Thermal sensation prediction device, program, and thermal sensation prediction method

Abstract

A warm / cold feeling prediction device (100) comprises: a personal region detection unit (104) that detects, from a thermal image indicating the temperature distribution in a predetermined space, a personal region that is narrower than the predetermined space and is a region of an individual present in the predetermined space; a local humidity estimation unit (106) that estimates a local humidity, which is the humidity of the personal region; and a warm / cold feeling prediction unit (107) that predicts the warm / cold feeling of the individual by using the local humidity.

Description

[Technical Field]

[0001] This disclosure relates to a thermal sensation prediction device, a program, and a thermal sensation prediction method. [Background technology]

[0002] A thermal sensation estimation device is known that estimates a person's feeling of heat or cold without requiring a person to report it and without directly attaching a sensor to the human body. If this thermal sensation estimation device is installed, for example, in an air conditioning system, the airflow and other parameters can be controlled based on the estimated thermal sensation, allowing for efficient operation of the air conditioning while keeping people comfortable.

[0003] One example of a technology for estimating the thermal comfort of people in a densely packed area is the railway vehicle air conditioning system described in Patent Document 1. [Prior art documents] [Patent Documents]

[0004] [Patent Document 1] Patent Publication No. 5361816 [Overview of the project] [Problems that the invention aims to solve]

[0005] In enclosed spaces such as rooms where many people gather, people feel hotter than usual due to heat radiating from the surface of the surrounding human body, as well as the increase in humidity caused by sweating and exhalation from those around them.

[0006] Conventional technology estimates the thermal comfort of densely packed individuals based on heat radiated from the surrounding human body surface, but it does not take into account the increase in humidity due to sweating and exhalation from the surrounding people. Therefore, conventional technology cannot accurately estimate the thermal comfort of densely packed individuals. On the other hand, installing numerous humidity sensors to detect increases in humidity due to sweating and exhalation from people in the surrounding area is costly.

[0007] Therefore, one or more aspects of this disclosure aim to enable accurate estimation of the thermal sensation of people in a densely populated area without incurring costs. [Means for solving the problem]

[0008] A thermal sensation prediction device according to one aspect of the present disclosure includes: a personal area detection unit that detects a personal area, which is the area of ​​an individual located within a predetermined space and is narrower than the predetermined space, from a thermal image showing the temperature distribution in a predetermined space; a local humidity estimation unit that estimates the local humidity, which is the humidity of the personal area; and a thermal sensation prediction unit that predicts the thermal sensation of the individual using the local humidity. The local humidity estimation unit determines the amount of water vapor emitted by the individual, which is the amount of water vapor emitted by the individual, from the temperature of the predetermined space, such that it increases as the temperature of the predetermined space increases. It calculates the amount of water vapor emitted by the individual by multiplying the amount of water vapor emitted by the individual by the number of people around the individual in the predetermined space plus 1. It calculates the amount of water vapor emitted by the local humidity by adding the average amount of water vapor determined by the temperature of the predetermined space to the amount of water vapor emitted by the local humidity. It estimates the local humidity by dividing the amount of water vapor emitted by the saturation amount of water vapor determined by the temperature of the predetermined space. It is characterized by the following.

[0009] A program according to one aspect of this disclosure causes a computer to function as a personal area detection unit that detects a personal area, which is the area of ​​an individual located within a predetermined space and is smaller than the predetermined space, from a thermal image showing the temperature distribution in a predetermined space; a local humidity estimation unit that estimates the local humidity of the personal area; and a thermal sensation prediction unit that predicts the individual's thermal sensation using the local humidity. The local humidity estimation unit determines the amount of water vapor emitted by the individual, which is the amount of water vapor emitted by the individual, from the temperature of the predetermined space, such that it increases as the temperature of the predetermined space increases. It calculates the amount of water vapor emitted by the individual by multiplying the amount of water vapor emitted by the individual by the number of people around the individual in the predetermined space plus 1. It calculates the amount of water vapor emitted by the local humidity by adding the average amount of water vapor determined by the temperature of the predetermined space to the amount of water vapor emitted by the local humidity. It estimates the local humidity by dividing the amount of water vapor emitted by the saturation amount of water vapor determined by the temperature of the predetermined space. It is characterized by the following.

