WO2023032771A1

WO2023032771A1 - Control method, program, and control system

Info

Publication number: WO2023032771A1
Application number: PCT/JP2022/031812
Authority: WO
Inventors: 千人浦; 仁吉澤; 達雄古賀
Original assignee: パナソニックＩｐマネジメント株式会社
Priority date: 2021-08-31
Filing date: 2022-08-24
Publication date: 2023-03-09
Also published as: JPWO2023032771A1

Abstract

A computer for, inter alia, a control system (10) for executing a control method performs the following: acquiring (S11) a thermal image (100) showing a temperature distribution of a to-be-air conditioned space detected by a sensor (20) installed on the ceiling of the to-be-air conditioned space; detecting (S12) the outline of a person (1) present in the to-be-air conditioned space on the basis of the thermal image (100); identifying (S13) a human body region(100a), which is a region surrounded by the outline of the person (1), in the thermal image (100); calculating (S14) a human body temperature including the temperature of clothing (1b) of the person (1) on the basis of the temperature distribution inside the human body region (100a); calculating (S15) an ambient temperature of a region (peripheral region (100b)) other than the human body region (100a) in the thermal image (100); calculating (S16) a heat dissipation amount of the person (1) on the basis of a differential value between the human body temperature and the ambient temperature; estimating (S17) a warm/cold sensation of the person (1) on the basis of the heat dissipation amount; and controlling (S18) an air conditioner (30) on the basis of the warm/cold sensation.

Description

Control method, program and control system

The present invention relates to an air conditioner control method, program, and control system.

Measure the temperature difference between the temperature of the occupant's nose and the temperature around the cheeks and / or forehead, measure the occupant's thermal state such as the occupant's sensation and comfort (hereinafter referred to as thermal sensation) based on the temperature difference, BACKGROUND ART There is known a technique for controlling an air conditioner mounted on a vehicle so that a passenger feels comfortable (see, for example, Patent Literature 1).

JP 2017-197195 A

However, in the technique described in Patent Document 1, the human thermal sensation is estimated only from the temperature around the person's face, and it is unbelievable that a comfortable environmental temperature can be realized by estimating the human thermal sensation. Hard to say.

Therefore, the present invention provides an air conditioner control method, program, and control system that estimate a person's thermal sensation and achieve a comfortable environmental temperature.

A control method according to an aspect of the present invention is an air conditioner control method executed by a computer, wherein the computer controls the temperature of the air-conditioned space detected by a sensor installed on the ceiling of the air-conditioned space. A thermal image showing the distribution is acquired, the outline of a person present in the air-conditioned space is detected based on the acquired thermal image, and a human body region, which is an area surrounded by the detected outline of the person, specifying in the thermal image, calculating the human body temperature including the temperature of the clothes of the person based on the specified temperature distribution in the human body region, and calculating the ambient temperature of the region other than the human body region in the thermal image; calculating the heat dissipation amount of the person based on the difference value between the human body temperature and the ambient temperature; estimating the thermal sensation of the person based on the calculated heat dissipation amount; The air conditioner is controlled based on the feeling of coolness.

A program according to one aspect of the present invention is a program for causing a computer to execute the control method.

A control system according to an aspect of the present invention includes an acquisition unit that acquires a thermal image showing the temperature distribution of the air-conditioned space detected by a sensor installed on the ceiling of the air-conditioned space, and the acquired thermal image: a detection unit that detects the contour of a person existing in the air-conditioned space based on the above; calculating a human body temperature including the temperature of clothes of the person based on the temperature distribution in the human body region, calculating an ambient temperature of a region other than the human body region in the thermal image, and calculating the human body temperature and the ambient temperature; a calculation unit that calculates the heat dissipation amount of the person based on the difference value between the heat dissipation amount of the person, an estimation unit that estimates the thermal sensation of the person based on the calculated heat dissipation amount, and based on the estimated thermal sensation and a control unit that controls the air conditioner installed in the air-conditioned space.

According to the present invention, an air conditioner control method and program that can estimate a person's thermal sensation and achieve a comfortable environmental temperature are realized.

FIG. 1 is a block diagram showing an example of a functional configuration of a control system according to an embodiment. FIG. 2 is a diagram showing an air-conditioned space to which the operating system according to the embodiment is applied. FIG. 3 is a diagram for explaining a thermal image. FIG. 4 is a flowchart of an operation example of the control system according to the embodiment.

Hereinafter, embodiments will be described with reference to the drawings. It should be noted that the embodiments described below are all comprehensive or specific examples. Numerical values, shapes, materials, components, arrangement positions and connection forms of components, steps, order of steps, and the like shown in the following embodiments are examples and are not intended to limit the present invention. Further, among the constituent elements in the following embodiments, constituent elements not described in independent claims will be described as optional constituent elements.

It should be noted that each figure is a schematic diagram and is not necessarily strictly illustrated. Moreover, in each figure, the same code|symbol is attached|subjected with respect to substantially the same structure, and the overlapping description may be abbreviate|omitted or simplified.

