Signal processing system, person detection system, signal processing method, and program

Abstract

The present disclosure addresses the problem of suppressing a decrease in accuracy of determination even when determining the presence of a person in a plurality of detection regions using biological information of the person. A signal processing system (2) is provided with a signal acquisition unit (231), a waveform estimation unit (232), a waveform comparison unit (233), and a determination unit (234). A signal acquisition unit (231) acquires, from a sensor system (10), a plurality of detection signals (for example, detection signals L1, L2) corresponding to each of a plurality of detection regions. The sensor system (10) is arranged in a space and is used for detecting persons in a plurality of detection areas which are different from one another. A waveform estimation unit (232) estimates a biological waveform relating to biological information of a person on the basis of each of the plurality of detection signals. A waveform estimation unit (232) compares a plurality of biological waveforms corresponding to each of the plurality of detection signals. The determination unit (234) determines the presence of a person in the space on the basis of the comparison result of the waveform comparison unit (233).

Description

Technical Field

[0001] The present disclosure generally relates to a signal processing system, a human detection system, a signal processing method, and a program, and more particularly, to a signal processing system, a human detection system, a signal processing method, and a program for determining the presence of a person in a space. Background Art

[0002] Conventionally, there is known a sensor system that uses a radio wave sensor to detect the state of a person in a predetermined area, such as the movement of a person or the presence or absence of a person (for example, see Patent Document 1).

[0003] The radio wave sensor included in the sensor system of Patent Document 1 outputs radio waves into a detection area, receives the radio waves reflected by objects within the detection area, and outputs a radio wave sensor signal corresponding to the object's state. The signal processing system included in the sensor system of Patent Document 1 processes the radio wave sensor signal to generate time-series data of a person's biological information, and uses this time-series data to determine the person's state.

[0004] Consider installing multiple radio wave sensors in multiple different detection areas and determining a person's presence in each detection area. In this case, a radio wave sensor that detects one of the multiple detection areas may receive radio waves reflected in other detection areas. The sensor system of Patent Document 1 does not anticipate receiving radio waves reflected in other detection areas. Therefore, if the sensor system of Patent Document 1 is used, the accuracy of determining a person's presence (presence) may be reduced.

[0005] Prior art literature

[0006] Patent Literature

[0007] Patent Document 1: Japanese Patent Application Laid-Open No. 2021-171271 Summary of the Invention

[0008] The present disclosure is made in view of the above-mentioned problems, and its purpose is to provide a signal processing system, a human detection system, a signal processing method and a program that can suppress the reduction in the accuracy of judgment even when using human biological information to judge the presence of people in multiple detection areas.

[0009] A signal processing system according to one embodiment of the present disclosure includes a signal acquisition unit, a waveform estimation unit, a waveform comparison unit, and a determination unit. The signal acquisition unit acquires a plurality of detection signals corresponding to a plurality of detection areas from a sensor system provided in a space and used to detect people in the plurality of different detection areas. The waveform estimation unit estimates a biological waveform related to a person's biological information based on each of the plurality of detection signals. The waveform comparison unit compares the plurality of biological waveforms corresponding to the plurality of detection signals. The determination unit determines the presence of a person in the space based on the comparison result of the waveform comparison unit.

[0010] A human detection system according to one embodiment of the present disclosure includes the signal processing system described above and a sensor system for detecting a human in the space.

[0011] The signal processing method involved in one embodiment of the present disclosure includes a signal acquisition step, a waveform estimation step, a waveform comparison step, and a determination step. In the signal acquisition step, a plurality of detection signals corresponding to a plurality of detection areas are acquired from a sensor system arranged in a space and used to detect people in a plurality of different detection areas. In the waveform estimation step, a biological waveform related to the biological information of a person is estimated based on each of the plurality of detection signals. In the waveform comparison step, a plurality of biological waveforms corresponding to the plurality of detection signals are compared. In the determination step, the presence of a person in the space is determined based on the comparison result in the waveform comparison step.

[0012] A program according to one embodiment of the present disclosure is a program for causing a computer system to execute the signal processing method. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] Figure 1 This is a block diagram showing the configuration of a signal processing system according to Embodiment 1 of the present disclosure and a human detection system including the same signal processing system.

[0014] Figure 2 1 is a system configuration diagram showing an example of use of the human detection system described above.

[0015] Figure 3 A and Figure 3 B is a waveform diagram showing an example of a biological waveform estimated by the same signal processing system.

[0016] Figure 4 Graph showing the relationship between the cross-correlation coefficient obtained from the same waveform graph and time (seconds).

[0017] Figure 5A is a waveform diagram showing an example of the first biological waveform and the second biological waveform. Figure 5 B is a transition graph showing an example of transition of the cross-correlation coefficient obtained from the first bio-waveform and the second bio-waveform. Figure 5 C is a transition diagram showing an example of transition of the determination result.

[0018] Figure 6 FIG. 8A is a waveform diagram showing another example of the first biological waveform and the second biological waveform. Figure 6 FIG. B is a transition diagram showing another example of transition of the cross-correlation coefficient obtained from the first bio-waveform and the second bio-waveform. Figure 6 C is a transition diagram showing another example of the transition of the determination result.

[0019] Figure 7 A and Figure 7 B is a diagram showing the relationship between the comparison result and a predetermined threshold value serving as a reference for determination.

[0020] Figure 8 Flowchart showing the operation of the same signal processing system.

[0021] Figure 9 This is a block diagram showing the configuration of a signal processing system according to Modification 1 of Embodiment 1 and a human detection system including the same signal processing system.

[0022] Figure 10 1 is a system configuration diagram showing an example of use of the human detection system described above.

[0023] Figure 11 This is a block diagram showing the configuration of a signal processing system according to Modification 2 of Embodiment 1 and a human detection system including the same signal processing system.

[0024] Figure 12 It is a graph showing the relationship between the mutual correlation coefficient and the probability of two people existing in the space.

[0025] Figure 13 This is a block diagram showing the configuration of a signal processing system according to Embodiment 2 of the present disclosure and a human detection system including the same signal processing system.

[0026] Figure 14 It is a graph showing the relationship between the cross-correlation coefficient and the suppression coefficient.

[0027] Figure 15 A and Figure 15 B is a waveform diagram showing biological waveforms before and after processing by the waveform adjustment unit included in the same signal processing system.

[0028] Figure 16Flowchart showing the operation of the same signal processing system.

[0029] Figure 17 This is a flowchart showing the operation of the signal processing system according to the first modification of the second embodiment. DETAILED DESCRIPTION

[0030] The embodiments and modifications described below are merely examples of the present disclosure, and the present disclosure is not limited to the embodiments and modifications. In addition to these embodiments and modifications, various changes can be made according to design, etc. as long as they do not depart from the scope of the technical ideas involved in the present disclosure.

[0031] (Implementation 1)

[0032] Next, use Figures 1 to 8 Next, the human detection system 1 according to the first embodiment and the signal processing system included in the human detection system 1 will be described.

[0033] (1) Summary

[0034] like Figure 1 As shown, the human detection system 1 according to the first embodiment includes a sensor system 10 and a signal processing device 20 as a signal processing system 2 .

[0035] The sensor system 10 is set in the space SP1 and is used to detect people in a plurality of different detection areas G1 and G2 (for example, Figure 2 The sensor system 10 outputs radio waves to multiple detection areas G1 and G2 in space SP1, receives radio waves reflected by objects within the multiple detection areas G1 and G2, and outputs radio wave sensor signals corresponding to the state of the objects. The state of an object can be, for example, the movement of the object, the presence or absence of the object, the speed or position of the object, etc. In the present disclosure, persons u1 and u2 are assumed as objects, and the state of persons u1 and u2 is biological information (breathing, heartbeat, pulse, etc.). In particular, in the present disclosure, the biological information is the person's breathing.

[0036] like Figure 1As shown, the signal processing device 20 (signal processing system 2) includes a signal acquisition unit 231, a waveform estimation unit 232, a waveform comparison unit 233, and a determination unit 234. The signal acquisition unit 231 is arranged in the space SP1 and acquires a plurality of detection signals corresponding to the plurality of detection areas G1 and G2 from the sensor system 10 for detecting people in the plurality of different detection areas G1 and G2. The waveform estimation unit 232 estimates the bio-waveform related to the bio-information of the persons u1 and u2 based on each of the plurality of detection signals. The waveform comparison unit 233 compares the plurality of bio-waveforms corresponding to the plurality of detection signals. The determination unit 234 determines the presence of a person in the space SP1 based on the comparison results of the waveform comparison unit 233.

[0037] According to this configuration, even when determining the presence of a person in a plurality of detection areas using biological information of the person, it is possible to suppress a decrease in the accuracy of the determination.

[0038] (2) Structure

[0039] (2.1) Sensor system

[0040] like Figure 1 As shown, the sensor system 10 includes a plurality (two in the illustrated example) of radio wave sensors 11 .

[0041] The plurality of radio wave sensors 11 detect people in a plurality of different detection areas G1 and G2 (for example, Figure 2 The multiple radio wave sensors 11 are, for example, Doppler sensors or FMCW (Frequency-Modulated Continuous-Wave) radio wave sensors. When it is necessary to describe the multiple radio wave sensors 11 individually, they are described as a first radio wave sensor 11a and a second radio wave sensor 11b.

[0042] like Figure 1 As shown, the radio wave sensor 11 includes a sensor unit 101, a signal generating unit 102, and a communication unit 103. Hereinafter, the sensor unit 101, signal generating unit 102, and communication unit 103 included in the first radio wave sensor 11a may be referred to as the sensor unit 101a, signal generating unit 102a, and communication unit 103a. Furthermore, the sensor unit 101, signal generating unit 102, and communication unit 103 included in the second radio wave sensor 11b may be referred to as the sensor unit 101b, signal generating unit 102b, and communication unit 103b.

[0043] The sensor unit 101 outputs radio waves into the detection area of space SP1 and receives radio waves reflected by objects within the detection area. For example, the sensor unit 101a of the first radio wave sensor 11a outputs radio waves into the detection area G1 and receives radio waves reflected by objects within the detection area G1. The sensor unit 101b of the second radio wave sensor 11b outputs radio waves into the detection area G2 and receives radio waves reflected by objects within the detection area G2.

