Human detection system, human detection method, and program

Abstract

To reduce a possibility to erroneously detect entering or exiting of a person.SOLUTION: A person detection system 1 detects a person on the basis of a plurality of temperature values detected using an infrared-ray sensor array 3. The person detection system 1 includes a temperature acquisition unit 61 and a determination unit 62. The temperature acquisition unit 61 acquires the plurality of temperature values. The determination unit 62, when one or more conditions including at least a first condition are satisfied, determines that a person has entered an area or exited from the area. The first condition is a condition that a time change amount of the variance or the standard deviation of the plurality of temperature values is a value out of a first range.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] The present disclosure generally relates to a human detection system, a human detection method, and a program, and more particularly to a human detection system, a human detection method, and a program that utilize detection signals of an infrared sensor array.

Background Art

[0002] The thermal body detection device (human detection system) described in Patent Document 1 includes a temperature detection sensor, a thermal body detection unit, and a setting change unit. The temperature detection sensor includes a plurality of temperature detection elements arranged two-dimensionally. The thermal body detection unit detects a thermal body within an inspection range based on the output of the temperature detection sensor. The setting change unit changes the setting of a non-detection area, which is an area to be excluded from the inspection range, based on the detection result of the thermal body detection unit.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the thermal body detection device (human detection system) described in Patent Document 1, there is a possibility of erroneously detecting the presence or absence of a person's entry or exit due to the influence of noise or the like.

[0005] An object of the present disclosure is to provide a human detection system, a human detection method, and a program that can reduce the possibility of erroneously detecting the presence or absence of a person's entry or exit.

Means for Solving the Problems

[0006] A person detection system according to one aspect of the present disclosure detects a person based on a plurality of temperature values ​​detected using an infrared sensor array. The infrared sensor array has a plurality of infrared sensors. The plurality of temperature values ​​are the temperature values ​​of a plurality of detection areas that correspond one-to-one with the plurality of infrared sensors. The person detection system comprises a temperature acquisition unit and a determination unit. The temperature acquisition unit acquires the plurality of temperature values. The determination unit determines whether or not a person has entered or left an area including the plurality of detection areas. The determination unit determines that a person has entered or left the area if one or more conditions, including at least a first condition, are met. The first condition is that the time change in the variance or standard deviation of the plurality of temperature values ​​is outside a first range.

[0007] A person detection method according to one aspect of the present disclosure detects a person based on a plurality of temperature values ​​detected using an infrared sensor array. The infrared sensor array has a plurality of infrared sensors. The plurality of temperature values ​​are the temperature values ​​of a plurality of detection areas that correspond one-to-one with the plurality of infrared sensors. The person detection method includes a temperature acquisition step and a determination step. In the temperature acquisition step, the plurality of temperature values ​​are acquired. In the determination step, it is determined whether a person has entered or left an area including the plurality of detection areas. In the determination step, it is determined that a person has entered or left the area if one or more conditions, including at least a first condition, are met. The first condition is that the time change in the variance or standard deviation of the plurality of temperature values ​​is outside a first range.

[0008] A program according to one aspect of this disclosure is a program that causes one or more processors of a computer system to execute the person detection method. [Effects of the Invention]

[0009] This disclosure has the advantage of reducing the possibility of false detection of whether or not a person is entering or leaving the premises. [Brief explanation of the drawing]

[0010] [Figure 1] Figure 1 is a block diagram of a human detection system according to one embodiment. [Figure 2] Figure 2 is a conceptual diagram showing an example of the use of the human detection system described above. [Figure 3] Figure 3 is a flowchart illustrating an example of a series of processes in the human detection system described above. [Figure 4] Figure 4 is a flowchart illustrating an example of a series of processes in the human detection system described above. [Modes for carrying out the invention]

[0011] (Embodiment) The following describes a person detection system 1, a person detection method, and a program according to an embodiment, with reference to the drawings. However, the embodiments described below are only one of many embodiments of this disclosure. The embodiments described below can be modified in various ways depending on the design, etc., as long as the objectives of this disclosure are achieved. In addition, the figures described in the embodiments below are schematic diagrams, and the ratios of the size and thickness of each component in the figures do not necessarily reflect the actual dimensional ratios.

[0012] (overview) Figure 1 shows an example configuration of the human detection system 1. The human detection system 1 of this embodiment detects a person based on multiple temperature values ​​detected using an infrared sensor array 3. The infrared sensor array 3 has multiple infrared sensors 31. The multiple temperature values ​​are the temperature values ​​(radiant temperatures) of multiple detection areas R1 (see Figure 2) that correspond one-to-one with the multiple infrared sensors 31. The infrared sensor array 3 of this embodiment has 64 infrared sensors 31 arranged in an 8x8 grid. Therefore, as shown in Figure 2, the temperature values ​​of each of the 64 detection areas R1 arranged in an 8x8 grid are detected.

[0013] The human detection system 1 comprises a temperature acquisition unit 61 and a determination unit 62. The temperature acquisition unit 61 acquires multiple temperature values. The determination unit 62 determines whether or not a person has entered or exited area A1 (see Figure 2), which includes multiple detection areas R1. The determination unit 62 determines that a person has entered or exited area A1 if one or more conditions, including at least a first condition, are met. The first condition is that the time change in the variance or standard deviation of the multiple temperature values ​​is outside a first range.

[0014] According to this embodiment, the possibility of the determination unit 62 falsely detecting whether or not a person has entered or exited (the presence or absence of a person) can be reduced.

