Air conditioning system and control method thereof

Abstract

The invention discloses an air conditioning system (10) and a control method thereof. The air conditioning system (10) comprises an outdoor unit (12), an indoor unit (11), infrared equipment (100) and a controller (102). The infrared device (100) is configured to thermally image a target object to detect position information of the target object. The controller (102) is configured to: determine a target number of preset lower viewing angles from a preset angle range; wherein the preset angle range is a mounting angle range of the infrared device (100); determining each first target distance corresponding to each preset lower view angle of the target pixel point according to the corresponding relationship between the lower view angle and the first distance; the target pixel point is an image pixel point imaged by the infrared device (100) on the target object in the target area; the first target distance is a predicted distance between the target pixel point and the infrared device (100); and determining the first target distance with the minimum absolute value of the distance difference between the first target distance and the second target distance from the first target distances.

Description

Air conditioning system and control method thereof

[0001] This application claims priority to Chinese patent application No. 202310086633.8 filed on January 28, 2023, and priority to Chinese patent application No. 202310065521.4 filed on January 13, 2023, the entire contents of which are incorporated by reference into this application. Technical Field

[0002] The present disclosure relates to the technical field of air conditioning, and in particular to an air conditioning system and a control method thereof. Background Art

[0003] With the development of technology, infrared devices are widely used in various electronic devices and household appliances. For example, infrared devices are installed on household appliances such as air conditioning systems to perform thermal imaging of users or objects to detect their location information.

[0004] Summary of the Invention

[0005] In one aspect, an air conditioning system is provided, comprising an outdoor unit, an indoor unit, an infrared device, and a controller. The indoor unit is connected to the outdoor unit. The infrared device is configured to perform thermal imaging of a target object to detect the target object's location information. The controller is configured to: determine a preset lower viewing angle for a number of targets within a preset angle range; wherein the preset angle range is the installation angle range of the infrared device; determine, based on a correspondence between the lower viewing angle and a first distance, respective first target distances corresponding to target pixels at respective preset lower viewing angles; wherein the first distance is the distance between an image pixel of the infrared device and the infrared device; the target pixel is the image pixel of the target object imaged by the infrared device in a target area; and the first target distance is the predicted distance between the target pixel and the infrared device; from each of the first target distances, determine the first target distance having the smallest absolute value of distance difference from a second target distance; wherein the second target distance is the actual distance between the target pixel and the infrared device; and use the preset lower viewing angle corresponding to the first target distance having the smallest absolute value of distance difference from the second target distance as the installation angle of the infrared device.

[0006] In another aspect, a method for controlling an air conditioning system is provided, wherein the air conditioning system includes an outdoor unit, an indoor unit, an infrared device, and a controller. The indoor unit is connected to the outdoor unit. The infrared device is configured to perform thermal imaging of a target object to detect the target object's location information. The controller is coupled to the outdoor unit, the indoor unit, and the infrared device. The control method includes: determining a preset lower viewing angle of a target number from a preset angle range; wherein the preset angle range is the installation angle range of the infrared device; determining each first target distance corresponding to each preset lower viewing angle of the target pixel point in the lower viewing angle of the target number according to the correspondence between the lower viewing angle and the first distance; wherein the first distance is the distance between the image pixel point of the infrared device and the infrared device; the target pixel point is the image pixel point of the target object imaged by the infrared device in the target area; the first target distance is the predicted distance between the target pixel point and the infrared device; from each first target distance, determining the first target distance with the smallest absolute value of the distance difference from the second target distance; wherein the second target distance is the actual distance between the target pixel point and the infrared device; the preset lower viewing angle corresponding to the first target distance with the smallest absolute value of the distance difference from the second target distance is used as the installation angle of the infrared device; and determining the position information of the target object corresponding to the target pixel point according to the installation angle of the infrared device.

[0007] In yet another aspect, a method for controlling an air conditioning system is provided, wherein the air conditioning system includes an outdoor unit, an indoor unit, an infrared device, and a controller. The indoor unit is connected to the outdoor unit. The infrared device is configured to perform thermal imaging of a target object to detect the target object's location information; the infrared device includes a thermal imaging device, disposed on the indoor unit, and configured to capture a thermal image of an infrared detection area. The controller is coupled to the outdoor unit, the indoor unit, the infrared device, and the thermal imaging device. The control method includes: acquiring a target thermal imaging image in an infrared detection area through a thermal imaging device, the target thermal imaging image including the measured temperature of each pixel; identifying a target image area corresponding to the target object from the target thermal imaging image; determining temperature measurement parameters of the target object in the target thermal imaging image based on the target image area corresponding to the target object in the target thermal imaging image and the installation height of the thermal imaging device, the temperature measurement parameters including at least a pitch angle and a heading angle of the target object in the target thermal imaging image relative to the thermal imaging device; and correcting the measured temperature of the target object in the target image area based on the temperature measurement parameters, a preset correction value, and a preset weight coefficient corresponding to the temperature measurement parameters to obtain the actual temperature of the target object. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] FIG1 is a structural diagram of an air conditioning system according to some embodiments;

[0009] FIG2 is a block diagram of an infrared device according to some embodiments;

[0010] FIG3 is a flow chart of a method for controlling an air conditioning system according to some embodiments;

[0011] FIG4 is a flow chart of another method for controlling an air conditioning system according to some embodiments;

[0012] FIG5 is an application scenario diagram of a control method for an air-conditioning system according to some embodiments;

[0013] FIG6 is an application scenario diagram of another method for controlling an air-conditioning system according to some embodiments;

[0014] FIG7 is a flowchart of another method for controlling an air conditioning system according to some embodiments;

[0015] FIG8 is a schematic diagram illustrating a mapping relationship between the height of an infrared device and the second target distance of each target pixel according to some embodiments;

[0016] 9 is a diagram illustrating the relationship between a pitch field of view angle of an infrared device, a horizontal field of view angle of the infrared device, and a first resolution according to some embodiments;

[0017] FIG10 is a flowchart of another method for controlling an air conditioning system according to some embodiments;

[0018] FIG11 is a flowchart of another method for controlling an air conditioning system according to some embodiments;

[0019] FIG12 is an installation diagram of a thermal imaging device according to some embodiments;

[0020] FIG13 is a flowchart of another method for controlling an air conditioning system according to some embodiments;

[0021] FIG14 is a diagram illustrating a temperature measurement principle of a thermal imaging device according to some embodiments;

[0022] FIG15 is a flowchart of another method for controlling an air conditioning system according to some embodiments;

[0023] FIG16 is a schematic diagram of a single convolution pooling of a human posture detection model according to some embodiments;

[0024] FIG17 is a diagram of a human posture detection network model according to some embodiments;

[0025] FIG18 is a flow chart of yet another method for controlling an air conditioning system according to some embodiments;

[0026] FIG19 is a schematic diagram of an application scenario of another method for controlling an air-conditioning system according to some embodiments;

[0027] FIG20 is a schematic diagram of an application scenario of another method for controlling an air-conditioning system according to some embodiments;

[0028] FIG21 is a schematic diagram of an application scenario of another method for controlling an air-conditioning system according to some embodiments;

[0029] FIG22 is a flow chart of yet another method for controlling an air conditioning system according to some embodiments;

[0030] FIG23 is a block diagram of a controller according to some embodiments. DETAILED DESCRIPTION

[0031] The following will be combined with the accompanying drawings to clearly and completely describe some embodiments of the present disclosure. Obviously, the embodiments described are only some embodiments of the present disclosure, rather than all embodiments. Based on the embodiments provided by the present disclosure, all other embodiments obtained by ordinary technicians in this field are within the scope of protection of the present disclosure.

[0032] Unless the context requires otherwise, throughout the specification and claims, the term "comprise" and its other forms, such as the third person singular form "comprises" and the present participle form "comprising", are to be interpreted as open and inclusive, that is, "including, but not limited to". In the description of the specification, the terms "one embodiment", "some embodiments", "exemplary embodiments", "example", "specific example" or "some examples" are intended to indicate that the particular features, structures, materials or characteristics associated with the embodiment or example are included in at least one embodiment or example of the present disclosure. The schematic representation of the above terms does not necessarily refer to the same embodiment or example. In addition, the particular features, structures, materials or characteristics may be included in any one or more embodiments or examples in any appropriate manner.

[0033] In the following, the terms "first" and "second" are used for descriptive purposes only and should not be understood to indicate or imply relative importance or implicitly specify the number of the technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of the embodiments of the present disclosure, unless otherwise specified, "plurality" means two or more.

[0034] When describing some embodiments, the expressions "coupled" and "connected" and their derivatives may be used. The term "connected" should be understood in a broad sense. For example, "connection" can be a fixed connection, a detachable connection, or an integral connection; it can be directly connected or indirectly connected through an intermediate medium. The term "coupled" indicates, for example, that two or more components are in direct physical or electrical contact. The term "coupled" or "communicatively coupled" may also refer to two or more components that are not in direct contact with each other, but still cooperate or interact with each other. The embodiments disclosed herein are not necessarily limited to the contents of this document.

[0035] “A and / or B” includes the following three combinations: A only, B only, and a combination of A and B.

[0036] The use of "adapted to" or "configured to" herein is intended to be open and inclusive language that does not exclude devices adapted or configured to perform additional tasks or steps.