[0044] The signal generating unit 102 generates a detection signal based on an oscillation signal corresponding to the output radio wave and a received signal corresponding to the received radio wave. For example, the detection signal is a Doppler signal containing an in-phase component and a quadrature component. The signal generating unit 102 generates a detection signal (Doppler signal) based on a signal having a component having a frequency difference between the received signal and the oscillation signal. For example, the signal generating unit 102a of the first radio wave sensor 11a generates a detection signal (Doppler signal) L1 based on an oscillation signal corresponding to the radio wave output by the sensor unit 101a and a received signal corresponding to the radio wave received by the sensor unit 101a. The signal generating unit 102b of the second radio wave sensor 11b generates a detection signal (Doppler signal) L2 based on an oscillation signal corresponding to the radio wave output by the sensor unit 101b and a received signal corresponding to the radio wave received by the sensor unit 101b. That is, the multiple detection signals include a first detection signal and a second detection signal. Hereinafter, the detection signal L1 may be referred to as a first detection signal L1 , and the detection signal L2 may be referred to as a second detection signal L2 .

[0045] The communication unit 103 has a communication interface for communicating with the signal processing device 20. The communication unit 103 outputs (transmits) the detection signal generated by the signal generation unit 102 to the signal processing device 20. For example, the communication unit 103a of the first radio wave sensor 11a outputs the first detection signal L1 generated by the signal generation unit 102a to the signal processing device 20. The communication unit 103b of the second radio wave sensor 11b transmits the second detection signal L2 generated by the signal generation unit 102b to the signal processing device 20.

[0046] (2.2) Signal processing device (signal processing system)

[0047] like Figure 1 As shown, the signal processing device 20 includes a communication unit 21 , a display unit 22 , and a control unit 23 .

[0048] The signal processing device 20 includes a computer system having, for example, a processor and memory. The processor executes a program stored in the memory, thereby allowing the computer system to function as the control unit 23. The program executed by the processor is pre-recorded in the computer system's memory here, but may also be recorded on a storage medium such as a memory card and provided, or provided via a telecommunication line such as the Internet.

[0049] The communication unit 21 has a communication interface for communicating with the plurality of radio wave sensors 11 of the sensor system 10. For example, the communication unit 21 receives the first detection signal L1 output from the first radio wave sensor 11a and the second detection signal L2 output from the second radio wave sensor 11b.

[0050] The display unit 22 is a thin display device such as a liquid crystal display or an organic EL (electroluminescence) display. The display unit 22 displays a biological waveform based on the detection signal received from the sensor system 10. Here, the biological waveform is, for example, a human breathing waveform.

[0051] like Figure 1 As shown, the control unit 23 includes a signal acquisition unit 231 , a waveform estimation unit 232 , a waveform comparison unit 233 , a determination unit 234 , and a display processing unit 235 .

[0052] The signal acquisition unit 231 is located in the space SP1 and acquires, via the communication unit 21, a plurality of detection signals corresponding to the plurality of detection areas G1 and G2 from the sensor system 10 for detecting people in the plurality of different detection areas G1 and G2. The signal acquisition unit 231 includes a first signal acquisition unit 241 and a second signal acquisition unit 242. The first signal acquisition unit 241 acquires the first detection signal L1 output from the first radio wave sensor 11a. The second signal acquisition unit 242 acquires the second detection signal L2 output from the second radio wave sensor 11b.

[0053] The waveform estimation unit 232 estimates a bio-waveform related to a person's biological information based on each of the multiple detection signals acquired by the signal acquisition unit 231. Here, the waveform estimation unit 232 estimates a person's respiratory waveform based on each of the multiple detection signals acquired by the signal acquisition unit 231. The waveform estimation unit 232 estimates multiple bio-waveforms corresponding to the multiple detection signals using a data estimation learning model constructed using a recursive neural network.

[0054] The waveform estimation section 232 includes a first waveform estimation section 251 and a second waveform estimation section 252 .

[0055] The first waveform estimation unit 251 estimates a bio-waveform (respiration waveform) based on the first detection signal L1 acquired by the first signal acquisition unit 241. The second waveform estimation unit 252 estimates a bio-waveform (respiration waveform) based on the second detection signal L2 acquired by the second signal acquisition unit 242. Specifically, the waveform estimation unit 232 estimates a bio-waveform (first bio-waveform) corresponding to the first detection signal L1 and a bio-waveform (second bio-waveform) corresponding to the second detection signal L2.

[0056] The first waveform estimation unit 251 estimates the human bio-waveform based on the first detection signal L1 using a learning model. The second waveform estimation unit 252 estimates the human bio-waveform based on the second detection signal L2 using the learning model. The learning model is a learning model for data estimation constructed by a recursive neural network (deep learning). The first waveform estimation unit 251 uses a recurrent neural network (RNN), a long short-term memory (LSTM), or a gated recurrent unit (GRU) as a recursive neural network. The learning model is pre-generated by supervised learning using a large amount of learning detection signals as learning data (training data). The first waveform estimation unit 251 and the second waveform estimation unit 252 can improve the estimation accuracy of the bio-waveform that changes over time by using the above-mentioned pre-generated learning model constructed by the recursive neural network. For the learning data during neural network learning, it is preferable to use a highly reliable bio-waveform obtained by a contact sensor directly worn on the human body. In addition, it is preferred that the learning model is adjusted so that when the quality of the detection signal serving as the input to the learning model (the signal level itself or the signal-to-noise ratio) is good, the amplitude of the biological waveform serving as the output of the learning model is standardized to be approximately 1; and when the quality of the detection signal is low or the signal is such that the learning model cannot be inferred, the amplitude of the biological waveform is less than 1.

[0057] The waveform comparison unit 233 compares the plurality of biological waveforms corresponding to the plurality of detection signals. Specifically, the waveform comparison unit 233 compares the biological waveform W1 (refer to Figure 3 A) and the biological waveform W2 based on the second detection signal L2 (refer to Figure 3 Hereinafter, the biological waveform W1 may be described as the first biological waveform W1, and the biological waveform W2 may be described as the second biological waveform W2.

[0058] The waveform comparison unit 233 calculates an evaluation index representing the similarity between multiple bio-waveforms (e.g., bio-waveforms W1 and W2) as a comparison result. For example, the evaluation index is a cross-correlation coefficient representing the cross-correlation relationship between multiple bio-waveforms (e.g., bio-waveforms W1 and W2) within a predetermined period. The waveform comparison unit 233 uses a cross-correlation function to calculate multiple cross-correlation coefficients for the multiple bio-waveforms within the predetermined period and extracts the calculation results as the comparison result. In this embodiment, the waveform comparison unit 233 calculates multiple cross-correlation coefficients for the first bio-waveform W1 and the second bio-waveform W2 within the predetermined period as the comparison result.

[0059] For example, the waveform comparison unit 233 calculates the cross-correlation coefficient between the first biological waveform W1 and the second biological waveform W2 in time series using the following equation 1: Wherein XC is the cross-correlation coefficient, corr() is the cross-correlation function, and max() is the maximum value.

[0060] [Number 1]

[0061]

[0062] That is, the waveform comparison unit 233 calculates the maximum value obtained by normalizing the cross-correlation function between the first biological waveform W1 and the second biological waveform W2 as the cross-correlation coefficient. The cross-correlation coefficient is a number greater than or equal to 0 and less than or equal to 1. Figure 4 The cross-correlation coefficients calculated by the waveform comparison unit 233 in time series are shown. Figure 4 The waveform Z1 shown shows the transition of the cross-correlation coefficient calculated in time series. Figure 5 A~ Figure 5 C shows, for example, waveform graphs of the first and second bio-waveforms, time-series outputs of cross-correlation coefficients, and an example of determination results (approximately 6 hours) in the case of one night's sleep. Figure 6 A~ Figure 6 C shows another example (about 6 hours) of waveform graphs of the first and second bio-waveforms, time-series outputs of cross-correlation coefficients, and determination results in the case of one night's sleep. Figure 5 A~ Figure 5 C is an example of a case where there is a person in space SP1. Figure 6 A~ Figure 6 C is an example of a case where two people exist in space SP1.

[0063] exist Figure 5 A and Figure 6 In A of FIG. 1 , the first biological waveforms W1a and W1b and the second biological waveforms W2a and W2b are shown. Figure 5B shows a waveform Z11 indicating a transition of the cross-correlation coefficient calculated by the waveform comparing section 233 based on the first biological waveform W1 a and the second biological waveform W2 a . Figure 6 B shows a waveform Z12 indicating the transition of the cross-correlation coefficient calculated by the waveform comparing section 233 based on the first biological waveform W1 b and the second biological waveform W2 b . Figure 5 C shows a waveform O11 indicating the transition of the determination result output by the determination unit 234 based on the waveform Z11 indicating the transition of the cross-correlation coefficient. Figure 6 C shows a waveform O12 indicating the transition of the determination result output by the determination unit 234 based on the waveform Z12 indicating the transition of the cross-correlation coefficient.

[0064] Determination unit 234 determines the presence of a person in space SP1 based on the comparison result of waveform comparison unit 233. Specifically, determination unit 234 determines the presence of a person in space SP1 based on the evaluation index. More specifically, determination unit 234 determines the presence of a person in space SP1 based on the cross-correlation coefficient extracted by waveform comparison unit 233.

[0065] Specifically, the determination unit 234 determines whether one person or two people exist in the space SP1 based on the determination result and a predetermined threshold. If the cross-correlation coefficient obtained as a result of the comparison is greater than the predetermined threshold, the determination unit 234 determines that one person exists in the space SP1. If the cross-correlation coefficient obtained as a result of the comparison is less than the predetermined threshold, the determination unit 234 determines that two people exist in the space SP1.

[0066] Here, the prescribed threshold value is based on the value of a reference cross-correlation coefficient corresponding to a peak value in a frequency distribution of multiple reference cross-correlation coefficients calculated using the first and second person bio-waveforms within a prescribed period. The first person bio-waveform is a bio-waveform estimated by the first waveform estimation unit 251 of the waveform estimation unit 232 when only the first person (e.g., person u1) exists in space SP1. The second person bio-waveform is a bio-waveform estimated by the second waveform estimation unit 252 of the waveform estimation unit 232 when only the second person (e.g., person u2) exists in space SP1. For example, the prescribed threshold value is a value greater than the calculated reference cross-correlation coefficient corresponding to a peak value in a frequency distribution of multiple reference cross-correlation coefficients. Alternatively, the prescribed threshold value may be based on the value of a reference cross-correlation coefficient corresponding to a median value in a frequency distribution of multiple reference cross-correlation coefficients calculated using the first and second person bio-waveforms within a prescribed period.