[0015] For example, consider a scenario where, out of multiple detection areas R1, the temperature values ​​detected by the infrared sensor 31 momentarily increase in only one or two detection areas R1 due to noise or other factors. In this case, if the determination unit 62 were to judge that a person has entered based solely on the time change in the temperature values ​​of these few detection areas R1, that judgment would be incorrect (false detection). On the other hand, even if the temperature values ​​increase in a few detection areas R1, the time change in the variance or standard deviation of the multiple temperature values ​​is smaller compared to the time change in the temperature values ​​of the few detection areas R1. Therefore, in this embodiment, even if the temperature values ​​of the few detection areas R1 increase, if the first range is appropriately set, the first condition is not met, and the determination unit 62 does not judge that a person has entered. Thus, according to this embodiment, the possibility of false detection of a person entering area A1 can be reduced.

[0016] Furthermore, even if the temperature value detected by the infrared sensor 31 is momentarily lower due to noise or other factors in only one or two detection areas R1, the effects of noise can be mitigated by taking the variance or standard deviation of multiple temperature values. Therefore, the possibility of false detection that a person has left area A1 can be reduced.

[0017] In addition, the same functions as those of the human detection system 1 can be embodied by a human detection method. The human detection method of the present embodiment detects a person based on a plurality of temperature values detected using the infrared sensor array 3. The infrared sensor array 3 has a plurality of infrared sensors 31. The plurality of temperature values are the temperature values of the respective detection regions R1 that correspond one-to-one with the plurality of infrared sensors 31. The human detection method has a temperature acquisition step and a determination step. In the temperature acquisition step, a plurality of temperature values are acquired. In the determination step, it is determined whether there has been entry or exit of a person into or from the area A1 including the plurality of detection regions R1. In the determination step, when one or more conditions including at least the first condition are satisfied, it is determined that there has been entry or exit of a person into or from the area A1. The first condition is a condition that the amount of change over time of the variance or standard deviation of the plurality of temperature values is outside the first range.

[0018] In addition, the human detection method can be embodied by a program. The program of the present embodiment is a program for causing one or more processors of a computer system to execute the human detection method. The program may be recorded on a non-temporary recording medium readable by the computer system.

[0019] (Details) (1) Overall configuration Next, referring to FIG. 1, the configuration of the human detection system 1 of the present embodiment will be described in more detail.

[0020] The human detection system 1 includes a sensor module 2 and a determination device 5. The sensor module 2 has an infrared sensor array 3 and is installed at a position where the temperature value of the area A1 can be detected. The determination device 5 is configured to be communicable with the sensor module 2. The determination device 5 acquires information on the temperature value detected by the sensor module 2 from the sensor module 2 and determines whether there has been entry or exit of a person into or from the area A1. In the present embodiment, the area A1 coincides with the area obtained by combining all the plurality of detection regions R1.

[0021] Area A1 is, for example, part or all of a room in a facility. The facility is, for example, an indoor facility such as a residence, office building, factory, mixed-use commercial complex, library, art museum, museum, amusement park, airport, train station, hotel, nursing home, and hospital. The facility may also be a mobile object such as a ship, train car, or aircraft. Area A1 may also be an outdoor area.

[0022] (2) Sensor module The sensor module 2 is installed, for example, on the ceiling of a facility, and when viewed from above, the multiple detection areas R1 are arranged in eight rows in the front-to-back direction and eight columns in the left-to-right direction along the horizontal plane (see Figure 2). However, the arrangement of the multiple detection areas R1 is not limited to this arrangement. For example, when viewed from the front-to-back direction, the multiple detection areas R1 may be arranged in eight rows in the vertical direction and eight columns in the left-to-right direction along the vertical plane.

[0023] As shown in Figure 1, the sensor module 2 includes an infrared sensor array 3, a processing unit 4, and a communication unit 21.

[0024] The infrared sensor array 3 has a plurality (64) of infrared sensors 31. The infrared sensors 31 include, for example, a thermopile. The infrared sensors 31 receive infrared light emitted from within their own field of view. More specifically, the plurality of infrared sensors 31 correspond one-to-one with a plurality of detection areas R1. Each of the plurality of infrared sensors 31 receives infrared light emitted from the corresponding detection area R1.

[0025] The infrared sensor 31 then outputs a value corresponding to the infrared light reception intensity, that is, a value corresponding to the radiant temperature of its own field of view. The sensor module 2 outputs a radiant temperature image that includes information on the values ​​corresponding to the radiant temperature of each of the fields of view of the multiple infrared sensors 31. As shown in Figure 2, the radiant temperature image is an 8x8 pixel image corresponding to the arrangement of the multiple infrared sensors 31, and represents the radiant temperature of each of the multiple detection areas R1 with color.

[0026] Tables 1 through 8 below correspond to the radiation temperature images output from sensor module 2. In Tables 1 through 8, the radiation temperature of each of the 64 pixels (64 detection regions R1) in the radiation temperature image is represented by a numerical value (in °C) instead of color.

[0027] If there are no people or heat sources within the range of multiple detection regions R1, the temperature value of each detection region R1 is constant, as shown in [Table 1] for example.

[0028] [Table 1]

[0029] Furthermore, if a person is present within the range of multiple detection regions R1, the temperature value of the detection region R1 where the person is present will be higher than the background temperature, as shown in Table 2 for example. The background temperature is the temperature of the detection region R1 where no person is present. In Table 2, the temperature value of the detection region R1 where a person is present is 34°C or 35°C, and the background temperature is 18°C.

[0030] [Table 2]

[0031] Next, the processing unit 4 will be described. The processing unit 4 includes a computer system having one or more processors and memory. At least some of the functions of the processing unit 4 are realized when the processor of the computer system executes a program recorded in the memory of the computer system. The program may be recorded in memory, provided via a telecommunication line such as the Internet, or provided on a non-temporary recording medium such as a memory card.