(Embodiment)
[composition]
First, the configuration of the control system according to the embodiment will be described. FIG. 1 is a block diagram showing an example of a functional configuration of a control system according to an embodiment. FIG. 2 is a diagram showing an air-conditioned space to which the control system according to the embodiment is applied.

The control system 10 extracts the contour of the person 1 existing in the air-conditioned space based on a thermal image showing the temperature distribution of the air-conditioned space, identifies a human body region surrounded by the extracted contour of the person 1, and identifies the human body region. A temperature difference value between the human body region and the other regions is calculated, and the heat release amount of the person 1 is calculated based on the calculated difference value. Then, the control system 10 estimates the thermal sensation of the person 1 based on the calculated heat release amount of the person 1, and controls the air conditioner 30 based on the estimated thermal sensation. The air-conditioned space is, for example, an indoor space in a building. A building may be, for example, an office, a commercial facility, a public facility, an educational facility, or a residence. As shown in FIG. 1 , control system 10 includes sensor 20 , air conditioner 30 , and server device 40 . Note that the control system 10 may include a plurality of sensors 20 .

[Sensor]
The sensor 20 is installed, for example, on the ceiling of the air-conditioned space, and generates a thermal image showing the temperature distribution when the air-conditioned space is viewed from the ceiling side (in other words, from above).

For example, as shown in FIG. 2, the sensor 20 may be installed directly on the ceiling of the air-conditioned space, or may be powered by a lighting device (not shown) or a fire alarm (not shown) installed on the ceiling. It may be detachably connected to the terminal. In the latter case, sensor 20 is powered by a lighting device or fire alarm. The power supply terminal is, for example, a USB (Universal Serial Bus) terminal.

The sensor 20 is, for example, an infrared sensor. The infrared sensor is, for example, an infrared array sensor (in other words, a thermal image sensor) configured by an array of 8×8 infrared detection elements. In other words, the thermal image produced by the infrared sensor has 8x8 pixels. The thermal image shows the temperature distribution in the sensing range of the infrared sensor with 8×8 resolution. FIG. 3 is a diagram for explaining a thermal image. FIG. 3A is a diagram schematically showing an image of the air-conditioned space detected by the sensor 20 (more specifically, the sensing range of the sensor 20 in the air-conditioned space) captured by a camera. (b) of FIG. 3 is a diagram schematically showing a thermal image detected by the sensor 20. As shown in FIG. Each of the 8×8 small regions in FIG. 3(a) represents a pixel included in the image, and each of the 8×8 small regions in FIG. 3(b) represents a pixel included in the thermal image 100. means Numerical values in the pixels shown in FIG. 3B are pixel values, and specifically indicate temperatures. The area surrounded by the thick line in FIG. 3B is the human body area 100a, and the area other than the human body area 100a in the thermal image 100 is the surrounding area 100b. In the following embodiments, for simplification of explanation, pixel value=temperature value will be explained.

Note that the sensor 20 may be installed on a wall or the like to generate a thermal image showing the temperature distribution when the air-conditioned space is viewed from the wall side (in other words, the side). In this case, the control system 10 may acquire a plurality of thermal images showing the temperature distribution when the air-conditioned space is viewed from above and from the sides.

[Air conditioner]
The air conditioner 30 controls the temperature around the person 1 in the air-conditioned space (also called environmental temperature) based on the thermal sensation of the person 1 present in the air-conditioned space. As shown in FIG. 1, the air conditioner 30 includes, for example, a communication section 31, a control section 32, a storage section 33, a louver 36, a compressor 37, and a fan .

The communication unit 31 is a communication circuit (communication module) for the air conditioner 30 to communicate with the sensor 20 and the server device 40 . The communication unit 31 includes a communication circuit (communication module) for communication via the wide area communication network 5 and a communication circuit (communication module) for communication via a local communication network (not shown). good too. The communication unit 31 is, for example, a wireless communication circuit that performs wireless communication, but may be a wired communication circuit that performs wired communication. Note that the communication standard for communication performed by the communication unit 31 is not particularly limited.

The control unit 32 performs various types of information processing based on the thermal image acquired from the sensor 20 and controls the operation of the air conditioner 30 . Specifically, the control unit 32 controls the louver 36, the compressor 37, and the fan 38 based on the thermal sensation of the person 1 estimated by the estimation unit 32e. For example, when it is estimated that the person 1 feels hot, the control unit 32 orients the louver 36 toward the person 1 and controls the compressor 37 and the fan 38 to generate cool air.

Specifically, the control unit 32 includes an acquisition unit 32a that acquires the thermal image received by the communication unit 31, and a detection unit that detects the contour of the person 1 including the skin 1a and the clothes 1b of the person 1 in the thermal image. an identification unit 32c that identifies a human body region 100a (see FIG. 3B) that is an area surrounded by the outline of the person 1; A calculation unit 32d that calculates the heat release amount, an estimation unit 32e that estimates the thermal sensation of the person 1 based on the heat release amount, and an estimation result of the thermal sensation of the person 1 or a control condition determined based on the estimation result. and an output unit 32f for outputting. The functions of the acquisition unit 32a, the detection unit 32b, the identification unit 32c, the calculation unit 32d, the estimation unit 32e, and the output unit 32f are such that the processor or microcomputer constituting the control unit 32 reads a computer program stored in the storage unit 33. It is realized by executing Details of functions of the acquisition unit 32a, the detection unit 32b, the identification unit 32c, the calculation unit 32d, the estimation unit 32e, and the output unit 32f will be described later in operation examples.