[0067] For example, Figure 7 A shows the frequency distribution of the cross-correlation coefficient when there is one person in the space SP1. Figure 7 B shows the frequency distribution of the mutual correlation coefficient when two people exist in space SP1. Here, TH1 is regarded as a predetermined threshold. Figure 7 As shown in A, the comparison results of the waveform comparison unit 233 can be set so that most of them are distributed in a region larger than the predetermined threshold value TH1. In other words, the cross-correlation coefficient R1 corresponding to the peak value of the distribution can be set to be greater than the predetermined threshold value TH1. Figure 7 As shown in FIG. 1B , the comparison results of waveform comparison unit 233 can be set so that the majority of the distribution is distributed within a region smaller than a predetermined threshold value TH1. In other words, the cross-correlation coefficient (R2) corresponding to the peak of the distribution can be set so as to be smaller than the predetermined threshold value TH1. By setting threshold value TH1 in this manner, when the comparison result of waveform comparison unit 233 is greater than or equal to the predetermined threshold value TH1, determination unit 234 determines that a single person is present in space SP1. When the comparison result of waveform comparison unit 233 is less than or equal to the predetermined threshold value TH1, determination unit 234 determines that two people are present in space SP1.

[0068] use Figure 5 B. Figure 5 C. Figure 6 B and Figure 6 The determination by the determination unit 234 will be specifically described based on C. Assume that the predetermined threshold is set to "0.5" for example. Figure 5 In the example of B, the waveform Z11 which is the comparison result output from the waveform comparison unit 233 is compared with a predetermined threshold value “0.5”. Figure 5 C represents the comparison result of the waveform Z11 and the predetermined threshold value "0.5", that is, the judgment result. Figure 5 In C, the transition of the result obtained by outputting the comparison result output from the waveform comparison unit 233 as "1" (equivalent to one person) to the part where the comparison result is greater than the predetermined threshold value "0.5" and outputting the rest of the parts as "2" (equivalent to two people) is shown. Figure 5 In C, most of the judgment results are "1", and it can be judged that there is a person at least in this time period based on the time series. Figure 6 In the example of B, the waveform Z12 which is the comparison result output from the waveform comparison unit 233 is compared with the predetermined threshold value “0.5”. Figure 6 C represents the comparison result of the waveform Z12 and the predetermined threshold value "0.5", that is, the judgment result. Figure 6 In C, the transition of the result obtained by outputting the comparison result output from the waveform comparison unit 233 as "1" (equivalent to one person) to the part where the comparison result is greater than the predetermined threshold value "0.5" and outputting the rest of the parts as "2" (equivalent to two people) is shown. Figure 6In C, most of the judgment results are "2", and it can be judged that there are two people based on the time series at least in this time period.

[0069] The display processing unit 235 causes the display unit 22 to display the determination result of the determination unit 234. The display processing unit 235 also causes the display unit 22 to display the biowaveform estimated by the first waveform estimation unit 251 (first biowaveform) and the biowaveform estimated by the second waveform estimation unit 252 (second biowaveform).

[0070] (3) Action

[0071] Here, use Figure 8 The operation of the signal processing device 20 will be described.

[0072] The signal acquisition unit 231 acquires multiple detection signals corresponding to the multiple detection areas G1 and G2 from the sensor system 10 (step S1). Specifically, the first signal acquisition unit 241 of the signal acquisition unit 231 acquires the first detection signal L1 output from the first radio wave sensor 11a. The second signal acquisition unit 242 of the signal acquisition unit 231 acquires the second detection signal L2 output from the second radio wave sensor 11b.

[0073] The waveform estimation unit 232 performs waveform estimation processing (step S2). Specifically, the first waveform estimation unit 251 of the waveform estimation unit 232 estimates the first bio-waveform W1 based on the first detection signal L1 acquired by the first signal acquisition unit 241. The second waveform estimation unit 252 of the waveform estimation unit 232 estimates the second bio-waveform W2 based on the second detection signal L2 acquired by the second signal acquisition unit 242.

[0074] The waveform comparison unit 233 performs waveform comparison processing (step S3). Specifically, the waveform comparison unit 233 compares the first biological waveform W1 with the second biological waveform W2. More specifically, the waveform comparison unit 233 uses a cross-correlation function to calculate multiple cross-correlation coefficients for multiple biological waveforms within a predetermined period.

[0075] The determination unit 234 performs a determination process (step S4). The determination unit 234 determines the presence of a person in space SP1 based on the cross-correlation coefficient extracted as a comparison result by the waveform comparison unit 233. Specifically, if the cross-correlation coefficient as a comparison result is greater than a predetermined threshold, the determination unit 234 determines that a single person exists in space SP1. If the cross-correlation coefficient as a comparison result is less than the predetermined threshold, the determination unit 234 determines that two people exist in space SP1.

[0076] The display processing unit 235 performs display processing (step S5 ). The display processing unit 235 displays the determination result of the determination unit 234 , the biowaveform estimated by the first waveform estimation unit 251 (first biowaveform), and the biowaveform estimated by the second waveform estimation unit 252 (second biowaveform) on the display unit 22 .

[0077] (4) Advantages

[0078] As described above, the signal processing system 2 of embodiment 1 includes a signal acquisition unit 231, a waveform estimation unit 232, a waveform comparison unit 233, and a determination unit 234. The signal acquisition unit 231 acquires a plurality of detection signals (e.g., detection signals L1, L2) corresponding to a plurality of detection areas (e.g., detection areas G1, G2) from the sensor system 10. The sensor system 10 is set in the space SP1 and is used to detect people in a plurality of different detection areas. The waveform estimation unit 232 estimates a biological waveform (e.g., a first biological waveform and a second biological waveform) related to the biological information of a person based on each of the plurality of detection signals. The waveform estimation unit 232 compares the plurality of biological waveforms corresponding to the plurality of detection signals. The determination unit 234 determines the presence of a person in the space SP1 based on the comparison result of the waveform comparison unit 233.

[0079] For example, a sensor system outputs radio waves to each of multiple detection areas and receives radio waves from each of the multiple detection areas. Radio waves reflected from one of the multiple detection areas may also be received after being reflected from another detection area. In such a case, even if no person is present in one detection area, the presence of a person in one detection area may be mistakenly determined based on radio waves received from another detection area.

[0080] Therefore, the waveform estimation unit 232 can extract similarities by comparing multiple biometric waveforms corresponding to multiple detection signals, as in Embodiment 1. This can suppress a decrease in determination accuracy even when determining the presence of a person in multiple detection areas using human biometric information.

[0081] (5) Modification

[0082] Modifications are listed below. The modifications described below can be applied in combination with the first embodiment as appropriate.

[0083] (5.1) Modification 1

[0084] In the first embodiment, the human detection system 1 is configured to determine whether one person or two people are present in the space SP1, but the present invention is not limited to this configuration.

[0085] The human detection system 1 can also determine whether there is one, two or three people in the space SP1. Figure 9 and Figure 10 The human detection system 1 of the modification 1 will be described focusing on the differences from the embodiment 1. Components identical to those of the embodiment 1 are denoted by the same reference numerals, and their descriptions are omitted as appropriate.

[0086] like Figure 9 As shown, the human detection system 1 according to the first modification includes a sensor system 10A and a signal processing device 20A as the signal processing system 2 .

[0087] like Figure 9 As shown, the sensor system 10A includes a plurality (three in the illustrated example) of radio wave sensors 11. When the plurality of radio wave sensors 11 need to be individually described, they are described as a first radio wave sensor 11a, a second radio wave sensor 11b, and a third radio wave sensor 11c.

[0088] The plurality of radio wave sensors 11 detect people in a plurality of different detection areas G1, G2, and G3 (for example, Figure 10 The biological information (human breathing) of the persons u1, u2, and u3 shown in the figure. For example, the sensor portion 101a of the first radio wave sensor 11a outputs radio waves into the detection area G1 and receives radio waves reflected by objects in the detection area G1. The sensor portion 101b of the second radio wave sensor 11b outputs radio waves into the detection area G2 and receives radio waves reflected by objects in the detection area G2. The sensor portion (not shown) of the third radio wave sensor 11c outputs radio waves into the detection area G3 and receives radio waves reflected by objects in the detection area G3. In addition, in Modification 1, as Figure 10 As shown, the detection areas G1, G2, and G3 are arranged in sequence along a specified direction.

[0089] The configuration of the plurality of radio wave sensors 11 is the same as that of the radio wave sensor 11 in the first embodiment, and therefore description thereof will be omitted here.

[0090] The signal generating unit 102 of the first radio wave sensor 11a (see Figure 1) generates a detection signal (Doppler signal) L1 based on an oscillation signal corresponding to the radio wave output by the sensor unit 101a and a wave reception signal corresponding to the radio wave received by the sensor unit 101 of the first radio wave sensor 11a. The signal generation unit 102 of the second radio wave sensor 11b generates a detection signal (Doppler signal) L2 based on an oscillation signal corresponding to the radio wave output by the sensor unit 101 of the second radio wave sensor 11b and a wave reception signal corresponding to the radio wave received by the sensor unit 101 of the second radio wave sensor 11b. The signal generation unit (not shown) of the third radio wave sensor 11c generates a detection signal (Doppler signal) L3 based on an oscillation signal corresponding to the radio wave output by the sensor unit (not shown) of the third radio wave sensor 11c and a wave reception signal corresponding to the radio wave received by the sensor unit of the third radio wave sensor 11c. Hereinafter, the detection signal L1 may be referred to as a first detection signal L1 , the detection signal L2 may be referred to as a second detection signal L2 , and the detection signal L3 may be referred to as a third detection signal L3 .