[0032] The processing unit 4 includes an acquisition unit 41 and an arithmetic unit 42. Note that these merely indicate the functions implemented by the processing unit 4 and do not necessarily represent an actual physical configuration.

[0033] The acquisition unit 41 acquires multiple detection signals from the infrared sensor array 3, with each signal corresponding to a single infrared sensor 31. The detection signals include values ​​corresponding to the infrared light reception intensity at the infrared sensors 31. The calculation unit 42 processes the multiple detection signals to calculate multiple temperature values. That is, the calculation unit 42 calculates the temperature value (radiant temperature) for each of the multiple detection regions R1.

[0034] The communication unit 21 includes a communication interface device. The communication unit 21 can communicate with the decision device 5 via the communication interface device. In this disclosure, "communication possible" means that signals can be sent and received directly or indirectly via a network or repeater, etc., by an appropriate communication method such as wired communication or wireless communication. The communication unit 21 outputs the temperature values ​​(radiant temperatures) of each of the multiple detection areas R1 determined by the calculation unit 42 to the decision device 5, in accordance with the control of the processing unit 4.

[0035] (3) Judgment device The decision-making device 5 comprises a processing unit 6, a communication unit 51, and a storage unit 52.

[0036] The communication unit 51 includes a communication interface device. The communication unit 51 can communicate with the sensor module 2 via the communication interface device.

[0037] The storage unit 52 is a storage device composed of a hard disk drive (HDD) or a solid-state drive (SSD), etc. The storage unit 52 stores, for example, information processed by the decision device 5 and information generated by the processing unit 6 of the decision device 5.

[0038] The processing unit 6 includes a computer system having one or more processors and memory. At least some of the functions of the processing unit 6 are realized by the computer system's processor executing a program stored in the computer system's memory. The program may be stored in memory, provided via a telecommunications line such as the Internet, or provided on a non-temporary recording medium such as a memory card.

[0039] The processing unit 6 includes a temperature acquisition unit 61, a determination unit 62, a first correction unit 63, and a second correction unit 64. Note that these merely represent the functions implemented by the processing unit 6 and do not necessarily represent an actual physical configuration.

[0040] The temperature acquisition unit 61 acquires the temperature values ​​(multiple temperature values) of each of the multiple detection areas R1. More specifically, the temperature acquisition unit 61 acquires the multiple temperature values ​​output from the sensor module 2 via the communication unit 51.

[0041] As described later, the determination unit 62 determines whether or not a person has entered or exited area A1, which includes multiple detection areas R1. The determination result of the determination unit 62 is notified to the user, for example, by a notification device provided outside the person detection system 1. The notification device includes, for example, a display and notifies the determination result via video. The person detection system 1 may also be equipped with a notification device.

[0042] For example, the person detection system 1 is used to manage seat occupancy. The person detection system 1 uses an infrared sensor array 3 to detect the radiant temperature around the seat, and based on the radiant temperature, the determination unit 62 determines whether a person is sitting in the seat or whether a person has left the seat. For example, multiple seats are provided, and one infrared sensor array 3 is installed for each seat. The determination result of the determination unit 62 is displayed, for example, on the display of a notification device, so that the user can find out which seats are available.

[0043] The notification device may be installed in the facility where the sensor module 2 is installed, or it may be located in a separate location. Alternatively, the determination result of the determination unit 62 may be transmitted to an information terminal owned by the user and displayed on the information terminal's display. In other words, the information terminal may be used as the notification device. The information terminal may be, for example, a mobile phone such as a smartphone, a tablet terminal, or a personal computer.

[0044] The first correction unit 63 and the second correction unit 64 will be described later.

[0045] (4) Judgment in the Judgment Section Next, with reference to Figures 3 and 4, the procedure by which the determination unit 62 determines whether or not a person has entered or exited area A1 (see Figure 2) will be described. Note that the flowcharts shown in Figures 3 and 4 are merely one example of a series of processes of the person detection system 1 according to this disclosure, and the order of processes may be changed as appropriate, or processes may be added or omitted as appropriate. For example, the correction process in step ST4 may be omitted.

[0046] First, the sensor module 2 detects multiple (64) temperature values. These detected temperature values ​​are stored in the storage unit 52 as initial values ​​(step ST1).

[0047] Next, the judgment device 5 registers multiple (64) temperature values ​​and variances that will be used for comparison in a later step (step ST2). Registration is completed when the multiple temperature values ​​and variances are recorded in the storage unit 52. More specifically, the judgment device 5 registers the multiple temperature values ​​detected in step ST1 as multiple temperature values ​​to be compared. The judgment device 5 also registers the first variance and second variance calculated from the multiple temperature values ​​detected in step ST1 as variances to be compared, respectively.

[0048] Variance is defined by [Equation 1].

[0049]

number

[0050] σ 2 x is the variance, n is the number of data points, x i is the observed value (here, temperature value), and the overlined x represents n x values. i This is the average value.

[0051] The first variance is the variance of multiple (64) temperature values. Therefore, when calculating the first variance, n=64.

[0052] Furthermore, area A1 is divided into multiple blocks. Each of the multiple blocks contains two or more detection areas R1 from among the multiple detection areas R1. Information about the block boundaries is pre-stored in the storage unit 52. The size of each block may or may not be constant.

[0053] Furthermore, each detection region R1 may be contained in only one specific block among multiple blocks. Alternatively, a portion of a detection region R1 contained in one block may also be contained in another block.