The storage unit 33 is a storage device that stores a dedicated application program and the like for the control unit 32 to execute. The storage unit 33 may store a learned machine learning model (hereinafter also referred to as a learned model) and the database 35 . The machine learning model is learned by the learning unit 44 of the server device 40 . The control unit 32 stores the learned machine learning model transmitted from the server device 40 in the storage unit 33 , thereby updating the learned machine learning model in the storage unit 33 . The storage unit 33 is implemented by, for example, a semiconductor memory.

A machine learning model may have a convolutional layer, for example, a convolutional neural network (CNN), but is not limited to this. Also, for example, as shown in FIG. 1, the machine learning model may consist of a first machine learning model (eg, trained model 34a) and a second machine learning model (eg, trained model 34b). . In this case, the first machine learning model (e.g., learned model 34a) outputs a super-resolution thermal image with input of a thermal image showing the temperature distribution of the air-conditioned space, and the second machine learning model (e.g., learned The model 34b) may receive the super-resolution thermal image output from the first machine learning model (for example, the trained model 34a) and output the outline of a person present in the air-conditioned space. In the example of FIG. 1, the storage unit 33 stores two trained

models

34a and 34b. may be stored.

The database 35 stores, for example, a thermal sensation corresponding to the amount of heat released by a person during the cooling operation and during the heating operation, and the control conditions of the air conditioner 30 corresponding to the thermal sensation in association with each other. may be

[Server device]
The server device 40 learns the machine learning model and updates the learned

models

34a and 34b. In the example of FIG. 1, the server device 40 is a cloud computer provided outside the building having the air-conditioned space, but it may be an edge computer provided inside the building. The server device 40 includes a communication section 41 , a control section 42 , a storage section 43 and a learning section 44 .

The communication unit 41 is a communication module (communication circuit) for the server device 40 to communicate with the air conditioner 30 . The communication unit 41 transmits the learned

models

45a and 45b to the air conditioner 30, for example. In the example of FIG. 1, the communication unit 41 is a communication circuit (communication module) for communicating via the wide area communication network 5, but a communication circuit for communicating via a local communication network (not shown). (communication module). The communication performed by the communication unit 41 may be wireless communication or wired communication. The communication standard used for communication is also not particularly limited.

The control unit 42 performs various types of information processing in the server device 40 . The controller 42 is specifically realized by a processor or a microcomputer.

The storage unit 43 stores machine learning models (learned

models

45a and 45b) learned by the learning unit 44, teacher data 46 used for learning, computer programs executed by the control unit 42, and the like. is. Specifically, the storage unit 43 is realized by a semiconductor memory, HDD (Hard Disk Drive), or the like.

The learning unit 44 performs machine learning using the teacher data 46. The learning unit 44 uses machine learning to generate a machine learning model (a so-called learned model) that outputs a contour of a person present in the air-conditioned space based on a thermal image representing the temperature distribution of the air-conditioned space. As mentioned above, the machine learning model, for example a CNN, may consist of a first machine learning model and a second machine learning model. In this case, the learning unit 44 uses machine learning to input a thermal image showing the temperature distribution of the air-conditioned space and outputs a super-resolution thermal image (for example, a trained model 45a), and A second machine learning model (for example, the learned model 45b) may be generated that inputs the super-resolution thermal image and outputs the outline of a person existing in the air-conditioned space. The trained

models

45a, 45b include trained parameters adjusted by machine learning. The generated learned

models

45 a and 45 b are stored in the storage unit 43 and transmitted to the air conditioner 30 via the communication unit 41 , for example. As a result, the air conditioner 30 updates the learned model 34a in the storage unit 33 using the acquired learned model 45a, and updates the learned model 34b using the learned model 45b. The learning unit 44 is realized by executing a program stored in the storage unit 43 by the processor, for example.

The teacher data 46 has a thermal image showing the temperature distribution of the air-conditioned space as input data, and the contours of people existing in the air-conditioned space as output data. Specifically, the teacher data 46 may be a data set including a set of a thermal image as input data and a contour of a person as output data, or may be a plurality of data sets (for example, first teacher data and second teacher data). two-supervised data). For example, the first teacher data is teacher data used for learning the first machine learning model (for example, the trained model 45a). , and a super-resolution thermal image obtained by converting the thermal image into super-resolution as output data. For example, the second teacher data is teacher data used for learning the second machine learning model (for example, the trained model 45b), and includes a super-resolution thermal image as input data and the output of the teacher data 46 as output data. A data set containing pairs of data (ie human contours).