[0091] The first radio wave sensor 11a outputs a first detection signal L1 to the signal processing device 20A. The second radio wave sensor 11b outputs a second detection signal L2 to the signal processing device 20A. The third radio wave sensor 11c outputs a third detection signal L3 to the signal processing device 20A.

[0092] like Figure 9 As shown, the signal processing device 20A includes a communication unit 21, a display unit 22, and a control unit 23A.

[0093] The signal processing device 20A includes a computer system having, for example, a processor and memory. The processor executes a program stored in the memory, thereby allowing the computer system to function as the control unit 23A. The program executed by the processor is pre-recorded in the computer system's memory here, but may also be recorded on a storage medium such as a memory card and provided, or provided via a telecommunication line such as the Internet.

[0094] like Figure 9 As shown, the control section 23A includes a signal acquisition section 231A, a waveform estimation section 232A, a waveform comparison section 233A, a determination section 234A, and a display processing section 235 .

[0095] The signal acquisition unit 231A is located in the space SP1 and acquires multiple detection signals corresponding to the multiple detection areas G1, G2, and G3 from the sensor system 10 for detecting people in the multiple different detection areas G1, G2, and G3 via the communication unit 21. The signal acquisition unit 231 includes a first signal acquisition unit 241, a second signal acquisition unit 242, and a third signal acquisition unit 243. The first signal acquisition unit 241 acquires the first detection signal L1 output from the first radio wave sensor 11a. The second signal acquisition unit 242 acquires the second detection signal L2 output from the second radio wave sensor 11b. The third signal acquisition unit 243 acquires the third detection signal L3 output from the third radio wave sensor 11c.

[0096] The waveform estimation unit 232A estimates a bio-waveform related to a person's biological information based on each of the multiple detection signals acquired by the signal acquisition unit 231A. Here, the waveform estimation unit 232A estimates a person's respiratory waveform based on each of the multiple detection signals acquired by the signal acquisition unit 231. The waveform estimation unit 232A estimates multiple bio-waveforms corresponding to the multiple detection signals using a data estimation learning model constructed using a recursive neural network.

[0097] The waveform estimation section 232A includes a first waveform estimation section 251 , a second waveform estimation section 252 , and a third waveform estimation section 253 .

[0098] The first waveform estimation unit 251 estimates a bio-waveform (respiration waveform) based on the first detection signal L1 acquired by the first signal acquisition unit 241. The second waveform estimation unit 252 estimates a bio-waveform (respiration waveform) based on the second detection signal L2 acquired by the second signal acquisition unit 242. The third waveform estimation unit 253 estimates a bio-waveform (respiration waveform) based on the third detection signal L3 acquired by the third signal acquisition unit 243. That is, the waveform estimation unit 232A estimates a bio-waveform (first bio-waveform) corresponding to the first detection signal L1, a bio-waveform (second bio-waveform) corresponding to the second detection signal L2, and a bio-waveform (third bio-waveform) corresponding to the third detection signal L3.

[0099] The first waveform estimation unit 251 estimates a human bio-waveform based on the first detection signal L1 using a learning model. The second waveform estimation unit 252 estimates a human bio-waveform based on the second detection signal L2 using the learning model. The third waveform estimation unit 253 estimates a human bio-waveform based on the third detection signal L3 using the learning model.

[0100] The waveform comparison unit 233A compares the multiple bio-waveforms corresponding to the multiple detection signals. Specifically, the waveform comparison unit 233 compares a first bio-waveform based on the first detection signal L1 with a second bio-waveform based on the second detection signal L2. The waveform comparison unit 233 compares the second bio-waveform based on the second detection signal L2 with a third bio-waveform based on the third detection signal L3.

[0101] The waveform comparison unit 233A calculates an evaluation index representing the similarity between the first bio-waveform and the second bio-waveform as a comparison result between the first and second bio-waveforms. For example, the evaluation index is a cross-correlation coefficient representing the cross-correlation relationship between multiple bio-waveforms (e.g., the first bio-waveform and the second bio-waveform) within a predetermined period. The waveform comparison unit 233 uses a cross-correlation function to calculate multiple cross-correlation coefficients for the multiple bio-waveforms within the predetermined period. The waveform comparison unit 233 extracts the calculated multiple cross-correlation coefficients as the first comparison result between the first and second bio-waveforms.

[0102] Furthermore, the waveform comparison unit 233A calculates an evaluation index representing the similarity between the second bio-waveform and the third bio-waveform as a comparison result between the second and third bio-waveforms. For example, the evaluation index is a cross-correlation coefficient representing the cross-correlation relationship between multiple bio-waveforms (e.g., the second and third bio-waveforms) within a predetermined period. The waveform comparison unit 233 uses a cross-correlation function to calculate multiple cross-correlation coefficients for the multiple bio-waveforms within the predetermined period. The waveform comparison unit 233 extracts the calculated multiple cross-correlation coefficients as the first comparison result between the second and third bio-waveforms.

[0103] The determination unit 234A determines the presence of a person in the space SP1 based on the first and second comparison results of the waveform comparison unit 233A. For example, the determination unit 234A uses the first and second comparison results of the waveform comparison unit 233A and Table 1 to determine the presence of a person in the space SP1.

[0104] [Table 1]

[0105]

[0106] Specifically, when the mutual correlation coefficient as a result of the first comparison is less than a predetermined first threshold value, and when the mutual correlation coefficient as a result of the second comparison is less than a predetermined second threshold value, the determination unit 234A determines that three people exist in the space SP1. When the mutual correlation coefficient as a result of the first comparison is less than the predetermined first threshold value, and when the mutual correlation coefficient as a result of the second comparison is greater than or equal to the predetermined second threshold value, the determination unit 234A determines that two people exist in the space SP1. When the mutual correlation coefficient as a result of the first comparison is greater than or equal to the predetermined first threshold value, and when the mutual correlation coefficient as a result of the second comparison is less than or equal to the predetermined second threshold value, the determination unit 234A determines that two people exist in the space SP1. When the mutual correlation coefficient as a result of the first comparison is greater than or equal to the predetermined first threshold value, and when the mutual correlation coefficient as a result of the second comparison is greater than or equal to the predetermined second threshold value, the determination unit 234A determines that one person exists in the space SP1.

[0107] Here, the prescribed first threshold is based on the value of the cross-correlation coefficient corresponding to the peak in the frequency distribution of the multiple cross-correlation coefficients calculated within a prescribed period using the first and second person bio-waveforms. The prescribed second threshold is based on the value of the cross-correlation coefficient corresponding to the peak in the frequency distribution of the multiple cross-correlation coefficients calculated within a prescribed period using the second and third person bio-waveforms. The first person bio-waveform is the bio-waveform estimated by the first waveform estimation unit 251 when only the first person (e.g., person u1) exists in space SP1. The second person bio-waveform is the bio-waveform estimated by the second waveform estimation unit 252 when only the second person (e.g., person u2) exists in space SP1. The third person bio-waveform is the bio-waveform estimated by the third waveform estimation unit 253 when only the third person (e.g., person u3) exists in space SP1. For example, the prescribed first threshold is a value greater than the calculated cross-correlation coefficient corresponding to the peak in the frequency distribution of the multiple cross-correlation coefficients. The prescribed second threshold is a value greater than the calculated cross-correlation coefficient corresponding to the peak in the frequency distribution of the multiple cross-correlation coefficients.

[0108] The display processing unit 235 causes the display unit 22 to display the determination result of the determination unit 234. Furthermore, the display processing unit 235 causes the display unit 22 to display the biowaveform estimated by the first waveform estimation unit 251 (first biowaveform), the biowaveform estimated by the second waveform estimation unit 252 (second biowaveform), and the biowaveform estimated by the third waveform estimation unit 253 (third biowaveform).

[0109] (5.2) Modification 2

[0110] In the first embodiment, the plurality of radio wave sensors 11 included in the human detection system 1 are configured as, for example, Doppler sensors, FMCW radio wave sensors, etc. However, the present invention is not limited to this configuration.

[0111] The human detection system 1 may also include a MIMO (Multiple Input Multiple Output) type radio wave sensor. Figure 11 The human detection system 1 of Modification 2 will be described focusing on differences from Embodiment 1. Components identical to those of Embodiment 1 are denoted by the same reference numerals, and description thereof will be omitted as appropriate.

[0112] like Figure 11 As shown, the human detection system 1 according to the second modification includes a sensor system 10B and a signal processing device 20 as the signal processing system 2 .

[0113] like Figure 11 As shown, the sensor system 10B includes a MIMO radio wave sensor 12. The radio wave sensor 12 has multiple (e.g., two) transmitting antennas and multiple (e.g., two) receiving antennas. Furthermore, the radio wave sensor 12 includes a sensor unit 121, a beam forming unit 122, a signal generating unit 123, and a communication unit 124.

[0114] The sensor unit 121 detects people in a plurality of different detection areas G1, G2, and G3 (for example, Figure 10 For example, the sensor unit 121 uses multiple transmitting antennas to output radio waves into the detection area G1 and the detection area G2, respectively, and uses multiple receiving antennas to receive radio waves reflected by objects in the detection area G1 and the objects in the detection area G1.

[0115] The beamforming unit 122 separates the received wave signal corresponding to the radio wave received by the sensor unit 121 into a first received wave signal corresponding to the radio wave reflected by an object in the detection area G1 and a second received wave signal corresponding to the radio wave reflected by an object in the detection area G2.

[0116] The signal generation unit 123 generates a first detection signal L1 based on a first oscillation signal, i.e., a first wave-receiving signal, corresponding to the radio waves output into the detection area G1. The signal generation unit 123 generates a second detection signal L2 based on a second oscillation signal, i.e., a second wave-receiving signal, corresponding to the radio waves output into the detection area G2. For example, the first detection signal L1 and the second detection signal L2 are Doppler signals containing an in-phase component and a quadrature component.

[0117] The communication unit 124 has a communication interface for communicating with the signal processing device 20. The communication unit 124 outputs (transmits) the first detection signal L1 and the second detection signal L2 generated by the signal generation unit 123 to the signal processing device 20.

[0118] When signal processing device 20 of Modification 2 receives first detection signal L1 and second detection signal L2 from sensor system 10B, it calculates a cross-correlation coefficient based on the received first detection signal L1 and second detection signal L2. Signal processing device 20 of Modification 2 uses the calculated cross-correlation coefficient and a predetermined threshold value TH1 to determine the presence of a person in space SP1.