[0054] In this embodiment, as shown in [Table 3], multiple detection areas R1 are divided into three sections vertically and horizontally, so that area A1 is divided into nine blocks. The thick lines in [Table 3] indicate the boundaries between blocks.

[0055] [Table 3]

[0056] The second variance is calculated for each block. In other words, nine second variances are calculated. The second variance is the variance of two or more temperature values ​​in two or more detection regions R1 contained within a block. For example, the upper left block in [Table 3] contains nine detection regions R1, so when calculating the second variance corresponding to this block using [Equation 1], n=9.

[0057] As described above, in step ST2, multiple temperature values, the first variance, and the second variance for comparison are registered.

[0058] Furthermore, the detection status of a person in area A1 is stored in association with multiple temperature values, a first variance, and a second variance. The detection status is either the presence or absence of a person in area A1. For example, the decision device 5 may unconditionally store in the storage unit 52 that there is no person in area A1. In this case, steps ST1 to ST2 must be executed with no person in area A1. Alternatively, the user may operate the decision device 5 to input the actual detection status. Alternatively, the user may operate a device that communicates with the decision device 5 to input the actual detection status, and the detection status may be input from the device to the decision device 5. Here, the detection status stored in the storage unit 52 is assumed to be the presence or absence of a person in area A1.

[0059] Next, in step ST3, the sensor module 2 again detects multiple (64) temperature values. These multiple temperature values ​​are stored in the storage unit 52 as multiple temperature values ​​at the most recent point in time.

[0060] Next, the determination unit 62 performs a correction process (step ST4). The correction process will be explained later.

[0061] The determination unit 62 determines the time change in the variance of multiple (64) temperature values. In other words, the determination unit 62 determines the time change in the first variance. More specifically, the determination unit 62 determines the time change in the first variance as the difference between the first variance (for comparison) registered in step ST2 and the first variance calculated from the multiple temperature values ​​detected in step ST3. Then, the determination unit 62 determines whether or not the time change in the first variance is outside the first range (step ST5).

[0062] Here, the first range is defined as the range between -10 and 10.

[0063] For example, consider a case where the difference between the first variance when multiple temperature values ​​are obtained as shown in [Table 1] and the first variance when multiple temperature values ​​are obtained as shown in [Table 2] is calculated as the time change of the first variance. According to [Table 1], the first variance is 0. According to [Table 2], the first variance is 43.8. The time change of the first variance is 43.8. Therefore, the time change of the first variance is outside the first range (Step ST5: Yes).

[0064] As another example, consider the case where the difference between the first variance when multiple temperature values ​​are obtained as shown in [Table 1] and the first variance when multiple temperature values ​​are obtained as shown in [Table 4] is calculated as the time change of the first variance. In [Table 4], the temperature value is 35°C in two detection regions R1, and the temperature value is 18°C ​​in the other detection region R1.

[0065] [Table 4]

[0066] According to [Table 1], the first variance is 0. According to [Table 4], the first variance is 8.9. The time change of the first variance is 8.9. Therefore, the time change of the first variance is within the first range (Step ST5: No). When the judgment in Step ST5 is "No", the judgment unit 62 determines that there was no entry or exit of people to or from Area A1 (Step ST11). Then, the process returns to Step ST3. Steps ST3 and ST5 are repeated until the time change of the first variance is outside the first range (until the judgment in Step ST5 becomes "Yes").

[0067] Therefore, as in the case of a transition from the state in [Table 1] to the state in [Table 4], if the temperature change occurs only in an area small compared to the size of a person, the possibility of false detection of a person entering or leaving can be reduced. On the other hand, as in the case of a transition from the state in [Table 1] to the state in [Table 2], if there is a sufficient temperature change in a relatively large area (about the size of a person), the judgment in step ST5 will be "Yes," and the system will proceed to step ST6.

[0068] In step ST6, the decision unit 62 calculates multiple (nine) second variances corresponding to each of the multiple (nine) blocks. The decision unit 62 then calculates the time change of the second variance. More specifically, the decision unit 62 calculates the time change of the second variance as the difference between the second variance (for comparison) registered in step ST2 and the second variance calculated from the temperature value detected in step ST3. The decision unit 62 then determines whether the time change of the second variance is outside the second range (step ST6). If the time change of the second variance for any block is outside the second range (step ST6: Yes), the storage unit 52 stores that block. If the time change of the second variance for any block is within the second range (step ST6: No), the decision unit 62 determines that there was no entry or exit of people to or from area A1 (step ST11). The process then returns to step ST3.

[0069] According to [Table 1], the second variance is 0 for all blocks. According to [Table 3], the second variance for the central block is 71.4. Here, the second range is defined as the range from -40 to 40. When transitioning from the state in [Table 1] to the state in [Table 3], the time change of the second variance for the central block is outside the second range (Step ST6: Yes).

[0070] In this way, the determination unit 62 determines whether the second condition is met for each of the multiple blocks. The second condition is that the time change of the variance (or standard deviation) of two or more temperature values, which are the temperature values ​​of two or more detection regions R1 within the block, is outside the second range.

[0071] In step ST7, the maximum value of two or more temperature values ​​in two or more detection areas R1 contained in the block that satisfies the second condition is compared with the first threshold. For example, according to [Table 3], the maximum value of the nine temperature values ​​in the central block is 35°C. Here, the first threshold is set to 33°C. Since the maximum value is greater than the first threshold (step ST7: Yes), the determination unit 62 determines that a person has entered area A1 (step ST8). If the maximum value is less than or equal to the first threshold (step ST7: No), the process proceeds to step ST9.