In FIG. 1, an example of generating a learned machine learning model in the server device 40 and transmitting the generated learned machine learning model to the air conditioner 30 to update the machine learning model has been described. , but not limited to this example. For example, the air conditioner 30 may have the configuration of the server device 40 . Further, for example, the server device 40 acquires the thermal image detected by the sensor 20, estimates the thermal sensation of the person 1, and outputs the estimation result of the thermal sensation of the person 1 to the control of the air conditioner 30. good too.

[Example of operation]
Next, an operation example of the control system 10 will be described. FIG. 4 is a flow chart of an example operation of the control system 10 .

The control unit 32 of the air conditioner 30 generates a thermal image 100 (for example, FIG. 3 (b)) of (S11). More specifically, the acquisition unit 32 a of the air conditioner 30 acquires the thermal image 100 from the sensor 20 via the communication unit 31 . At this time, the acquisition unit 32 a may store the acquired thermal image 100 in the storage unit 33 .

Next, the detection unit 32b detects the outline of the person 1 existing in the air-conditioned space based on the thermal image 100 acquired by the acquisition unit 32a in step S11 (S12). For example, the detection unit 32b divides a plurality of adjacent pixels having the same characteristics in at least a part of the thermal image 100 into two or more temperature distribution regions as one temperature distribution region. Based on two or more temperature distribution areas, the contour of the person 1 including the clothing 1b of the person 1 (see FIG. 2) is detected. For example, the detection unit 32b may perform segmentation on the thermal image 100 using a machine learning model to divide the thermal image 100 into an area where the person 1 is shown and an area where the person 1 is not shown. good. As described above, the machine learning model may have convolutional layers, such as, but not limited to, a convolutional neural network (CNN). Note that the machine learning model (for example, the learned model 34b in FIG. 1) may be applied to a super-resolution thermal image obtained by converting the thermal image 100 into super-resolution.

The detection unit 32b interpolates at least one pixel between pixels adjacent to a plurality of pixels in the thermal image 100 to generate a super-resolution thermal image having higher resolution than the thermal image 100. The contour of the person 1 may be detected based on the super-resolution thermal image obtained. For example, in generating a super-resolution thermal image, the detection unit 32b obtains an average value of pixel values (that is, temperature values) of pixels adjacent to each other in the thermal image 100, so that the average value Thermal image 100 may be super-resolved using a method that inserts new pixels with pixel values corresponding to . Further, for example, the detection unit 32b may super-resolve the thermal image 100 using a learned machine learning model (for example, the learned model 34a in FIG. 1). The trained model 34a may be, for example, SRGAN (Generative Adversarial Network for Super-Resolution), but is not limited to this.

In step S12, the detection unit 32b detects the outline of the person 1 from the thermal image 100 using, for example, the learned machine learning models (for example, the learned

models

34a and 34b in FIG. 1) stored in the storage unit 33. You may

Next, the specifying unit 32c specifies, in the thermal image 100, a human body region 100a (see (b) of FIG. 3), which is a region surrounded by the outline of the person 1 detected by the detecting unit 32b in step S12. (S13).

Next, the calculation unit 32d calculates the human body temperature including the temperature of the clothing 1b of the person 1 based on the temperature distribution within the human body region 100a specified by the specifying unit 32c in step S13 (S14). Specifically, in step S14, the calculation unit 32d calculates an average value of the surface temperature of the skin 1a (see FIG. 2) of the person 1 and the surface temperature of the clothes 1b of the person 1 as the human body temperature. For example, the calculator 32d may calculate an average value of pixel values (ie, temperature values) of the human body region 100a as the human body temperature.

Next, the calculator 32d calculates the ambient temperature of the person 1 based on the temperature distribution in the area other than the human body area 100a (so-called surrounding area 100b) (S15). For example, in step S15, the calculation unit 32d may calculate the average value (that is, the temperature value) of the pixel values of the surrounding area 100b as the ambient temperature. In addition, step S14 and step S15 may be performed in parallel.

Next, the calculator 32d calculates the amount of heat released by the person 1 based on the difference between the human body temperature and the ambient temperature (S16). Specifically, the calculation unit 32d calculates a difference value between the human body temperature calculated in steps S14 and S15 and the ambient temperature, and calculates the heat dissipation amount of the person 1 based on the calculated difference value.

Next, the estimation unit 32e estimates the thermal sensation of the person 1 based on the amount of heat released by the person 1 calculated by the calculation unit 32d in step S16 (S17). For example, the estimation unit 32e estimates that the person 1 feels cold when the amount of heat dissipation is greater than the threshold, and estimates that the person 1 feels hot when the amount of heat dissipation is less than the threshold. The threshold may include a threshold for cooling operation and a threshold for heating operation. The thermal sensation of the person 1 corresponds to the amount of heat released by the person 1, but the thermal sensation of the person 1 may differ depending on the season even if the amount of heat released is the same. Therefore, by estimating the thermal sensation of the person 1 using the threshold for the cooling operation and the threshold for the heating operation, the thermal sensation of the person 1 can be estimated more accurately.