[0119] (5.3) Modification 3

[0120] The waveform comparison unit 233 may also calculate multiple cross-correlation coefficients for each of a plurality of predetermined periods and extract the cross-correlation coefficient corresponding to the peak in the frequency distribution of the multiple cross-correlation coefficients as the maximum cross-correlation coefficient. Furthermore, the waveform comparison unit 233 uses a calculated value obtained from the multiple maximum cross-correlation coefficients extracted for each of the plurality of predetermined periods as the comparison result. In this case, the determination unit 234 determines the presence of a person in the space SP1 based on the calculated value.

[0121] Here, the calculated value is any one of an average value, a median value, a maximum value, and a minimum value of a plurality of maximum cross-correlation coefficients.

[0122] (5.4) Modification 4

[0123] The predetermined threshold value may also be based on a cross-correlation coefficient value corresponding to a peak in a frequency distribution obtained by combining a plurality of first benchmark cross-correlation coefficients and a plurality of second benchmark cross-correlation coefficients. The plurality of first benchmark cross-correlation coefficients are a plurality of benchmark cross-correlation coefficients within a predetermined period when only a first person (e.g., person u1) exists in space SP1. The plurality of second benchmark cross-correlation coefficients are a plurality of benchmark cross-correlation coefficients within a predetermined period when only a second person (e.g., person u2) exists in space SP1.

[0124] Here, a plurality of first reference cross-correlation coefficients are obtained based on the first waveform as the first bio-waveform estimated by the first waveform estimation unit 251 within a predetermined period when only the first person exists in the space SP1, and the second waveform as the second bio-waveform estimated by the second waveform estimation unit 252 within a predetermined period. Furthermore, a plurality of second reference cross-correlation coefficients are obtained based on the third waveform as the first bio-waveform estimated by the first waveform estimation unit 251 within a predetermined period when only the second person exists in the space SP1, and the fourth waveform as the second bio-waveform estimated by the second waveform estimation unit 252 within a predetermined period. That is, the waveform comparison unit 233 calculates a plurality of first reference cross-correlation coefficients within a predetermined period based on the first waveform and the second waveform. The waveform comparison unit 233 calculates a plurality of second reference cross-correlation coefficients within a predetermined period based on the third waveform and the fourth waveform.

[0125] (5.5) Modification 5

[0126] The display processing unit 235 may also display the determination result of the determination unit 234, the bio-waveform estimated by the first waveform estimation unit 251 (first bio-waveform), and the bio-waveform estimated by the second waveform estimation unit 252 (second bio-waveform) on an external terminal such as an information terminal having a display unit. Here, the information terminal is a smartphone, a tablet terminal, or the like.

[0127] (5.6) Modification 6

[0128] The determination unit 234 may also determine the presence of a person using the following equation 2.

[0129] [Number 2]

[0130]

[0131] Here, the parameter TH in Equation 2 is 12 is a parameter for setting the limit of amplitude suppression. In addition, parameter g is a parameter for setting the intensity of suppression. 12 is a variable representing the mutual correlation coefficient.

[0132] By using the above number 2, we can get Figure 12 Here, Figure 12 The horizontal axis represents XC 12 The vertical axis represents the value obtained according to number 2 (J prob ). Value (J prob ) represents the probability that there are two people in space SP1.

[0133] The determination unit 234 substitutes the cross-correlation coefficient, which is the comparison result of the waveform comparison unit 233, into the variable XC. 12 The obtained value (Jprob ), to determine the presence of people in space SP1. Specifically, if the value (J prob ) is 0.5 or more, the determination unit 234 determines that there are two people in the space SP1. prob ) is less than 0.5, the determination unit 234 determines that there is one person in the space SP1.

[0134] (Implementation Method 2)

[0135] The difference between the second embodiment and the first embodiment is that the bio-waveform is adjusted according to the determination result of the determination unit 234. The following description will focus on the difference. Components identical to those in the first embodiment are denoted by the same reference numerals, and their description will be omitted as appropriate.

[0136] (1) Structure

[0137] like Figure 13 As shown, the human detection system 1 according to the second embodiment includes a sensor system 10 and a signal processing device 20C as the signal processing system 2 .

[0138] like Figure 13 As shown, the signal processing device 20C includes a communication unit 21, a display unit 22, and a control unit 23C.

[0139] The signal processing device 20C includes a computer system having, for example, a processor and memory. The processor executes a program stored in the memory, thereby allowing the computer system to function as a control unit 23C. The program executed by the processor is pre-recorded in the computer system's memory here, but may also be recorded on a storage medium such as a memory card and provided, or provided via a telecommunication line such as the Internet.

[0140] like Figure 13 As shown, the control unit 23C includes a signal acquisition unit 231 , a waveform estimation unit 232 , a waveform comparison unit 233 , a determination unit 234 , a display processing unit 235 , and a waveform adjustment unit 236 .

[0141] The waveform adjustment unit 236 adjusts the biological waveform according to the determination result of the determination unit 234 .

[0142] If the determination unit 234 determines that a person is present in the space SP1, the waveform adjustment unit 236 calculates a first average amplitude of the first bio-waveform and a second average amplitude of the second bio-waveform. The waveform adjustment unit 236 adjusts the amplitude of the bio-waveform with the smaller average amplitude of the first or second bio-waveform by multiplying the amplitude by a suppression coefficient, while not adjusting the amplitude of the bio-waveform with the larger average amplitude of the first or second bio-waveform.

[0143] Specifically, the waveform adjustment unit 236 adjusts the amplitude of the biological waveform with the smaller average amplitude among the first biological waveform and the second biological waveform using the suppression coefficient corresponding to the value of the cross-correlation coefficient as the comparison result of the waveform comparison unit 233. For example, the waveform adjustment unit 236 uses the line segment P11 (see Figure 14 ), and determines a suppression coefficient corresponding to the value of the cross-correlation coefficient as the comparison result of the waveform comparison unit 233. The waveform adjustment unit 236 multiplies the amplitude of the biological waveform with the smaller average amplitude between the first biological waveform and the second biological waveform by the determined suppression coefficient.

[0144] When the determination unit 234 determines that two people exist in the space SP1 , the waveform adjustment unit 236 does not adjust the amplitudes of both the first biological waveform and the second biological waveform.

[0145] Here, the line segment P11 can be obtained using the following equation 3. The parameter TH in equation 3 is 12 is a parameter for setting the limit of amplitude suppression. In addition, parameter g is a parameter for setting the intensity of suppression. 12 is a variable representing the mutual correlation coefficient.

[0146] [Number 3]

[0147]

[0148] By using the number 3, when it is considered that one person exists in the space SP1, the amplitude of one waveform (the waveform with a smaller average amplitude) between the first and second biological waveforms can be adjusted (suppressed) by a suppression coefficient corresponding to the cross-correlation coefficient.

[0149] If the determination unit 234 determines that one person is present in the space SP1, the display processing unit 235 causes the display unit 22 to display the amplitude-adjusted bio-waveform of the first and second bio-waveforms and the non-amplitude-adjusted bio-waveform with the larger average amplitude. If the determination unit 234 determines that two people are present in the space SP1, the display processing unit 235 causes the display unit 22 to display the amplitude-unadjusted first and second bio-waveforms.

[0150] For example, the waveform estimation unit 232 estimates Figure 15In the case of the first bio-waveform W11 and the second bio-waveform W12 shown in A, the cross-correlation coefficient as the comparison result in the waveform comparison unit 233 is less than the specified value. As a result, the determination unit 234 determines that there are two people in the space SP1. In this case, the waveform adjustment unit 236 does not adjust the waveforms of both the first bio-waveform W11 and the second bio-waveform W12, but outputs the first bio-waveform W21 and the second bio-waveform W22. In other words, Figure 15 The first biological waveform W11 and the first biological waveform W21 shown in A are the same waveform. Figure 15 The second bio-waveform W12 and the second bio-waveform W22 shown in A are the same waveform. The display processing unit 235 causes the display unit 22 to display the first bio-waveform W21 and the second bio-waveform W22 output from the waveform adjustment unit 236 , that is, the first bio-waveform W11 and the second bio-waveform W12 .

[0151] In addition, the waveform estimation unit 232 estimates Figure 15 In the case of the first biological waveform W31 and the second biological waveform W32 shown in B, the mutual correlation coefficient as the comparison result in the waveform comparison unit 233 is greater than the specified value. As a result, the determination unit 234 determines that there is a person in the space SP1. In this case, the waveform adjustment unit 236 calculates the first average amplitude of the first biological waveform W31 and the second average amplitude of the second biological waveform W32. The waveform adjustment unit 236 uses the suppression coefficient corresponding to the value of the mutual correlation coefficient as the comparison result of the waveform comparison unit 233 to adjust the amplitude of the biological waveform with a smaller average amplitude in the first biological waveform and the second biological waveform. For example, when the second average amplitude is less than the first average amplitude, the waveform adjustment unit 236 uses the suppression coefficient to adjust the amplitude of the second biological waveform W32. The waveform adjustment unit 236 does not adjust the amplitude of the first biological waveform W31. The waveform adjustment unit 236 outputs the biological waveform with adjusted amplitude (here, the second biological waveform W42) and the biological waveform with unadjusted amplitude (here, the first biological waveform W41). That is, Figure 15 The first bio-waveform W31 and the first bio-waveform W41 shown in FIG. B are the same waveform. The display processing unit 235 causes the display unit 22 to display the first bio-waveform W41 and the second bio-waveform W42 output from the waveform adjustment unit 236 .

[0152] (2) Action

[0153] use Figure 16 Next, the operation of the signal processing device 20C will be described.

[0154] The signal acquisition unit 231 acquires signals corresponding to the plurality of detection areas G1 and G2 (see FIG. Figure 2) respectively corresponding to the plurality of detection signals (step S101). Specifically, the first signal acquisition unit 241 of the signal acquisition unit 231 acquires the first detection signal L1 output from the first radio wave sensor 11a. The second signal acquisition unit 242 of the signal acquisition unit 231 acquires the second detection signal L2 output from the second radio wave sensor 11b.