[0010] A thermal sensation prediction method according to one aspect of this disclosure involves detecting a personal area, which is a smaller area of ​​an individual within a predetermined space, from a thermal image showing the temperature distribution in a predetermined space; estimating the local humidity of the personal area; and using the local humidity to predict the individual's thermal sensation. A method for predicting thermal sensation, wherein the amount of water vapor emitted by an individual, which is the amount of water vapor emitted by the individual, is determined from the temperature of a predetermined space such that it increases as the temperature of the predetermined space increases; the amount of water vapor emitted by the individual is calculated by multiplying the amount of water vapor emitted by the individual by the number of people around the individual in the predetermined space plus 1; the amount of water vapor is calculated by adding the average amount of water vapor determined by the temperature of the predetermined space to the amount of water vapor emitted by the local water vapor; and the local humidity is estimated by dividing the amount of water vapor by the saturated water vapor amount determined by the temperature of the predetermined space. It is characterized by the following. [Effects of the Invention]

[0011] According to one or more aspects of this disclosure, it is possible to accurately estimate the thermal sensation of people in a densely packed area without incurring costs. [Brief explanation of the drawing]

[0012] [Figure 1]It is a block diagram schematically showing the configuration of the warm and cold feeling prediction device according to Embodiment 1. [Figure 2] (A) and (B) are schematic diagrams for explaining the process of identifying the human area. [Figure 3] It is a histogram of the temperature shown in the thermal image. [Figure 4] It is a schematic diagram for explaining the human body area. [Figure 5] (A) and (B) are schematic diagrams for explaining the process of identifying the individual area. [Figure 6] It is a schematic diagram for explaining the process of identifying the number of individuals and the number of people existing around an individual. [Figure 7] It is a graph showing the relationship between the form factor and the human density. [Figure 8] It is a graph showing the relationship between the indoor temperature and the amount of human body water vapor generation. [Figure 9] It is a graph showing the relationship between the indoor temperature and the amount of saturated water vapor. [Figure 10] (A) and (B) are block diagrams showing an example of the hardware configuration. [Figure 11] It is a flowchart showing the operation of the warm and cold feeling prediction device according to Embodiment 1. [Figure 12] It is a block diagram schematically showing the configuration of the warm and cold feeling prediction device according to Embodiment 2. [Figure 13] It is a graph showing the relationship between the amount of individual water vapor generation for each build and the indoor temperature. [Figure 14] It is a flowchart showing the operation of the warm and cold feeling prediction device according to Embodiment 2.

Embodiments for Carrying Out the Invention

[0013] Embodiment 1. FIG. 1 is a block diagram schematically showing the configuration of the warm and cold feeling prediction device 100 according to Embodiment 1. The thermal sensation prediction device 100 includes a thermal image acquisition unit 101, an indoor temperature acquisition unit 102, an indoor humidity acquisition unit 103, a personal area detection unit 104, a radiant temperature calculation unit 105, a local humidity estimation unit 106, and a thermal sensation prediction unit 107.

[0014] The thermal image acquisition unit 101 acquires a thermal image showing the temperature distribution in a predetermined space. It is assumed that a person is present in that space. For example, the thermal image acquisition unit 101 may acquire a thermal image from a thermal camera connected to a communication interface (interface) or connection interface (not shown), or if a thermal image is already stored in a storage unit (not shown), it may acquire a thermal image from that storage unit. The thermal camera may be installed in an air conditioner (not shown) located in a space where people are present. The acquired thermal image is provided to the personal area detection unit 104.

[0015] The indoor temperature acquisition unit 102 acquires the temperature of the space where people are present as the indoor temperature. For example, the indoor temperature acquisition unit 102 may acquire the indoor temperature from a thermometer connected to a communication I / F or connection I / F (not shown), or if the indoor temperature is already stored in a storage unit (not shown), it may acquire the indoor temperature from that storage unit. The thermometer may be installed in an air conditioner (not shown) located in a space where people are present. The indoor temperature is communicated to the thermal sensation prediction unit 107.