[0037] Additionally, the use of “based on” is meant to be open and inclusive, as a process, step, calculation, or other action “based on” one or more stated conditions or values ​​may, in practice, be based on additional conditions or values ​​beyond those stated.

[0038] Figure 1 is a block diagram of an air conditioning system according to some embodiments. As shown in Figure 1 , air conditioning system 10 includes an indoor unit 11 and an outdoor unit 12. Indoor unit 11 is located indoors and is configured to exchange heat with the indoor environment. In some embodiments, indoor unit 11 is an indoor wall mounted unit.

[0039] The outdoor unit 12 is installed outdoors and is configured to exchange heat with the indoor environment. The outdoor unit 12 is represented by a dotted line in FIG1 .

[0040] In some embodiments, the air conditioning system 10 further includes a refrigerant pipeline 13 , which may also be referred to as a circulation pipeline. The refrigerant pipeline 13 connects the indoor unit 11 and the outdoor unit 12 to form a refrigerant circulation loop.

[0041] In some embodiments, the air-conditioning system 10 also includes a remote control 14, which is configured to enable interaction between the user and the air-conditioning system 10 through infrared or other communication methods. The user can use the display device and buttons on the remote control 14 to perform operations such as turning the air-conditioning system 10 on and off, setting the temperature, setting the wind direction, and setting the air volume.

[0042] In some embodiments, the air conditioning system 10 further includes an infrared device, which is configured to perform thermal imaging of a target object (eg, a user or a target object) to detect location information of the user or the target object.

[0043] It should be noted that the principle of infrared thermal imaging is that due to the existence of blackbody radiation, any object will radiate electromagnetic waves due to temperature differences. If the surface temperature of an object exceeds absolute zero, it will radiate electromagnetic waves. As temperature changes, the intensity and wavelength distribution of the electromagnetic waves also change. The wavelength range of [2.0μm, 1000μm] is called "thermal infrared light," while the range of "visible light" visible to human vision is [0.4μm, 0.75μm]. Infrared radiation, which can be referred to as infrared light or infrared rays, refers to electromagnetic waves with wavelengths between approximately 0.75 microns and 1000 microns. Infrared thermal imaging uses photoelectric technology to detect infrared signals in specific wavelength bands emitted by an object's thermal radiation, converting these signals into visually distinguishable images and graphics, and further calculating the temperature value.

[0044] Because thermal images lack distinct color information compared to color images, they do not infringe on user privacy in daily life. Furthermore, thermal images are generated based on the varying temperatures of different objects within the infrared detection area, accurately identifying the presence of a target object within the area. This improves the temperature measurement accuracy of the thermal imaging device without compromising user privacy. Based on this precise temperature, the air conditioning system 10 can be intelligently controlled to meet user needs.

[0045] It should be noted that the location information of the user or target object is usually determined based on the downward viewing angle (i.e., the installation angle of the infrared device). Therefore, the accuracy of the downward viewing angle determines the accuracy of the location information detected by the infrared device. In the related art, when installing an infrared device, it is usually installed according to a fixed preset installation angle to reduce the error between the installation angle during actual installation and the preset installation angle, thereby improving the accuracy of the location information detected by the infrared device. However, in actual applications, the actual installation angle of the infrared device will change due to changes in the installation environment, resulting in a large error and large difference between the actual installation angle and the preset installation angle, and poor stability, which leads to poor accuracy of the location information determined by the preset installation angle.

[0046] To address the above-mentioned issues, some embodiments of the present disclosure provide an infrared device 100 and a method for determining its installation angle. The infrared device 100 and the method for determining its installation angle determine the position information of the target object based on a preset lower viewing angle that has an uncertain error from the actual installation angle of the infrared device 100. The obtained position information is more accurate, thereby making the detection results of the infrared device 100 more accurate. At the same time, the method for determining the installation angle in some embodiments of the present disclosure takes into account the impact of different installation environments on the actual installation angle, allowing users to install the infrared device 100 according to their desired installation angle without restricting the actual installation angle, thereby making the installation of the infrared device 100 faster and more convenient.

[0047] FIG2 is a structural block diagram of an infrared device according to some embodiments. As shown in FIG2 , in some embodiments of the present disclosure, the infrared device 100 includes a thermal imaging device 101 .

[0048] In some embodiments of the present disclosure, the thermal imaging device 101 is configured to capture thermal images of the infrared detection area. For example, the thermal imaging device 101 receives the radiant energy of thermal radiation from objects within the infrared detection area and converts the radiant energy of the thermal radiation from the objects into electrical signals. Users can set the operating time and on-time of the thermal imaging device 101 through a terminal device. The thermal imaging device 101 receives the thermal radiation energy from the infrared detection area and converts it into an electrical signal. After amplification, integer shaping, and analog-to-digital conversion, the signal is converted into a digital signal, which is then displayed as an image to obtain a thermal image of the infrared detection area. In some embodiments of the present disclosure, the thermal imaging device 101 can be deployed externally to the air conditioning system 10, such as the upper portion of the air conditioning system 10 in FIG. 12 ; the thermal imaging device 101 can also be deployed internally as part of the air conditioning system 10.

[0049] In some embodiments of the present disclosure, the infrared device 100 accurately determines the position information of the target object, thereby using it as prior information to eliminate false target objects in the identification of the target object.

[0050] In some embodiments of the present disclosure, the air conditioning system 10 also includes a distance detection device, which can be set at the center point of the infrared device 100 and is configured to determine the second target distance (i.e., the actual distance between the target pixel point and the center point of the infrared device 100).

[0051] In some embodiments of the present disclosure, the infrared device 100 further includes a controller 102. The controller 102 is a device that can generate an operation control signal based on an instruction operation code and a timing signal, thereby instructing the air conditioning system 10 to execute the control instruction. The controller 102 is configured to control the operation of various components within the air conditioning system 10, so that the various components of the air conditioning system 10 operate to implement various predetermined functions of the air conditioning system 10. For example, the controller 102 receives an electrical signal from the thermal imaging device 101 and, based on the resolution of the thermal imaging device 101, restores the electrical signal to an image size matrix corresponding to the resolution of the thermal imaging device 101, thereby obtaining an original thermal imaging image of the infrared detection area. The controller 102 then processes the original thermal imaging image to obtain a target thermal imaging image of the infrared detection area.

[0052] For example, the controller 102 is configured to predict the predicted distances corresponding to different preset lower viewing angles based on the correspondence between the lower viewing angles and the first distances, that is, the first target distances between the target pixel and the infrared device 100. The actual installation angle of the infrared device 100 is then determined based on the minimum error between the actual distance between the target pixel and the center point of the infrared device 100 (that is, the second target distance) and the predicted first target distance, and the position information of the target object of the infrared device 100 is determined based on the installation angle.

[0053] In other embodiments of the present disclosure, the controller 102 determines the position information of the target object corresponding to the target pixel point according to the installation angle of the infrared device 100 .

[0054] In some embodiments of the present disclosure, the infrared device 100 further includes a display 103. The display 103 is configured to display status information corresponding to the infrared device 100 in various operating states.

[0055] In some embodiments of the present disclosure, the infrared device 100 further includes an alarm 104. The alarm 104 is configured to send corresponding prompt information when starting the running program to remind the user of the stage of the infrared device 100 detecting the installation angle, for example, sending prompt information corresponding to the stage of the infrared device 100 being detected, the stage of detection being completed, etc.

[0056] In some embodiments of the present disclosure, the infrared device 100 further includes a communication device 105. The communication device 105 is configured to communicate with an external device or an external server according to various communication protocol types.

[0057] The infrared device 100 transmits control signals and data signals to the user's terminal device (e.g., mobile phone, tablet computer, wearable mobile device), other household devices (e.g., air conditioner, monitoring equipment), and server through the communication device 105. For example, a user issues a command to turn on the infrared device 100 through the mobile phone, and the infrared device 100 receives the command through the communication device 105. In response to the user's device turn-on command indicating the turn-on mode, the controller 102 of the infrared device 100 turns on.

[0058] In some embodiments of the present disclosure, the infrared device 100 further includes a human-computer interaction device 106. Human-computer interaction device 106 is configured to enable interaction between a user and the infrared device 100. Human-computer interaction device 106 may include, for example, at least one of a physical button, a touch display panel, or a voice recognition device. A user may activate the infrared device 100 through human-computer interaction device 106 to begin operation and may also configure a program corresponding to an operating mode of the infrared device 100 through human-computer interaction device 106.

[0059] In some embodiments of the present disclosure, the infrared device 100 further includes a power supply 107. The power supply 107 is configured to provide power supply support for the infrared device 100 using power input from an external power source.

[0060] In some embodiments of the present disclosure, the air conditioning system 10 further includes a timer 108, which is a device capable of detecting the operating hours of various air conditioning system components. In some embodiments of the present disclosure, the timer 108 is configured to record the operating hours of the thermal imaging device 101. For example, if the user sets the thermal imaging device 101 to operate once every hour, the timer 108 will send a prompt message to the controller 102 after counting one hour, prompting the controller 102 to control the operation of the thermal imaging device 101.