[0155] The waveform estimation unit 232 performs waveform estimation processing (step S102). Specifically, the first waveform estimation unit 251 of the waveform estimation unit 232 estimates the first bio-waveform based on the first detection signal L1 acquired by the first signal acquisition unit 241. The second waveform estimation unit 252 of the waveform estimation unit 232 estimates the second bio-waveform based on the second detection signal L2 acquired by the second signal acquisition unit 242.

[0156] The waveform comparison unit 233 performs waveform comparison processing (step S103). Specifically, the waveform comparison unit 233 compares the first bio-waveform with the second bio-waveform. More specifically, the waveform comparison unit 233 uses a cross-correlation function to calculate a plurality of cross-correlation coefficients for a plurality of bio-waveforms within a predetermined period.

[0157] The determination unit 234 uses the comparison result (comprehensive correlation coefficient) of the waveform comparison unit 233 to determine the presence of a person in the space SP1 (step S104). Here, the determination unit 234 uses the comparison result (comprehensive correlation coefficient) of the waveform comparison unit 233 to determine whether there are two people or one person in the space SP1. The determination unit 234 determines the presence of a person in the space SP1 based on the mutual correlation coefficient extracted as the comparison result by the waveform comparison unit 233. Specifically, when the mutual correlation coefficient as the comparison result is greater than a predetermined threshold value, the determination unit 234 determines that one person exists in the space SP1. When the mutual correlation coefficient as the comparison result is less than a predetermined threshold value, the determination unit 234 determines that two people exist in the space SP1.

[0158] If the determination unit 234 determines that two people exist in the space SP1 (Yes in step S104 ), the display processing unit 235 performs a first display process (step S105 ). The display processing unit 235 causes the display unit 22 to display the first and second bio-waveforms whose amplitudes have not been adjusted.

[0159] When the determination unit 234 determines that there are not two people in the space SP1, that is, when one person exists in the space SP1 (No in step S104), the waveform adjustment unit 236 calculates the first average amplitude of the first bio-waveform and the second average amplitude of the second bio-waveform (step S106).

[0160] The waveform adjustment unit 236 determines the suppression coefficient (step S107). For example, the waveform adjustment unit 236 uses the line segment P11 (see Figure 14 ) that is, the above-mentioned number 3, is used to determine the suppression coefficient corresponding to the value of the cross-correlation coefficient as the comparison result of the waveform comparison unit 233.

[0161] The waveform adjustment unit 236 determines whether the first average amplitude is equal to or greater than the second average amplitude based on the calculation result in step S106 (step S108 ).

[0162] If it is determined that the first average amplitude is greater than or equal to the second average amplitude ("YES" in step S108), the waveform adjustment unit 236 adjusts the amplitude of the second biometric waveform having the smaller average amplitude between the first and second biometric waveforms (step S109). Specifically, the waveform adjustment unit 236 adjusts the amplitude of the second biometric waveform by multiplying the amplitude of the second biometric waveform by the suppression coefficient.

[0163] If it is determined that the first average amplitude is not greater than the second average amplitude ("No" in step S108), the waveform adjustment unit 236 adjusts the amplitude of the first bio-waveform having the smaller average amplitude between the first and second bio-waveforms (step S110). Specifically, the waveform adjustment unit 236 adjusts the amplitude of the second bio-waveform by multiplying the amplitude of the first bio-waveform by the suppression coefficient determined in step S107.

[0164] The display processing unit 235 performs the second display process (step S111). The display processing unit 235 causes the display unit 22 to display, of the first and second bio-waveforms, the bio-waveform with amplitude adjustment and the bio-waveform without amplitude adjustment. Specifically, when step S109 is executed, the display processing unit 235 causes the display unit 22 to display the second bio-waveform with amplitude adjustment and the first bio-waveform without amplitude adjustment. Furthermore, when step S110 is executed, the display processing unit 235 causes the display unit 22 to display the first bio-waveform with amplitude adjustment and the second bio-waveform without amplitude adjustment.

[0165] (3) Advantages

[0166] In the second embodiment, similarly to the first embodiment, even when determining the presence of a person in a plurality of detection areas using the biological information of the person, it is possible to suppress a decrease in the accuracy of the determination.

[0167] Furthermore, the determination unit 234 can also perform determinations as shown in Table 2 below by comparing the average amplitudes of the plurality of biological waveforms.

[0168] [Table 2]

[0169]

[0170] For example, when the comparison result of the waveform comparison unit 233 is smaller than a predetermined threshold value and the difference between the first average amplitude and the second average amplitude is smaller than a predetermined value, the determination unit 234 determines that two people exist in the space SP1 .

[0171] If the comparison result of the waveform comparison unit 233 is greater than a predetermined threshold value and the difference between the first and second average amplitudes is greater than a predetermined value, the determination unit 234 determines that a person is present in space SP1. In this case, if the first average amplitude is greater than the second average amplitude, the determination unit 234 determines that a person is present in detection area G1. If the second average amplitude is greater than the first average amplitude, the determination unit 234 determines that a person is present in detection area G2.

[0172] Furthermore, when the comparison result of the waveform comparison unit 233 is above a predetermined threshold and the difference between the first average amplitude and the second average amplitude is smaller than a predetermined value, the determination unit determines that a person exists in the space SP1 so as to straddle the detection area G1 and the detection area G2.

[0173] As described above, the signal processing system 2 according to the second embodiment can determine the presence of a person with high accuracy even when the person exists so as to straddle the detection area G1 and the detection area G2.

[0174] (4) Modification

[0175] Modifications are listed below. The modifications described below can be applied in combination with the second embodiment as appropriate.

[0176] (4.1) Modification 1

[0177] The value obtained by equation 2 used in the sixth modification of the first embodiment (J prob ) as the suppression coefficient. Use Figure 17 The operation of the signal processing system 2 (signal processing device 20C) in the first modification of the second embodiment will be described.

[0178] The signal acquisition unit 231 acquires signals corresponding to the plurality of detection areas G1 and G2 (see FIG. Figure 2 ) respectively corresponding to the plurality of detection signals (step S201). Specifically, the first signal acquisition unit 241 of the signal acquisition unit 231 acquires the first detection signal L1 output from the first radio wave sensor 11a. The second signal acquisition unit 242 of the signal acquisition unit 231 acquires the second detection signal L2 output from the second radio wave sensor 11b.

[0179] The waveform estimation unit 232 performs waveform estimation processing (step S202). Specifically, the first waveform estimation unit 251 of the waveform estimation unit 232 estimates the first bio-waveform based on the first detection signal L1 acquired by the first signal acquisition unit 241. The second waveform estimation unit 252 of the waveform estimation unit 232 estimates the second bio-waveform based on the second detection signal L2 acquired by the second signal acquisition unit 242.

[0180] The waveform comparison unit 233 performs waveform comparison processing (step S203). Specifically, the waveform comparison unit 233 compares the first bio-waveform with the second bio-waveform. More specifically, the waveform comparison unit 233 uses a cross-correlation function to calculate a plurality of cross-correlation coefficients for a plurality of bio-waveforms within a predetermined period.

[0181] The determination unit 234 uses the comparison result (comprehensive correlation coefficient) of the waveform comparison unit 233 to determine the presence of a person in the space SP1 (step S204). Here, the determination unit 234 uses the comparison result (comprehensive correlation coefficient) of the waveform comparison unit 233 and equation 2 to calculate the suppression coefficient (J prob The determination unit 234 calculates the suppression coefficient (J prob ), to determine the presence of people in space SP1. For example, in the suppression coefficient (J prob ) is less than 0.5, the determination unit 234 determines that there is one person in the space SP1. prob ) is 0.5 or greater, the determination unit 234 determines that two people exist in the space SP1.

[0182] When the determination unit 234 determines that two people exist in the space SP1 ("Yes" in step S204), the waveform adjustment unit 236 performs the first adjustment process (step S205). Specifically, the waveform adjustment unit 236 multiplies both the first biometric waveform and the second biometric waveform by the suppression coefficient (J prob ) to adjust the amplitudes of both the first biological waveform and the second biological waveform.

[0183] The display processing unit 235 performs a first display process (step S206 ) and causes the display unit 22 to display the first and second bio-waveforms whose amplitudes have been adjusted by the first adjustment process.

[0184] When the determination unit 234 determines that there are not two people in the space SP1, that is, when one person exists in the space SP1 (No in step S204), the waveform adjustment unit 236 calculates the first average amplitude of the first bio-waveform and the second average amplitude of the second bio-waveform (step S207).

[0185] The waveform adjustment unit 236 determines whether the first average amplitude is equal to or greater than the second average amplitude based on the calculation result in step S207 (step S208 ).

[0186] If it is determined that the first average amplitude is greater than or equal to the second average amplitude ("Yes" in step S208), the waveform adjustment unit 236 performs the second adjustment process (step S209). Specifically, the waveform adjustment unit 236 multiplies the amplitude of the second biological waveform having the smaller average amplitude among the first biological waveform and the second biological waveform by the suppression coefficient (J). prob ) to adjust the amplitude of the second biological waveform. The waveform adjustment unit 236 multiplies the amplitude of the first biological waveform with the larger average amplitude among the first biological waveform and the second biological waveform by the value "1-suppression coefficient (J prob )” to adjust the amplitude of the first biological waveform.

[0187] If it is determined that the first average amplitude is not greater than the second average amplitude ("No" in step S208), the waveform adjustment unit 236 performs the third adjustment process (step S210). Specifically, the waveform adjustment unit 236 multiplies the amplitude of the first biological waveform having the smaller average amplitude of the first biological waveform and the second biological waveform by the suppression coefficient (J). prob ) to adjust the amplitude of the first biological waveform. The waveform adjustment unit 236 multiplies the amplitude of the second biological waveform with a larger average amplitude among the first biological waveform and the second biological waveform by a value of "1-suppression coefficient (J prob )” to adjust the amplitude of the second bio-waveform.

[0188] The display processing unit 235 performs the second display process (step S211). Specifically, when step S209 is executed, the display processing unit 235 causes the display unit 22 to display the image multiplied by the suppression coefficient (J prob ) and is multiplied by the value "1-inhibition coefficient (J prob )”. When step S210 is executed, the display processing unit 235 causes the display unit 22 to display the waveform multiplied by the suppression coefficient (J prob ) after the first biological waveform and is multiplied by the value "1-inhibition coefficient (J prob )” after the second biological waveform.