Next, the control unit 32 controls the air conditioner 30 based on the thermal sensation of the person 1 estimated by the estimation unit 32e in step S17 (S18). For example, when the estimation unit 32e estimates in step S17 that the person 1 feels cold, the control unit 32 controls the air conditioner 30 to increase the ambient temperature, and the estimation unit 32e determines that the person 1 is hot. If it is estimated that the air conditioner 30 is feeling The control unit 32 determines control conditions during cooling or heating operation corresponding to the thermal sensation of the person 1 based on the database 35, and operates the louver 36, the compressor 37 and the fan 38 based on the determined control conditions. may be controlled. Since the database 35 has been described above, a description thereof will be omitted here.

At this time, the control unit 32 may control the air conditioner 30 based on the position of the human body region 100a and the thermal sensation of the person 1. Specifically, the calculator 32d calculates the position of the person 1 in the air-conditioned space based on the position of the human body region in the thermal image. For example, the storage unit 33 stores table information indicating the correspondence between the positions of pixels in the thermal image and the coordinates in the air-conditioned space. The position (specifically, the coordinates) of the person 1 in the air-conditioned space may be calculated from the position (pixel position) where the person 1 is detected.

Note that when the thermal image shows the temperature distribution of the air-conditioned space when the air-conditioned space is viewed from above (that is, from the ceiling side) as in the present embodiment, the temperature distribution of the air-conditioned space calculated by the calculator 32d The coordinates of 1 are two-dimensional coordinates when the air-conditioned space is viewed from above.

As described above, the control system 10 can estimate the thermal sensation of the person 1 present in the air-conditioned space and control the air conditioner 30 based on the estimated thermal sensation. Therefore, the control system 10 can estimate the thermal sensation of the person 1 and achieve a comfortable environmental temperature.

[Modification]
The control unit 32 controls the air conditioner 30 based on the estimation result (the thermal sensation of the person 1) estimated by the estimation unit 32e, but may output the estimation result. The output unit 32f may output the result estimated by the estimation unit 32e to an information terminal (not shown) possessed by the person 1. FIG. As a result, the person 1 can confirm the estimation result displayed on the display unit of the information terminal. , the person 1 can input the actual thermal sensation to the information terminal to correct the estimation result. Note that both the estimation result and the corrected estimation result are stored in the storage unit 33 .

Note that the detection unit 32b may perform information processing on the thermal image based on a rule-based algorithm that does not use a machine learning model. For example, the detection unit 32b may perform processing for detecting a pixel having a maximum pixel value among a plurality of pixels included in the thermal image. Here, a pixel having a maximum pixel value means a pixel having a maximum pixel value in a two-dimensional arrangement of pixels. A pixel having a maximum pixel value means, in other words, a pixel having a higher pixel value than surrounding pixels when comparing pixel values at the same time in a two-dimensional arrangement of pixels. There may be a plurality of pixels with maximum pixel values in one thermal image.

Here, assuming that there is no heat source with a higher temperature than the person in the air-conditioned space, even if the pixel value is the maximum value, if the pixel value is smaller than the predetermined value (that is, the temperature is low), , it is considered that there is no person at the position corresponding to the pixel. Therefore, when the detection unit 32b detects a pixel having a maximum pixel value and a pixel value equal to or higher than a predetermined value (for example, 30° C. or higher), the detection unit 32b determines that the person 1 is present in the air-conditioned space. Then, the contour of the person 1 may be detected based on the detected pixels.

Further, the calculation unit 32d applies the above-described table information to the position of a pixel having a maximum pixel value and having a pixel value equal to or higher than a predetermined value (for example, 30° C. or higher), thereby determining the air conditioning target. The position (that is, the coordinates) of person 1 in space can be calculated.

Another example of information processing based on a rule-based algorithm is processing that detects temporal changes in the pixel values (temperature) of each of a plurality of pixels included in a thermal image. Assuming that there are no heat sources other than people in the air-conditioned space, and if there are no people in the air-conditioned space, the pixel values (temperatures) of the plurality of pixels included in the thermal image change slowly over time. be. In this state, when the person 1 enters the air-conditioned space, the pixel values of the pixels in the portion of the thermal image where the person 1 is shown change (increase) abruptly. The detection unit 32b detects changes in the pixel values of each of the plurality of pixels over time, for example, when the pixel values rise sharply, it is estimated that the person 1 exists in the air-conditioned space, and the outline of the person 1 is detected. processing may be performed.

[Effects, etc.]
As described above, the control method is a control method for the air conditioner 30 executed by a computer such as the control system 10. The computer controls the air conditioning detected by the sensor 20 installed on the ceiling of the space to be air conditioned. A thermal image 100 showing the temperature distribution of the target space is acquired (step S11 in FIG. 4), the contour of the person 1 existing in the air conditioning target space is detected based on the acquired thermal image 100 (step S12), and the contour of the detected person 1 is detected. The human body region 100a, which is the region surrounded by the outline of the person 1, is specified in the thermal image 100 (step S13), and the temperature of the clothes 1b of the person 1 is calculated based on the temperature distribution in the specified human body region 100a. (Step S14), calculates the ambient temperature of a region (surrounding region 100b) other than the human body region 100a in the thermal image 100 (Step S15), and calculates the difference value between the human body temperature and the ambient temperature. Calculate the heat dissipation amount of the person 1 (step S16), estimate the thermal sensation of the person 1 based on the calculated heat dissipation amount (step S17), and control the air conditioner 30 based on the estimated thermal sensation. (step S18).