[0061] In some embodiments of the present disclosure, the air conditioning system 10 further includes a voice prompt device 109. The voice prompt device 109 is configured to provide a voice prompt after the user successfully adjusts the operating parameters of the air conditioning system 10, such as a power on / off prompt tone, a temperature adjustment prompt tone, or an air volume adjustment prompt tone. The content of the voice prompt can be pre-set or customized by the user through the terminal device or human-computer interaction device 106. For example, if the controller 102 detects a high-temperature object in the thermal image captured by the thermal imaging device 101, the voice prompt device 109 can play a prompt message to prompt the user to check the infrared detection area for any danger.

[0062] In some embodiments of the present disclosure, the infrared device 100 further includes a memory 110 , and the memory 110 is configured to store computer program codes related to a control method of the air-conditioning system 10 .

[0063] FIG3 is a flow chart of a method for controlling an air conditioning system according to some embodiments. Some embodiments of the present disclosure provide a method for determining the installation angle of an infrared device 100, which is applied to a controller 102. As shown in FIG3 , the method for determining the installation angle of the infrared device 100 includes steps S201 to S204.

[0064] S201, determining a target number of preset lower viewing angles from a preset angle range.

[0065] The preset angle range is the installation angle range of the infrared device 100. In some embodiments of the present disclosure, the preset angle range is an angle interval consisting of a first preset angle and a second preset angle, and the first preset angle is smaller than the second preset angle. Determining a target number of preset lower viewing angles from the preset angle range may include: dividing the preset angle range into a target number of preset lower viewing angles according to a target angle interval; the target angle interval is the average angle difference after evenly dividing the target angle difference into a target number of equal parts; and the target angle difference is the angle difference between the second preset angle and the first preset angle.

[0066] The target angle interval can be understood as an angle step size, and the target angle interval is determined based on the installation environment or the required accuracy of the installation angle. It is understood that the preset angle range is the installation angle range within which the infrared device 100 can be reasonably installed in the installation environment. That is, the installation angle range is related to the installation environment of the infrared device 100.

[0067] In some embodiments of the present disclosure, when the installation space of the installation environment is greater than or equal to the space occupied by the infrared device 100, the preset angle range is, for example, [0, π / 2]. Starting from a first preset angle of 0 degrees and an angle step of 1°, the preset angle range is traversed until all angles within the preset angle range are a target number of preset lower viewing angles (0°, 1°, 2°, ..., 90°), where the target number is, for example, 91.

[0068] The entire preset angle range is traversed according to the target angle interval to obtain multiple preset lower viewing angles, so that the multiple preset lower viewing angles can cover each angle interval in the preset angle range, thereby making the installation angle of the infrared device 100 determined based on the multiple preset lower viewing angles more accurate.

[0069] In other embodiments of the present disclosure, the preset angle range can be determined based on the expected installation angle used by the infrared device 100 to determine position information. For example, the angle range that differs from the expected installation angle within a preset angle difference range is determined as the preset angle range. The preset angle difference range is the angle error caused by the installation environment. For example, if the preset angle difference range is within 10° and the expected installation angle is, for example, 30°, then the preset angle range is [20°, 40°].

[0070] S202 : Determine, based on a correspondence between a lower viewing angle and a first distance, first target distances corresponding to respective preset lower viewing angles of a target pixel point within a target number of lower viewing angles.

[0071] It should be noted that the preset lower viewing angle corresponds to the first target distance.

[0072] The first distance is the distance between the image pixel of the infrared device 100 and the infrared device 100. The target pixel is the image pixel formed by the infrared device 100 on the target object in the target area.

[0073] The target area may be an area determined from an image projected onto a target plane (eg, the ground) after the infrared device 100 images the target object.

[0074] The target area and target pixel point can be determined based on the area imaged by the target object. FIG4 is a flowchart of another method for controlling an air conditioning system according to some embodiments. As shown in FIG4 , in some embodiments of the present disclosure, the method for determining the target area and target pixel point includes S301 to S303.

[0075] S301 , obtaining a planar imaging area where a target object is imaged on a target plane from an image area of ​​an image captured by the infrared device 100 .

[0076] For example, after the infrared device 100 is fixed to a bracket or a wall, the infrared device 100 is powered on and an image of the target object is captured. From the image area of ​​the captured image, the image area where the target object is imaged on the target plane is marked and recorded as the plane imaging area. FIG5 is an application scenario diagram of a control method for an air conditioning system according to some embodiments. For example, as shown in FIG5 , the plane imaging area can be a quadrilateral area enclosed by line segment AB, line segment BC, line segment CD, and line segment AD, and is recorded as plane image area ABCD.

[0077] It can be understood that the target plane is a wall, or the ground, etc.

[0078] S302: Determine a target area from the planar imaging area.

[0079] In some embodiments of the present disclosure, a target area is obtained by setting a boundary area for a planar imaging area and removing the boundary area.

[0080] Figure 6 is an application scenario diagram of another control method for an air-conditioning system according to some embodiments. For example, as shown in Figure 6, boundaries accounting for 5% of the length of each segment are set on the line segment AB, line segment BC, line segment CD and line segment AD of the plane image area ABCD, and the area corresponding to the 5% boundary is removed to obtain the plane image area EFGI, and the target area is the image area EFGI.

[0081] S303: Determine one or more target pixels in the target area.

[0082] In some embodiments of the present disclosure, when there are multiple target pixel points determined, under a preset lower viewing angle, the multiple target pixel points correspond to multiple first target distances, that is, a preset lower viewing angle corresponds to a group of first target distances, and the number of first target distances included in a group of first target distances is the same as the number of target pixel points.

[0083] At this time, a plurality of target pixel points can be determined from the target area by a grid marking method. For example, the target area is grid-divided, and the target area is divided into M*N grid areas with (M+1)*(N+1) grid points, for example, the target area is divided into M*N equal grid areas. In some embodiments of the present disclosure, the above-mentioned (M+1)*(N+1) grid points are determined as target pixel points. Among them, M represents dividing the target area into M equal intervals in a first direction (for example, the Y direction in Figure 6); N represents dividing the target area into N equal intervals in a second direction (for example, the Z direction in Figure 6). In some embodiments of the present disclosure, the first direction is set perpendicular to the second direction.

[0084] As shown in Figure 6, for example, when M=N=8, the central vertical line of the planar image area EFGI is used as the image centerline, and the image area EFGI is divided into 8 equal intervals in the second direction using the 9 vertical dividing points of the line segment EF. At positions perpendicular to the image centerline, 9 horizontal dividing points are set, and the image area EFGI is also divided into 8 equal intervals in the first direction using the 9 horizontal dividing points, thereby forming 81 grid points from P1, P2 to P81. These 81 grid points are then used as target pixels. In this way, the target planar area can be covered as required, and subsequent calculations can be simplified.

[0085] When only one target pixel is determined, the first target distance is determined using that single target pixel. In this case, the center point of the target area is typically used as the target pixel. This simplifies the steps for determining the target pixel and further simplifies the steps for determining the first target distance, allowing for faster determination of the installation angle of the infrared device 100.

[0086] S203 , determining, from among the first target distances, a first target distance having the smallest absolute value of distance difference with the second target distance.

[0087] The controller 102 compares the predicted first target distances corresponding to the respective preset angles with the second target distances, and determines the first target distance having the smallest distance difference with the second target distance according to the difference comparison results.

[0088] The second target distance is the actual distance between the target pixel and the center point of the infrared device 100. In some embodiments of the present disclosure, the second target distance can be measured by a distance detection device (eg, a laser rangefinder).

[0089] It is understandable that the smallest absolute value of the distance difference represents the smallest distance error. In this way, the accuracy of the first target distance can be improved, thereby ensuring the accuracy of determining the installation angle of the infrared device 100.

[0090] S204 , taking the preset lower viewing angle corresponding to the first target distance having the smallest absolute value of the distance difference with the second target distance as the installation angle of the infrared device 100 .

[0091] For example, when there are five targets and the target pixel is Q, the controller 102 selects angles 1, 2, 3, 4, and 5 from the five preset lower viewing angles and predicts the first target distances Q1, Q2, Q3, Q4, and Q5 corresponding to angles 1, 2, 3, 4, and 5, respectively. The distance between the target pixel Q and the center point of the infrared device 100 is the second target distance.

[0092] If it is determined that the first target distance Q3 has the smallest absolute value of the distance difference with the second target distance among the first target distances Q1 , Q2 , Q3 , Q4 and Q5 , then the angle 3 corresponding to Q3 is the installation angle of the infrared device 100 .

[0093] In this way, the position information determined based on the actual installation angle is more accurate, which can ensure the accuracy of the determined installation angle of the infrared device 100, thereby making the detection results of the infrared device 100 more accurate. At the same time, the method for determining the installation angle provided in some embodiments of the present disclosure takes into account the impact of different installation environments on the actual installation angle, allowing users to install the infrared device 100 according to their desired installation angle without being restricted by the actual installation angle, thereby making the installation of the infrared device 100 faster and more convenient.

[0094] FIG7 is a flowchart of another method for controlling an air-conditioning system according to some embodiments. In some embodiments of the present disclosure, as shown in FIG7 , S202 may also be implemented as S202A.

[0095] S202A: Determine each first target distance according to the corresponding relationship between the downward viewing angle, the parameters of the infrared device 100 and the first distance.

