Detection system, detection method, and program

Abstract

The present disclosure addresses the problem of improving detection accuracy. A detection system (1) comprises a first generation unit (233), a second generation unit (234), a detection unit (235), and an adjustment unit (236). The first generation unit (233) performs signal processing on an output signal of an infrared sensor (3) to generate a first thermal image which has a plurality of pixels corresponding to a plurality of detection units (31) and in which pixel values are temperatures. The second generation unit (234) generates, on the basis of the first thermal image, a second thermal image that is a background thermal image corresponding to a state in which no person is present in a detection area. The detection unit (235) compares a plurality of corresponding pixels between the second thermal image and a third thermal image, which is a first thermal image to be subjected to determination as to whether a person is present in the detection area, and determines that a person is present in the detection area when there is a specific pixel at which the temperature of the third thermal image is higher than that of the second thermal image by a threshold temperature or more. The adjustment unit (236) adjusts, on the basis of the first thermal image, a threshold temperature for each of the plurality of pixels.

Description

Detection system, detection method, and program

[0001] The present disclosure generally relates to a detection system, a detection method, and a program, and more particularly to a detection system, a detection method, and a program using an infrared sensor.

[0002] Patent Literature 1 discloses an infrared sensor system that receives infrared rays from an object to be imaged, captures the object as a thermal image, and detects the temperature of the object from the thermal image.

[0003] In the infrared sensor system (detection system) such as that disclosed in Patent Document 1, it is desired to improve the accuracy of detecting objects (for example, people).

[0004] International Publication No. 2021 / 106322

[0005] The present disclosure has been made in consideration of the above-mentioned circumstances, and aims to provide a detection system, a detection method, and a program that can improve detection accuracy.

[0006] A detection system according to one aspect of the present disclosure detects a person present in a detection area of ​​an infrared sensor based on an output signal from the infrared sensor. The infrared sensor has multiple detectors arranged in a two-dimensional array. The detection system includes a first generator, a second generator, a detector, and an adjuster. The first generator processes the output signal from the infrared sensor to continuously generate first thermal images having multiple pixels whose pixel values ​​are temperature and correspond to the multiple detectors. The second generator generates a second thermal image, based on the first thermal image generated by the first generator, as a background thermal image corresponding to a state in which no person is present in the detection area. The detector compares the corresponding multiple pixels in the second thermal image with a third thermal image, which is the first thermal image to be used to determine whether a person is present in the detection area, and determines that a person is present in the detection area if the third thermal image has a specific pixel whose temperature is higher than the second thermal image by at least a threshold temperature. The adjuster adjusts the threshold temperature for each of the multiple pixels based on the first thermal image.

[0007] A detection method according to one aspect of the present disclosure detects a person present in a detection area of ​​an infrared sensor based on an output signal from the infrared sensor. The infrared sensor has multiple detectors arranged in a two-dimensional array. The detection method includes a first generation step, a second generation step, a detection step, and an adjustment step. In the first generation step, the output signal from the infrared sensor is processed to continuously generate first thermal images having multiple pixels whose pixel values ​​are temperature and correspond to the multiple detectors. In the second generation step, a second thermal image is generated based on the first thermal image generated in the first generation step, serving as a background thermal image corresponding to a state in which no person is present in the detection area. In the detection step, a third thermal image, which is the first thermal image to be used to determine whether a person is present in the detection area, is compared with the corresponding multiple pixels in the second thermal image. If a specific pixel in the third thermal image has a temperature higher than that of the second thermal image by at least a threshold temperature, it is determined that a person is present in the detection area. In the adjustment step, the threshold temperature for each of the multiple pixels is adjusted based on the first thermal image.

[0008] A program according to one aspect of the present disclosure is a program for causing one or more processors to execute the detection method.

[0009] Fig. 1 is a schematic diagram showing the configuration of a detection system according to an embodiment. Fig. 2 is an explanatory diagram for explaining a threshold temperature in the detection system. Fig. 3 is a flowchart showing the operation of a detection device included in the detection system. Fig. 4 is an explanatory diagram for explaining a threshold temperature in a detection system according to a first modification.