Such a control method can realize an environmental temperature that the person 1 feels comfortable by estimating the thermal sensation of the person 1 existing in the air-conditioned space.

Further, for example, the computer estimates that the person 1 feels cold when the heat release amount is greater than the threshold, and operates the air conditioner 30 to increase the ambient temperature based on the estimated thermal sensation. When the heat release amount is smaller than a threshold value, it is estimated that the person 1 feels hot, and the air conditioner 30 is controlled to lower the ambient temperature based on the estimated thermal sensation.

Such a control method can estimate the thermal sensation of person 1 from the amount of heat released by person 1 based on the threshold.

Further, for example, in detecting the contour of the person 1, the computer has the same characteristics in at least a part of the thermal image 100, and uses two or more adjacent pixels as one temperature distribution area. It is divided into distribution areas (for example, a human body area 100a and a surrounding area 100b), and the outline of the person 1 including the clothing 1b of the person 1 is detected based on two or more divided temperature distribution areas.

Such a control method has the same characteristics in at least a part of the thermal image, and divides a plurality of adjacent pixels into one temperature distribution area, thereby converting the thermal image into an area corresponding to the person 1 ( It can be divided into a human body area 100a) and an area (surrounding area 100b) corresponding to other than the person 1. FIG. Thereby, the control method can detect the outline of the person 1 based on the pixel values of the plurality of pixels included in the area corresponding to the person 1 .

Also, for example, the computer interpolates at least one pixel between adjacent pixels in a plurality of pixels in the thermal image 100 to generate a super-resolution thermal image having a higher resolution than the thermal image 100. Then, the contour of the person 1 is detected based on the super-resolution thermal image.

Since such a control method detects the contour of the person 1 with a finer resolution than the thermal image 100, the contour of the person 1 can be detected more accurately.

Also, for example, the computer detects the contour of the person 1 from the thermal image 100 using a learned machine learning model (for example, the learned

models

34a and 34b).

Such a control method can quickly and accurately detect the contour of the person 1 from the thermal image 100 by using a machine learning model.

Also, for example, the machine learning model is learned using teacher data 46, and the teacher data 46 has a thermal image as input data and a human contour as output data.

Such a control method can detect the contour of the person 1 by inputting the thermal image 100 into a trained machine learning model.

Also, for example, the machine learning model is composed of a first machine learning model (e.g., trained model 34a) and a second machine learning model (e.g., trained model 34b), and the first machine learning model is The second machine learning model is learned using the first teacher data including a set of the input data of the teacher data 46 as input data and the super-resolution thermal image of the input data as output data, and the second machine learning model uses the above Learning is performed using second teacher data including a set of a super-resolution thermal image and the output data of the teacher data 46 as output data.

Such a control method includes a first machine learning model (for example, a trained model 34a) that receives the thermal image 100 as an input and outputs a super-resolution thermal image of the thermal image 100, and a human machine learning model that receives the super-resolution thermal image as an input. The contour of person 1 can be detected from thermal image 100 using a second machine learning model (eg, trained model 34b) that outputs contours. Therefore, since the control method can detect the contour of the person 1 from the super-resolution thermal image having finer resolution than the thermal image 100, the contour of the person 1 can be detected with higher accuracy.

Also, the program is a program for causing the computer to execute any of the above control methods.

Such a program can realize an environmental temperature that the person 1 feels comfortable by estimating the thermal sensation of the person 1 existing in the air-conditioned space.

The control system 10 also includes an acquisition unit 32a that acquires a thermal image 100 showing the temperature distribution of the air-conditioned space detected by the sensor 20 installed on the ceiling of the air-conditioned space, and based on the acquired thermal image 100: a detection unit 32b that detects the contour of the person 1 existing in the air-conditioned space; Based on the obtained temperature distribution in the human body region 100a, the human body temperature including the temperature of the clothes 1b of the person 1 is calculated, and the ambient temperature of the region other than the human body region 100a (so-called surrounding region 100b) in the thermal image 100 is calculated. a calculation unit 32d for calculating the amount of heat dissipation of the person 1 based on the difference value between the human body temperature and the ambient temperature; and a control unit 32 that controls the air conditioner 30 installed in the air-conditioned space based on the received thermal sensation.

Such a control system 10 can realize an environmental temperature that the person 1 feels comfortable by estimating the thermal sensation of the person 1 existing in the air-conditioned space.

(Other embodiments)
Although the control system and the control method according to the embodiments have been described above, the present invention is not limited to the above embodiments.

Also, in the above embodiments, the control system was implemented by a plurality of devices, but it may be implemented as a single device. For example, the control system may be implemented as a single device that corresponds to the server device. When the control system is realized by a plurality of devices, each component included in the control system may be distributed to the plurality of devices in any way.