[0096] In some embodiments of the present disclosure, the parameters of the infrared device 100 include a first parameter and a second parameter. The first parameter includes a pitch field angle of the infrared device 100 in a first direction of the target area and a first resolution of an image formed by the infrared device 100 in the first direction, and the second parameter includes a horizontal field angle of the infrared device 100 in a second direction of the target area and a second resolution of the image formed by the infrared device 100 in the second direction.

[0097] Among them, the first resolution of the image formed by the infrared device 100 in the first direction is the resolution of multiple target pixels in the first direction; the second resolution of the image formed by the infrared device 100 in the second direction is the resolution of each target pixel in the second direction.

[0098] It should be noted that the first parameter and the second parameter are determined according to the model of the infrared device 100 , that is, the first parameter and the second parameter corresponding to the same infrared device 100 are determined.

[0099] Figure 8 is a diagram showing a relationship between the height of an infrared device and the second target distance of each target pixel according to some embodiments, and Figure 9 is a diagram showing a relationship between the pitch field angle of an infrared device, the horizontal field angle of the infrared device, and the first resolution according to some embodiments. Figure 8 shows the distance H between the infrared device 100 and the target area plane, and the actual distances S1 to S2 between the 81 target pixels and the infrared device 100. 81 9 shows the relationship between the pitch field angle α of the infrared device 100, the horizontal field angle β of the infrared device and the first resolution.

[0100] In some embodiments of the present disclosure, the corresponding relationship between the lower viewing angle, the parameters of the infrared device 100 and the first distance is, for example, formula (1).

[0101] Among them, D (x，y) is the first distance, Z is the position coordinate of the image pixel point in the second direction, Y is the position coordinate of the image pixel point in the first direction, α is the pitch field angle of the infrared device 100, β is the horizontal field angle of the infrared device 100, γ is the downward viewing angle, the first resolution is h pixels, and the second resolution is W pixels; H is the vertical distance between the infrared device 100 and the plane of the target area.

[0102] Based on this, each preset lower viewing angle is substituted into the corresponding relationship between the lower viewing angle, the infrared device 100 parameters and the first distance to determine the first target distance between the target pixel point and the infrared device 100 at each preset lower viewing angle.

[0103] In some other embodiments of the present disclosure, FIG10 is a flowchart of another method for controlling an air-conditioning system according to some embodiments. As shown in FIG10 , S202 may also be implemented as S401 to S403.

[0104] S401 , determining a first target pitch angle of a target pixel point according to a correspondence between a downward viewing angle, a first parameter, position information of an image pixel point in a first direction, and a first pitch angle (ie, a pitch field angle) of the image pixel point.

[0105] The first pitch angle is the pitch angle of the target pixel in the first direction.

[0106] In some embodiments of the present disclosure, the correspondence between the lower viewing angle, the first parameter, the position information of the image pixel in the first direction and the first pitch angle of the image pixel is, for example, formula (2).

[0107] Among them, θ Y is the first pitch angle.

[0108] S402 : Determine a second target pitch angle of a target pixel according to the lower viewing angle, the second parameter, the correspondence between the position information of the image pixel in the second direction and the second pitch angle of the image pixel.

[0109] The second pitch angle is the pitch angle of the target pixel in the second direction.

[0110] In some embodiments of the present disclosure, the correspondence between the lower viewing angle, the second parameter, the position information of the image pixel in the second direction and the second pitch angle of the image pixel is, for example, formula (3).

[0111] Among them, θ Z is the second pitch angle.

[0112] S403: Determine the distance of each first target according to the second distance, the first target pitch angle, and the second target pitch angle.

[0113] The second distance is the distance between the infrared device 100 and the plane of the target area.

[0114] The first target distance is determined based on the pitch angle in the first direction and the pitch angle in the second direction of the target pixel. For example, the angle and distance conversion relationship between the first pitch angle, the second pitch angle, the distance between the infrared device and the target area plane, and the first target distance can be obtained based on the trigonometric function relationship of a right triangle, thereby obtaining formula (1). In this way, the complexity of determining the first target distance can be reduced.

[0115] FIG11 is a flowchart of another method for controlling an air-conditioning system according to some embodiments. As shown in FIG11 , in some embodiments of the present disclosure, the installation angle of the infrared device 100 may also be determined through S801 to S803 .

[0116] S801: Determine a plurality of first target distances corresponding to a plurality of target pixel points under respective preset viewing angles as a first target distance group.

[0117] When multiple target pixels are determined, a preset lower viewing angle corresponds to multiple target pixels and multiple first target distances. The multiple first target distances corresponding to multiple target pixels under a preset lower viewing angle are defined as a first target distance group, and the target number of preset lower viewing angles corresponds to the target number of first target distance groups. Furthermore, target pixels correspond to second target distances, with each target pixel corresponding to a different second target distance. A second target distance for the same target pixel corresponds to a target number of first target distances.

[0118] S802 : Determine the first target distance group with the smallest sum of the absolute values ​​of the distance differences between the plurality of first target distances and the corresponding plurality of second target distances in each first target distance group as the target distance group.

[0119] The controller 102 compares the predicted first target distances corresponding to each preset angle with the second target distances, and determines the first target distance group with the smallest sum of distance differences from the second target distances based on the difference comparison results. In some embodiments of the present disclosure, as shown in FIG6 , the first target distances of 81 target pixel points P1, P2 to P81 corresponding to any downward viewing angle γ are recorded as D1, D2, ..., D 81 At the same time, the second target distances corresponding to the 81 target pixel points from P1, P2 to P81 are recorded as S1, S2, ..., S 81 The first target distances D1, D2, ..., D corresponding to the above 81 target pixels under any downward viewing angle γ are 81 The distances to the corresponding second targets are recorded as S1, S2, ..., S 81 The distance difference is recorded as V error Then, at any downward viewing angle γ, the sum of the absolute values ​​of the distance differences between the multiple first target distances and the corresponding multiple second target distances is, for example, formula (4).

[0120] Among them, S k is the second target distance of the kth target pixel, D k is the first target distance of the kth target pixel.

[0121] In some embodiments of the present disclosure, the first target distance group having the smallest sum of squares of distance differences between the first target distances and the corresponding second target distances among the plurality of first target distance groups is determined as the target distance group.

[0122] It can be understood that the minimum sum of the squares of the distance differences represents the minimum sum of the distance differences.

[0123] In other embodiments of the present disclosure, at any downward viewing angle γ, the sum of the squares of the distance differences between the multiple first target distances and the corresponding multiple second target distances is, for example, formula (5).

[0124] When the target number of angles is 91 preset angles of view, which are 0°, 1°, 2°...90°, the distance error corresponding to each angle of view is 81 S. k and the corresponding 81 D k The sum of the absolute values ​​of the distance differences, or 81 S k and the corresponding 81 D k The sum of the absolute squares of the distance differences.

[0125] S803 : Determine the preset lower viewing angle corresponding to the target distance group as the installation angle of the infrared device 100 .

[0126] In this way, compared with determining the installation angle of the infrared device 100 based on a single target pixel point, the method of determining the installation angle of the infrared device 100 based on multiple target pixel points is more accurate.

[0127] In some embodiments of the present disclosure, the thermal imaging device 101 is an electronic device that uses infrared radiation for target detection, such as a thermopile, a thermal imager, etc. Infrared radiation can be referred to as infrared light or infrared rays, and refers to electromagnetic waves with a wavelength in the range of [0.75 μm, 1000 μm].

[0128] Figure 13 is a flowchart of another control method for an air-conditioning system according to some embodiments. As shown in Figure 13, some embodiments of the present disclosure provide a control method for an air-conditioning system 10, which is applied to a controller 102. In some embodiments of the present disclosure, the method includes S11 to S14.

[0129] S11 . Obtain a target thermal imaging image in the infrared detection area through the thermal imaging device 101 .

[0130] The target thermal imaging image is a thermal imaging image of the infrared detection area captured by the thermal imaging device 101 at any time during the operation of the air conditioning system 10. In some embodiments of the present disclosure, the target thermal imaging image includes the measured temperature of each pixel.

[0131] FIG12 is an installation diagram of a thermal imaging device according to some embodiments. As shown in FIG12 , in some embodiments of the present disclosure, the infrared detection area may be an area where the air-conditioning system 10 is installed, such as a living room, a bedroom, and a study.

[0132] It should be noted that in some embodiments of the present disclosure, the measured temperature of each pixel in the target thermal imaging image may be the radiant temperature obtained after the thermal imaging device 101 detects the infrared detection area. In this case, the temperature of the infrared detection area can be reflected while saving computing resources of the thermal imaging device 18. The measured temperature of each pixel in the target thermal imaging image may also be the detected temperature of the infrared detection area after the thermal imaging device 101 processes and calculates the radiant temperature. In this case, the target image area corresponding to the target object in the target thermal imaging image can be more intuitively identified based on the detected temperature of the infrared detection area, thereby improving the accuracy of detecting the target image area corresponding to the target object.

[0133] FIG14 is a diagram illustrating a temperature measurement principle of a thermal imaging device according to some embodiments. As shown in FIG14 , in some embodiments of the present disclosure, a thermal imaging device 101 includes a lens 1011 and a baffle 1012. Infrared rays emitted by a target object enter the thermal imaging device 101 through the lens 1011 and the baffle 1012.