[0010] Preferred embodiments of the present disclosure will be described in detail below with reference to the drawings. Common elements in the embodiments described below are designated by the same reference numerals, and redundant descriptions of the common elements may be omitted. The following embodiments and modifications are merely a portion of various embodiments of the present disclosure. Various modifications of the following embodiments and modifications may be made depending on the design, etc., as long as the object of the present disclosure can be achieved. The configurations of the embodiments and modifications may also be combined as appropriate.

[0011] The drawings described in this disclosure are schematic drawings, and the ratios of the sizes and thicknesses of the components in the drawings do not necessarily reflect the actual dimensional ratios.

[0012] (1) Overview First, an overview of a detection system 1 according to this embodiment will be described with reference to FIG.

[0013] As shown in FIG. 1 , the detection system 1 of this embodiment is installed in a facility 100. The detection system 1 is a system that detects people within the facility 100. In this embodiment, it is assumed that the facility 100 is an office. In this disclosure, the term "facility" includes residential facilities used for residential purposes, as well as non-residential facilities such as stores, offices, welfare facilities, educational facilities, hospitals, and factories. Non-residential facilities also include restaurants, amusement parks, hotels, inns, kindergartens, nurseries, and community centers. In other words, the facility 100 may be a residential facility such as an apartment building, or a non-residential facility such as an office. Furthermore, the facility 100 also includes a facility in which residential and non-residential facilities coexist, for example, with stores on the lower floors and residences on the upper floors.

[0014] The detection system 1 detects a person present in the detection area of ​​the infrared sensor 3 based on the output signal of the infrared sensor 3. The infrared sensor 3 has a plurality of detection units 31 arranged in a two-dimensional array. The infrared sensor 3 of this embodiment has a detection area that is a three-dimensional area including the floor of an office or the like. In other words, the detection system 1 of this embodiment detects a person present on the floor of an office or the like.

[0015] The detection system 1 includes a first generation unit 233 , a second generation unit 234 , a detection unit 235 , and an adjustment unit 236 .

[0016] The first generation unit 233 processes the output signal of the infrared sensor 3 to continuously generate a first thermal image having a plurality of pixels 41 (see FIG. 2 ) whose pixel values ​​represent temperatures and correspond to a plurality of detection units 31 .

[0017] The second generation unit 234 generates a second thermal image, which serves as a background thermal image corresponding to a state in which no person is present in the detection area, based on the first thermal image generated by the first generation unit 233.

[0018] The detection unit 235 compares the third thermal image, which is the first thermal image to be used to determine whether a person is present in the detection area, with multiple corresponding pixels 41 in the second thermal image, and determines that a person is present in the detection area if the third thermal image contains a specific pixel (pixel 41) whose temperature is higher than the threshold temperature or more in the second thermal image.

[0019] The adjustment unit 236 adjusts the threshold temperature for each of the plurality of pixels 41 based on the first thermal image.

[0020] The detection system 1 of this embodiment can improve the accuracy of human detection by adjusting the threshold temperature for each of the pixels 41 based on the thermal image (first thermal image). For example, the detection system 1 of this embodiment can accurately detect a human even when there are variations in the temperature of the floor surface included in the detection area.

[0021] (2) Details The detailed configuration of the detection system 1 according to this embodiment will be described below with reference to FIGS. 1 and 2. FIG.

[0022] As shown in FIG. 1 , the detection system 1 includes a detection device 2 and an infrared sensor 3 .

[0023] (2.1) Configuration of Infrared Sensor The infrared sensor 3 is installed directly or indirectly on a construction material such as a wall or ceiling of the facility 100. In this embodiment, the infrared sensor 3 is installed on the ceiling of an office, and the detection area is a three-dimensional area including the floor surface of the office.

[0024] The infrared sensor 3 has optical components such as lenses and multiple (64 in the example of FIG. 1 ) detecting units 31 (multiple thermal imaging elements). The 64 detecting units 31 are arranged in a two-dimensional array of m rows and n columns (m and n are natural numbers) on the main surface of the substrate 30. In this embodiment, m = 8 and n = 8. For example, the detecting units 31 are thermal infrared detecting units. The detecting units 31 receive infrared rays, such as far-infrared rays, emitted by an object and convert them into electrical signals (output signals). The infrared sensor 3 transmits output signals from each of the multiple detecting units 31 to the detection device 2. In the following description, the output signals from each of the multiple detecting units 31 may be simply referred to as the "output signals of the infrared sensor 3."