[0016] The indoor humidity acquisition unit 103 acquires the humidity of the space where people are present as the indoor humidity. For example, the indoor humidity acquisition unit 103 may acquire indoor humidity from a hygrometer connected to a communication I / F or connection I / F (not shown), or if indoor humidity is already stored in a storage unit (not shown), it may acquire indoor humidity from that storage unit. The hygrometer may be installed in an air conditioner (not shown) installed in a space where people are present. The indoor humidity is communicated to the thermal sensation prediction unit 107.

[0017] The personal area detection unit 104 detects personal areas, which are the areas of each individual person in a space, from the thermal image. For example, the personal area detection unit 104 detects personal areas from the thermal image that are the areas of individuals located in a predetermined space that is smaller than a predetermined space.

[0018] Specifically, the personal area detection unit 104 first identifies the human area, which is the area of ​​a person contained in the thermal image, by inputting the thermal image into a pre-trained model. The model used here is trained to identify human regions from thermal images using training data that includes thermal images and ground truth data indicating human regions contained within those thermal images.

[0019] For example, the personal area detection unit 104 inputs a thermal image 120, as shown in Figure 2(A), into the model to identify person areas 122A to 122F, which are rectangular regions containing each of the people 121A to 121F shown in the thermal image 120, as shown in Figure 2(B).

[0020] Next, the personal area detection unit 104 calculates the average value T of the pixel values ​​in all identified personal areas. m Calculate.

[0021] Next, the personal area detection unit 104 generates a histogram of temperatures shown in the thermal image, and the average value T m Threshold temperature T is the temperature at which a threshold is used to distinguish between the human body region, which contains the human body, and the background region, which is outside the human body region. θ The personal area detection unit 104 identifies the threshold temperature T using a known binarization method such as Otsu's binarization method, mode method, P-tile method, or discriminant analysis method. θ You just need to identify it.

[0022] Specifically, as shown in Figure 3, in the temperature histogram shown in the thermal image, the area corresponding to the human body has a higher temperature than the background area. Therefore, the personal area detection unit 104 calculates the average value T mA threshold temperature T for distinguishing a human body region including the same and a background region outside the human body region θ can be specified by using a known binarization method.

[0023] Then, the personal area detection unit 104 sets, in the thermal image, a region having a temperature higher than the threshold temperature T θ as the human body region, and sets a region having a temperature lower than the threshold temperature T θ as the background region. For example, as shown in FIG. 4, the personal area detection unit 104 specifies, as the human body region, a region having a temperature higher than the threshold temperature T θ . In FIG. 4, the hatched region is the human body region.

[0024] Next, the personal area detection unit 104 specifies pixels having maximum values in the human body region as face pixels. This is because, in a person, the face has the highest temperature, and it is considered that one maximum value in the human body region corresponds to one human. For example, as shown in FIG. 5(A), the personal area detection unit 104 can specify face pixels 123A to 123F by specifying maximum values in the human body region in the vertical direction or the horizontal direction, in other words, in the x direction or the y direction shown in FIG. 5(A). Each of the face pixels 123A to 123F may be one pixel or a set of a plurality of pixels.

[0025] Then, the personal area detection unit 104 specifies the position of the individual in the thermal image from the respective positions of the face pixels 123A to 123F in the thermal image, and specifies a personal area, which is the area of the individual, so that each of the face pixels 123A to 123F is included. For example, as shown in FIG. 5(B), the personal area detection unit 104 specifies personal areas 124A to 124F with frames in which the closer the respective positions of the face pixels 123A to 123F are to the thermal camera, the larger they are. Note that it is assumed that in the thermal camera that captures the thermal image, each pixel is associated in advance with the position of the individual when a face pixel coincides with the pixel by an experiment or the like. Hereinafter, the one or more personal areas detected by the personal area detection unit 104 that are subject to processing will also be referred to as the target personal area.