[0134] In some embodiments of the present disclosure, the thermal imaging device 101 further includes a detector 1013 and a main control board 1014. Infrared rays entering the thermal imaging device 101 through the lens 1011 and the barrier 1012 converge onto the detector 1013, which converts the received thermal energy into an electrical signal and outputs it to the main control board 1014. In some embodiments of the present disclosure, the controller 102 is disposed on the main control board 1014.

[0135] The data sent between the detector 1013 and the main control board 1014 includes raw data (raw 14bit), the baffle temperature T2 (i.e., the ambient temperature), and the temperature T1 of the detector 1013. Thermal imaging can be achieved through the raw data, and temperature measurement can be achieved through the raw data + baffle temperature + detector temperature. Among them, △raw14, T1, and T2 are the output data of the thermal imaging device 101 receiving infrared light radiated by the target object. T0 represents the target temperature value calculated by the temperature measurement formula; it should be noted that the basic law of blackbody radiation is the basis of theoretical research and technological application of infrared radiation. A blackbody refers to an object that can absorb radiation of any wavelength at any temperature and is configured to perform temperature correction on the thermal imaging device 101 to ensure the temperature measurement accuracy of the thermal imaging device 101.

[0136] For example, the temperature of a black body is 37° C., and the thermal imaging device 101 detects the temperature of the black body and obtains a temperature value of 37.1° C., which indicates that an error occurs in the temperature measurement of the thermal imaging device 101 and the error is 0.1° C.

[0137] The Stefan-Boltzmann law states that the total radiation power of various wavelengths emitted per unit area of ​​a black body surface (i.e., the monochromatic radiance of the black body) is proportional to the fourth power of its thermodynamic temperature. In other words, the monochromatic radiance of a black body satisfies formula (6). b =σT 4 Formula (6)

[0138] Among them, E b is the monochromatic radiance of the black body, σ is the total radiant power of the black body, and T is the thermodynamic temperature of the black body.

[0139] It should be noted that at the same temperature, the power radiated by the target object within the same wavelength range is always less than the power radiated by a blackbody. That is, within the same wavelength range, the monochromatic radiance of the target object is less than that of a blackbody. The ratio of the monochromatic radiance of the target object to that of the blackbody is called the monochromatic blackness of the target object. Monochromatic blackness indicates the degree to which the radiation of the target object approaches that of a blackbody. The calculation method for monochromatic blackness is, for example, formula (7).

[0140] Where E(λ, T) is the monochromatic radiance of the target object, and ε(λ) is the monochromatic darkness of the target object.

[0141] Transform formula (7) to obtain formula (8). E(λ, T) = ε(λ) × E b (λ, T) Formula (8)

[0142] By integrating both sides of formula (8), we can obtain formula (9).

[0143] As shown in formula 10 and formula 11, E(λ, T) and E b (λ, T) integration to obtain E(T) and E b (T).

[0144] It should be noted that if the monochromatic blackness ε(λ) of the target object is a constant that does not change with the wavelength λ, that is, ε(λ) = ε, then such an object is called a gray body. In this case, combining formula (10) and formula (11) can obtain formula (12). E(T) = εE b(T) Formula (12)

[0145] Where ε is the emissivity of the target object, which represents the ratio of the radiation ability of the target object to the radiation ability of a blackbody at the same temperature and measurement conditions.

[0146] Combining formula (12) and formula (5), we can get formula (13). b =εσT 4 Formula (13)

[0147] At this time, the thermal radiation of the target object is within the infrared wavelength range and can be approximately regarded as gray body radiation.

[0148] The radiant illumination acting on the thermal imaging device 101 is obtained by, for example, formula (14). λ =A0d -2 [τ αλ ε λ L bλ (T0)+τ αλ (1-α λ )L bλ (T u )+ε αλ L bλ (T a )] Formula (14)

[0149] Among them, ε λ is the surface emissivity of the target object, α λ is the surface absorption rate of the target object, τ αλ is the spectral transmittance of the atmosphere, ε αλ is the atmospheric emissivity, T0 is the surface temperature of the target object, T u is the ambient temperature, T a is the atmospheric temperature, and d is the distance between the target object and the thermal imaging device. -2 It is usually a constant, and A0 is the visible area of ​​the target corresponding to the minimum spatial opening angle of the thermal imaging device 101. It should be noted that ε λ ,αλ,τ αλ It can usually be considered to be independent of λ.

[0150] The thermal imaging device 101 generally operates in a relatively narrow wavelength range, for example, between 8 μm and 14 μm or between 3 μm and 5 μm. The response voltage of the thermal imaging device 101 is obtained, for example, by formula (15).

[0151] Among them, A R K = A is the area of ​​the lens of the thermal imaging device 101. R A0d-2 Formula (16)

[0152] As shown in formula (16) and formula (17), assuming that A R A0d -2 The value of is K, The value of is f(T), then combining formula (15) and formula (17) we can get formula (18). S =K{τ a [εf(T0)+(1-α)f(T u )]+ε a f(T a )} Formula (18)

[0153] It should be noted that in the thermal imaging image, the grayscale value of each pixel corresponds to the radiation energy emitted by the pixel on the target object and reaching the thermal imaging device 101. However, the temperature directly read from the thermal imaging image is the radiation temperature T of the target object surface. r , is not the detected temperature T0 detected by the thermal imaging device 101. The detected temperature T0 is equal to the temperature of a blackbody radiating the same energy. Therefore, if the detected temperature is used during detection, the thermal imaging device 101 must first be calibrated using a blackbody to determine the corresponding relationship between the blackbody temperature and the output voltage of the photoelectric conversion device of the thermal imaging device 101 (represented as grayscale on the thermal image).

[0154] According to Planck's radiation law, we get formula (19).

[0155] At this time, according to the deformation of formula (19), the formula (20) for the detection temperature T0 of the surface of the target object can be obtained.

[0156] It should be noted that when using thermal imaging devices 101 with different bands, the value of n is different. For example, for indium antimonide (InSb detector) with a response band of 3μm to 5μm, the n value is 8.68; for mercury cadmium telluride (HgCdTe) detector with a response band of 6μm to 9μm, the n value is 5.33; for mercury cadmium telluride (HgCdTe) detector with a response band of 8μm to 14μm, the n value is 4.09.

[0157] When the surface of the target object satisfies the gray body approximation, that is, ε = α, and if the atmospheric emissivity ε a =α a =1-τ a , then formula (19) can be transformed into formula (21).

[0158] Formula (21) can be transformed into formula (22).

[0159] Formula (22) is the calculation formula for the gray body surface detection temperature.

[0160] When measuring temperature at close distance, the influence of atmospheric transmittance can be ignored. In this case, τ a =1, then formula (19) can be transformed into formula (23).

[0161] In summary, if the emissivity ε of the target object surface is obtained, the above formula (22) or formula (23) and the detected radiation temperature T can be used to obtain r and ambient temperature T u Calculate the detection temperature of the target object surface. For example, if the emissivity of the target human body is ε = 0.98, then the radiation temperature T measured by the thermal imaging device 101 can be calculated by formula (22) and formula (23). r and ambient temperature T u Calculate the body surface temperature.

[0162] FIG15 is a flowchart of another method for controlling an air-conditioning system according to some embodiments. As shown in FIG15 , the method includes S21 to S28 .

[0163] S21, obtain 16-bit level data.

[0164] In some embodiments of the present disclosure, the controller 102 obtains the original 16-bit level data of the infrared detection area at the current moment.

[0165] S22, converting the level data into an image size matrix to obtain an original thermal imaging image.

[0166] The controller 102 converts the original 16-bit level data into an image size matrix of equal resolution according to the resolution of the thermal imaging device 101 , and obtains the original thermal imaging image of the infrared detection area at the current moment.

[0167] S23, homogenization processing of the original thermal imaging image.

[0168] After obtaining the original thermal imaging image of the infrared detection area, the controller 102 may perform data preprocessing on the original thermal imaging image to generate a clearer infrared thermal imaging image.

[0169] The uniformization process includes at least one of bad pixel removal, image correction, and pot-lid removal.

[0170] It should be noted that a bad pixel is a pixel in a thermal image whose grayscale value is significantly different from that of its surrounding pixels. In other words, noticeable noise in a thermal image is called a bad pixel. The presence of bad pixels can affect the denoising effect of the thermal image, so it is necessary to remove bad pixels from the original thermal image.

[0171] In some embodiments of the present disclosure, the controller 102 removes the bad pixel by replacing the bad pixel with the average value of nine non-bad pixels adjacent to the bad pixel.

[0172] Due to current technological and software limitations, the thermal imaging device 101 cannot automatically adjust its detection parameters based on the ambient temperature and humidity. Therefore, after the thermal imaging device 101 has been powered on for a period of time, or after the user observes a change in the ambient temperature or humidity, the lens 1011 must be shielded with a barrier 1012. The device's detection parameters must be adjusted based on the environment in which the device 101 is located to achieve optimal detection results. Without using the barrier 1012 to calibrate the device's detection parameters, the device 101 may produce an irregular gray background or horizontal or vertical stripes during detection, necessitating correction of the original thermal image.