[0025] (2.2) Configuration of the Detection Device The detection device 2 includes a communication unit 21, a storage unit 22, and a processing unit 23.

[0026] The communication unit 21 includes a communication interface configured to be able to communicate with the infrared sensor 3. The communication unit 21 receives output signals of each of the plurality of detection units 31 from the infrared sensor 3.

[0027] The storage unit 22 is a semiconductor memory such as a read-only memory (ROM), a random access memory (RAM), or an electrically erasable programmable read-only memory (EEPROM). Note that the storage unit 22 is not limited to a semiconductor memory and may be a hard disk drive or the like.

[0028] The processing unit 23 is mainly composed of a computer system having one or more processors and a memory. The functions of the processing unit 23 are realized by the processor of the computer system executing a program recorded in the memory or storage unit 22 of the computer system. The program may be recorded in the memory or storage unit 22, or may be provided via a telecommunications line such as the Internet, or may be recorded on a non-transitory recording medium such as a memory card and provided.

[0029] The processing unit 23 includes an acquisition unit 231 , a filter unit 232 , a first generation unit 233 , a second generation unit 234 , a detection unit 235 , and an adjustment unit 236 .

[0030] The acquisition unit 231 acquires the output signal of the infrared sensor 3 via the communication unit 21 .

[0031] The filter unit 232 is a digital filter such as an IIR (Infinite Impulse Response) filter. The filter unit 232 performs filtering on the output signal of the infrared sensor 3 acquired by the acquisition unit 231 to remove noise components contained in the output signal. The filter unit 232 may also be an FIR (Finite Impulse Response) filter.

[0032] The first generating unit 233 processes the output signal filtered by the filter unit 232 to continuously generate first thermal images, which are still images (first generating step). The first thermal image (thermal image 4) has a plurality of pixels 41 corresponding to the plurality of detectors 31. The pixel value of the pixel 41 is a temperature.

[0033] FIG. 2B shows an example of a thermal image 4. In this embodiment, the thermal image 4 has 64 pixels 41. The 64 pixels 41 are arranged in a two-dimensional array of m rows and n columns (m and n are natural numbers). In this embodiment, m = 8 and n = 8. That is, the 64 pixels 41 of the first thermal image correspond one-to-one to the 64 detectors 31. In FIG. 2B, the temperature of each of the multiple pixels 41 is indicated by the density of the dot hatching. In the example of FIG. 2B, the higher the density of the dot hatching, the higher the temperature. The parts without dot hatching are the parts with the lowest temperature in the thermal image 4.

[0034] The second generation unit 234 generates a second thermal image (thermal image 4) based on the first thermal image (thermal image 4) generated by the first generation unit 233 (second generation step). The second thermal image is a background thermal image in a state where no person is present in the detection area of ​​the infrared sensor 3. Like the first thermal image, the second thermal image also has 64 pixels 41 arranged in 8 rows and 8 columns. The 64 pixels 41 of the second thermal image correspond one-to-one to the 64 detection units 31.

[0035] In this embodiment, the second generation unit 234 updates the second thermal image based on a plurality of chronologically consecutive first thermal images. When generating the second thermal image, the second generation unit 234 does not use the pixel value of the pixel 41 (specific pixel) where a person is detected by the detection unit 235.

[0036] The detection unit 235 performs a human detection process. In the human detection process, the detection unit 235 compares a plurality of corresponding pixels 41 between the third thermal image (thermal image 4) and the second thermal image, and determines that a person is present in the detection area if a specific pixel in the third thermal image has a temperature higher than that of the second thermal image by at least a threshold (detection step). In other words, in the human detection process, the detection unit 235 compares a plurality of corresponding pixels 41 between the third thermal image and the second thermal image, and determines that a person is present in the detection area if a specific pixel in the third thermal image has a temperature higher than that of the second thermal image by at least a threshold. For example, the detection unit 235 determines that a person is present in the detection area if a specific area formed by a plurality of (e.g., four or more) specific pixels is included in the third thermal image. Furthermore, in the human detection process, the detection unit 235 compares corresponding pixels 41 between the third thermal image and the second thermal image, and determines that no human is present in the detection area if there is no specific pixel in the third thermal image whose temperature is higher than the threshold temperature in the second thermal image by at least the threshold temperature. The third image is the first thermal image that is used to determine whether or not a human is present in the detection area. In other words, the third thermal image is the thermal image 4 generated by the first generation unit 233. Like the first and second thermal images, the third thermal image also has 64 pixels 41 arranged in 8 rows and 8 columns. The 64 pixels 41 in the third thermal image correspond one-to-one to the 64 detection units 31.