[0026] The radiation temperature calculation unit 105 calculates the radiation temperature, which is the temperature radiated from the surroundings, for each personal area detected by the personal area detection unit 104. Radiant temperature is greatly influenced by the body temperature of surrounding people when the population density is high, and greatly influenced by the floor temperature when the population density is low. Therefore, the radiant temperature Tr is calculated using the following equation (1). Tr = F1(x) × T1 + F2(x) × T2(1)

[0027] Here, F1 is the shape coefficient between people, F2 is the shape coefficient between a person and the floor, T1 is the average temperature of the target personal area which is the personal area to be calculated, T2 is the room temperature, and x is the density of people around the target personal area. T1 is calculated as the average temperature of all pixels included in the target individual's region.

[0028] Furthermore, as shown in Figure 6, x is identified as the number of people present within a predetermined range 125 surrounding personal area 124C, when the target personal area is personal area 124C. In the example in Figure 6, there are four personal areas 124B, 124C, 124D, and 124E within the predetermined range 125, so the value of x is "4".

[0029] Here, the predetermined range is assumed to be a square centered on the target individual's area. The field of view of the thermal image is assumed to be known, and the pixels in the thermal image are assumed to correspond to their positions within the field of view. Therefore, once the target individual's area is identified, the radiation temperature calculation unit 105 can identify the position of the square centered on that target individual's area. As shown in Figure 6, the predetermined range 125 is assumed to be the range set on the floor surface within the field of view.

[0030] For example, a function, graph, or table showing the relationship between F1 and F2 and x, as shown in Figure 7, is pre-stored in a memory unit (not shown). The radiation temperature calculation unit 105 then identifies F1 and F2 according to that function, graph, or table and calculates the radiation temperature Tr. As shown in Figure 7, F1 increases as x increases, and F2 decreases as x increases. The acquired radiant temperature is provided to the thermal sensation prediction unit 107.

[0031] The local humidity estimation unit 106 estimates the local humidity for each personal area detected by the personal area detection unit 104. Local humidity is the local humidity within the personal area. Local humidity is the humidity actually felt by the subject, who is a person identified within the subject's personal domain, and represents the humidity in the local space, which is a predetermined area of ​​space surrounding the subject. The local space is smaller than the space in which indoor humidity is measured, and is a very narrow space that can contain the subject. Here, the local space is assumed to coincide with the subject's personal domain. The estimated local humidity is provided to the thermal sensation prediction unit 107. Methods for estimating local humidity include, for example, the first estimation method and the second estimation method described below.

[0032] First, we will explain the first estimation method for estimating local humidity. In the first estimation method, the local humidity estimation unit 106 estimates local humidity by inputting the indoor humidity, which is the humidity of a predetermined space, and the portion of the thermal image that includes the personal area for which local humidity is to be calculated, into a pre-trained model. The model here is assumed to have been trained using training data in which the humidity of the subject space, which is the space in which the subject person is located, and a thermal image of the subject space that includes at least the subject, are input data, and the humidity measured within a predetermined range around the subject, which is narrower than the subject space, is the ground truth data.

[0033] Specifically, in the first estimation method, the local humidity estimation unit 106 inputs a local image, which is an image of a predetermined range including the target individual's area from a thermal image, and the room humidity as input data to a pre-trained model, and obtains the estimated local humidity as the output of that model.

[0034] The model used here is one that was trained using local images and indoor humidity as input data, with local humidity as training data. Furthermore, it is desirable that the local images include personal areas that are determined to be located within a predetermined range identified when calculating the density x mentioned above.

[0035] Next, we will explain a second estimation method for estimating local humidity. In the second estimation method, the local humidity estimation unit 106 identifies the amount of water vapor emitted by an individual corresponding to a personal area, which is the amount of water vapor emitted by the individual, based on the room temperature, which is the temperature of a predetermined space, such that it increases as the room temperature increases. The local humidity estimation unit 106 calculates the amount of water vapor emitted by the individual by multiplying the amount of water vapor emitted by the individual by the number of people around the individual in the predetermined space plus 1. The local humidity estimation unit 106 calculates the amount of water vapor by adding the average amount of water vapor determined by the room temperature to the amount of water vapor emitted by the local humidity. Then, the local humidity estimation unit 106 estimates the local humidity by dividing the amount of water vapor by the saturation water vapor amount determined by the room temperature.

