Human detection system, human detection device, human detection method, and program

Abstract

To provide a person detection system, a person detection device, and a program capable of precisely detecting a person by performing presence / absence determination of a person considering characteristics of multiple kinds of person detection sensors.SOLUTION: An individual determination part 103 determines presence or absence of a person in an object space for each of multiple kinds of person detection sensors 210 on the basis of information acquired by the multiple kinds of person detection sensors 210 that acquire information for determining presence or absence of the person in the object space and acquires different information and acquires an individual determination result for showing a determined result. A reliability calculation part 104 calculates reliability for showing reliability of the individual determination result on the basis of characteristics that the person detection sensors 210 have for each of the multiple kinds of person detection sensors. A total determination part 105 determines presence or absence of the person in the object space on the basis of multiple pieces of reliability calculated for each of the multiple kinds of person detection sensors 210 and acquires a total determination result for showing a total determined result.SELECTED DRAWING: Figure 3

Description

Technical Field

[0001] The present disclosure relates to a human detection system, a human detection device, a human detection method, and a program.

Background Art

[0002] There is known a human detection system that installs a human presence sensor indoors and determines the presence or absence of a person indoors using information obtained from the human presence sensor. Such a human detection system is applied to various purposes, such as a monitoring service for the elderly family members to remotely monitor the condition of the residents, and a control service that automatically performs energy-saving control of equipment such as air conditioners and lighting.

[0003] Regarding human detection systems, various techniques using human presence sensors have been proposed. For example, the human detection system disclosed in Patent Document 1 uses an infrared sensor as a human presence sensor, and determines the presence or absence of a person in the target space by analyzing a thermal image obtained by the infrared sensor imaging the target space. Then, the human detection system disclosed in Patent Document 1 further improves the detection accuracy of presence or absence by using information of a system that manages entry and exit to the target space using a card reader.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] On the other hand, in recent years, with the advancement of IoT (Internet of Things) technology, a wide variety of sensors are being installed indoors, and in some cases, multiple types of motion sensors are installed. In this situation, there is a need to improve the accuracy of detecting the presence or absence of people by combining the information acquired by each motion sensor. However, each motion sensor has its own advantages and disadvantages in terms of detecting the presence or absence of people, and in order to improve the accuracy of detecting the presence or absence of people, it is necessary to take into account the characteristics of each sensor, including its own advantages and disadvantages.

[0006] This disclosure is made in view of the above circumstances and aims to provide a human detection system, human detection device, human detection method, and program that enable highly accurate human detection by determining the presence or absence of a person while considering the characteristics of each of multiple types of human presence sensors. [Means for solving the problem]

[0007] To achieve the above objectives, the human detection system relating to this disclosure is A motion sensor that acquires information for determining the presence or absence of a person in a target space, comprising multiple types of motion sensors that acquire different information, A collection means for collecting information acquired by the aforementioned multiple types of human presence sensors, For each of the aforementioned multiple types of human presence sensors, an individual determination means is provided to determine whether or not there is a person in the target space based on the collected information and to acquire an individual determination result indicating the determination result. For each of the aforementioned multiple types of human presence sensors, a reliability calculation means calculates a reliability score indicating the reliability of the individual judgment result based on the characteristics of the human presence sensor, The system includes a comprehensive determination means that determines the presence or absence of a person in the target space based on multiple confidence levels calculated for each of the multiple types of human presence sensors, and obtains a comprehensive determination result indicating the result of the determination. picture, The aforementioned reliability calculation means is A presence confidence calculation means calculates a presence confidence level indicating the reliability of the presence determination that a person is present in the target space, for each of the individual determination results obtained for each of the multiple types of human presence sensors, The system includes an absence confidence calculation means that calculates an absence confidence level indicating the reliability of the absence determination that no person is present in the target space, for each of the individual determination results obtained for each of the multiple types of human presence sensors, The comprehensive determination means obtains the comprehensive determination result by comparing the sum of the presence confidence scores calculated for each of the individual determination results obtained for each of the multiple types of human presence sensors with the sum of the absence confidence scores calculated for each of the individual determination results obtained for each of the multiple types of human presence sensors, The aforementioned multiple types of human presence sensors include a pyroelectric sensor that detects changes in the amount of infrared radiation emitted by an object in the target space, an infrared sensor that acquires the amount of infrared radiation emitted by an object in the target space as a thermal image, and a CO2 sensor that measures the concentration of carbon dioxide in the target space. The system further includes a first open / close sensor that detects the opening and closing of a window installed in the aforementioned target space, The collection means collects information indicating the opening and closing of the window from the first opening / closing sensor, When the absence reliability calculation means determines that the window is open based on information indicating whether the window is open or closed, it calculates a value indicating low reliability of the absence determination as the absence reliability of the CO2 sensor. 。 [Effect of the Invention]

[0008] According to the present disclosure, it is possible to provide a human detection system, a human detection device, a human detection method, and a program that enable highly accurate human detection by performing presence / absence determination of a person in consideration of the characteristics of a plurality of types of human sensors. [Brief Description of the Drawings]

[0009] [Figure 1] Block diagram of a human detection system and a facility equipment control system according to an embodiment [Figure 2] Block diagram showing the hardware configuration of a human detection device according to an embodiment [Figure 3] Block diagram showing the functional configuration of a human detection device according to an embodiment [Figure 4] Diagram for explaining an area information table according to an embodiment [Figure 5] Flowchart showing control processing executed by a facility equipment control system according to an embodiment [Figure 6] Flowchart showing human detection processing executed by a human detection device according to an embodiment [Modes for Carrying Out the Invention]

[0010] (Embodiment) The human detection system according to the embodiment is a system that determines the presence or absence of a person in a target space by using information acquired by sensors installed in the target space.

[0011] As shown in FIG. 1, the human detection system 1 includes a human detection device 100 and a sensor group 200 installed in the target space. The human detection system 1 is also included in the facility equipment control system 2. The facility equipment control system 2 includes the human detection system 1, facility equipment 300 installed in the target space, and a facility equipment control device 400 that controls the facility equipment 300. The human detection device 100, the sensor group 200, the facility equipment 300, and the facility equipment control device 400 are communicably connected via a network 500.

[0012] The determination result of the presence or absence of a person detected in the human detection system 1 is used to control the facility equipment 300 installed in the target space. Here, the target space is the space for determining the presence or absence of a person, and it is an indoor space. The target space is not limited to a space such as a room partitioned by walls, partitions, etc., but also includes an unpartitioned space. For example, the target space is a section of space in a conference room where one air conditioner can perform air conditioning control for the space.

[0013] The human detection device 100 collects information acquired by the sensors from the sensors included in the sensor group 200, and determines the presence or absence of a person in the target space based on the collected information.