[0189] (4.2) Modification 2

[0190] The waveform adjustment unit 236 may determine the biological waveform whose amplitude is to be adjusted between the first biological waveform and the second biological waveform based on the amplitude of each of the plurality of Doppler signals L1 and L2 output from the sensor system 10 .

[0191] (4.3) Modification 3

[0192] Modifications 1 to 5 of the first embodiment can also be appropriately applied to the second embodiment.

[0193] (Other Modifications)

[0194] The above embodiment is only one of the various embodiments of the present disclosure. As long as the above embodiment can achieve the purpose of the present disclosure, various changes can be made according to the design, etc. In addition, the same function as the signal processing system 2 can also be achieved by a signal processing method, a computer program, or a non-transitory recording medium having a program recorded thereon. The signal processing method of the signal processing system 2 involved in one embodiment includes a signal acquisition step, a waveform estimation step, a waveform comparison step, and a determination step. In the signal acquisition step, a plurality of detection signals (for example, detection signals L1, L2) corresponding to the plurality of detection areas are acquired from the sensor systems 10, 10A, 10B provided in the space SP1 and used to detect people in a plurality of different detection areas G1, G2. In the waveform estimation step, a biological waveform related to the biological information of the person is estimated based on each of the plurality of detection signals. In the waveform comparison step, a plurality of biological waveforms corresponding to the plurality of detection signals are compared. In the determination step, the presence of a person in the space SP1 is determined based on the comparison result in the waveform comparison step. The program involved in one embodiment is a program for causing a computer system to function as the above-mentioned signal processing system 2 or the signal processing method of the signal processing system 2.

[0195] The signal processing system 2 or the signal processing method of the signal processing system 2 in the present disclosure includes a computer system. The computer system has a processor and a memory as hardware. The program recorded in the memory of the computer system is executed by the processor, thereby realizing the function of the signal processing system 2 or the signal processing method of the signal processing system 2 in the present disclosure. The program can be pre-recorded in the memory of the computer system or provided through an electrical communication line. In addition, the program can also be recorded on a non-transitory recording medium such as a memory card, an optical disc, a hard disk drive, etc. that can be read by the computer system. The processor of the computer system is composed of one or more electronic circuits including a semiconductor integrated circuit (IC) or a large-scale integrated circuit (LSI). The name of the integrated circuit such as IC or LSI mentioned here varies according to the degree of integration, including integrated circuits called system LSI, VLSI (Very Large Scale Integration) or ULSI (Ultra Large Scale Integration). Furthermore, as a processor, an FPGA (Field-Programmable Gate Array) that is programmed after LSI manufacturing, or a logic device that allows for reconfiguration of the internal LSI connections or circuit partitioning can also be used. Multiple electronic circuits can be integrated into a single chip or distributed across multiple chips. Multiple chips can be integrated into a single device or distributed across multiple devices.

[0196] Furthermore, it is not essential for signal processing system 2 to have multiple functions concentrated in a single housing. Components of signal processing system 2 may be dispersed across multiple housings. Furthermore, at least a portion of the functions of signal processing system 2, such as a portion of the functions of signal processing system 2, may be implemented via the cloud (cloud computing).

[0197] (Summarize)

[0198] As described above, the signal processing system (2) of the first embodiment includes a signal acquisition unit (231), a waveform estimation unit (232; 232A), a waveform comparison unit (233; 233A), and a determination unit (234; 234A). The signal acquisition unit (231) acquires a plurality of detection signals (e.g., detection signals L1, L2) corresponding to a plurality of detection areas (G1, G2) from a sensor system (10; 10A; 10B). The sensor system (10; 10A; 10B) is set in a space (SP1) and is used to detect people in a plurality of different detection areas (G1, G2). The waveform estimation unit (232; 232A) estimates a bio-waveform (e.g., a first bio-waveform and a second bio-waveform) related to the bio-information of the person based on each of the plurality of detection signals. The waveform estimation unit (232; 232A) compares the plurality of bio-waveforms corresponding to the plurality of detection signals. A determination unit (234; 234A) determines the presence of a person in a space (SP1) based on a comparison result of a waveform comparison unit (233; 233A).

[0199] According to this aspect, even when determining the presence of a person in a plurality of detection areas ( G1 , G2 ) using the biological information of the person, it is possible to suppress a decrease in the accuracy of the determination.

[0200] The signal processing system (2) of the second embodiment is that in the first embodiment, the waveform estimation unit (232; 232A) estimates a plurality of biological waveforms corresponding to the plurality of detection signals using a learning model for data estimation constructed by a recursive neural network.

[0201] According to this aspect, the accuracy of bio-waveform estimation can be improved by using a learning model constructed using a recursive neural network.

[0202] A third aspect of the signal processing system (2) is characterized in that, in the first aspect or the second aspect, the waveform comparison unit (233; 233A) calculates an evaluation index representing the similarity of a plurality of biological waveforms as a comparison result, and the determination unit (234; 234A) determines the presence of a person in the space (SP1) based on the evaluation index.

[0203] According to this aspect, since the presence of a person is determined using an evaluation index indicating the degree of similarity, a decrease in the accuracy of determination can be suppressed.

[0204] A signal processing system (2) according to a fourth aspect is characterized in that, in the third aspect, the evaluation index is a cross-correlation coefficient indicating a cross-correlation relationship between a plurality of biological waveforms within a predetermined period. A waveform comparison unit (233; 233A) calculates a plurality of cross-correlation coefficients for the plurality of biological waveforms within the predetermined period as comparison results using a cross-correlation function. A determination unit (234; 234A) determines the presence of a person in a space (SP1) based on the cross-correlation coefficients calculated by the waveform comparison unit (233; 233A).

[0205] According to this aspect, even when determining the presence of a person in a plurality of detection areas ( G1 , G2 ) using the biological information of the person, it is possible to suppress a decrease in the accuracy of the determination.

[0206] A fifth aspect of the signal processing system (2) is characterized in that, in the fourth aspect, a waveform comparison unit (233; 233A) calculates a plurality of cross-correlation coefficients within a predetermined period for each of a plurality of predetermined periods, extracts a cross-correlation coefficient corresponding to a peak value in a frequency distribution of the plurality of cross-correlation coefficients from the plurality of cross-correlation coefficients as a maximum cross-correlation coefficient, and uses a calculated value obtained based on the extracted plurality of maximum cross-correlation coefficients as the comparison result. A determination unit (234; 234A) determines the presence of a person in a space (SP1) based on the calculated value.

[0207] According to this aspect, even when determining the presence of a person in a plurality of detection areas ( G1 , G2 ) using the biological information of the person, it is possible to suppress a decrease in the accuracy of the determination.

[0208] The signal processing system (2) of the sixth aspect is the signal processing system of the fifth aspect, wherein the calculated value is any one of an average value, a median value, a maximum value, and a minimum value of a plurality of maximum cross-correlation coefficients.

[0209] According to this aspect, any one of the average value, median value, maximum value, and minimum value of a plurality of maximum cross-correlation coefficients can be used as the calculated value.

[0210] The signal processing system (2) of the seventh aspect is that, in any one of the fourth to sixth aspects, the plurality of detection signals include a first detection signal (L1) and a second detection signal (L2). A waveform estimation unit (232; 232A) estimates a first bio-waveform corresponding to the first detection signal (L1) and a second bio-waveform corresponding to the second detection signal (L2). A waveform comparison unit (233; 233A) calculates a plurality of cross-correlation coefficients between the first bio-waveform and the second bio-waveform within a predetermined period as a comparison result. A determination unit (234; 234A) determines whether one person or two people are present in the space (SP1) based on the comparison result and a predetermined threshold value.

[0211] According to this aspect, even when determining the presence of a person in a plurality of detection areas ( G1 , G2 ) using the biological information of the person, it is possible to suppress a decrease in the accuracy of the determination.

[0212] The signal processing system (2) of the eighth embodiment is characterized in that, in the seventh embodiment, the predetermined threshold value is a value of a reference cross-correlation coefficient corresponding to a peak value in a frequency distribution of the plurality of reference cross-correlation coefficients calculated using a first person's biological waveform and a second person's biological waveform within a predetermined period. The first person's biological waveform is a waveform estimated by a waveform estimation unit (232; 232A) when only a first person (person u1) exists in a space (SP1). The second person's biological waveform is a waveform estimated by a waveform estimation unit (232; 232A) when only a second person (person u2) exists in the space (SP1).

[0213] According to this aspect, a predetermined threshold value can be set according to the person to be detected, thereby improving the accuracy of determination.

[0214] The signal processing system (2) of the ninth embodiment is that, in the seventh embodiment, the waveform estimation unit (232; 232A) includes a first waveform estimation unit (251) for estimating a first biological waveform, and a second waveform estimation unit (252) for estimating a second biological waveform. The predetermined threshold value is based on a value of a reference cross-correlation coefficient corresponding to a peak value in a frequency distribution obtained by combining a plurality of first reference cross-correlation coefficients and a plurality of second reference cross-correlation coefficients. The plurality of first reference cross-correlation coefficients are a plurality of reference cross-correlation coefficients within a predetermined period when only a first person (person u1) exists in a space (SP1). The plurality of second reference cross-correlation coefficients are a plurality of reference cross-correlation coefficients within a predetermined period when only a second person (person u2) exists in a space (SP1). The plurality of first reference cross-correlation coefficients are obtained based on a first waveform estimated as a first biological waveform within a predetermined period by the first waveform estimation unit (251) and a second waveform estimated as a second biological waveform within a predetermined period by the second waveform estimation unit (252) when only the first person (person u1) exists in the space (SP1). The plurality of second reference mutual correlation coefficients are obtained based on a third waveform estimated by the first waveform estimation unit (251) as a first biological waveform within a prescribed period when only a second person (person u2) exists in the space (SP1) and a fourth waveform estimated by the second waveform estimation unit (252) as a second biological waveform within a prescribed period.

[0215] According to this aspect, a predetermined threshold value can be set according to the person to be detected, thereby improving the accuracy of determination.

