal composed of band noise, or a sine wave.

[0181] Furthermore, the signal period and the no-signal period are not limited to 43ms, and the signal period and the no-signal period can also be of different lengths.

[0182] (4) In Embodiment 1, the detection unit 14 was described as having an absolute value calculation unit 23. However, as another structural example of the detection unit 14, a structure without the absolute value calculation unit 23 can also be considered. In this case, the difference calculation unit 22 causes the change position calculation unit 24 to calculate the calculated difference signal. When the difference signal is input from the difference calculation unit 22, the change position calculation unit 24 detects seating within the vehicle 30 based on the difference signal and outputs detection information indicating the detection result. More specifically, if a difference of a predetermined value or higher occurs in the difference signal, the change position calculation unit 24 detects seating and outputs seating information indicating seating; if no difference of a predetermined value or higher occurs, it detects no seating and outputs seating information indicating no seating. Furthermore, if a difference of a predetermined value or higher occurs in the difference signal, the change position calculation unit 24 calculates the seating position based on the position of the difference signal on the time axis and includes information indicating the calculated seating position in the seating information to be output.

[0183] (5) In embodiment 1, the receiver 12 may also be a digital MEMS (Micro ElectroMechanical System) microphone. In this case, since the output of the receiver 12 is a digital signal, the amplifier 15 and ADC 17 are no longer needed.

[0184] (6) In Embodiment 1, a passenger car, i.e., a vehicle, was described as an example of a space with multiple seats. However, a space with multiple seats is not limited to a passenger car, i.e., a vehicle, and can also be a mobile body other than a passenger car, i.e., a vehicle. The seating detection device 10 can also be applied to seating detection in vehicles, buses, trains, airplanes, etc., which are mobile bodies other than passenger cars, i.e., vehicles, buses, trains, airplanes, etc., where passengers travel around to confirm seating. By applying the seating detection device 10, the number of times passengers travel around can be reduced, and the risk of infectious diseases such as coronaviruses can be reduced.

[0185] Furthermore, spaces with multiple seats are not limited to mobile spaces; they can also be other locations, such as indoor spaces with seating, like movie theaters.

[0186] (7) In Embodiment 4, it is assumed that the seating detection device 10C uses the sound generated when the vehicle door of the vehicle 30C closes to detect the presence or absence of a person or whether they are seated. However, the sound used by the seating detection device 10C in detecting the presence or absence of a person or whether they are seated can be any sound generated inside or outside the vehicle 30C, and is not necessarily limited to the sound generated when the vehicle door of the vehicle 30C closes. For example, the sound used by the seating detection device 10C in detecting the presence or absence of a person or whether they are seated could be the sound of the door mirror retracting, or it could be external noise from the vehicle 30C. Furthermore, the type of sound used by the seating detection device 10C in detecting the presence or absence of a person or whether they are seated is not particularly limited; for example, it could be either audible sound or ultrasound.

[0187] (8) The technical solution of this disclosure is not only related to the seating detection device of embodiments 1 to 4, but also to the seating detection method which uses the characteristic structural parts included in the seating detection device as steps. In addition, the technical solution of this disclosure may also be a program that causes a device including a computer to execute the characteristic steps included in the seating detection method. In addition, the technical solution of this disclosure may also be a computer-readable non-transitory recording medium that records such a program.

[0188] Industrial availability

[0189] This disclosure can be widely used in seating detection devices, etc., to detect the presence or absence of people in a space with multiple seats or the presence or absence of people sitting.

[0190] Symbol Explanation

[0191] 10, 10A, 10B Seating detection device; 11, 51 Transmitter; 12, 12A, 12B, 12N, 52 Receiver; 13, 13C Sound characteristic analysis unit; 14, 14A, 14C Detection unit; 15, 15A, 15B, 15N, 16 Amplifier; 17, 17A, 17B, 17N ADC; 18 DAC; 19 Transmit signal generation unit; 20 Door sensor; 21 Pulse response holding unit; 22 Difference calculation unit; 23 Absolute value calculation unit; 24 Change position calculation unit; 30, 30C Vehicle; 31A, 31B, 31C, 31D Seat; 32 Overhead console; 50 Notification device; 60 Directional control unit; 70 Conditional learning model storage unit; 71A Learning model A; 71B Learning model B; 71C Learning model C; 71N Learning model N; 140 Recognizer.

Claims

1. A seating detection device, have: One or more receivers are configured in a space with multiple seats to receive sound occurring inside or outside the space. The sound characteristic analysis unit calculates the time or frequency characteristics of the sound in the space based on signals received from one or more of the aforementioned receivers; and The detection unit, based on the time characteristics or frequency characteristics calculated by the sound characteristic analysis unit, detects the presence or absence of people or those seated in the space, and outputs the detection results. The aforementioned seating detection device also includes a transmitter that sends a specified sound into the aforementioned space. The aforementioned one or more receivers receive the reflected waves of the aforementioned sound. The aforementioned sound characteristic analysis unit calculates the aforementioned time characteristics or frequency characteristics of the aforementioned sound based on the aforementioned defined sound signal and the signals received by the aforementioned one or more receivers. The aforementioned detection unit detects the presence or absence of the person or the presence or absence of the seated person based on the difference between the time characteristic or frequency characteristic of the prescribed sound transmitted by the aforementioned transmitter at a first timing, calculated by the aforementioned sound characteristic analysis unit, and the time characteristic or frequency characteristic of the prescribed sound transmitted by the aforementioned transmitter at a second timing, calculated by the aforementioned sound characteristic analysis unit. The aforementioned acoustic characteristic analysis unit calculates the impulse response of the specified sound. The detection unit calculates the difference between the pulse response of the specified sound transmitted by the transmitter at the first timing calculated by the sound characteristic analysis unit and the pulse response of the specified sound transmitted by the transmitter at the second timing calculated by the sound characteristic analysis unit. If the difference signal representing the calculated difference has a difference of more than a specified value on the time axis, the detection unit determines that the person is seated.