[0014] The sensor group 200 is a sensor that detects the state of the target space and includes a plurality of types of sensors that acquire different information. Hereinafter, the information acquired by the sensors included in the sensor group 200 is referred to as "sensing information". The sensor group 200 includes a human presence sensor 210 that acquires information for determining the presence or absence of a person in the target space. The sensor group 200 includes, for example, a pyroelectric sensor 201, an infrared sensor 202, a CO2 sensor 203, a first opening / closing sensor 204, a second opening / closing sensor 205, a temperature sensor 206, and a humidity sensor 207. Among these, the human presence sensor 210 is the pyroelectric sensor 201, the infrared sensor 202, and the CO2 sensor 203. The pyroelectric sensor 201, the infrared sensor 202, and the CO2 sensor 203 are installed in the target space at least one or more. Each sensor of the sensor group 200 has a wireless communication function.

[0015] The pyroelectric sensor 201 is a sensor that detects changes in the amount of infrared radiation emitted by an object in a target space. The amount of infrared radiation emitted by an object depends on the surface temperature of the object, and the observed amount of infrared radiation changes when the object moves. The pyroelectric sensor 201 detects changes in the amount of infrared radiation caused by the movement of an object. For example, when the pyroelectric sensor 201 detects a change in the amount of infrared radiation that exceeds a predetermined value, it transmits information indicating that a change has been detected as sensing information to the human detection device 100. Since the pyroelectric sensor 201 is a sensor that detects changes in the amount of infrared radiation, there is a problem that it cannot detect a person if the person remains stationary, such as when sleeping. In addition, the pyroelectric sensor 201 has a problem that it is prone to false detection in environments exposed to sunlight.

[0016] The infrared sensor 202 is a sensor that acquires the amount of infrared radiation emitted by an object in a target space as a thermal image. For example, the infrared sensor 202 takes a thermal image of the target space every minute and transmits the captured thermal image as sensing information to the human detection device 100. The infrared sensor 202 has a problem in that it cannot detect the amount of infrared radiation emitted by an object if there is an obstacle between the infrared sensor 202 and the object, so it cannot detect a person when an obstacle is present. In addition, the infrared sensor 202 also has a problem in that it detects the amount of infrared radiation from heat sources other than people, such as a display, so it may make false detections.

[0017] The CO2 sensor 203 is a sensor that measures the concentration of carbon dioxide in a target space. For example, the CO2 sensor 203 acquires the carbon dioxide concentration value every minute and transmits the acquired value as sensing information to the human detection device 100. In an environment with open windows and sufficient ventilation, the CO2 concentration value does not rise easily, so the CO2 sensor 203 has the problem of not being able to detect people in a well-ventilated environment. Also, if the target space is large, the CO2 concentration value does not rise easily, so the CO2 sensor 203 has the problem of not being able to detect people in a large target space.

[0018] The first open / close sensor 204 is a sensor that detects the opening and closing of a window installed in the target space. When the first open / close sensor 204 detects the opening and closing of a window, it transmits information indicating the opening and closing of the window as sensing information to the human detection device 100.

[0019] The second opening / closing sensor 205 is a sensor that detects the opening and closing of blinds, curtains, or other shading objects that block sunlight and are installed on windows in the target space. Here, the fact that the shading object is open indicates that sunlight is not blocked from entering the target space. When the second opening / closing sensor 205 detects the opening or closing of the shading object, it transmits information indicating the opening or closing of the shading object as sensing information to the human detection device 100.

[0020] The temperature sensor 206 is a sensor that measures the temperature of the target space. The temperature sensor 206 acquires a temperature value, for example, every minute, and transmits the acquired value as sensing information to the equipment control device 400.

[0021] The humidity sensor 207 is a sensor that measures the humidity of the target space. The humidity sensor 207 acquires the humidity value, for example, every minute, and transmits the acquired value as sensing information to the equipment control device 400.

[0022] Equipment 300 is an electrical device installed in the target space. Examples of equipment 300 include air conditioners, lighting fixtures, ventilation systems, etc. Equipment 300 operates according to instructions from equipment control device 400.

[0023] The equipment control device 400 controls the equipment 300 based on information acquired from the human detection device 100 and sensing information acquired from each sensor of the sensor group 200. The equipment control device 400 is, for example, a system controller.

[0024] Network 500 is a wireless or wired communication network, such as the Internet, intranet, extranet, LAN (Local Area Network), VPN (Virtual Private Network), telephone network, etc.

[0025] Next, the hardware configuration of the human detection device 100 will be described with reference to Figure 2.

[0026] The human detection device 100 includes a processor 11 that performs various processes, a main memory unit 12 used as a workspace for the processor 11, an auxiliary memory unit 13 that stores various data used in the processing of the processor 11, a communication unit 14 for communicating with external devices, an input unit 15 that acquires input information, an output unit 16 that presents various information, and an RTC (Real Time Clock) 17 for timing. The main memory unit 12, auxiliary memory unit 13, communication unit 14, input unit 15, output unit 16, and RTC 17 are all connected to the processor 11 via a bus 18.

[0027] The processor 11 includes a CPU (Central Processing Unit). The processor 11 realizes various functions of the human detection device 100 by executing programs stored in the auxiliary storage unit 13.

[0028] The main memory unit 12 includes RAM (Random Access Memory). Programs are loaded into the main memory unit 12 from the auxiliary memory unit 13. The main memory unit 12 is then used as a workspace for the processor 11.

[0029] The auxiliary storage unit 13 includes non-volatile memory, such as EEPROM (Electrically Erasable Programmable Read-Only Memory). In addition to the program, the auxiliary storage unit 13 stores various data used in the processing of the processor 11. The auxiliary storage unit 13 supplies data to be used by the processor 11 according to the instructions of the processor 11, and stores the data supplied by the processor 11.

[0030] The communication unit 14 includes a network interface circuit for communicating with an external device. The communication unit 14 receives a signal from the external device and outputs the data indicated by this signal to the processor 11. The communication unit 14 also transmits a signal indicating the data output from the processor 11 to the external device.

[0031] The input unit 15 includes input devices such as input keys and pointing devices. The input unit 15 acquires information entered by the user of the human detection device 100 and notifies the processor 11 of the acquired information.

[0032] The output unit 16 includes output devices such as an LCD (Liquid Crystal Display) and a speaker. The output unit 16 may also form a touchscreen integrated with the pointing device that constitutes the input unit 15. The output unit 16 presents various information to the user according to instructions from the processor 11.

[0033] The RTC17 is a timing device equipped with an oscillation circuit using a crystal oscillator. The RTC17, for example, has a built-in battery and continues timing even when the power to the human detection device 100 is turned off.

[0034] Furthermore, the equipment control device 400 has the same hardware configuration as the human detection device 100.