[0072] In step ST9, the maximum value of two or more temperature values ​​in two or more detection areas R1 included in the block that satisfies the second condition is compared with the second threshold. The second threshold is less than or equal to the first threshold. For example, the second threshold is 30°C. If the maximum value is less than the second threshold (step ST9: Yes), the determination unit 62 determines that a person has left area A1 (step ST10). If the maximum value is greater than or equal to the second threshold (step ST9: No), the determination unit 62 determines that there was neither entry nor exit of a person to area A1 (step ST11). The process then returns to step ST3.

[0073] For example, when transitioning from the state in [Table 3] to the state in [Table 1], the maximum temperature value in the central block is 18°C, so the determination unit 62 determines that a person has left area A1 (step ST10).

[0074] Sensor module 2 detects multiple temperature values ​​at regular intervals (for example, every few seconds). Therefore, steps ST3 to ST11 are repeated at regular intervals.

[0075] When the judgment unit 62 detects a person entering in step ST8, or a person leaving in step ST10, multiple temperature values, a first variance, and a second variance to be compared are newly registered (step ST2). More specifically, the judgment device 5 registers the multiple temperature values ​​detected in step ST3 at the most recent time as multiple temperature values ​​to be compared. The judgment device 5 also registers the first variance and second variance calculated from these multiple temperature values ​​as the first variance and second variance to be compared, respectively.

[0076] In this way, when the determination unit 62 determines that a person has entered or left, the determination device 5 registers the multiple temperature values ​​detected at the most recent point in time, and the first and second variances calculated from these multiple temperature values, as the multiple temperature values, first variance, and second variance of the comparison target, respectively. In the subsequent steps ST5 to ST9, the determination unit 62 determines whether a person has entered or left based on the newly registered multiple temperature values, first variance, and second variance of the comparison target. For example, in step ST5, the most recent first variance is calculated based on the multiple temperature values ​​detected at the most recent point in time from the time of execution of step ST5, and the difference between this most recent first variance and the first variance of the comparison target is taken as the time change amount of the first variance.

[0077] Furthermore, as explained above, the determination unit 62 determines that a person has entered or exited area A1 if at least one condition, including at least the first condition, is met. The first condition is that the time change in the variance (or standard deviation) of multiple temperature values ​​is outside the first range (see step ST5). The one or more conditions include the condition that there is a block among the multiple blocks that satisfies the second condition (see step ST6).

[0078] Furthermore, the determination unit 62 determines that a person has entered area A1 if the maximum value of two or more temperature values ​​in two or more detection areas R1 included in the block that satisfies the second condition is greater than the first threshold (see step ST7).

[0079] Furthermore, the determination unit 62 determines that a person has left area A1 if the maximum value of two or more temperature values ​​in two or more detection areas R1 included in a block that satisfies the second condition is smaller than the second threshold (see step ST9).

[0080] The judgment unit 62 may, instead of using variance, determine whether a person has entered or exited area A1 based on the change in standard deviation over time. The standard deviation σ can be calculated using [Equation 2].

[0081]

number

[0082] Next, we will explain the correction process (step ST4).

[0083] As the background temperature approaches the human radiation temperature, the variance decreases. In [Table 3], the background temperature is 18°C, and the first variance is 43.8. Therefore, when transitioning from a state where the first variance is 0, as in [Table 1], to the state in [Table 3], the time change in the first variance is 43.8.

[0084] In [Table 3], when the background temperature rises to 22°C, for example, as shown in [Table 5], the first variance becomes 25.5. Therefore, when the first variance transitions from a state of 0 as shown in [Table 6] to the state in [Table 5], the time change in the first variance is 25.5. In other words, as the difference between the background temperature and the radiant temperature of a person decreases, the time change in the first variance when a person enters area A1 decreases.

[0085] [Table 5]

[0086] [Table 6]

[0087] Therefore, in order to correct the first range, which is compared with the time change of the first variance, and the second range, which is compared with the time change of the second variance, in accordance with the increase or decrease in background temperature, the judgment device 5 performs a correction process.

[0088] As shown in Figure 4, in the correction process, the judgment device 5 first determines whether there is a block that satisfies the third condition among the multiple blocks that do not satisfy the second condition (step ST21). The third condition is that the amount of change over time of the temperature variance (second variance) is within the third range. The upper limit of the third range is a positive number, and the lower limit is a negative number. The third range is encompassed within the second range. The third range is pre-stored in the memory unit 52. Here, the third range is defined as the range of -10 or more and 10 or less. In [Table 5] and [Table 6], for example, the second variance of the upper right block is 0. When transitioning from the state in [Table 6] to the state in [Table 5], the amount of change over time of the second variance of the upper right block is 0, which is within the third range. Therefore, the determination in step ST21 is "Yes", and the process proceeds to step ST22.

[0089] In step ST22, the determination device 5 compares the absolute value of the temperature change of two or more detection areas R1 within the block that satisfies the third condition with a third threshold. The third threshold is a value of 0 or greater. That is, step ST22 is a step to determine whether or not there has been a temperature change of a certain level or more. The temperature change of two or more detection areas R1 is, for example, the average value of the change in each of the two or more temperature values ​​in the two or more detection areas R1. In step ST22, the determination device 5 first calculates the change in each of the two or more temperature values, and then calculates the average value of the change amounts obtained in this way. Then, the determination device 5 compares the absolute value of the average value of the temperature change amounts with the third threshold. If the absolute value of the average value of the temperature change amounts is greater than the third threshold (step ST22: Yes), the first correction unit 63 corrects the first range, and the second correction unit 64 corrects the second range (step ST23).