[0036] In the second estimation method, the local humidity estimation unit 106 estimates the local humidity by determining the amount of water vapor in the target personal area from the number of people present around the target personal area plus the person corresponding to the target personal area, and the amount of water vapor emitted by people, which is the amount of water vapor emitted by people.

[0037] Specifically, the local humidity estimation unit 106 first calculates the local water vapor generation amount, which is the amount of water vapor emitted by the target individual's area and people in the surrounding area, using equation (2) below. Local water vapor generation (g / m³) 3) = number of people in the area × amount of water vapor generated by the human body (g / m³) 3 ) (2)

[0038] Here, the local population may be the same value as the density x mentioned above, or it may be a different value. Furthermore, a function, graph, or table showing the relationship between the amount of water vapor generated by the human body and the room temperature, as shown in Figure 8, is pre-stored in a memory unit (not shown), and the local humidity estimation unit 106 determines the amount of water vapor generated by the human body from the room temperature according to that function, graph, or table. As shown in Figure 8, the amount of water vapor generated by the human body increases as the indoor temperature rises.

[0039] Next, the local humidity estimation unit 106 calculates the average water vapor content using equation (3) below. Average water vapor content (g / m³) 3 ) = Saturated water vapor amount (g / m³) 3 ) x indoor humidity (%) ÷ 100 (3)

[0040] Furthermore, as shown in Figure 9, the saturated water vapor amount increases with increasing temperature. A function, graph, or table showing the relationship as shown in Figure 9 is pre-stored in a memory unit (not shown). The temperature here refers to the room temperature.

[0041] Next, the local humidity estimation unit 106 calculates the local water vapor amount, which is the amount of water vapor in the target personal area and the area surrounding the target personal area, using equation (4) below. Local water vapor content (g / m³) 3 ) = Local water vapor generation (g / m³) 3 ) + average water vapor content (g / m³) 3 ) (4)

[0042] The local humidity estimation unit then calculates the local humidity using equation (5) below. Local humidity (%) = Local water vapor content (g / m³) 3 ) ÷ Saturated water vapor amount (g / m³) 3 ) × 100 (5)

[0043] The thermal sensation prediction unit 107 predicts the thermal sensation of a corresponding individual for each individual area using the corresponding local humidity. Here, the thermal sensation prediction unit 107 calculates a PMV (Personal Mass Value) for each individual area. Typically, the thermal comfort index is calculated using a known formula with respect to indoor temperature, radiant temperature, humidity, airflow, clothing weight, and metabolic rate. Here, the thermal comfort prediction unit 107 uses the indoor temperature acquired by the indoor temperature acquisition unit 102 and the radiant temperature calculated by the radiant temperature calculation unit 105 as the indoor temperature and radiant temperature for calculating the thermal comfort index value. The thermal sensation prediction unit 107 then uses the local humidity estimated by the local humidity estimation unit 106 as the humidity for calculating the thermal sensation index value.

[0044] The thermal comfort prediction unit 107 uses a predetermined value or a value corresponding to the airflow set in an air conditioner (not shown) installed in the space where people are present as the airflow for calculating the thermal comfort index value. Furthermore, the amount of clothing worn is predetermined for each season, and the thermal sensation prediction unit 107 uses the value corresponding to the season for calculating the thermal sensation index as the amount of clothing worn to calculate the thermal sensation index. Furthermore, since crowds typically remain still, the thermal sensation prediction unit 107 uses a predetermined value corresponding to upright, motionless posture as the metabolic rate for calculating the thermal sensation index value.

[0045] Some or all of the thermal image acquisition unit 101, room temperature acquisition unit 102, room humidity acquisition unit 103, personal area detection unit 104, radiant temperature calculation unit 105, local humidity estimation unit 106, and thermal sensation prediction unit 107 described above can be configured, for example, with a memory 10 and a processor 11 such as a CPU (Central Processing Unit) that executes the program stored in the memory 10, as shown in Figure 10(A). In other words, the thermal sensation prediction device 100 can be implemented using a computer such as a PC (Personal Computer). Such a program may be provided via a network, or it may be provided by recording it on a recording medium. That is, such a program may be provided, for example, as a computer program product.