[0035] Next, with reference to Figure 3, the functions of the human detection device 100 included in the human detection system 1 will be described.

[0036] Functionally, the human detection device 100 includes an area information storage unit 101 that stores information about the target space, a collection unit 102 that collects sensing information acquired by multiple types of human presence sensors 210, an individual determination unit 103 that determines the presence or absence of a person in the target space based on the sensing information for each human presence sensor 210, a reliability calculation unit 104 that calculates a reliability level for each of the presence or absence determination results of the human presence sensors 210, and an overall determination unit 105 that determines the presence or absence based on multiple reliability levels calculated for each of the determination results of the human presence sensors 210.

[0037] The area information storage unit 101 stores information about the target space. Hereinafter, the target space will be referred to as an "area". The human detection system 1 determines the presence or absence of people in N (where N is a natural number greater than or equal to 1) areas. The area information storage unit 101 is implemented by the auxiliary storage unit 13.

[0038] Figure 4 shows an example of an area information table. The area information table in Figure 4 registers the area ID for identifying the area, the equipment ID of the equipment installed in the area, the sensor ID of the sensor installed in the area, the area area, and the absence confidence level, which will be described later, in association with each other. For example, the first record in the area information table in Figure 4 shows that the area with area ID "Area 1" is equipped with an air conditioner with air conditioner ID "0x0010", lighting with lighting ID "0x0020", a temperature sensor with temperature sensor ID "0x0100", a humidity sensor with humidity sensor ID "0x0110", a pyroelectric sensor with humidity sensor ID "0x0120", an infrared sensor with infrared sensor ID "0x0130", a CO2 sensor with CO2 sensor ID "0x0140", a first on / off sensor with first on / off sensor ID "0x0150", and a second on / off sensor with second on / off sensor ID "0x0160", and the area area of ​​area ID "Area 1" is "100[m 2 This indicates that the absence confidence level for the infrared sensor is "0.8" and the absence confidence level for the CO2 sensor is "0.5".

[0039] The information included in the area information table in Figure 4 are values ​​set by the administrator of the human detection system 1 or the equipment control system 2.

[0040] The data collection unit 102 collects information acquired by multiple types of human presence sensors 210. The data collection unit 102 is realized through the cooperation of the processor 11 and the communication unit 14. Note that the data collection unit 102 is just one example of a data collection method.

[0041] For example, the collection unit 102 periodically collects sensing information from each sensor included in the sensor group 200. Here, "periodically collecting" means that the collection unit 102 repeatedly collects sensing information, and the collection interval is not limited to a constant interval. The interval is arbitrarily determined by the administrator of the human detection system 1. The interval may be set according to a predetermined rule, or it may be set to an irregular value. The collection unit 102 stores the collected sensing information in the auxiliary storage unit 13.

[0042] Specifically, when the collection unit 102 receives information from the pyroelectric sensor 201 indicating that a change has been detected, it associates the time of reception with the information indicating that a change has been detected and stores it in the auxiliary storage unit 13. Also, when the collection unit 102 receives, for example, a thermal image from the infrared sensor 202 every minute, it associates the time of reception with the thermal image and stores it in the auxiliary storage unit 13. Also, when the collection unit 102 receives, for example, a CO2 concentration value from the CO2 sensor 203 every minute, it associates the time of reception with the CO2 concentration value and stores it in the auxiliary storage unit 13. Also, when the collection unit 102 receives information from the first open / close sensor 204 indicating the opening or closing of a window, it associates the time of reception with the information indicating the opening or closing of a window and stores it in the auxiliary storage unit 13. Furthermore, when the collection unit 102 receives information indicating the opening or closing of the shielding object from the second opening / closing sensor 205, it associates the time of receipt with the information indicating the opening or closing of the shielding object and stores it in the auxiliary storage unit 13.

[0043] The individual determination unit 103 determines the presence or absence of a person in the target space based on the information collected for each of the multiple types of human presence sensors 210, and obtains an individual determination result indicating the determination result. The individual determination unit 103 is implemented by the processor 11. Note that the individual determination unit 103 is an example of an individual determination means.

[0044] For example, the individual determination unit 103 determines the presence or absence of a person in area i (where i is 1 to N) based on sensing information collected from the pyroelectric sensor 201. Specifically, the individual determination unit 103 refers to the auxiliary storage unit 13 to obtain the time when information indicating that a change has been detected was received, and if the current time is within a predetermined time (for example, 10 minutes) from the time obtained, it determines that a person is present in area i where the change was detected. Hereinafter, the determination that a person is present in the target space (area) will be referred to as "presence determination," and the determination that a person is not present in the target space (area) will be referred to as "absence determination." For example, if the individual determination unit 103 determines that a person is present in area i based on the sensing information from the pyroelectric sensor 201, it obtains the presence determination for area i as the individual determination result of the pyroelectric sensor 201. The predetermined time is a value arbitrarily set by the administrator of the person detection system 1.

[0045] Furthermore, the individual determination unit 103 determines whether or not a person is present in area i based on sensing information collected from the infrared sensor 202. Specifically, the individual determination unit 103 first determines whether the most recently captured thermal image of area i contains an area with an infrared radiation amount equal to or greater than a predetermined value and an area equal to or greater than a predetermined value. Hereinafter, an area with an infrared radiation amount equal to or greater than a predetermined value and an area equal to or greater than a predetermined value will be referred to as a "person candidate area". Next, the individual determination unit 103 compares the thermal image of area i containing the person candidate area with a thermal image of area i taken over a predetermined period of time in the past (for example, the past 10 minutes) to determine whether or not the person candidate area has moved. If the person candidate area has not moved, the individual determination unit 103 considers the person candidate area to be a stationary object that emits heat, such as a display, and determines that it is not a person area. On the other hand, if the person candidate area has moved, the individual determination unit 103 considers that area to be a "person area" where a person is present. The individual determination unit 103 determines that a person is present in the area where the thermal image was captured when it detects one or more human areas in the thermal image. For example, if the individual determination unit 103 determines that a person is present in area i based on sensing information from the infrared sensor 202, it obtains the presence determination for area i as the individual determination result of the infrared sensor 202. The predetermined infrared amount value and predetermined area are values ​​arbitrarily set by the administrator of the human detection system 1.

[0046] Furthermore, the individual determination unit 103 determines whether or not a person is present in area i based on sensing information collected from the CO2 sensor 203. Specifically, the individual determination unit 103 determines that a person is present in area i if the most recently measured CO2 concentration value in area i is above a predetermined threshold. For example, if the individual determination unit 103 determines that a person is present in area i, it obtains the presence determination in area i as the individual determination result of the CO2 sensor 203. The threshold is a value set considering the size of the area and is a value that can be arbitrarily set by the administrator of the human detection system 1.