[0090] For example, the upper bounds of the first and second ranges are positive numbers, and their lower bounds are negative numbers.

[0091] As shown in [Table 5], in relatively high-temperature environments, the time variation of the variance when a person enters or exits becomes small. Therefore, when the temperature change of two or more detection areas R1 is a positive number, the larger the temperature change, the closer the upper limit and lower limit are to 0. This allows for the detection of a person's entry or exit even when the time variation of the variance is relatively small.

[0092] Furthermore, as shown in [Table 3], in relatively low-temperature environments, the time variation of the variance when a person enters or exits becomes large. Therefore, when the temperature change of two or more detection areas R1 is a negative number, the larger the temperature change, the further the upper limit is moved from 0 (i.e., increased), and the further the lower limit is moved from 0 (i.e., decreased). As a result, when the time variation of the variance is relatively small, the entry or exit of a person will not be detected. Here, the temperature change of two or more detection areas R1 is, for example, the average value of the changes in each of the two or more temperature values ​​of the two or more detection areas R1.

[0093] Thus, the human detection system 1 includes a first correction unit 63 that corrects the first range, and the first correction unit 63 corrects the first range according to the amount of change over time of two or more temperature values ​​in two or more detection areas R1 included in the block that does not satisfy the second condition among the multiple blocks.

[0094] Furthermore, the human detection system 1 includes a second correction unit 64 that corrects the second range, and the second correction unit 64 corrects the second range according to the amount of change over time of two or more temperature values ​​in two or more detection areas R1 included in the block that does not satisfy the second condition among the multiple blocks.

[0095] Next, we will explain how the human detection system 1 detects the entry or exit of people when a heat source is present in area A1.

[0096] Table 7 shows an example of the temperature distribution when a person and a heat source (e.g., a fan heater) are present in area A1. In detection area R1 where a person is present, the temperature is 34°C or 35°C, and in detection area R1 where a heat source is present, the temperature is 22°C. In detection area R1 where neither a person nor a heat source is present, the temperature is 18°C.

[0097] [Table 7]

[0098] Table 8 shows an example of the temperature distribution when a person leaves area A1 and a heat source is present in area A1. In detection area R1 where the heat source is present, the temperature value is 22°C, and in detection area R1 where the heat source is absent, the temperature value is 18°C.

[0099] [Table 8]

[0100] In Table 7, the first variance is 42.6. In Table 8, the first variance is 0.9. Therefore, when transitioning from the state in Table 7 to the state in Table 8, the change in the first variance over time is 0.9 - 42.6 = -41.7.

[0101] In step ST5, the decision unit 62 determines whether the time change of the first variance is outside the first range. Here, the first range is defined as the range of -10 or more and 10 or less. Therefore, the time change of the first variance is outside the first range (step ST5: Yes).

[0102] Next, in step ST6, the decision unit 62 determines whether the time change of the second variance for any block is outside the second range. Here, the second range is defined as the range of -40 or more and 40 or less. For the central block, the second variance is 60.7 in [Table 7] and 2.8 in [Table 8]. Therefore, the time change of the second variance is 2.8 - 60.7 = -57.9. Thus, the time change of the second variance is outside the second range (step ST6: Yes).

[0103] Furthermore, the maximum temperature value of the central block (22°C) is lower than both the first threshold (33°C) and the second threshold (30°C). Therefore, the determination unit 62 determines that a person has left area A1 (see steps ST7 to ST11). In this way, even if an object with a temperature different from the background temperature is present, the possibility of the determination unit 62 misidentifying the object as a person is small.

[0104] As another example, the judgment device 5 stores the temperature distribution when there is no person in area A1 in the storage unit 52, and when determining the amount of change in temperature over time, it may subtract the difference from the background temperature for detection areas R1 that show a temperature different from the background temperature. As a result, for example, [Table 7] and [Table 8] are changed to [Table 3] and [Table 1], respectively, thereby reducing the possibility that pre-existing heat sources may affect the detection of people.

[0105] (modified version) The following are examples of modifications of the embodiment. These modifications may be implemented by combining them as appropriate.

[0106] It is not essential that the human detection system 1 includes an infrared sensor array 3. The human detection system 1 only needs to include at least a temperature acquisition unit 61 and a determination unit 62. For example, the human detection system 1 may include a determination device 5 but not a sensor module 2.

[0107] The parameters compared with the temperature value when detecting a person's entry or exit, such as the upper and lower limits of the first and second ranges, may be determined based on the simulation results of the radiant temperature distribution generated as a radiant temperature image by the sensor module 2. Alternatively, the above parameters may be determined based on the radiant temperature image actually generated by the sensor module 2 during the testing phase. In the simulation or testing, for example, a radiant temperature image is generated when a person is in area A1 and when there is no person in area A1. The person detection system 1 may also be equipped with an operating device that accepts input of the above parameters by user operation.

[0108] The timing at which the determination device 5 registers the multiple temperature values, first variances, and second variances to be compared with the most recent multiple temperature values, first variances, and second variances is not limited to when the determination unit 62 determines that a person has entered or left. The determination device 5 may, for example, register the multiple temperature values, first variances, and second variances to be compared at regular intervals.

[0109] It is not essential for the determination unit 62 to determine whether a person has entered or exited area A1. The determination unit 62 only needs to be configured to determine whether either an entry or exit has occurred.

[0110] The one or more conditions used by the determination unit 62 to determine whether a person has entered or left only need to include at least the first condition, and do not need to include the second condition, etc. For example, the determination unit 62 may determine that a person has entered or left as soon as the first condition is met. Alternatively, the determination unit 62 may determine whether a person has entered or left by determining whether the first condition is met and by comparing multiple temperature values ​​with at least one of the first threshold and the second threshold.