[0037] The detection unit 235 outputs the detection result. For example, the detection unit 235 transmits the detection result to a device other than the detection device 2 via the communication unit 21. Furthermore, if the detection device 2 has a display unit such as an LCD (Liquid Crystal Display), the detection unit 235 may display the detection result on the display unit.

[0038] The adjustment unit 236 calculates a moving average value [°C] of the time-series data for each of the pixels 41 over a predetermined period using multiple consecutive first thermal images. The predetermined period is, for example, one minute. However, the predetermined period may be set as appropriate. The adjustment unit 236 adjusts (or sets) the threshold temperature for each of the pixels 41 based on the calculated moving average value. In other words, the adjustment unit 236 adjusts the threshold temperature for each of the pixels 41 based on the first thermal image (adjustment step). According to the detection system 1 of this embodiment, the threshold temperature for each of the pixels 41 is set using the moving average value for each of the pixels 41, thereby further improving the accuracy of human detection.

[0039] Fig. 2A shows a graph G1 indicating the moving average values ​​calculated by the adjustment unit 236. Note that the graph G1 corresponds to the eight pixels 41 in the fifth row in Fig. 2B. In this embodiment, it is assumed that the temperature distribution of the eight pixels 41 in the fifth row in Fig. 2B matches the distribution of the eight moving average values ​​in Fig. 2A calculated by the adjustment unit 236.

[0040] The adjustment unit 236 adjusts the threshold temperature for each of the plurality of pixels 41 based on the calculated moving average value for each of the plurality of pixels 41 and the specified temperature T1. Specifically, the adjustment unit 236 adjusts the threshold temperature for each of the plurality of pixels 41 based on a value (difference) obtained by subtracting the moving average value for each of the plurality of pixels 41 from the specified temperature T1. More specifically, the adjustment unit 236 sets the threshold temperature for each of the plurality of pixels 41 to a value obtained by dividing the value obtained by subtracting the moving average value for each of the plurality of pixels 41 from the specified temperature T1 by 2.

[0041] However, it is not essential that the adjustment unit 236 set the value obtained by subtracting the moving average value for each of the plurality of pixels 41 from the specified temperature T1 and dividing the result by 2 as the threshold temperature for each of the plurality of pixels 41. The adjustment unit 236 may adjust the threshold temperature so that the threshold temperature is lower than the value (difference) obtained by subtracting the moving average value for each of the plurality of pixels 41 from the specified temperature T1.

[0042] In this embodiment, the specified temperature T1 is 36° C. The specified temperature T1 is based on the temperature (body temperature) of a person, which is the object to be detected by the detection system 1. However, the specified temperature T1 may be set as appropriate.

[0043] Graph G0 in FIG. 2A is a graph showing the specified temperature T1. The difference X1 in FIG. 2A is the value obtained by subtracting from the specified temperature T1 the moving average values ​​of the pixel 41 in row 5, column 1, the pixel 41 in row 5, column 4, the pixel 41 in row 5, column 5, and the pixel 41 in row 5, column 7. The difference X2 in FIG. 2A is the value obtained by subtracting from the specified temperature T1 the moving average values ​​of the pixel 41 in row 5, column 2, the pixel 41 in row 5, column 3, and the pixel 41 in row 5, column 6. The difference X3 in FIG. 2A is the value obtained by subtracting from the specified temperature T1 the moving average value of the pixel 41 in row 5, column 8. Graph G2 in FIG. 2A is a graph showing the threshold temperatures of the eight pixels 41 in the fifth row.

[0044] 2A, if the moving average value of pixel 41 in row 5, column 1 is, for example, 24° C., the difference X1 is 12° C., and the threshold temperature of pixel 41 in row 5, column 1 is 6° C. Furthermore, if the moving average value of pixel 41 in row 5, column 2 is, for example, 26° C., the difference X2 is 10° C., and the threshold temperature of pixel 41 in row 5, column 2 is 5° C. Furthermore, if the moving average value of pixel 41 in row 5, column 8 is, for example, 28° C., the difference X3 is 8° C., and the threshold temperature of pixel 41 in row 5, column 8 is 4° C.