[0047] The reliability calculation unit 104 calculates a reliability score for each of the multiple types of human presence sensors 210, based on the characteristics of the human presence sensor 210, indicating the reliability of the individual judgment result. The reliability calculation unit 104 is implemented by the processor 11. Note that the reliability calculation unit 104 is just one example of a reliability calculation means.

[0048] The characteristics of a sensor refer to its advantages and disadvantages, or strengths and weaknesses. For example, the pyroelectric sensor 201 detects changes in the amount of infrared radiation, so it can detect a person when they are moving, but it cannot detect a person when they are stationary. The pyroelectric sensor 201 also has the characteristic of being prone to false detections in environments with sunlight. The infrared sensor 202 can detect a person when they are stationary, but it also has the characteristic of detecting stationary objects and may fail to detect objects if there are obstacles. In addition, since people are generally the source of CO2 emissions in an area, if the CO2 sensor 203 measures a CO2 concentration above a predetermined threshold, it can be determined with a high probability that a person is present. However, it has the characteristic that it is difficult to detect people when there is ventilation or when the area is large.

[0049] Here, the reliability calculation unit 104 calculates both the reliability of the presence determination and the reliability of the absence determination for each individual determination result obtained for each human presence sensor 210. That is, even if the individual determination result is a presence determination, the reliability calculation unit 104 calculates not only the reliability of the presence determination but also the reliability of the absence determination. Hereinafter, the reliability of the presence determination will be referred to as "presence reliability," and the reliability of the absence determination will be referred to as "absence reliability." The presence reliability takes a value from 0 to 1, with a higher value indicating higher reliability of the presence determination. Similarly, the absence reliability takes a value from 0 to 1, with a higher value indicating higher reliability of the absence determination.

[0050] As shown in Figure 3, the reliability calculation unit 104 includes an presence reliability calculation unit 104-1 and an absence reliability calculation unit 104-2. The presence reliability calculation unit 104-1 calculates the presence reliability for each of the individual judgment results acquired for each of the multiple types of human presence sensors 210. The absence reliability calculation unit 104-2 also calculates the absence reliability for each of the individual judgment results acquired for each of the multiple types of human presence sensors 210. The presence reliability calculation unit 104-1 and the absence reliability calculation unit 104-2 are implemented by the processor 11. Note that the presence reliability calculation unit 104-1 and the absence reliability calculation unit 104-2 are examples of presence reliability calculation means and absence reliability calculation means, respectively.

[0051] For example, if the individual determination result of the pyroelectric sensor 201 is "Present", the presence reliability calculation unit 104-1 calculates the presence reliability of the pyroelectric sensor 201 using the following formula 1. On the other hand, if the individual determination result of the pyroelectric sensor 201 is "Absent", the presence reliability calculation unit 104-1 calculates the presence reliability of the pyroelectric sensor 201 as "0".

[0052] The reliability of the pyroelectric sensor = 1 - elapsed time / 10 ... (Equation 1)

[0053] The elapsed time (minutes) is the time elapsed since the individual determination unit 103 received information from the pyroelectric sensor 201 indicating that a change had been detected. In other words, the shorter the elapsed time since the pyroelectric sensor 201 detected a change, the higher the reliability of the presence of the pyroelectric sensor 201. In Equation 1, if the elapsed time exceeds 10 minutes, the reliability of the presence becomes 0. Since the pyroelectric sensor 201 is a sensor that detects changes in the amount of infrared radiation, the longer the time elapsed since the detection of a change in the amount of infrared radiation, the lower the reliability of the presence determination is considered to be.

[0054] Furthermore, the presence reliability calculation unit 104-1 corrects the presence reliability of the pyroelectric sensor 201 based on the opening and closing information of the second opening / closing sensor 205. The presence reliability calculation unit 104-1 refers to the information indicating the most recent opening and closing of the shielding object stored in the auxiliary storage unit 13 and determines the current opening and closing state of the shielding object. If the presence reliability calculation unit 104-1 determines that the shielding object is open, that is, that solar radiation is not being blocked by the shielding object, it calculates a presence reliability for the pyroelectric sensor 201 that is lower than the presence reliability calculated by Equation 1. For example, the presence reliability calculation unit 104-1 multiplies the presence reliability of the pyroelectric sensor 201 obtained by Equation 1 by a value of, for example, 0.5. On the other hand, if the presence reliability calculation unit 104-1 determines that the shielding object is closed, it does not correct the presence reliability of the pyroelectric sensor 201 obtained by Equation 1. The pyroelectric sensor 201 may make false detections if there is sunlight in the area. Therefore, if there is an open shading object and it is possible that it will be affected by sunlight, the reliability of the presence detection is corrected to be lower.

[0055] Furthermore, if the individual determination result of the infrared sensor 202 is "Present", the presence reliability calculation unit 104-1 calculates the presence reliability of the infrared sensor 202 using the following formula 2. On the other hand, if the individual determination result of the infrared sensor 202 is "Absent", the presence reliability calculation unit 104-1 calculates the presence reliability of the infrared sensor 202 as "0".

[0056] Infrared sensor presence reliability = 1 - 1 / (2 × number of people in the area) ... (Equation 2)

[0057] In other words, the more areas of people detected by the individual determination unit 103, the higher the reliability of the presence detection by the infrared sensor 202. Since the infrared sensor 202 can sometimes detect stationary objects, the more areas of people detected, the higher the reliability of the presence detection is considered to be.

[0058] Furthermore, the presence reliability calculation unit 104-1 calculates the presence reliability of the CO2 sensor 203 as "1" if the individual judgment result of the CO2 sensor 203 is "Present", and calculates the presence reliability of the CO2 sensor 203 as "0" if the individual judgment result of the CO2 sensor 203 is "Absent". When the CO2 concentration value measured by the CO2 sensor 203 exceeds a predetermined threshold, it is considered that there is a high probability that a person is present, and therefore the reliability of the presence judgment is considered high.

[0059] Next, the absence reliability calculation unit 104-2 calculates the absence reliability of the pyroelectric sensor 201 as "0" regardless of whether the individual judgment result of the pyroelectric sensor 201 is "present" or "absent". The pyroelectric sensor 201 cannot detect a person even if they are present in the area if the person remains stationary, so even if an individual judgment result of absence is obtained, the reliability of the absence judgment is considered low.