[0111] The entity that executes the human detection system 1 or human detection method in this disclosure includes a computer system. The computer system mainly consists of a processor and memory as hardware. At least a part of the functions of the entity that executes the human detection system 1 or human detection method in this disclosure is realized by the processor executing a program recorded in the memory of the computer system. The program may be pre-recorded in the memory of the computer system, provided via a telecommunications line, or provided on a non-temporary recording medium such as a memory card, optical disk, or hard disk drive that can be read by the computer system. The processor of the computer system consists of one or more electronic circuits including semiconductor integrated circuits (ICs) or large-scale integrated circuits (LSIs). The integrated circuits such as ICs or LSIs referred to here are named differently depending on the degree of integration, and include integrated circuits called system LSIs, VLSIs (Very Large Scale Integration), or ULSIs (Ultra Large Scale Integration). Furthermore, FPGAs (Field-Programmable Gate Arrays) that are programmed after the manufacture of LSIs, or logic devices that allow for the reconfiguration of junction relationships or circuit compartments within LSIs, can also be used as processors. Multiple electronic circuits may be integrated onto a single chip or distributed across multiple chips. Multiple chips may be integrated onto a single device or distributed across multiple devices. The computer system referred to here includes a microcontroller having one or more processors and one or more memories. Therefore, the microcontroller also consists of one or more electronic circuits, including semiconductor integrated circuits or large-scale integrated circuits.

[0112] Furthermore, in this embodiment, multiple functions that are integrated into one device may be distributed across multiple devices. For example, the devices constituting the infrared sensor array 3 may be provided separately from the devices constituting the processing unit 4. Also, at least some of the functions of the human detection system 1, for example, some of the functions of the processing unit 6, may be implemented by a server or the cloud (cloud computing), etc.

[0113] Conversely, in the embodiment, at least some of the functions of the human detection system 1, which are distributed across multiple devices, may be consolidated into a single device. For example, the sensor module 2 and the determination device 5 may be consolidated into a single device. In this case, the processing unit 4 and the processing unit 6 may be integrated. As another example, the human detection system 1 may comprise a device including an infrared sensor array 3 and a device including processing unit 4 and processing unit 6.

[0114] (summary) Based on the embodiments described above, the following aspects are disclosed.

[0115] The first embodiment of the human detection system (1) detects a person based on a plurality of temperature values ​​detected using an infrared sensor array (3). The infrared sensor array (3) has a plurality of infrared sensors (31). The plurality of temperature values ​​are the temperature values ​​of a plurality of detection areas (R1) that correspond one-to-one with the plurality of infrared sensors (31). The human detection system (1) includes a temperature acquisition unit (61) and a determination unit (62). The temperature acquisition unit (61) acquires the plurality of temperature values. The determination unit (62) determines whether or not a person has entered or left an area (A1) that includes the plurality of detection areas (R1). The determination unit (62) determines that a person has entered or left an area (A1) if one or more conditions, including at least a first condition, are met. The first condition is that the time change in the variance or standard deviation of the plurality of temperature values ​​is outside a first range.

[0116] The above configuration reduces the possibility of false detection of whether or not a person is entering or leaving the facility.

[0117] Furthermore, in the human detection system (1) according to the second embodiment, the area (A1) is divided into multiple blocks as in the first embodiment. Each of the multiple blocks contains two or more detection areas (R1) from among the multiple detection areas (R1). The determination unit (62) determines for each of the multiple blocks whether the second condition is met. One or more conditions include the condition that there is a block among the multiple blocks that satisfies the second condition. The second condition is that the time change of the variance or standard deviation of two or more temperature values, which are the temperature values ​​of each of the two or more detection areas (R1), is outside the second range.

[0118] The above configuration further reduces the possibility of false detection of whether or not a person is entering or leaving the system.

[0119] Furthermore, in the third embodiment of the human detection system (1), in the second embodiment, the determination unit (62) determines that a person has entered area (A1) if the maximum value of two or more temperature values ​​of two or more detection areas (R1) included in a block that satisfies the second condition is greater than the first threshold.

[0120] According to the above configuration, the judgment unit (62) can determine whether a person has entered.

[0121] Furthermore, in the human detection system (1) according to the fourth embodiment, in the second or third embodiment, the determination unit (62) determines that a person has left area (A1) if the maximum value of two or more temperature values ​​of two or more detection areas (R1) included in a block that satisfies the second condition is less than the second threshold.

[0122] According to the above configuration, the judgment unit (62) can determine when a person is leaving.

[0123] Furthermore, the human detection system (1) according to the fifth embodiment further comprises a first correction unit (63) that corrects the first range in any one of the second to fourth embodiments. The first correction unit (63) corrects the first range according to the amount of change over time of two or more temperature values ​​in two or more detection areas (R1) included in a block that does not satisfy the second condition among a plurality of blocks.

[0124] According to the above configuration, it is possible to suppress the decrease in detection accuracy of whether or not a person is entering or leaving due to changes in background temperature.

[0125] Furthermore, the human detection system (1) according to the sixth embodiment further comprises a second correction unit (64) that corrects the second range in any one of the second to fifth embodiments. The second correction unit (64) corrects the second range according to the amount of change over time of two or more temperature values ​​in two or more detection areas (R1) included in a block that does not satisfy the second condition among a plurality of blocks.

[0126] According to the above configuration, it is possible to suppress the decrease in detection accuracy of whether or not a person is entering or leaving due to changes in background temperature.