[0046] Furthermore, some or all of the thermal image acquisition unit 101, the room temperature acquisition unit 102, the room humidity acquisition unit 103, the personal area detection unit 104, the radiant temperature calculation unit 105, the local humidity estimation unit 106, and the thermal sensation prediction unit 107 can also be composed of processing circuits 12 such as a single circuit, a composite circuit, a program-operated processor, a program-operated parallel processor, an ASIC (Application Specific Integrated Circuit), or an FPGA (Field Programmable Gate Array), as shown in Figure 10(B). As described above, the thermal image acquisition unit 101, the room temperature acquisition unit 102, the room humidity acquisition unit 103, the personal area detection unit 104, the radiant temperature calculation unit 105, the local humidity estimation unit 106, and the thermal sensation prediction unit 107 can be realized by a processing circuit network.

[0047] Figure 11 is a flowchart showing the operation of the thermal sensation prediction device 100 according to Embodiment 1. Here, we will explain assuming that the thermal image acquisition unit 101 has already acquired a thermal image, the indoor temperature acquisition unit 102 has acquired the indoor temperature, and the indoor humidity acquisition unit 103 has acquired the indoor humidity.

[0048] First, the personal area detection unit 104 detects personal areas, which are the areas of each individual person in the space, from the thermal image (S10).

[0049] The radiation temperature calculation unit 105 calculates the radiation temperature for each personal area detected in step S10 (S11).

[0050] The local humidity estimation unit 106 estimates the local humidity for each personal area detected in step S10 (S12).

[0051] The thermal sensation prediction unit 107 acquires indoor temperature, airflow rate, metabolic rate, and clothing amount in order to calculate a thermal sensation index value (S13).

[0052] Then, the thermal sensation prediction unit 107 calculates a thermal sensation index value for each individual area using the radiant temperature calculated in step S11, the local humidity estimated in step S12, and the indoor temperature, airflow rate, metabolic rate, and clothing amount obtained in step S13 (S14).

[0053] As described above, according to Embodiment 1, in a crowd, the increase in humidity due to sweat and exhalation from people in the surrounding area is taken into consideration, and it is possible to accurately predict a person's thermal sensation. Furthermore, by using the accurately predicted thermal sensations as described above, it is possible to control, for example, an air conditioner, to keep the crowd comfortable while operating the air conditioner efficiently.

[0054] Embodiment 2. Figure 12 is a schematic block diagram showing the configuration of the thermal sensation prediction device 200 according to Embodiment 2. The thermal sensation prediction device 200 includes a thermal image acquisition unit 101, an indoor temperature acquisition unit 102, an indoor humidity acquisition unit 103, a personal area detection unit 104, a radiant temperature calculation unit 105, a local humidity estimation unit 206, a thermal sensation prediction unit 107, and a personal water vapor generation amount estimation unit 208.

[0055] The thermal image acquisition unit 101, room temperature acquisition unit 102, room humidity acquisition unit 103, personal area detection unit 104, radiant temperature calculation unit 105, and thermal sensation prediction unit 107 of the thermal sensation prediction device 200 according to Embodiment 2 are the same as those of the thermal image acquisition unit 101, room temperature acquisition unit 102, room humidity acquisition unit 103, personal area detection unit 104, radiant temperature calculation unit 105, and thermal sensation prediction unit 107 of the thermal sensation prediction device 100 according to Embodiment 1.

[0056] The individual water vapor generation estimation unit 208 estimates the individual water vapor generation, which is the amount of water vapor generated by an individual's body included in the thermal image. For example, the individual water vapor generation estimation unit 208 estimates the individual water vapor generation so that it is higher the larger the individual's physique. Here, the individual water vapor generation estimation unit 208 determines that the larger the area of ​​a person in the thermal image, the larger the person's physique. For example, the individual water vapor generation estimation unit 208 identifies the physique of an individual included in the thermal image according to the total number of pixels of the human body area identified by the individual area detection unit 104, and estimates the individual water vapor generation amount so that it increases as the identified individual's physique increases.