[0060] Furthermore, if the individual determination result of the infrared sensor 202 is "absent," the absence reliability calculation unit 104-2 calculates the absence reliability of the infrared sensor 202 by referring to the area information table in Figure 4. The absence reliability of the infrared sensor 202 in the area information table in Figure 4 is set to a lower value the more obstacles there are in the area, and is set by the administrator of the human detection system 1 or the equipment control system 2. For example, for area 1 of area ID "area 1," the absence reliability calculation unit 104-2 calculates the absence reliability of the infrared sensor 202 as "0.8" by referring to the area information table in Figure 4. On the other hand, if the individual determination result of the infrared sensor 202 is "present," the absence reliability calculation unit 104-2 calculates the absence reliability of the infrared sensor 202 as "0." The more obstacles there are in the area, the more blind spots the infrared sensor 202 will have, and even if a person is present, it will not be able to acquire infrared radiation. Therefore, the more obstacles there are in the area, the lower the reliability of the absence determination is considered to be.

[0061] Furthermore, if the individual determination result of the CO2 sensor 203 is "absence determined", the absence reliability calculation unit 104-2 calculates the absence reliability of the CO2 sensor 203 by referring to the open / closed information of the first open / closed sensor 204 and the area information table in Figure 4. The absence reliability calculation unit 104-2 refers to the information indicating the most recent open / closed state of the window stored in the auxiliary storage unit 13 and determines the current open / closed state of the window. If the absence reliability calculation unit 104-2 determines that the window is open, it calculates a value indicating that the reliability of the absence determination is low as the absence reliability of the CO2 sensor 203. For example, the absence reliability calculation unit 104-2 calculates the absence reliability of the CO2 sensor 203 as "0". On the other hand, if the absence reliability calculation unit 104-2 determines that the window is closed, it calculates by referring to the area information table in Figure 4. The absence confidence level of the CO2 sensor 203 in the area information table in Figure 4 is set to a lower value the larger the area area is, and is set by the administrator of the human detection system 1 or the equipment control system 2. For example, the absence confidence level calculation unit 104-2 calculates the absence confidence level of the CO2 sensor 203 for area ID "Area 1" as "0.5" by referring to the area information table in Figure 4. Also, if the individual judgment result of the CO2 sensor 203 is "occupied", the absence confidence level of the CO2 sensor 203 is calculated as "0". When the area is well ventilated, the CO2 concentration does not rise easily, and the CO2 concentration rises less easily the larger the area area is, so the CO2 sensor 203 cannot accurately measure the CO2 concentration emitted by a person.Therefore, when a window is open, the reliability of the absence judgment is considered low, and the reliability of the absence judgment is considered lower the larger the area area is.

[0062] For example, suppose that for area ID "Area 1", the individual determination unit 103 obtains an individual determination result of "Present" for the pyroelectric sensor 201, an individual determination result of "Absent" for the infrared sensor 202, and an individual determination result of "Present" for the CO2 sensor 203. Also, suppose that 2 minutes have passed since the time when information indicating that a change was detected from the pyroelectric sensor 201 was received. In this case, the presence reliability calculation unit 104-1 calculates the presence reliability of the pyroelectric sensor 201 as "0.8", the presence reliability of the infrared sensor 202 as "0", and the presence reliability of the CO2 sensor 203 as "1". Also, the absence reliability calculation unit 104-2 calculates the absence reliability of the pyroelectric sensor 201 as "0", the absence reliability of the infrared sensor 202 as "0.8", and the absence reliability of the CO2 sensor 203 as "0".

[0063] The integrated determination unit 105 determines the presence or absence of a person in the target space based on multiple confidence levels calculated for each of the multiple types of sensors, and obtains an integrated determination result indicating the determination result. The integrated determination unit 105 is implemented by the processor 11. Note that the integrated determination unit 105 is an example of an integrated determination means.

[0064] Specifically, the comprehensive determination unit 105 obtains a comprehensive determination result by comparing the sum of the presence confidence scores calculated for each individual determination result obtained for each of the multiple types of human presence sensors 210 with the sum of the absence confidence scores calculated for each individual determination result obtained for each of the multiple types of human presence sensors. If the sum of the presence confidence scores is greater than the sum of the absence confidence scores, the comprehensive determination unit 105 obtains a comprehensive determination result that a person is present in the target space. On the other hand, if the sum of the presence confidence scores is less than or equal to the sum of the absence confidence scores, the comprehensive determination unit 105 obtains a comprehensive determination result that a person is not present in the target space.

[0065] For example, if, for the area with area ID "Area 1", the presence reliability of the pyroelectric sensor 201 is "0.8", the presence reliability of the infrared sensor 202 is "0", and the presence reliability of the CO2 sensor 203 is "1", the absence reliability of the pyroelectric sensor 201 is "0", the absence reliability of the infrared sensor 202 is "0.8", and the absence reliability of the CO2 sensor 203 is "0", then the sum of the presence reliability values ​​"1.8" is greater than the sum of the absence reliability values ​​"0.8", so the overall determination unit 105 obtains an overall determination result that a person is present in the area with area ID "Area 1".

[0066] Next, the control processing performed by the equipment control system 2, which includes the human detection system 1 according to this embodiment, will be explained using the flowchart in Figure 5.

[0067] The sensors included in the sensor group 200 acquire sensing information at predetermined timings for each sensor and transmit the acquired information to the human detection device 100 or the equipment control device 400 (step S101).

[0068] For example, when the pyroelectric sensor 201 detects a change in the amount of infrared radiation exceeding a predetermined value, it transmits information indicating that a change has been detected to the human detection device 100 as sensing information. The infrared sensor 202 captures a thermal image of the target space every minute and transmits the captured thermal image to the human detection device 100 as sensing information. The CO2 sensor 203 acquires the carbon dioxide concentration value every minute and transmits the acquired value to the human detection device 100 as sensing information. When the first open / close sensor 204 detects the opening or closing of a window, it transmits information indicating the opening or closing of the window to the human detection device 100 as sensing information. When the second open / close sensor 205 detects the opening or closing of an obstruction, it transmits information indicating the opening or closing of the obstruction to the human detection device 100 as sensing information. The temperature sensor 206 acquires the temperature value every minute and transmits the acquired value to the equipment control device 400 as sensing information. The humidity sensor 207 acquires the humidity value every minute and transmits the acquired value to the equipment control device 400 as sensing information.

[0069] Next, the human detection device 100 or the equipment control device 400 collects and stores sensing information (step S102).

[0070] For example, the data collection unit 102 of the human detection device 100 receives sensing information from the pyroelectric sensor 201, infrared sensor 202, CO2 sensor 203, first open / close sensor 204, and second open / close sensor 205, associates the received sensing information with the time it was received, and stores it in the auxiliary storage unit 13. In addition, the equipment control device 400 receives sensing information from the temperature sensor 206 and humidity sensor 207, associates the received sensing information with the time it was received, and stores it in the auxiliary storage unit of the equipment control device 400.

[0071] The human detection device 100 performs human detection processing (step S103). The human detection processing performed by the human detection device 100 will be explained using the flowchart in Figure 6. The human detection device 100 determines whether or not there are people in N areas.