[0127] Furthermore, the human detection system (1) according to the seventh embodiment further comprises an infrared sensor array (3) in any one of the first to sixth embodiments.

[0128] The above configuration reduces the possibility of false detection of whether or not a person is entering or leaving the facility.

[0129] Furthermore, in the eighth aspect of the human detection system (1), in any one of the first to seventh aspects, an acquisition unit (41) and a calculation unit (42) are further included. The acquisition unit (41) acquires multiple detection signals from the infrared sensor array (3) that correspond one-to-one with multiple infrared sensors (31). The calculation unit (42) processes the multiple detection signals and calculates multiple temperature values.

[0130] According to the above configuration, the human detection system (1) can calculate multiple temperature values ​​based on the output of the infrared sensor array (3).

[0131] Configurations other than those in the first embodiment are not essential to the human detection system (1) and can be omitted as appropriate.

[0132] Furthermore, the person detection method according to the ninth embodiment detects a person based on multiple temperature values ​​detected using an infrared sensor array (3). The infrared sensor array (3) has multiple infrared sensors (31). The multiple temperature values ​​are the temperature values ​​of multiple detection areas (R1) that correspond one-to-one with the multiple infrared sensors (31). The person detection method has a temperature acquisition step and a determination step. In the temperature acquisition step, multiple temperature values ​​are acquired. In the determination step, it is determined whether or not a person has entered or left an area (A1) that includes the multiple detection areas (R1). In the determination step, it is determined that a person has entered or left an area (A1) if one or more conditions, including at least a first condition, are met. The first condition is that the time change in the variance or standard deviation of the multiple temperature values ​​is outside a first range.

[0133] The above configuration reduces the possibility of false detection of whether or not a person is entering or leaving the facility.

[0134] Furthermore, the program relating to the tenth embodiment is a program that causes one or more processors of a computer system to execute the human detection method relating to the ninth embodiment.

[0135] The above configuration reduces the possibility of false detection of whether or not a person is entering or leaving the facility.

[0136] Not limited to the above embodiments, various configurations (including modifications) of the human detection system (1) according to the embodiment can be embodied in a human detection method, a (computer) program, or a non-temporary recording medium on which the program is recorded. [Explanation of Symbols]

[0137] 1-person detection system 3. Infrared sensor array 31 Infrared Sensor 41 Acquisition Department 42 Arithmetic section 61 Temperature acquisition section 62 Judgment Department 63. First Correction Section 64 Second Correction Section A1 Area R1 detection area

Claims

1. A human detection system that detects a person based on multiple temperature values ​​detected using an infrared sensor array having multiple infrared sensors, The aforementioned multiple temperature values ​​are the temperature values ​​of each of the multiple detection areas that correspond one-to-one with the multiple infrared sensors. The aforementioned human detection system A temperature acquisition unit that acquires the aforementioned multiple temperature values, The system includes a determination unit that determines whether or not a person has entered or exited an area including the aforementioned plurality of detection areas, The determination unit determines that a person has entered or exited the area when one or more conditions, including at least the first condition, are met. The first condition is that the time rate of change of the variance or standard deviation of the plurality of temperature values ​​is outside the first range. Human detection system.

2. The aforementioned area is divided into multiple blocks, Each of the aforementioned plurality of blocks includes two or more detection regions from the plurality of detection regions, The determination unit determines whether the second condition is met for each of the plurality of blocks, The above one or more conditions include the condition that there is a block among the plurality of blocks that satisfies the second condition, The second condition is that the time change of the variance or standard deviation of the two or more temperature values, which are the temperature values ​​of each of the two or more detection regions, is outside the second range. The human detection system according to claim 1.

3. The determination unit determines that a person has entered the area if the maximum value of the two or more temperature values ​​in the two or more detection areas included in the block that satisfies the second condition is greater than the first threshold. The human detection system according to claim 2.

4. The determination unit determines that a person has left the area if the maximum value of the two or more temperature values ​​in the two or more detection areas included in the block that satisfies the second condition is less than the second threshold. The human detection system according to claim 2.

5. The system further includes a first correction unit for correcting the first range, The first correction unit corrects the first range according to the time change in the two or more temperature values ​​in the two or more detection areas included in the block that does not satisfy the second condition among the plurality of blocks. The human detection system according to claim 2.

6. The system further includes a second correction unit for correcting the second range, The second correction unit corrects the second range according to the time change in the two or more temperature values ​​in the two or more detection areas included in the block that does not satisfy the second condition among the plurality of blocks. The human detection system according to claim 2.

7. The infrared sensor array further comprises the above-mentioned The human detection system according to claim 1.

8. An acquisition unit that acquires multiple detection signals from the infrared sensor array that correspond one-to-one with the multiple infrared sensors, The system further includes a calculation unit that processes the plurality of detection signals to calculate the plurality of temperature values. The human detection system according to claim 1.

9. A person detection method that detects a person based on multiple temperature values ​​detected using an infrared sensor array having multiple infrared sensors, The aforementioned multiple temperature values ​​are the temperature values ​​of each of the multiple detection areas that correspond one-to-one with the multiple infrared sensors. The aforementioned person detection method is: A temperature acquisition step in which the aforementioned multiple temperature values ​​are acquired, The system includes a determination step of determining whether or not a person has entered or exited an area that includes the aforementioned plurality of detection areas, In the aforementioned determination step, if one or more conditions, including at least the first condition, are met, it is determined that a person has entered or exited the area. The first condition is that the time rate of change of the variance or standard deviation of the plurality of temperature values ​​is outside the first range. Human detection method.

10. To cause one or more processors of a computer system to execute the person detection method described in claim 9, program.

Images