[0057] The individual water vapor generation estimation unit 208 classifies the body size of individuals included in the thermal image into "small," "medium," and "large" by comparing the total number of pixels of the human body region identified by the individual region detection unit 104 with a first threshold and a second threshold. Here, it is assumed that the first threshold < the second threshold. Specifically, the individual water vapor generation estimation unit 208 classifies the body size of individuals included in the thermal image as "small" if the total number of pixels in the human body region is less than or equal to the first threshold. Furthermore, the individual water vapor generation estimation unit 208 classifies the body size of an individual included in the thermal image as "medium size" if the first threshold < total number of pixels in the human body region < second threshold. Furthermore, the individual water vapor generation estimation unit 208 classifies the physique of an individual included in the thermal image as "large physique" if the second threshold ≤ the total number of pixels in the human body region.

[0058] Then, a function, graph, or table showing the relationship between individual water vapor generation for each body size and the room temperature, as shown in Figure 13, is pre-stored in a memory unit (not shown), and the individual water vapor generation estimation unit 208 identifies the individual water vapor generation amount corresponding to the body size classified from the room temperature according to that function, graph, or table. Furthermore, as shown in Figure 13, the amount of water vapor generated by an individual for each body size increases as the indoor temperature rises.

[0059] The local humidity estimation unit 206 estimates the local humidity, which is the local humidity in each personal area detected by the personal area detection unit 104. In Embodiment 2, the local humidity estimation unit 206 estimates the local humidity using the second estimation method described above. However, in Embodiment 2, the local humidity estimation unit 206 calculates the local water vapor generation amount using equation (6) below instead of equation (2). Local water vapor generation (g / m³) 3 ) = number of people in the area × amount of water vapor generated per person (g / m³) 3 ) (6)

[0060] The personal water vapor generation estimation unit 208 described above can also be configured, for example, as shown in Figure 10(A), with a memory 10 and a processor 11 such as a CPU that executes the program stored in the memory 10. Furthermore, the individual water vapor generation estimation unit 208 can also be configured with a processing circuit 12, for example, as shown in Figure 10(B). As described above, the individual water vapor generation estimation unit 208 can also be realized by a processing circuit network.

[0061] Figure 14 is a flowchart showing the operation of the thermal sensation prediction device 200 according to Embodiment 2. Here, we will explain assuming that the thermal image acquisition unit 101 has already acquired a thermal image, the indoor temperature acquisition unit 102 has acquired the indoor temperature, and the indoor humidity acquisition unit 103 has acquired the indoor humidity. Furthermore, among the steps included in the flowchart shown in Figure 14, steps that perform the same processing as the steps included in the flowchart shown in Figure 11 are denoted by the same reference numerals as those shown in Figure 11.

[0062] The processes in steps S10 and S11 in Figure 14 are the same as those in steps S10 and S11 in Figure 11. However, after step S11 in Figure 14, the process proceeds to step S20.

[0063] In step S20, the personal water vapor generation estimation unit 208 estimates the personal water vapor generation amount, which is the amount of water vapor generated by the individual's body included in the thermal image.

[0064] Next, the local humidity estimation unit 206 estimates the local humidity for each personal area detected in step S10 (S21). Here, the local humidity estimation unit 206 estimates the local humidity using the personal water vapor generation amount estimated in step S20 and the second estimation method described above. Then, the process proceeds to step S13.

[0065] The processes in steps S13 and S14 in Figure 14 are the same as those in steps S13 and S14 in Figure 11.

[0066] First, the personal area detection unit 104 detects personal areas, which are the areas of each individual person in the space, from the thermal image (S10).

[0067] The radiation temperature calculation unit 105 calculates the radiation temperature for each personal area detected in step S10 (S11).

[0068] The local humidity estimation unit 106 estimates the local humidity for each personal area detected in step S10 (S12).

[0069] The thermal sensation prediction unit 107 acquires indoor temperature, airflow rate, metabolic rate, and clothing amount in order to calculate a thermal sensation index value (S13).

[0070] Then, the thermal sensation prediction unit 107 calculates a thermal sensation index value for each individual area using the radiant temperature calculated in step S11, the local humidity estimated in step S12, and the indoor temperature, airflow rate, metabolic rate, and clothing amount obtained in step S13 (S14).