[0072] The human detection device 100 sets the variable i to 1 (step S201). Then, the human detection device 100 sets the area to be determined as the area with area ID "area i" (step S202). For example, the human detection device 100 sets area 1 with area ID "area 1" as the area to be determined as the area to be determined as the area to be determined as the area to be determined as the area to be determined as the area to be determined as the area to be present or absent.

[0073] The individual determination unit 103 of the human detection device 100 acquires individual determination results for the pyroelectric sensor 201 for each area based on the information from the pyroelectric sensor 201 (step S203). For example, the individual determination unit 103 acquires individual determination results for the pyroelectric sensor 201 that indicate "occupancy" for area 1.

[0074] The individual determination unit 103 acquires individual determination results for the infrared sensor 202 for each area based on the information from the infrared sensor 202 (step S204). For example, the individual determination unit 103 acquires an individual determination result for the infrared sensor 202 of "absence detected" for area 1.

[0075] The individual determination unit 103 acquires individual determination results for the CO2 sensor 203 for each area based on the information from the CO2 sensor 203 (step S205). For example, the individual determination unit 103 acquires individual determination results for the CO2 sensor 203 that are "occupied" for area 1.

[0076] Next, the presence reliability calculation unit 104-1 of the human detection device 100 calculates the presence reliability for the individual judgment result of the pyroelectric sensor 201 (step S206). For example, if it is currently 2 minutes since the time when information indicating that a change was detected was received from the pyroelectric sensor 201, the presence reliability calculation unit 104-1 calculates the presence reliability as "0.8" for the individual judgment result "Presence Detected" of the pyroelectric sensor 201 in area 1.

[0077] The presence reliability calculation unit 104-1 calculates the presence reliability for the individual judgment result of the infrared sensor 202 (step S207). For example, the presence reliability calculation unit 104-1 calculates the presence reliability as "0" for the individual judgment result "absence" of the infrared sensor 202 in area 1.

[0078] The presence reliability calculation unit 104-1 calculates the presence reliability for the individual determination result of the CO2 sensor 203 (step S208). For example, the presence reliability calculation unit 104-1 calculates the presence reliability as "1" for the individual determination result "Presence determined" of the CO2 sensor 203 in area 1.

[0079] Next, the absence confidence calculation unit 104-2 of the human detection device 100 calculates the absence confidence for the individual judgment result of the pyroelectric sensor 201 (step S209). For example, the absence confidence calculation unit 104-2 calculates the absence confidence as "0" for the individual judgment result "Present" of the pyroelectric sensor 201 in area 1.

[0080] The absence confidence calculation unit 104-2 calculates the absence confidence for the individual judgment result of the infrared sensor 202 (step S210). For example, the absence confidence calculation unit 104-2 calculates the absence confidence as "0.8" for the individual judgment result "absence judgment" of the infrared sensor 202 in area 1.

[0081] The absence confidence calculation unit 104-2 calculates the absence confidence for the individual determination result of the CO2 sensor 203 (step S211). For example, the absence confidence calculation unit 104-2 calculates the absence confidence as "0" for the individual determination result "Present" of the CO2 sensor 203 in area 1.

[0082] Next, the overall determination unit 105 compares the sum of the presence confidence scores with the sum of the absence confidence scores to obtain an overall determination result (step S212). For example, the overall determination unit 105 determines that the sum of the presence confidence scores "1.8" is greater than the sum of the absence confidence scores "0.8", and therefore obtains an overall determination result that a person is present in area 1.

[0083] The human detection device 100 increments the variable i (step S213). Then, the human detection device 100 determines whether the variable i is equal to N+1 (step S214). If the human detection device 100 finds that the variable i is equal to N+1 (step S214; YES), it terminates the human detection process. On the other hand, if the human detection device 100 finds that the variable i is not equal to N (step S214; NO), it proceeds to step S202. The process is repeated by the human detection device 100 until the variable i becomes equal to N+1, that is, until the processes from step S202 to step S212 are executed for all areas.

[0084] Once the human detection process shown in Figure 6 is complete, the equipment control device 400 controls the equipment 300 installed in the area based on the collected sensing information and the overall judgment result obtained by the human detection device 100 (step S104). For example, in Area 1 of Area ID "Area 1", where an overall judgment result indicating the presence of a person has been obtained, the equipment control device 400 turns on the power to the air conditioner with air conditioner ID "0x0010" and the lighting with lighting ID "0x0020". Also, for example, if an overall judgment result indicating that no person is present in Area 1 is obtained, the equipment control device 400 turns off the power to the air conditioner with air conditioner ID "0x0011" and the lighting with lighting ID "0x0021".

[0085] The detection system 1 of this embodiment performs a presence or absence determination for each of several types of motion sensors, calculates a reliability score indicating the reliability of the presence or absence determination based on the characteristics of each motion sensor, and uses these reliability scores to comprehensively determine the presence or absence of a person in the target space. According to this embodiment, the reliability score of the presence or absence determination obtained for each motion sensor reflects the advantages and disadvantages of each motion sensor, so that the presence or absence of a person in the target space can be determined by considering the characteristics of each motion sensor. As a result, even if there is a possibility of false detection due to the characteristics of the sensor, the reliability score of the presence or absence determination will be low, and if the possibility of false detection due to the characteristics of the sensor is low when detecting a person based on information obtained from other motion sensors, the reliability score of the presence or absence determination will be high, thus compensating for the shortcomings of the motion sensors and enabling highly accurate person detection.

[0086] Furthermore, according to this embodiment, since the reliability is calculated for both presence detection and absence detection, human detection can be performed taking into account the characteristics of the presence detection and absence detection of the human presence sensor. This enables more accurate human detection.

[0087] (modified version) Although embodiments of this disclosure have been described above, various forms of modification and application are possible when implementing this disclosure.

[0088] In the above embodiment, the human detection device 100 may include an area information storage unit 101, a collection unit 102, an individual determination unit 103, a reliability calculation unit 104, and an overall determination unit 105, but it is not limited to this configuration. Each unit may be provided in a different device.

[0089] Furthermore, in the above embodiment, the individual determination unit 103 acquires individual determination results for the three sensors, the presence reliability calculation unit 104-1 calculates the presence reliability, and the absence reliability calculation unit 104-2 calculates the absence reliability for the three sensors, the pyroelectric sensor 201, the infrared sensor 202, and the CO2 sensor 203, but this is not limited to this. The individual determination unit 103 may acquire individual determination results for at least two of the pyroelectric sensor 201, the infrared sensor 202, and the CO2 sensor 203, the presence reliability calculation unit 104-1 may calculate the presence reliability, and the absence reliability calculation unit 104-2 may calculate the absence reliability. The overall determination unit 105 may then acquire an overall determination result by comparing the sum of the two presence reliability values ​​with the sum of the two absence reliability values.