Further, in the above embodiment, the processing executed by a specific processing unit may be executed by another processing unit. In addition, the order of multiple processes may be changed, and multiple processes may be executed in parallel.

Also, in the above embodiments, each component may be realized by executing a software program suitable for each component. Each component may be realized by reading and executing a software program recorded in a recording medium such as a hard disk or a semiconductor memory by a program execution unit such as a CPU or processor.

Also, each component may be realized by hardware. For example, each component may be a circuit (or integrated circuit). These circuits may form one circuit as a whole, or may be separate circuits. These circuits may be general-purpose circuits or dedicated circuits.

Also, general or specific aspects of the present invention may be implemented in a system, apparatus, method, integrated circuit, computer program, or recording medium such as a computer-readable CD-ROM. Also, any combination of systems, devices, methods, integrated circuits, computer programs and recording media may be implemented. For example, the present invention may be implemented as a computer-implemented control method, such as a control system. Further, the present invention may be implemented as a program for causing a computer to execute the control method, or as a computer-readable non-temporary recording medium storing such a program.

In addition, forms obtained by applying various modifications to each embodiment that a person skilled in the art can think of, or realized by arbitrarily combining the constituent elements and functions of each embodiment without departing from the spirit of the present invention. Also included in the present invention.

(Appendix)
Hereinafter, the inventions obtained from the disclosure of the present specification will be exemplified, and the effects and the like obtained from the inventions will be described.

[Invention 1]
A control method for an air conditioner executed by a computer, comprising:
The computer is
Acquiring a thermal image showing the temperature distribution of the air-conditioned space detected by a sensor installed on the ceiling of the air-conditioned space,
detecting a contour of a person existing in the air-conditioned space based on the acquired thermal image;
identifying a human body region, which is a region surrounded by the detected outline of the person, in the thermal image;
calculating a human body temperature including a temperature of clothes of the person based on the identified temperature distribution in the human body region;
calculating the ambient temperature of a region other than the human body region in the thermal image;
calculating the heat radiation amount of the person based on the difference value between the human body temperature and the ambient temperature;
estimating the thermal sensation of the person based on the calculated amount of heat dissipation;
controlling the air conditioner based on the estimated thermal sensation;
control method.

[Effect of Invention 1]
Such a control method can realize an environmental temperature that people feel comfortable by estimating the thermal sensation of people existing in the air-conditioned space.

[Invention 2]
The computer is
estimating that the person feels cold when the heat release amount is greater than a threshold, and controlling the air conditioner to raise the ambient temperature based on the estimated thermal sensation;
estimating that the person feels hot when the heat release amount is smaller than the threshold value, and controlling the air conditioner to lower the ambient temperature based on the estimated thermal sensation;
The control method according to Invention 1.

[Effect of Invention 2]
Such a control method can estimate a person's thermal sensation from the amount of heat released by the person based on the threshold value.

[Invention 3]
The computer, in detecting the contour of the person,
dividing a plurality of adjacent pixels into two or more temperature distribution areas having the same characteristics in at least a part of the thermal image, and
detecting the contour of the person including the clothing of the person based on the two or more divided temperature distribution areas;
The control method according to invention 1 or 2.

[Effect of Invention 3]
Such a control method has the same characteristics in at least a part of the thermal image, and divides a plurality of adjacent pixels as one temperature distribution area, thereby dividing the thermal image into an area corresponding to a person (so-called , human body region) and regions other than the person 1 (so-called surrounding region). Thereby, the control method can detect the outline of the person based on the pixel values of the plurality of pixels included in the area corresponding to the person.

[Invention 4]
The computer is
generating a super-resolution thermal image having a higher resolution than the thermal image by interpolating at least one pixel between adjacent pixels for a plurality of pixels in the thermal image;
detecting a contour of the person based on the super-resolution thermal image;
A control method according to any one of Inventions 1 to 3.

[Effect of Invention 4]
Since such a control method detects the contour of a person with finer resolution than a thermal image, the contour of a person can be detected more accurately.

[Invention 5]
The computer detects the contour of the person from the thermal image using a trained machine learning model.
A control method according to any one of Inventions 1 to 4.

[Effect of Invention 5]
Such a control method can quickly and accurately detect the contour of a person from a thermal image by using a machine learning model.

[Invention 6]
The machine learning model is learned using teacher data,
The training data has the thermal image as input data and the outline of the person as output data,
A control method according to invention 5.

[Effect of Invention 6]
Such a control method can detect the contour of a person by inputting a thermal image into a trained machine learning model.

[Invention 7]
The machine learning model comprises a first machine learning model and a second machine learning model,
The first machine learning model is learned using first teacher data including a set of the input data of the teacher data and a super-resolution thermal image of the input data,
The second machine learning model is learned using second teacher data including a set of the super-resolution thermal image and the output data of the teacher data,
A control method according to invention 6.