[0216] The signal processing system (2) of the tenth embodiment is, in the seventh embodiment, further comprising a waveform adjustment unit (236) and a display processing unit (235). When the determination unit (234; 234A) determines that there is one person in the space (SP1), the waveform adjustment unit (236) calculates the first average amplitude of the first biological waveform and the second average amplitude of the second biological waveform. The waveform adjustment unit (236) adjusts the amplitude of the biological waveform with a smaller average amplitude among the first biological waveform and the second biological waveform by multiplying the suppression coefficient for suppressing the amplitude. The waveform adjustment unit (236) does not adjust the amplitude of the biological waveform with a larger average amplitude among the first biological waveform and the second biological waveform. When the determination unit (234; 234A) determines that there are two people in the space (SP1), the amplitude of both the first biological waveform and the second biological waveform is not adjusted. When the determination unit (234; 234A) determines that one person exists in the space (SP1), the display processing unit (235) causes the display unit (22) to display the amplitude-adjusted bio-waveform of the first and second bio-waveforms and the non-amplitude-adjusted bio-waveform with the larger average amplitude. When the determination unit (234; 234A) determines that two people exist in the space (SP1), the display processing unit (235) causes the display unit (22) to display the amplitude-unadjusted first and second bio-waveforms.

[0217] According to this aspect, it is possible to clearly distinguish between an erroneously detected biological waveform and a normally detected biological waveform. Therefore, when visually confirming each biological waveform, the possibility of misidentification can be reduced.

[0218] The signal processing system (2) of the eleventh aspect is any one of the first to tenth aspects, wherein the biological waveform is a human breathing waveform.

[0219] According to this aspect, the presence of a person in the space (SP1) can be determined based on the person's breathing.

[0220] A twelfth embodiment of a human detection system (1) comprises: a signal processing system (2) according to any one of the first to eleventh embodiments; and a sensor system (10; 10A; 10B) for detecting a human in a space (SP1).

[0221] According to this aspect, even when determining the presence of a person in a plurality of detection areas ( G1 , G2 ) using the biological information of the person, it is possible to suppress a decrease in the accuracy of the determination.

[0222] The signal processing method of the thirteenth embodiment includes a signal acquisition step, a waveform estimation step, a waveform comparison step, and a determination step. In the signal acquisition step, a plurality of detection signals (e.g., detection signals L1, L2) corresponding to the plurality of detection areas (G1, G2) are acquired from a sensor system (10; 10A; 10B) disposed in a space (SP1) and used to detect people in a plurality of different detection areas (G1, G2). In the waveform estimation step, a biological waveform related to biological information of the person is estimated based on each of the plurality of detection signals. In the waveform comparison step, a plurality of biological waveforms corresponding to the plurality of detection signals are compared. In the determination step, the presence of a person in the space (SP1) is determined based on the comparison result in the waveform comparison step.

[0223] According to this aspect, even when determining the presence of a person in a plurality of detection areas ( G1 , G2 ) using the biological information of the person, it is possible to suppress a decrease in the accuracy of the determination.

[0224] The program according to the fourteenth aspect is a program for causing a computer system to execute the signal processing method according to the thirteenth aspect.

[0225] According to this aspect, even when determining the presence of a person in a plurality of detection areas ( G1 , G2 ) using the biological information of the person, it is possible to suppress a decrease in the accuracy of the determination.

[0226] Description of Reference Numerals

[0227] 1: Human detection system; 2: Signal processing system; 10, 10A, 10B: Sensor system; 20, 20A, 20C: Signal processing device; 22: Display unit; 232, 232A: Waveform estimation unit; 233, 233A: Waveform comparison unit; 234, 234A: Determination unit; 235: Display processing unit; 236: Waveform adjustment unit; 251: First waveform estimation unit; 252: Second waveform estimation unit; 253: Third waveform estimation unit; G1, G 2: detection area; G3: detection area; L1: detection signal (first detection signal, Doppler signal); L2: detection signal (second detection signal, Doppler signal); L3: detection signal (third detection signal, Doppler signal); SP1: space; u1, u2, u3: people; W1, W11, W21, W31, W41: biological waveform (first biological waveform); W2, W12, W22, W32, W42: biological waveform (second biological waveform).

Claims

1. A signal processing system comprising: a signal acquisition unit for acquiring a plurality of detection signals corresponding to the plurality of detection areas, respectively, from a sensor system provided in the space and configured to detect a person in a plurality of mutually different detection areas; a waveform estimation unit that estimates a biological waveform related to biological information of a person based on each of the plurality of detection signals; a waveform comparison unit for comparing a plurality of biological waveforms corresponding to the plurality of detection signals; as well as A determination unit determines the presence of a person in the space based on the comparison result of the waveform comparison unit.

2. The signal processing system according to claim 1, wherein The waveform estimation unit estimates the plurality of biological waveforms corresponding to the plurality of detection signals, respectively, using a learning model for data estimation constructed using a recursive neural network.

3. The signal processing system according to claim 1 or 2, wherein: The waveform comparison unit calculates an evaluation index indicating the similarity of the plurality of biological waveforms as the comparison result. The determination unit determines the presence of a person in the space based on the evaluation index.

4. The signal processing system according to claim 3, wherein: The evaluation index is a cross-correlation coefficient indicating a cross-correlation relationship between a plurality of the biological waveforms within a predetermined period. The waveform comparison unit calculates a plurality of the cross-correlation coefficients for the plurality of the biological waveforms within the predetermined period as the comparison results using a cross-correlation function. The determination unit determines the presence of a person in the space based on the cross-correlation coefficient calculated by the waveform comparison unit.

5. The signal processing system according to claim 4, wherein: The waveform comparison unit calculates a plurality of cross-correlation coefficients within each of the plurality of predetermined periods, extracts a cross-correlation coefficient corresponding to a peak value in a frequency distribution of the plurality of cross-correlation coefficients from the plurality of cross-correlation coefficients as a maximum cross-correlation coefficient, and uses a calculated value obtained based on the extracted plurality of maximum cross-correlation coefficients as the comparison result. The determination unit determines the presence of a person in the space based on the calculated value. The signal processing system according to claim 5 , wherein: The calculated value is any one of an average value, a median value, a maximum value, and a minimum value of the plurality of maximum cross-correlation coefficients.

7. The signal processing system according to any one of claims 4 to 6, wherein: The plurality of detection signals include a first detection signal and a second detection signal, The waveform estimation unit estimates a first biological waveform corresponding to the first detection signal and a second biological waveform corresponding to the second detection signal. The waveform comparison section calculates a plurality of the cross-correlation coefficients between the first biological waveform and the second biological waveform within the predetermined period as the comparison result. The determination unit determines whether one person or two people exist in the space based on the comparison result and a predetermined threshold value.

8. The signal processing system according to claim 7, wherein: The prescribed threshold value is a value of a benchmark cross-correlation coefficient corresponding to a peak in the frequency distribution of a plurality of benchmark cross-correlation coefficients calculated using a first person's biological waveform and a second person's biological waveform within the prescribed period, wherein the first person's biological waveform is a biological waveform estimated by the waveform estimation unit when only the first person exists in the space, and the second person's biological waveform is a biological waveform estimated by the waveform estimation unit when only the second person exists in the space.

9. The signal processing system according to claim 7, wherein: The waveform estimation section includes a first waveform estimation section that estimates the first biological waveform and a second waveform estimation section that estimates the second biological waveform. The prescribed threshold value is based on a value of a reference cross-correlation coefficient corresponding to a peak in a frequency distribution obtained by combining a plurality of first reference cross-correlation coefficients and a plurality of second reference cross-correlation coefficients, wherein the plurality of first reference cross-correlation coefficients are a plurality of reference cross-correlation coefficients within the prescribed period when only the first person exists in the space, and the plurality of second reference cross-correlation coefficients are a plurality of reference cross-correlation coefficients within the prescribed period when only the second person exists in the space. The plurality of first reference cross-correlation coefficients are obtained based on a first waveform estimated by the first waveform estimation unit as the first biometric waveform within the predetermined period and a second waveform estimated by the second waveform estimation unit as the second biometric waveform within the predetermined period when only the first person exists in the space. The multiple second benchmark mutual correlation coefficients are obtained based on the third waveform of the first biological waveform within the specified period estimated by the first waveform estimation unit when only the second person exists in the space, and the fourth waveform of the second biological waveform within the specified period estimated by the second waveform estimation unit.

10. The signal processing system according to claim 7, wherein: It also has a waveform adjustment unit and a display processing unit. Wherein, when the determination unit determines that there is a person in the space, the waveform adjustment unit calculates the first average amplitude of the first bio-waveform and the second average amplitude of the second bio-waveform, and adjusts the amplitude of the bio-waveform with a smaller average amplitude between the first bio-waveform and the second bio-waveform by multiplying the suppression coefficient for suppressing the amplitude, while not adjusting the amplitude of the bio-waveform with a larger average amplitude between the first bio-waveform and the second bio-waveform. When the determination unit determines that two people are present in the space, the waveform adjustment unit does not adjust the amplitudes of both the first bio-waveform and the second bio-waveform. When the determination unit determines that a person exists in the space, the display processing unit causes the display unit to display the amplitude-adjusted bio-waveform of the first bio-waveform and the second bio-waveform, and the bio-waveform with the larger average amplitude that has not been amplitude-adjusted of the first bio-waveform and the second bio-waveform. When the determination unit determines that two persons are present in the space, the display processing unit causes a display unit to display the first bio-waveform and the second bio-waveform whose amplitudes have not been adjusted.

11. The signal processing system according to any one of claims 1 to 10, wherein: The biological waveform is a human breathing waveform.

12. A human detection system comprising: The signal processing system according to any one of claims 1 to 11; and A sensor system is provided for detecting persons in the space.

13. A signal processing method, comprising: a signal acquisition step of acquiring, from a sensor system disposed in the space and configured to detect a person in a plurality of different detection areas, a plurality of detection signals corresponding to the plurality of detection areas; a waveform estimating step of estimating a biological waveform related to biological information of a person based on each of the plurality of detection signals; a waveform comparison step of comparing the plurality of biological waveforms corresponding to the plurality of detection signals; as well as The determination step determines the presence of a person in the space based on the comparison result in the waveform comparison step.

14. A program for causing a computer system to execute the signal processing method according to claim 13.

Images