[0090] Furthermore, in the above embodiment, the absence reliability calculation unit 104-2 calculates the absence reliability of the CO2 sensor 203 by referring to the open / closed information of the first open / closed sensor 204, but this is not limited to this. For example, the equipment 300 includes a ventilation device that ventilates the target space, and the collection unit 102 collects information indicating the operating status of the ventilation device. Then, if the individual judgment result is an absence judgment, the absence reliability calculation unit 104-2 calculates the absence reliability by referring to the information indicating the operating status of the ventilation device and the area information table in Figure 4. For example, if the absence reliability calculation unit 104-2 determines that the ventilation device is operating, it calculates the absence reliability as "0", and if it determines that the ventilation device is stopped, it calculates the absence reliability as "0.5" by referring to the area information table in Figure 4.

[0091] Furthermore, although the flowchart in Figure 6 of the above embodiment shows the processes performed by the human detection device 100, the order of the processes is not limited to this. The order of the processes from step S206 to step S211 can be any order.

[0092] Furthermore, by applying an operating program that defines the operation of the devices included in the human detection system 1 according to the above embodiment to an existing personal computer or information terminal device, it is also possible to make the personal computer or information terminal device function as a device included in the human detection system 1 according to the embodiment.

[0093] Furthermore, the method of distributing such programs is optional. For example, they may be distributed by storing them on computer-readable storage media such as CD-ROMs (Compact Disk Read-Only Memory), DVDs (Digital Versatile Disks), or memory cards, or they may be distributed via communication networks such as the Internet.

[0094] This disclosure allows for various embodiments and modifications without departing from the broad spirit and scope of this disclosure. Furthermore, the embodiments described above are for illustrative purposes only and do not limit the scope of this disclosure. In other words, the scope of this disclosure is indicated by the claims, not by the embodiments. Various modifications made within the scope of the claims and the equivalent significance of the disclosure are considered to be within the scope of this disclosure. [Industrial applicability]

[0095] This disclosure provides a human detection system, human detection device, human detection method, and program that enable highly accurate human detection by determining the presence or absence of a person while considering the characteristics of each of several types of human presence sensors. [Explanation of symbols]

[0096] 1 Human detection system, 2 Equipment control system, 11 Processor, 12 Main memory unit, 13 Auxiliary memory unit, 14 Communication unit, 15 Input unit, 16 Output unit, 17 RTC, 18 Bus, 100 Human detection device, 101 Area information storage unit, 102 Collection unit, 103 Individual judgment unit, 104 Reliability calculation unit, 104-1 Presence reliability calculation unit, 104-2 Absence reliability calculation unit, 105 Overall judgment unit, 200 Sensor group, 210 Human presence sensor, 201 Pyroelectric sensor, 202 Infrared sensor, 204 CO2 sensor, 204 First open / close sensor, 205 Second open / close sensor, 206 Temperature sensor, 207 Humidity sensor, 300 Equipment, 400 Equipment control device, 500 Network.

Claims

1. A motion sensor that acquires information for determining the presence or absence of a person in a target space, comprising multiple types of motion sensors that acquire different information, A collection means for collecting information acquired by the aforementioned multiple types of human presence sensors, For each of the aforementioned multiple types of human presence sensors, an individual determination means is provided to determine whether or not there is a person in the target space based on the collected information and to acquire an individual determination result indicating the determination result. For each of the aforementioned multiple types of human presence sensors, a reliability calculation means calculates a reliability score indicating the reliability of the individual judgment result based on the characteristics of the human presence sensor, The system includes a comprehensive determination means that determines the presence or absence of a person in the target space based on multiple confidence levels calculated for each of the multiple types of human presence sensors, and obtains a comprehensive determination result indicating the result of the determination, The aforementioned reliability calculation means is A presence confidence calculation means calculates a presence confidence level indicating the reliability of the presence determination that a person is present in the target space, for each of the individual determination results obtained for each of the multiple types of human presence sensors, The system includes an absence confidence calculation means that calculates an absence confidence level indicating the reliability of the absence determination that no person is present in the target space, for each of the individual determination results obtained for each of the multiple types of human presence sensors, The comprehensive determination means obtains the comprehensive determination result by comparing the sum of the presence confidence scores calculated for each of the individual determination results obtained for each of the multiple types of human presence sensors with the sum of the absence confidence scores calculated for each of the individual determination results obtained for each of the multiple types of human presence sensors, The aforementioned multiple types of human presence sensors include a pyroelectric sensor that detects changes in the amount of infrared radiation emitted by an object in the target space, an infrared sensor that acquires the amount of infrared radiation emitted by an object in the target space as a thermal image, and a CO2 sensor that measures the concentration of carbon dioxide in the target space. The system further includes a first open / close sensor that detects the opening and closing of a window installed in the aforementioned target space, The collection means collects information indicating the opening and closing of the window from the first opening / closing sensor, When the absence reliability calculation means determines that the window is open based on information indicating the opening or closing of the window, it calculates a value as the absence reliability of the CO2 sensor indicating that the reliability of the absence determination is low. Human detection system.

2. The system further includes a second opening / closing sensor that detects the opening and closing of an obstruction that blocks sunlight in the aforementioned target space, The collection means collects information from the second opening / closing sensor indicating the opening and closing of the shielding object. If the presence reliability calculation means determines, based on information indicating the opening and closing of the shield, that solar radiation is not being blocked by the shield, it calculates a presence reliability for the pyroelectric sensor that is lower than the previously calculated presence reliability. The human detection system according to claim 1.

3. A motion sensor that acquires information for determining the presence or absence of a person in a target space, comprising multiple types of motion sensors that acquire different information, A collection means for collecting information acquired by the aforementioned multiple types of human presence sensors, For each of the aforementioned multiple types of human presence sensors, an individual determination means is provided to determine whether or not there is a person in the target space based on the collected information and to acquire an individual determination result indicating the determination result. For each of the aforementioned multiple types of human presence sensors, a reliability calculation means calculates a reliability score indicating the reliability of the individual judgment result based on the characteristics of the human presence sensor, The system includes a comprehensive determination means that determines the presence or absence of a person in the target space based on multiple confidence levels calculated for each of the multiple types of human presence sensors, and obtains a comprehensive determination result indicating the result of the determination, The aforementioned reliability calculation means is A presence confidence calculation means calculates a presence confidence level indicating the reliability of the presence determination that a person is present in the target space, for each of the individual determination results obtained for each of the multiple types of human presence sensors, The system includes an absence confidence calculation means that calculates an absence confidence level indicating the reliability of the absence determination that no person is present in the target space, for each of the individual determination results obtained for each of the multiple types of human presence sensors, The comprehensive determination means obtains the comprehensive determination result by comparing the sum of the presence confidence scores calculated for each of the individual determination results obtained for each of the multiple types of human presence sensors with the sum of the absence confidence scores calculated for each of the individual determination results obtained for each of the multiple types of human presence sensors, The aforementioned multiple types of human presence sensors include a pyroelectric sensor that detects changes in the amount of infrared radiation emitted by an object in the target space, an infrared sensor that acquires the amount of infrared radiation emitted by an object in the target space as a thermal image, and a CO2 sensor that measures the concentration of carbon dioxide in the target space. The system further includes a second opening / closing sensor that detects the opening and closing of an obstruction that blocks sunlight in the aforementioned target space, The collection means collects information from the second opening / closing sensor indicating the opening and closing of the shielding object. If the presence reliability calculation means determines, based on information indicating the opening and closing of the shield, that solar radiation is not being blocked by the shield, it calculates a presence reliability for the pyroelectric sensor that is lower than the previously calculated presence reliability. Human detection system.