[Effect of Invention 7]
Such a control method includes a first machine learning model that takes a thermal image as an input and outputs a super-resolution thermal image of the thermal image, and a second machine learning model that takes a super-resolution thermal image as an input and outputs a human contour. can be used to detect human contours from thermal images. Therefore, since the control method can detect the contour of a person from the super-resolution thermal image having finer resolution than the thermal image, the contour of the person can be detected with higher accuracy.

[Invention 8]
A program for causing a computer to execute the control method according to any one of Inventions 1 to 7.

[Effect of Invention 8]
Such a program can realize an environmental temperature that people feel comfortable by estimating the thermal sensation of people existing in the air-conditioned space.

[Invention 9]
an acquisition unit that acquires a thermal image showing the temperature distribution of the air-conditioned space detected by a sensor installed on the ceiling of the air-conditioned space;
a detection unit that detects a contour of a person present in the air-conditioned space based on the acquired thermal image;
a specifying unit that specifies, in the thermal image, a human body region, which is a region surrounded by the detected outline of the person;
calculating a human body temperature including a temperature of clothes of the person based on the specified temperature distribution in the human body region, calculating an ambient temperature of a region other than the human body region in the thermal image, and calculating the human body temperature and the human body temperature; a calculation unit that calculates the heat dissipation amount of the person based on the difference value from the ambient temperature;
an estimating unit that estimates the thermal sensation of the person based on the calculated amount of heat release;
a control unit that controls an air conditioner installed in the air-conditioned space based on the estimated thermal sensation;
comprising
control system.

[Effect of invention 9]
Such a control system can realize an environmental temperature that people feel comfortable by estimating the thermal sensation of people existing in the air-conditioned space.

1 person 1b clothing 10 control system 20 sensor 30 air conditioner 32 control unit

32a acquisition unit

32b detection unit

32c identification unit

32d calculation unit

32e estimation unit 34a learned model 34b learned model 45a learned model 45b learned model 46 teacher data 100 thermal image 100a human body region 100b surrounding region

Claims

A control method for an air conditioner executed by a computer, comprising:
The computer is
Acquiring a thermal image showing the temperature distribution of the air-conditioned space detected by a sensor installed on the ceiling of the air-conditioned space,
detecting a contour of a person existing in the air-conditioned space based on the acquired thermal image;
identifying a human body region, which is a region surrounded by the detected outline of the person, in the thermal image;
calculating a human body temperature including a temperature of clothes of the person based on the identified temperature distribution in the human body region;
calculating the ambient temperature of a region other than the human body region in the thermal image;
calculating the heat radiation amount of the person based on the difference value between the human body temperature and the ambient temperature;
estimating the thermal sensation of the person based on the calculated amount of heat dissipation;
controlling the air conditioner based on the estimated thermal sensation;
control method.
The computer is
estimating that the person feels cold when the heat release amount is greater than a threshold, and controlling the air conditioner to raise the ambient temperature based on the estimated thermal sensation;
estimating that the person feels hot when the heat release amount is smaller than the threshold value, and controlling the air conditioner to lower the ambient temperature based on the estimated thermal sensation;
The control method according to claim 1.
The computer, in detecting the contour of the person,
dividing a plurality of adjacent pixels into two or more temperature distribution areas having the same characteristics in at least a part of the thermal image, and
detecting the contour of the person including the clothing of the person based on the two or more divided temperature distribution areas;
The control method according to claim 1 or 2.
The computer is
generating a super-resolution thermal image having a higher resolution than the thermal image by interpolating at least one pixel between adjacent pixels for a plurality of pixels in the thermal image;
detecting a contour of the person based on the super-resolution thermal image;
The control method according to claim 1 or 2.
The computer detects the contour of the person from the thermal image using a trained machine learning model.
The control method according to claim 1 or 2.
The machine learning model is learned using teacher data,
The training data has the thermal image as input data and the outline of the person as output data,
The control method according to claim 5.
The machine learning model comprises a first machine learning model and a second machine learning model,
The first machine learning model is learned using first teacher data including a set of the input data of the teacher data and a super-resolution thermal image of the input data,
The second machine learning model is learned using second teacher data including a set of the super-resolution thermal image and the output data of the teacher data,
The control method according to claim 6.
A program for causing a computer to execute the control method according to claim 1 or 2.
an acquisition unit that acquires a thermal image showing the temperature distribution of the air-conditioned space detected by a sensor installed on the ceiling of the air-conditioned space;
a detection unit that detects a contour of a person present in the air-conditioned space based on the acquired thermal image;
a specifying unit that specifies, in the thermal image, a human body region, which is a region surrounded by the detected outline of the person;
calculating a human body temperature including a temperature of clothes of the person based on the specified temperature distribution in the human body region, calculating an ambient temperature of a region other than the human body region in the thermal image, and calculating the human body temperature and the human body temperature; a calculation unit that calculates the heat dissipation amount of the person based on the difference value from the ambient temperature;
an estimating unit that estimates the thermal sensation of the person based on the calculated amount of heat release;
a control unit that controls an air conditioner installed in the air-conditioned space based on the estimated thermal sensation;
comprising
control system.