[0071] As described above, according to Embodiment 2, the amount of water vapor emitted by each person in the surrounding area can be accurately estimated from their body size. Therefore, the local humidity at the subject's location can also be accurately estimated. As a result, the subject's thermal sensation can be estimated more accurately. [Explanation of Symbols]

[0072] 100,200 Thermal sensation prediction device, 101 Thermal image acquisition unit, 102 Indoor temperature acquisition unit, 103 Indoor humidity acquisition unit, 104 Personal area detection unit, 105 Radiation temperature calculation unit, 106,206 Local humidity estimation unit, 107 Thermal sensation prediction unit, 208 Personal water vapor generation amount estimation unit.

Claims

1. A personal area detection unit detects a personal area, which is the area of ​​an individual located within a predetermined space and is smaller than the predetermined space, from a thermal image showing the temperature distribution in a predetermined space. A local humidity estimation unit that estimates the local humidity, which is the humidity of the personal area, The system includes a thermal sensation prediction unit that predicts the individual's thermal sensation using the local humidity, The local humidity estimation unit determines the amount of water vapor emitted by the individual, which is the amount of water vapor emitted by the individual, from the temperature of the predetermined space, such that it increases as the temperature of the predetermined space increases. It calculates the amount of water vapor emitted by the individual by multiplying the amount of water vapor emitted by the individual by the number of people around the individual in the predetermined space plus 1. It calculates the amount of water vapor emitted by the local humidity by adding the average amount of water vapor determined by the temperature of the predetermined space to the amount of water vapor emitted by the local humidity. It estimates the local humidity by dividing the amount of water vapor emitted by the saturation amount of water vapor determined by the temperature of the predetermined space. A thermal sensation prediction device characterized by the following.

2. The system further includes a personal water vapor generation estimation unit that estimates the amount of water vapor generated by the human body so that the amount increases as the individual's physique increases. The thermal sensation prediction device according to claim 1, characterized by the above.

3. The personal water vapor generation estimation unit determines that the larger the area of ​​the person in the thermal image, the larger the person's physique. The thermal sensation prediction device according to claim 2, characterized by the above.

4. Computers, A personal area detection unit detects a personal area, which is the area of ​​an individual located within a predetermined space and is smaller than the predetermined space, from a thermal image showing the temperature distribution in a predetermined space. A local humidity estimation unit that estimates the local humidity, which is the humidity of the personal area, and Using the aforementioned local humidity, it functions as a thermal sensation prediction unit that predicts the individual's thermal sensation. The local humidity estimation unit determines the amount of water vapor emitted by the individual, which is the amount of water vapor emitted by the individual, from the temperature of the predetermined space, such that it increases as the temperature of the predetermined space increases. It calculates the amount of water vapor emitted by the individual by multiplying the amount of water vapor emitted by the individual by the number of people around the individual in the predetermined space plus 1. It calculates the amount of water vapor emitted by the local humidity by adding the average amount of water vapor determined by the temperature of the predetermined space to the amount of water vapor emitted by the local humidity. It estimates the local humidity by dividing the amount of water vapor emitted by the saturation amount of water vapor determined by the temperature of the predetermined space. A program characterized by the following.

5. From a thermal image showing the temperature distribution in a predetermined space, a personal area, which is the personal domain of an individual located within the predetermined space and is smaller than the predetermined space, is detected. The local humidity, which is the humidity of the personal area, is estimated. A method for predicting a person's thermal sensation using the local humidity, The amount of water vapor emitted by the individual, which is the amount of water vapor generated by the human body, is determined such that it increases as the temperature of the predetermined space increases, based on the temperature of the predetermined space. The amount of water vapor generated by the human body is calculated by multiplying the amount of water vapor generated by adding 1 to the number of people around the individual in the predetermined space by the amount of water vapor generated by the human body. The amount of localized water vapor is calculated by adding the average amount of water vapor determined by the temperature of the predetermined space to the amount of localized water vapor generated. The local humidity is estimated by dividing the local water vapor amount by the saturated water vapor amount determined by the temperature of the predetermined space. A method for predicting thermal sensation characterized by the following.

Images