[0045] That is, when adjusting the threshold temperature, the adjuster 236 adjusts the threshold temperature lower as the moving average value of the plurality of pixels 41 increases. In other words, in this embodiment, the threshold temperature for each of the plurality of pixels 41 decreases as the moving average value of the pixel increases.

[0046] If the threshold temperature for each of the multiple pixels 41 is constant, there is a possibility that the detection unit 235 will not detect a person even if they are on a hot floor. For example, if the threshold temperature for each of the multiple pixels 41 is constant at 6°C and the floor temperature is 32°C, a person with a body temperature of 36°C will not be detected by the detection unit 235 even if they are on the floor. According to the detection system 1 of this embodiment, when the floor temperature is 32°C, the threshold temperature for the pixel 41 corresponding to the 32°C floor is adjusted to 2°C, making it possible to detect a person on a 32°C floor. In other words, by having the adjustment unit 236 adjust the threshold temperature so that the higher the moving average value of the multiple pixels 41, the lower the threshold temperature, thereby reducing the possibility that the detection unit 235 will not be able to detect the presence of a person and further improving the accuracy of person detection.

[0047] (3) Operation of the Detection Device Next, the operation of the detection device 2 will be described with reference to FIG.

[0048] First, the detection device 2 acquires temperature data (output signal) from the infrared sensor 3 (step S1). Next, the detection device 2 performs filtering on the acquired output signal (step S2). After filtering, the detection device 2 generates a plurality of first thermal images and a second thermal image that are successive in time series.

[0049] Next, the detection device 2 uses multiple consecutive first images to calculate a time-series moving average value for each of the multiple pixels 41 over a predetermined period, and sets a threshold temperature for each of the multiple pixels 41 based on the calculated moving average value (step S3).

[0050] Next, the detection device 2 performs a human detection process (step S4), outputs the detection result (step S5), and ends the series of processes shown in FIG.

[0051] The flowchart shown in FIG. 3 is merely an example, and the order of the processes may be changed as appropriate, and processes may be added or deleted as appropriate.

[0052] (4) Modifications Modifications of the above embodiment are listed below.

[0053] (4.1) Modification 1 In Modification 1, when one pixel 41 among the plurality of pixels 41 in the third thermal image is a specific pixel for a predetermined time or more, the detection unit 235 determines that the detection of a person at the pixel 41 is a false detection. The predetermined time is, for example, 0.5 seconds. However, the predetermined time may be set as appropriate.

[0054] In Figure 4(b), pixel 41 at row 5, column 6 has been a specific pixel for a predetermined period of time or more. The detection unit 235 of Modification 1 does not determine the presence of a person even if the temperature difference between pixel 41 at row 5, column 6 in the third thermal image and pixel 41 at row 5, column 6 in the second thermal image is equal to or greater than the threshold temperature. This prevents the detection unit 235 from determining the presence of a person when, for example, sunlight is shining on the floor surface included in the detection area, thereby further improving the accuracy of person detection.

[0055] Furthermore, when adjusting the threshold temperature, the adjustment unit 236 of Modification 1 adjusts the threshold temperature without using the pixel value of the pixel 41 related to the erroneous detection by the detection unit 235. In FIG. 4B , the pixel 41 in row 5, column 6 is the pixel 41 related to the erroneous detection by the detection unit 235. That is, when adjusting the threshold temperature, the adjustment unit 236 adjusts the threshold temperature without using the pixel value (e.g., approximately 32°C) of the pixel 41 in row 5, column 6 when it is a specific pixel. When adjusting the threshold temperature, the adjustment unit 236 adjusts the threshold temperature using the pixel value (e.g., approximately 24°C) of the pixel 41 in row 5, column 6 before it became a specific pixel. The adjustment unit 236 of Modification 1 calculates a time-series moving average value [°C] for each of the pixels 41 over a predetermined period using multiple consecutive first thermal images without using the pixel value of the pixel 41 related to the erroneous detection by the detection unit 235.