[0173] In some embodiments of the present disclosure, a two-point correction method is used to correct the original thermal image. This method involves transforming the response characteristic curves of all detectors 1013 into a single response characteristic curve through rotation and translation. After correction, under uniform radiation input, the output electrical signals of each detector 1013 are identical, thereby eliminating the non-uniform noise in the original thermal image. This results in a more uniform original thermal image. It also compensates for the gain coefficient of the thermal imaging device 101 and corrects the bias coefficient.

[0174] In some embodiments of the present disclosure, the process of the two-point correction method can satisfy formula (24). Y = A (XB) Formula (24)

[0175] Wherein, Y is the corrected level data, X is the original level data, B is the original data of the baffle 1012, and A is the sensitivity correction coefficient.

[0176] For the thermal imaging device 101, a single calibration based on a reference radiation source can typically effectively compensate for the system response non-uniformity defects introduced by the optical system, detector 1013, and post-processing circuitry. However, as the thermal imaging device 101 switches its field of view, adjusts its focus, and is affected by factors such as ambient temperature and shock and vibration, the non-uniformity introduced by the optical system can change significantly, leading to the pot-lid effect. This pot-lid effect is a special type of noise introduced by the optical system, resulting from the failure to effectively compensate for the non-uniformity introduced by the thermal imaging device 101. In this case, the thermal image output by the thermal imaging device 101 often appears dark in the center and bright at the edges and corners.

[0177] By performing de-bottlenecking processing on the original thermal imaging image, the phenomenon of black center and bright edges and corners in the thermal imaging image can be avoided, thereby improving the uniformity of the thermal imaging image.

[0178] By homogenizing the original thermal imaging image, a more uniform original thermal imaging image can be obtained.

[0179] S24, temporal noise reduction (noise reduction operation) processing of the original thermal imaging image.

[0180] In some embodiments of the present disclosure, the controller 102 may perform temporal noise reduction on the original thermal imaging image by multi-frame filtering, that is, performing low-pass filtering on the corresponding pixels at the same position in multiple consecutive frames.

[0181] It should be noted that low-pass filtering is a filtering method that allows low-frequency signals to pass normally, while high-frequency signals exceeding a set threshold are blocked or weakened. However, the extent of blocking and weakening varies depending on the frequency and the filtering process. In other words, when the signal frequency is greater than the preset frequency point (i.e., the cutoff frequency), it is not allowed to pass, while when the signal frequency is lower than the preset frequency point, it is allowed to pass. In this way, the purpose of eliminating noise, interference information, and texture can be achieved.

[0182] S25, processing of spatial noise reduction (i.e., vertical stripe removal) of the original thermal imaging image.

[0183] In some embodiments of the present disclosure, the controller 102 may perform spatial noise reduction on the original thermal imaging image through Gaussian filtering to ensure the smoothness of the image.

[0184] Gaussian filtering scans each pixel in a thermal image using a preset template (also called a convolution or mask) and replaces the grayscale value of the central pixel in the template with the weighted average grayscale value of the pixels in the neighborhood determined by the template. Gaussian filtering is a linear smoothing filter configured to eliminate Gaussian noise. In other words, Gaussian filtering performs a weighted average of the entire image. The value of each pixel is the weighted average of its own value and the values ​​of its neighboring pixels.

[0185] The original thermal imaging image is processed by low-pass filtering and Gaussian filtering to improve the signal-to-noise ratio of the original thermal imaging image and make the original thermal imaging image easier to extract.

[0186] S26, filtering the original image to obtain a base layer image.

[0187] In some embodiments of the present disclosure, the filtering process is, for example, a bilateral filter process.

[0188] Bilateral filtering is a nonlinear filtering method that compromises the spatial proximity and pixel value similarity of an image. It considers both spatial information and grayscale similarity to achieve edge-preserving denoising. It is simple, non-iterative, and local. Bilateral filtering of the original thermal image produces the base layer image.

[0189] Bilateral filtering has an additional Gaussian variance, sigma-d, compared to Gaussian filtering. Gaussian variance is based on the spatial distribution of the Gaussian filter function. Therefore, near the edge of a thermal image, pixels farther away will not significantly affect the pixel values ​​on the edge. Therefore, bilateral filtering can perform edge preservation, ensuring that the pixel values ​​near the edge are preserved.

[0190] S27, performing enhancement processing on the base layer image.

[0191] Because thermal images contain excessive high-frequency information, bilateral filtering cannot filter out high-frequency noise and can only effectively filter low-frequency information. Therefore, after bilateral filtering the original thermal image to obtain the base layer image, it is necessary to enhance this base layer image.

[0192] In some embodiments of the present disclosure, differential processing can be performed on a base layer image of a thermal image to separate high-frequency data from the base layer image to obtain a detail layer image of the thermal image. This detail layer image can then be amplified by high frequencies to ultimately obtain an enhanced detail layer image of the thermal image.

[0193] In other embodiments of the present disclosure, histogram processing may be performed on the base layer image of the thermal imaging image to enhance the contrast of the thermal imaging image, and ultimately obtain an enhanced base layer image of the thermal imaging image.

[0194] It's important to note that histogram processing is an image enhancement method that targets the contrast of thermal images. By making the probability distribution of grayscale values ​​in the input image as uniform as possible, it expands the dynamic range of thermal images and enhances contrast. Full grayscale information is detrimental to thermal image observation. Histogram processing reduces the original information in a thermal image, for example, by reducing the grayscale information. This allows the desired grayscale information to be stretched and the unwanted grayscale information to be compressed, thereby enhancing contrast.

[0195] Because visible light has a small background, a large target proportion, and a high signal-to-noise ratio, histogram processing is relatively simple. For example, simply performing histogram equalization can achieve a good contrast enhancement effect. However, infrared light has a large background, a small target proportion, and a low signal-to-noise ratio. If simple histogram processing is used, thermal images will show flickering, potholes, and excessive black or white. This is less effective for uniform targets and images. Therefore, histogram processing for infrared light is more complex than that for visible light.

[0196] S28, outputting a thermal imaging image.

[0197] In some embodiments of the present disclosure, infrared histogram processing utilizes 14-bit to 8-bit conversion, removing compressed areas with low grayscale levels and stretching areas with high grayscale levels. For example, the grayscale data of the previous frame can be used to generate a corresponding stretching coefficient and apply it to the next frame. It should be noted that the stretching coefficient is adjusted based on demand to ensure the stretching effect.

[0198] Because background and noise occupy a large number of grayscale levels, while the target object has fewer grayscale levels, histogram equalization increases the contrast between the background and noise, while reducing the contrast of the target object. In some embodiments of the present disclosure, if only histogram processing is performed on the original thermal image, the thermal image may flicker, appear too dark, or appear too white. In such cases, a plateau histogram equalization algorithm can be employed. This algorithm modifies the thermal image's histogram by selecting an appropriate plateau threshold, thereby appropriately suppressing background and noise.

[0199] It's important to note that when using the platform histogram equalization algorithm to process raw thermal images, a main peak smoothing parameter can be added. This modifies the main peak suppression width to change the thermal image's stretching strength. Smoothing and multi-frame processing are employed when capturing the main peak of the thermal image to avoid image oscillation caused by drastic changes in the main peak. This significantly improves image contrast while also ensuring a uniform image and preventing flicker.

[0200] In this way, a clearer thermal imaging image of the infrared detection area can be obtained, so that the user can accurately identify the temperature of each object in the infrared detection area based on the clearer thermal imaging image, thereby improving the user experience.

[0201] S12: Identify a target image area corresponding to the target object from the target thermal imaging image.

[0202] In some embodiments of the present disclosure, the controller 102 may determine a connected area in the thermal imaging image that meets a preset condition as an image area corresponding to the target object.

[0203] In some embodiments of the present disclosure, the preset condition may include: the temperature value of each pixel point in the connected area is greater than a preset temperature threshold.

[0204] The preset temperature threshold is determined based on the temperature of the target object.

[0205] For example, if the target object is a human body, since the human body maintains a constant temperature, when a human body appears in the target thermal image, the temperature values ​​of each pixel in the human body area are within a connected area within a predetermined threshold range. Since the normal human temperature range is between 36°C and 37°C, the preset temperature threshold can be set to 35.5°C when identifying a human body.

[0206] In some embodiments of the present disclosure, the preset condition may further include: the number of pixels included in the connected area is greater than a preset number.

[0207] The area percentage of the target image region corresponding to the target object in the target thermal image is typically not at the pixel level. Therefore, when identifying the target object from the target thermal image, multiple experiments can be conducted in advance to determine the number of pixels in the target thermal image corresponding to the target object at different positions in the infrared detection area. This can then determine the preset number of pixels that comprise the connected region that can identify the target object. This can reduce interference from other connected regions in the infrared detection area.

[0208] In some embodiments of the present disclosure, when the target object is a human body, the preset condition may further include: the height of the connected area is greater than the width of the connected area. Due to the specific shape of the human body, the height of the human body area appearing in the thermal imaging image is greater than its width. This setting can reduce interference from other warm-blooded animals in the infrared detection area.

[0209] There is a correlation between the temperature value of the target object and the target image area in the target thermal imaging image. Therefore, if a connected area satisfies the above conditions at the same time, the probability that this connected area is the target object is high, and this connected area can be used as the target image area corresponding to the target object.