2. The seating detection device as described in claim 1, The sound emitted by the aforementioned transmitter is ultrasonic.

3. The seating detection device as described in claim 1 or 2, The aforementioned transmitter is located in a position capable of transmitting sound to all seats within the aforementioned space.

4. The seating detection device as described in claim 1 or 2, The aforementioned space refers to the interior space inside the vehicle. At least one of the aforementioned transmitters and receivers is located at a position offset from the centerline extending along the direction of travel of the vehicle. The aforementioned transmitter is not located at a position that is linearly symmetrical about the aforementioned center line with respect to at least one of the aforementioned one or more receivers.

5. The seating detection device as described in claim 4, The aforementioned transmitter and one or more receivers are located in the overhead console of the aforementioned vehicle.

6. The seating detection device as described in claim 1 or 2, The above-mentioned "one or more receivers" refers to multiple receivers. The aforementioned acoustic characteristic analysis unit calculates the aforementioned time characteristics or the aforementioned frequency characteristics by performing directional control, and the aforementioned directional control uses at least two of a plurality of received signals representing the waveforms of the aforementioned reflected waves received by the plurality of receivers.

7. The seating detection device as described in claim 1 or 2, Furthermore, if a difference of a predetermined value or more exists between the time characteristic or frequency characteristic of the prescribed sound transmitted by the transmitter at a first timing calculated by the sound characteristic analysis unit and the time characteristic or frequency characteristic of the prescribed sound transmitted by the transmitter at a second timing calculated by the sound characteristic analysis unit, the detection unit calculates the seating position based on the position of the time characteristic or frequency characteristic on the time axis where the difference occurred.

8. The seating detection device as described in claim 1 or 2, The aforementioned transmitter and at least one of the aforementioned receivers are respectively a speaker and a microphone used in the vehicle emergency notification system.

9. The seating detection device as described in claim 1 or 2, The aforementioned detection department uses the communication device used in the vehicle emergency notification system to send the detected information about the presence or absence of seats in the aforementioned space to the emergency notification center that is linked to the vehicle emergency notification system.

10. A method for detecting seating, comprising a seating detection device having one transmitter, one or more receivers, an acoustic characteristic analysis unit, and a detection unit. The aforementioned transmitter sequentially sends a specified sound into the space. The aforementioned one or more receivers sequentially receive the reflected waves of the aforementioned specified sound transmitted by the aforementioned one transmitter. The aforementioned sound characteristic analysis unit sequentially calculates the time characteristics or frequency characteristics of the sound inside the vehicle interior space based on the specified sound, based on at least one of a transmitted signal representing the waveform of the specified sound transmitted by the one or more transmitters and a received signal representing the waveform of the reflected wave of the specified sound received by the one or more receivers. The aforementioned detection unit detects the presence or absence of persons in the vehicle interior space based on the difference between the time or frequency characteristics of the sound in the vehicle interior space calculated by the aforementioned sound characteristic analysis unit based on the aforementioned sound transmitted by the aforementioned transmitter at a first time interval, and the time or frequency characteristics of the sound in the vehicle interior space calculated by the aforementioned sound characteristic analysis unit based on the aforementioned sound transmitted by the aforementioned transmitter at a second time interval, and outputs the detection result. The aforementioned acoustic characteristic analysis unit calculates the impulse response of the specified sound. The detection unit calculates the difference between the pulse response of the specified sound transmitted by the transmitter at the first timing calculated by the sound characteristic analysis unit and the pulse response of the specified sound transmitted by the transmitter at the second timing calculated by the sound characteristic analysis unit. If the difference signal representing the calculated difference has a difference of more than a specified value on the time axis, the detection unit determines that the person is seated.

11. A program recording medium for recording a program used to cause a seating detection apparatus comprising one transmitter, one or more receivers, an acoustic characteristic analysis unit, and a detection unit to perform seating detection processing. The above-mentioned seating inspection process includes the following steps: The aforementioned transmitter sequentially sends a specified sound into the space. The aforementioned one or more receivers sequentially receive the reflected waves of the aforementioned specified sound transmitted by the aforementioned one transmitter. The aforementioned sound characteristic analysis unit sequentially calculates the time characteristics or frequency characteristics of the sound inside the vehicle interior space based on the specified sound, based on at least one of a transmitted signal representing the waveform of the specified sound transmitted by the one or more transmitters and a received signal representing the waveform of the reflected wave of the specified sound received by the one or more receivers. The aforementioned detection unit detects the presence or absence of persons in the vehicle interior space based on the difference between the time or frequency characteristics of the sound in the vehicle interior space calculated by the aforementioned sound characteristic analysis unit based on the aforementioned sound transmitted by the aforementioned transmitter at a first time interval, and the time or frequency characteristics of the sound in the vehicle interior space calculated by the aforementioned sound characteristic analysis unit based on the aforementioned sound transmitted by the aforementioned transmitter at a second time interval, and outputs the detection result. The aforementioned acoustic characteristic analysis unit calculates the impulse response of the specified sound. The detection unit calculates the difference between the pulse response of the specified sound transmitted by the transmitter at the first timing calculated by the sound characteristic analysis unit and the pulse response of the specified sound transmitted by the transmitter at the second timing calculated by the sound characteristic analysis unit. If the difference signal representing the calculated difference has a difference of more than a specified value on the time axis, the detection unit determines that the person is seated.

Images