[0056] 4A shows a graph G3 indicating the moving average value calculated by the adjustment unit 236. Graph G3 corresponds to the eight pixels 41 in the fifth row in FIG. 4B. In Modification 1, the temperature distribution of the eight pixels 41 in the fifth row in FIG. 4B is assumed to match the distribution of the eight moving average values ​​in FIG. 4A calculated by the adjustment unit 236. The dashed line in FIG. 4A indicates the moving average value when it is assumed that the pixel value (e.g., approximately 32°C) of the pixel 41 in the fifth row and sixth column that is a specific pixel is used.

[0057] Graph G0 in FIG. 4A is a graph showing the specified temperature T1. The difference X1 in FIG. 4A is the value obtained by subtracting the moving average values ​​of the pixel 41 in row 5, column 1, the pixel 41 in row 5, column 4, the pixel 41 in row 5, column 5, and the pixel 41 in row 5, column 7 from the specified temperature T1. The difference X2 in FIG. 4A is the value obtained by subtracting the moving average values ​​of the pixel 41 in row 5, column 2 and the pixel 41 in row 5, column 3 from the specified temperature T1. The difference X3 in FIG. 4A is the value obtained by subtracting the moving average value of the pixel 41 in row 5, column 8 from the specified temperature T1. In Modification 1, the moving average value using the pixel value of the pixel 41 in row 5, column 6 before it became a specific pixel is equal to that of the pixel 41 in row 5, column 1, etc. 4A is a value obtained by subtracting from the specified temperature T1 a moving average value using the pixel value of the pixel 41 in the fifth row and sixth column before the pixel 41 became a specific pixel. Graph G4 in FIG. 4A is a graph showing the threshold temperatures of the eight pixels 41 in the fifth row.

[0058] 4A, if the moving average value of the pixel 41 in the first row and the pixel 41 in the sixth row is, for example, 24° C., the difference X1 is 12° C., and the threshold temperature of the pixel 41 in the first row and the pixel 41 in the sixth row is 6° C. Furthermore, if the moving average value of the pixel 41 in the second row and the pixel 41 in the sixth row is, for example, 26° C., the difference X2 is 10° C., and the threshold temperature of the pixel 41 in the second row and the pixel 41 in the sixth row is 5° C. Furthermore, if the moving average value of the pixel 41 in the eighth row and the pixel 41 in the eighth row is, for example, 28° C., the difference X3 is 8° C., and the threshold temperature of the pixel 41 in the eighth row and the pixel 41 in the eighth row is 4° C.

[0059] (4.2) Other Modifications Functions equivalent to those of the detection system 1 according to the above embodiment may be embodied as a detection method, a (computer) program, a non-transitory recording medium having a program recorded thereon, or the like. A detection method according to one aspect detects a person present in the detection area of ​​the infrared sensor 3 based on an output signal from the infrared sensor 3. The infrared sensor 3 has a plurality of detection units 31 arranged in a two-dimensional array. The detection method includes a first generation step, a second generation step, a detection step, and an adjustment step. In the first generation step, the output signal from the infrared sensor 3 is processed to continuously generate first thermal images having a plurality of pixels 41, each pixel value representing temperature and corresponding to the plurality of detection units 31. In the second generation step, a second thermal image is generated based on the first thermal image generated in the first generation step, serving as a background thermal image corresponding to a state in which no person is present in the detection area. In the detection step, the third thermal image, which is the first thermal image to be used to determine whether a person is present in the detection area, is compared with the second thermal image for corresponding pixels 41, and it is determined that a person is present in the detection area if there is a specific pixel 41 in the third thermal image whose temperature is higher than that of the second thermal image by at least a threshold temperature. In the adjustment step, the threshold temperature for each of the pixels 41 is adjusted based on the first thermal image. A program according to one aspect is a program for causing one or more processors to execute the above detection method.