4. A motion sensor that acquires information for determining the presence or absence of a person in a target space, comprising a collection means for collecting information acquired by multiple types of motion sensors that acquire different information, For each of the aforementioned multiple types of human presence sensors, an individual determination means is provided to determine whether or not there is a person in the target space based on the collected information and to acquire an individual determination result indicating the determination result. For each of the aforementioned multiple types of human presence sensors, a reliability calculation means calculates a reliability score indicating the reliability of the individual judgment result based on the characteristics of the human presence sensor, The system includes a comprehensive determination means that determines the presence or absence of a person in the target space based on multiple confidence levels calculated for each of the multiple types of human presence sensors, and obtains a comprehensive determination result indicating the result of the determination, The aforementioned reliability calculation means is A presence confidence calculation means calculates a presence confidence level indicating the reliability of the presence determination that a person is present in the target space, for each of the individual determination results obtained for each of the multiple types of human presence sensors, The system includes an absence confidence calculation means that calculates an absence confidence level indicating the reliability of the absence determination that no person is present in the target space, for each of the individual determination results obtained for each of the multiple types of human presence sensors, The comprehensive determination means obtains the comprehensive determination result by comparing the sum of the presence confidence scores calculated for each of the individual determination results obtained for each of the multiple types of human presence sensors with the sum of the absence confidence scores calculated for each of the individual determination results obtained for each of the multiple types of human presence sensors, The aforementioned multiple types of human presence sensors include a pyroelectric sensor that detects changes in the amount of infrared radiation emitted by an object in the target space, an infrared sensor that acquires the amount of infrared radiation emitted by an object in the target space as a thermal image, and a CO2 sensor that measures the concentration of carbon dioxide in the target space. The collection means collects information indicating the opening and closing of a window from a first opening / closing sensor that detects the opening and closing of a window installed in the target space, When the absence reliability calculation means determines that the window is open based on information indicating the opening or closing of the window, it calculates a value as the absence reliability of the CO2 sensor indicating that the reliability of the absence determination is low. Human detection device.

5. A human presence sensor that acquires information for determining the presence or absence of a person in a target space, wherein, based on information acquired by multiple types of human presence sensors that acquire different information, the presence or absence of a person in the target space is determined for each of the multiple types of human presence sensors, and an individual determination result indicating the determination result is acquired. For each of the aforementioned multiple types of motion sensors, a reliability score indicating the reliability of the individual judgment result is calculated based on the characteristics of the motion sensor. Based on the multiple confidence levels calculated for each of the multiple types of human presence sensors, the presence or absence of a person in the target space is determined, and an overall determination result showing the determination is obtained. In calculating the confidence level, For each of the individual judgment results obtained for each of the multiple types of human presence sensors, a presence confidence score is calculated to indicate the reliability of the presence judgment that a person is present in the target space. For each of the individual judgment results obtained for each of the multiple types of human presence sensors, an absence confidence score is calculated to indicate the reliability of the absence judgment that no person is present in the target space. The overall judgment result is obtained by comparing the sum of the presence confidence scores calculated for each of the individual judgment results obtained for each of the multiple types of human presence sensors with the sum of the absence confidence scores calculated for each of the individual judgment results obtained for each of the multiple types of human presence sensors. The aforementioned multiple types of human presence sensors include a pyroelectric sensor that detects changes in the amount of infrared radiation emitted by an object in the target space, an infrared sensor that acquires the amount of infrared radiation emitted by an object in the target space as a thermal image, and a CO2 sensor that measures the concentration of carbon dioxide in the target space. In calculating the aforementioned absence confidence level, Based on information indicating the opening and closing of a window collected from a first open / close sensor that detects the opening and closing of a window installed in the target space, if it is determined that the window is open, the CO2 sensor calculates a value indicating that the reliability of the absence determination is low as the absence confidence level. Human detection method.

6. Computers, A human presence sensor that acquires information for determining the presence or absence of a person in a target space, wherein, based on information acquired by multiple types of human presence sensors that acquire different information, an individual determination means determines the presence or absence of a person in the target space for each of the multiple types of human presence sensors and acquires an individual determination result indicating the determination result, For each of the aforementioned multiple types of human presence sensors, a reliability calculation means calculates a reliability score indicating the reliability of the individual judgment result based on the characteristics of the human presence sensor. Based on multiple confidence levels calculated for each of the multiple types of human presence sensors, it functions as a comprehensive determination means that determines whether or not there is a person in the target space and obtains a comprehensive determination result showing the result of the determination. The confidence calculation means is A presence confidence calculation means calculates a presence confidence level indicating the reliability of the presence determination that a person is present in the target space, for each of the individual determination results obtained for each of the multiple types of human presence sensors. For each of the individual judgment results obtained for each of the multiple types of human presence sensors, the absence confidence level is calculated to indicate the reliability of the absence judgment that no person is present in the target space. The comprehensive determination means obtains the comprehensive determination result by comparing the sum of the presence confidence scores calculated for each of the individual determination results obtained for each of the multiple types of human presence sensors with the sum of the absence confidence scores calculated for each of the individual determination results obtained for each of the multiple types of human presence sensors, The aforementioned multiple types of human presence sensors include a pyroelectric sensor that detects changes in the amount of infrared radiation emitted by an object in the target space, an infrared sensor that acquires the amount of infrared radiation emitted by an object in the target space as a thermal image, and a CO2 sensor that measures the concentration of carbon dioxide in the target space. The absence confidence calculation means, when it determines that the window is open based on information indicating the opening and closing of the window collected from the first open / close sensor which detects the opening and closing of the window installed in the target space, calculates a value as the absence confidence of the CO2 sensor indicating that the reliability of the absence determination is low. program.

Images