[0210] In other embodiments of the present disclosure, the controller 102 may also input the thermal imaging image into a target object recognition model to obtain a recognition result of a target image area corresponding to the target object.

[0211] For example, a target object recognition model can be pre-trained using a machine learning algorithm. The target thermal image is then fed into the pre-trained model to obtain a recognition result for the target image region corresponding to the target object. This recognition result indicates whether the target object is present in the target thermal image.

[0212] In some embodiments of the present disclosure, detection using a target object recognition model based on a machine learning algorithm can be performed in a variety of different forms and implementation methods. For example, a traditional machine learning-based dangerous area recognition model can be obtained using a support vector machine (SVM) algorithm, or a deep learning-based dangerous area recognition model can be obtained using a convolutional neural network (CNN) algorithm.

[0213] It's understandable that deep convolutional neural networks can automatically extract and learn essential image features from massive amounts of training data. Applying deep convolutional neural networks to hazard detection based on thermal imaging can significantly enhance classification and further improve hazard detection accuracy. It's important to note that convolutional neural networks are a type of feedforward neural network with a deep structure that incorporates convolutional computations and are a representative algorithm for deep learning.

[0214] Figure 16 is a schematic diagram of a single convolutional pooling of a human pose detection model according to some embodiments, Figure 17 is a diagram of a human pose detection network model according to some embodiments, and Figure 18 is a flow chart of another method for controlling an air conditioning system according to some embodiments. As shown in Figures 16, 17, and 18, in some embodiments of the present disclosure, when the target object is a human body, the control method further includes S31 to S34.

[0215] S31, convolution and pooling units and network structure confirmation.

[0216] In some embodiments of the present disclosure, a deep learning-based action recognition system includes preprocessing thermal images and then inputting the preprocessed thermal images into a convolutional neural network. This deep learning is achieved through feedforward input of the image and backpropagation of the error.

[0217] The preprocessing of thermal imaging images includes image average normalization and image size adjustment.

[0218] As shown in Figure 16, in the single convolution pooling unit information involved in the algorithm, each convolution pooling unit includes three operations: convolution, non-linear activation processing (Non-linear Activation), and pooling layer. For example, the three-step operation can be shown as the feature map (Feature Maps), activation map (Activation Maps) and subsampled map (Subsampled Maps) in Figure 16.

[0219] As shown in Figure 17, the network architecture consists of a first layer of convolutional pooling units, a second layer of convolutional pooling units, a flattening layer, and two fully connected layers.

[0220] Among them, the input of the first layer convolution pooling unit is a 1@32×32 input image, which includes 32 3×3 convolution kernels. The padding pixels of each convolution kernel are 0, the stride is 1, and the output size of the convolution layer is: 32-3+2×0 / 1+1=30. The output channel is 32, so the output result is: 32@30×30; the first layer pooling step is 2, then the pooling output size is: 30 / 2=15, the output channel is 32, that is, the final output result after the first layer convolution and pooling is: 32@15×15, and then after a downsampling, the output result is: 32@7×7.

[0221] The input unit of the second layer convolution pooling unit is: 32@7×7 feature maps. The feature map has 32 3×3 convolution kernels. The padding pixel of each convolution kernel is 0, the stride is 1, and the output size of the convolution layer is: 7-3+2×0 / 1+1=5. The output channel is 32, that is, the output result is: 32@5×5; the second layer pooling step is 2, then the pooling output size is: 5 / 2=2, the output channel is 32, that is, the final output result after the second layer convolution and pooling is: 32@5×5, and then after a downsampling, the output result is: 32@2×2.

[0222] The flattening layer flattens the 32@2×2 input into 128 neurons. These 128 neurons undergo two fully connected operations, ultimately outputting a 6-neuron output layer. Each neuron outputs a score corresponding to one of the six action categories. The action corresponding to the neuron with the highest score is classified as the action performed in the input image. It should be noted that the score refers to the probability of a particular category appearing.

[0223] S32, data collection and annotation.

[0224] The high-resolution thermal imaging device 101 is used to simulate actual usage environments. For example, standing, sitting, and lying people can be simulated at different distances and angles. This allows for diverse simulation scenarios, covering both near and far distances, as well as imaging edges. The captured data can be labeled with corresponding human body categories (standing, sitting, and lying). In some embodiments of the present disclosure, this labeling can be accomplished using tools (e.g., labelimage).

[0225] S33, model training.

[0226] Image data and annotation files are used as input. The Yolo v5 (You Only Look Once Version 5) project is used, using Yolov5s.pt as a pre-trained model, or training from scratch using Yolov5s.yaml. The trained pt (PyTorch, an open source Python machine learning library) model is converted to an ONNX model. ONNX is an open file format designed for machine learning and is configured to perform inference on videos captured by the thermal imaging device 101, enabling human body selection and accurate body posture identification.

[0227] It's important to note that the Yolo v5 project is a deep learning-based object detection model configured to identify and locate objects in videos or images. Yolov5s.pt is the Yolo v5 model weight file, configured for object detection. Yolov5s.yaml is the YAML file that defines the Yolo v5 network model structure, located in the models folder.

[0228] S34, transplantation quantification.

[0229] The model obtained through the model training process in S33 can only be run on a desktop computer. If it needs to be run on an embedded development board, it needs to be transplanted and quantized. Commonly used embedded development boards for AI chips provide transplantation and quantization tools. For example, the model transplantation tool for Rockchip AI chips is RKNN_ToolKit.

[0230] FIG19 is a schematic diagram of an application scenario of another method for controlling an air conditioning system according to some embodiments. As shown in FIG19 , in some embodiments of the present disclosure, if a target object is determined to exist in a target thermal imaging image, the controller 102 marks a target image area corresponding to the target object in the target thermal imaging image. For example, the controller 102 may darken or thicken the outline of the target image area in the target thermal imaging image (the circled portion of the human body in FIG19 ). For another example, the controller 102 may also add text indicating the target image area next to the outline of the target image area to achieve the effect of highlighting the target image area, so that the target image area can be highlighted in the target thermal imaging image (the marked portions of the human body, searchlight 1, and searchlight 2 in FIG19 ).

[0231] S13 , determining a temperature measurement parameter of the target object in the target thermal imaging image according to a target image area corresponding to the target object in the target thermal imaging image and an installation height of the thermal imaging device 101 .

[0232] The temperature measurement parameters at least include the pitch angle and heading angle (ie, horizontal field of view angle) of the target object in the target thermal imaging image relative to the thermal imaging device 101 .

[0233] In some embodiments of the present disclosure, the controller 102 first establishes a preset rectangular coordinate system in the target thermal imaging image with the vertical projection point of the thermal imaging device 101 on the target thermal imaging image as the origin and a straight line passing through the origin and parallel to the width of the target thermal imaging image as the horizontal axis, and determines the reference pixel point used to represent the position of the target object from the target image area corresponding to the target object.

[0234] The preset rectangular coordinate system is a rectangular coordinate system established in the target thermal imaging image with the vertical projection point of the thermal imaging device 101 on the target thermal imaging image as the origin and a straight line passing through the origin and parallel to the width of the target thermal imaging image as the horizontal axis.

[0235] Furthermore, the controller 102 uses the ratio of the installation height of the thermal imaging device 101 to the horizontal coordinate of the reference pixel point in the preset rectangular coordinate system and the installation height of the thermal imaging device 101 as the tangent value of the heading angle of the target object relative to the thermal imaging device 101, and determines the heading angle of the target object relative to the thermal imaging device based on the tangent value.

[0236] Then, the controller 102 determines a first distance based on the Pythagorean theorem according to the horizontal coordinate of the reference pixel point in the preset rectangular coordinate system and the installation height of the thermal imaging device 101. The first distance is the distance between the projection point of the reference pixel point on the horizontal axis and the thermal imaging device 101.

[0237] And according to the ordinate of the reference pixel point in the preset rectangular coordinate system and the first distance, the ratio of the ordinate of the reference pixel point to the first distance is used as the tangent value of the pitch angle of the target object relative to the thermal imaging device 101, and the pitch angle of the target object relative to the thermal imaging device 101 is determined based on the tangent value.

[0238] In some embodiments of the present disclosure, the reference pixel point can be any pixel point in the target image area. For example, when the target object is a human body, the reference pixel point can be a pixel point at the head position of the human body area, or a pixel point at the waist position of the human body area. In this case, the reference pixel point can be a random pixel point at the human head or waist position pre-set at the factory, or it can be a pixel point selected by the user based on personal needs within the human body area presented in the target thermal imaging image when viewing the target thermal imaging image through a terminal device.

[0239] In some embodiments of the present disclosure, the resolution of the thermal imaging device 101 is width*height, the pitch field angle is defined as α, the horizontal field angle is defined as β, the installation angle of the thermal imaging device 101 and the vertical direction is defined as α1, and the installation height of the thermal imaging device 101 is defined as H.