[0060] The execution entity of the detection system 1 or the detection method of the present disclosure includes a computer system. The computer system is primarily composed of a processor and memory as hardware. The processor executes a program stored in the memory of the computer system to realize the functions of the execution entity of the detection system 1 or the detection method of the present disclosure. The program may be pre-recorded in the memory of the computer system, provided via a telecommunications line, or provided in a non-transitory recording medium readable by the computer system, such as a memory card, optical disk, or hard disk drive. The processor of the computer system is composed of one or more electronic circuits including a semiconductor integrated circuit (IC) or a large-scale integrated circuit (LSI). The integrated circuits, such as ICs or LSIs, are referred to by different names depending on the degree of integration, and include integrated circuits called system LSIs, very large-scale integrations (VLSIs), or ultra-large-scale integrations (ULSIs). Furthermore, field-programmable gate arrays (FPGAs), which are programmed after the LSI is manufactured, or logic devices capable of reconfiguring the connections within the LSI or the circuit partitions within the LSI, can also be used as processors. The electronic circuits may be integrated into one chip or distributed across multiple chips. The chips may be integrated into one 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 is also composed of one or more electronic circuits including a semiconductor integrated circuit or a large-scale integrated circuit.

[0061] Furthermore, it is not essential for the detection system 1 that multiple functions are concentrated in one housing, and the components of the detection system 1 may be distributed across multiple housings. Furthermore, at least some of the functions of the detection system 1, for example, some of the functions of the detection device 2, may be realized by the cloud (cloud computing) or the like.

[0062] In the above embodiment, at least some of the functions of the detection system 1 that are distributed among multiple devices may be integrated into a single housing. For example, some of the functions of the detection system 1 that are distributed among the detection device 2 and the infrared sensor 3 may be integrated into a single housing.

[0063] In the above embodiment, the 64 pixels 41 in the thermal image 4 (first to third thermal images) correspond one-to-one to the 64 detectors 31. However, the first generator 233 and the second generator 234 may increase the number of pixels in the thermal image 4 by performing image interpolation when generating the thermal image 4. For example, the thermal image 4 may have 256 pixels 41. The 256 pixels 41 are arranged in a two-dimensional array of, for example, 16 rows and 16 columns. For example, the 256 pixels 41 correspond four-to-one to the 64 detectors 31.

[0064] As is apparent from the above-described embodiment and modified examples, a detection system (1) according to a first embodiment detects a person present in the detection area of ​​an infrared sensor (3) based on an output signal from the infrared sensor (3). The infrared sensor (3) has a plurality of detection units (31) arranged in a two-dimensional array. The detection system (1) includes a first generation unit (233), a second generation unit (234), a detection unit (235), and an adjustment unit (236). The first generation unit (233) processes the output signal from the infrared sensor (3) to continuously generate a first thermal image (thermal image 4) having a plurality of pixels (41) whose pixel values ​​represent temperatures and correspond to the plurality of detection units (31). The second generation unit (234) generates a second thermal image, which serves as a background thermal image corresponding to a state in which no person is present in the detection area, based on the first thermal image generated by the first generation unit (233). The detection unit (235) compares a plurality of corresponding pixels (41) between the third thermal image, which is the first thermal image to be used to determine whether a person is present in the detection area, and the second thermal image, and determines that a person is present in the detection area if there is a specific pixel (41) in the third thermal image whose temperature is higher than that of the second thermal image by at least a threshold temperature. The adjustment unit (236) adjusts the threshold temperature for each of the plurality of pixels (41) based on the first thermal image.

[0065] According to this aspect, it is possible to improve the detection accuracy.

[0066] In the detection system (1) according to the second aspect, in the first aspect, the adjustment unit (236) calculates a time-series moving average value for each of the plurality of pixels (41) using a plurality of consecutive first thermal images (thermal images 4), and adjusts the threshold temperature for each of the plurality of pixels (41) based on the calculated moving average value.

[0067] According to this aspect, it is possible to further improve the detection accuracy.

[0068] In the detection system (1) according to the third aspect, in the second aspect, the threshold temperature for each of the plurality of pixels (41) is lower for pixels (41) with a higher moving average value.

[0069] According to this aspect, it is possible to further improve the detection accuracy.

[0070] In the detection system (1) according to the fourth aspect, in any of the first to third aspects, the detection unit (235) determines that the detection of a person relating to one pixel (41) is a false detection when one pixel (41) among the plurality of pixels (41) is a specific pixel (41) for a predetermined period of time or more.

[0071] According to this aspect, it is possible to further improve the detection accuracy.

[0072] In the detection system (1) according to the fifth aspect, in the fourth aspect, the adjustment unit (236) adjusts the threshold temperature without using the pixel value of one pixel (41) related to the erroneous detection by the detection unit (235).

[0073] The configurations other than the first aspect are not essential for the detection system (1) and can be omitted as appropriate.

[0074] A detection method according to a sixth aspect detects a person present in the detection area of ​​an infrared sensor (3) based on an output signal from the infrared sensor (3). The infrared sensor (3) has a plurality of detection units (31) arranged in a two-dimensional array. The detection method includes a first generation step, a second generation step, a detection step, and an adjustment step. In the first generation step, signal processing is performed on the output signal from the infrared sensor (3) to continuously generate first thermal images having a plurality of pixels (41) whose pixel values ​​represent temperatures and correspond to the plurality of detection units (31). In the second generation step, a second thermal image is generated based on the first thermal image generated in the first generation step, serving as a background thermal image corresponding to a state in which no person is present in the detection area. In the detection step, a third thermal image, which is the first thermal image to be used to determine whether a person is present in the detection area, is compared with the corresponding plurality of pixels (41) in the second thermal image, and it is determined that a person is present in the detection area if the third thermal image has a specific pixel (41) whose temperature is higher than the second thermal image by at least a threshold temperature. In the adjusting step, the threshold temperature for each of the plurality of pixels (41) is adjusted based on the first thermal image.

[0075] According to this aspect, it is possible to improve the detection accuracy.

[0076] A program according to a seventh aspect is a program for causing one or more processors to execute the detection method according to the sixth aspect.

[0077] According to this aspect, it is possible to improve the detection accuracy.

[0078] REFERENCE SIGNS LIST 1 Detection system 233 First generation unit 234 Second generation unit 235 Detection unit 236 Adjustment unit 3 Infrared sensor 31 Detection unit 4 Thermal image (first thermal image, second thermal image, third thermal image) 41 Pixel

Claims

1. A detection system that detects the presence of a person in the detection area of ​​an infrared sensor based on the output signal of the infrared sensor having multiple detection units arranged in a two-dimensional array, comprising: a first generation unit that processes the output signal of the infrared sensor and continuously generates first thermal images having multiple pixels whose pixel values ​​are temperature and correspond to the multiple detection units; a second generation unit that generates a second thermal image based on the first thermal image generated by the first generation unit, which serves as a background thermal image corresponding to a state where no person is present in the detection area; a detection unit that compares a third thermal image, which is the first thermal image that is used to determine whether or not a person is present in the detection area, with multiple corresponding pixels in the second thermal image, and determines that a person is present in the detection area if the third thermal image has a specific pixel whose temperature is higher than the second thermal image by at least a threshold temperature; and an adjustment unit that adjusts the threshold temperature for each of the multiple pixels based on the first thermal image.

2. The detection system according to claim 1, wherein the adjustment unit calculates a time-series moving average value for each of the plurality of pixels using a plurality of consecutive first thermal images, and adjusts the threshold temperature for each of the plurality of pixels based on the calculated moving average value.

3. The detection system according to claim 2, wherein the threshold temperature for each of the plurality of pixels is lower for pixels with a higher moving average value.

4. The detection system according to any one of claims 1 to 3, wherein the detection unit determines that the detection of a person relating to one pixel is a false detection when one pixel among the plurality of pixels remains the specific pixel for a predetermined period of time or more.

5. The detection system according to claim 4, wherein the adjustment unit adjusts the threshold temperature without using the pixel value of the pixel related to the false detection by the detection unit.

6. A detection method for detecting a person present in a detection area of ​​an infrared sensor based on an output signal from the infrared sensor having a plurality of detection units arranged in a two-dimensional array, the detection method comprising: a first generation step of processing the output signal from the infrared sensor to continuously generate first thermal images having a plurality of pixels, each pixel value being temperature and corresponding to the plurality of detection units; a second generation step of generating a second thermal image, based on the first thermal image generated in the first generation step, as a background thermal image corresponding to a state in which no person is present in the detection area; a detection step of comparing a third thermal image, which is the first thermal image that is used to determine whether or not a person is present in the detection area, with a plurality of corresponding pixels in the second thermal image, and determining that a person is present in the detection area if the third thermal image has a specific pixel whose temperature is higher than the second thermal image by at least a threshold temperature; and an adjustment step of adjusting the threshold temperature for each of the plurality of pixels based on the first thermal image.

7. A program for causing one or more processors to execute the detection method according to claim 6.

Images