[0240] FIG20 is an application scenario diagram of another method for controlling an air conditioning system according to some embodiments. As shown in FIG20 , in some embodiments of the present disclosure, taking the reference pixel point located at the middle of height pixels in the horizontal coordinate as an example, point P is the installation point of the thermal imaging device 101, point O is the vertical projection point of point P on the target thermal imaging image, point I is the closest point between plane POA and the cross-sectional field of view of the shooting range of the thermal imaging device 101, point J is the farthest point in the cross-sectional field of view of the shooting range, and plane POI is a cross-sectional view passing through point P and parallel to the width of the target thermal imaging image. Line segment IJ corresponds to the position of the pixel point 0-height in the pitch direction (i.e., the vertical coordinate direction) within the thermal imaging device 101. IJ also corresponds to the position of the pixel point width / 2 in the heading direction (i.e., the horizontal coordinate direction) within the thermal imaging device 101 (the middle of width pixels in the heading direction).

[0241] Assuming the reference pixel point is any point M between I and J, and the corresponding pixel position is (width / 2, Y1), (Y1 can be 0-height), the pixel distance corresponding to IM can be obtained as height-Y1. Assuming that the vertical coordinate of the thermal imaging device 101 corresponding to point J is 0 pixel point, since the shooting distance of the thermal imaging device 101 is usually less than or equal to 5 meters, and the angular distribution in the vertical pitch direction can be assumed to be uniform, the angle α2 (i.e., angle IPM) in Figure 20 can be calculated using formula (25). α2 = α*(height-Y1) / height Formula (25)

[0242] According to Figure 20 and formula (25), formula (26) and formula (27) can be obtained. cos(α1+α2)=H / PM Formula (26)

[0243] Where PM is the distance between point M and the thermal imaging device 101; (α1 + α2) is the corresponding heading angle of point M relative to the thermal imaging device 101. It should be noted that the pitch angle of point M is 0°. tg(α1 + α2) = OM / H Formula (27)

[0244] Wherein, OM is the distance between point M and the thermal imaging device 101 in the horizontal direction, that is, the distance between the target object and the thermal imaging device 101 in the horizontal direction.

[0245] Figure 21 illustrates an application scenario of another method for controlling an air conditioning system according to some embodiments. Still assuming that the reference pixel point is located in the horizontal coordinate direction of point M, as shown in Figure 21, plane POM is a cross-section passing through point P in the horizontal coordinate direction, OM perpendicularly bisects SU, points S and U are points on the boundary of the image captured by the thermal imaging device 101, and plane PSU is perpendicular to plane POM. The pixel position corresponding to point S is (X1, Y1), where Y1 is equal to Y1 corresponding to point M, and the value range of X1 is 0-width / 2. The pixel position corresponding to point U is (X2, Y1), where Y1 is equal to Y1 corresponding to point M, and the value range of X2 is width / 2-width.

[0246] Assuming the angle between PS and PM is α3, α3 can be calculated by formula (28). α3=β*X1 / width Formula (28)

[0247] Assume that the angle between PU and PM is α4, then α4 can be calculated by formula (29). α4=β*(X2-width / 2) / width / 2 Formula (29)

[0248] According to formula (28) and Figure 21, formula (30) and formula (31) can be obtained. cos(α3)=PM / PS Formula (30) OM 2 +SM 2 =OS 2 Formula (31)

[0249] Where PS is the distance between point S and the thermal imaging device 101; OS is the horizontal distance between point S and the thermal imaging device 101, that is, the horizontal distance between the target object and the thermal imaging device 101. At this time, the corresponding heading angle of point S relative to the thermal imaging device 101 is (α1+α2), and the pitch angle is α3.

[0250] According to formula (29) and Figure 21, formula (32) and formula (33) can be obtained. cos(α4)=PM / PU Formula (32) OM 2 +UM 2 =OU 2 Formula (33)

[0251] Wherein, PU is the distance between point U and the thermal imaging device 101; OU is the horizontal distance between point U and the thermal imaging device 101, that is, the horizontal distance between the target object and the thermal imaging device 101; at this time, the heading angle of point U relative to the thermal imaging device 101 is (α1+α2), and the pitch angle is α4.

[0252] In this way, the temperature measurement parameters of the target object relative to the thermal imaging device 101 can be accurately determined, thereby completing the correction of the measured temperature of the target object.

[0253] S14 , correcting the measured temperature of the target object in the target image area based on the temperature measurement parameters, the preset correction value, and the preset weight coefficient corresponding to the temperature measurement parameters to obtain the actual temperature of the target object.

[0254] It should be noted that the preset correction value and the preset weight coefficient are configured to indicate the relationship between the measured temperature of the target object and the temperature measurement parameter and the actual temperature. The preset weight coefficient corresponds to the temperature measurement parameter.

[0255] FIG22 is a flowchart of another method for controlling an air-conditioning system according to some embodiments. As shown in FIG22 , in some embodiments of the present disclosure, the controller 102 may obtain a preset weight coefficient and a preset correction value through S41 to S44 .

[0256] S41 , acquiring a plurality of thermal imaging image samples through the thermal imaging device 101 .

[0257] The multiple thermal imaging image samples are thermal imaging images of the target object at different positions in the infrared detection area, and each thermal imaging image sample contains the measured temperature of each pixel point.

[0258] S42: Obtain the measured temperature of the target object in each thermal imaging image sample.

[0259] S43 , determining the temperature measurement parameters of the target object in each thermal imaging image sample according to the target image area corresponding to the target object in each thermal imaging image sample and the installation height of the thermal imaging device 101 .

[0260] S44 , determining a preset correction value and a preset weight coefficient corresponding to the temperature measurement parameter based on a linear regression algorithm according to the temperature measurement parameter of the target object in each thermal imaging image sample.

[0261] In this way, when the installation height of the thermal imaging device 101 is determined, the preset correction value and the preset weight coefficient corresponding to the temperature measurement parameter can be determined in advance, so that when the user uses the air-conditioning system 10, the controller of the air-conditioning system 10 does not need to perform the calculation process of the preset correction value and the preset weight coefficient, thereby making the controller 102's correction process for the measured temperature faster and simpler.

[0262] In some embodiments of the present disclosure, the controller 102 uses the product of the preset weight coefficient and the temperature measurement parameter of the target object in the target thermal imaging image corresponding to the preset weight coefficient, the measured temperature of the target object in the target thermal imaging image, and the sum of the preset correction value as the actual temperature of the target object. That is, the actual temperature T of the target object and the measured temperature T0 of the target object in the target thermal imaging image, the preset correction value W0, the pitch angle X1 of the target object in the target thermal imaging image relative to the thermal imaging device 101, the heading angle X2 of the target object in the target thermal imaging image relative to the thermal imaging device 101, the preset weight coefficient W1 corresponding to the pitch angle X1, and the preset weight coefficient W2 corresponding to the heading angle X2 satisfy formula (34). T = T0 + W0 + W1 × X1 + W2 × X2 Formula (34)

[0263] For example, if the preset correction value W0 determined by the controller 102 of the air conditioning system 10 is 158.98, the preset weight coefficient W1 corresponding to the pitch angle X1 of the target object relative to the thermal imaging device 101 is -2.6, and the preset weight coefficient W2 corresponding to the heading angle X2 of the target object relative to the thermal imaging device 101 is 1.2, then the actual temperature T of the target object can be calculated using formula (35). T = T0 + 158.98 + -2.6 × X1 + 1.2 × X2 Formula (35)

[0264] In this way, the controller 102 corrects the measured temperature of the target object according to the preset correction value, measurement parameters and preset weight coefficients corresponding to the measurement parameters, so that the measured temperature of the target object can be closer to the actual temperature of the target object, thereby improving the temperature measurement accuracy of the thermal imaging device 101.

[0265] In some embodiments of the present disclosure, the temperature measurement parameter further includes: the horizontal distance between the target object in the target thermal imaging image and the thermal imaging device 101. The controller 102 of the air conditioning system 10 determines the horizontal distance between the target object in the target thermal imaging image and the thermal imaging device 101 based on the abscissa and ordinate of the reference pixel point in a preset rectangular coordinate system and the Pythagorean theorem.

[0266] For example, as shown in FIG21 , assuming that the reference pixel point is point S, the horizontal distance between the target object and the thermal imaging device 101 in the target thermal imaging image is OS, then it can be known that That is, the length of OS is the arithmetic square root of the sum of the square of the abscissa of point S and the square of the ordinate of point S.

[0267] In this way, the controller 102 takes into account the horizontal distance between the target object in the target thermal imaging image and the thermal imaging device 101, and corrects the measured temperature of the target object, so that the obtained temperature of the target object is closer to the actual temperature, thereby improving the temperature measurement accuracy of the thermal imaging device 101.

[0268] In some embodiments of the present disclosure, when the temperature measurement parameters simultaneously include: the heading angle and pitch angle of the target object relative to the thermal imaging device 101, and the horizontal distance between the target object and the thermal imaging device 101 in the target thermal imaging image, the actual temperature T of the target object and the measured temperature T0 of the target object in the target thermal imaging image, the preset correction value W0, the pitch angle X1 of the target object relative to the thermal imaging device in the target thermal imaging image, the heading angle X2 of the target object relative to the thermal imaging device in the target thermal imaging image, the preset weight coefficient W1 corresponding to the pitch angle X1, the preset weight coefficient W2 corresponding to the heading angle X2, the horizontal distance X3 between the target object and the thermal imaging device in the target thermal imaging image and its corresponding preset weight coefficient W3 satisfy formula (36). T = T0 + W0 + W1 × X1 + W2 × X2 + W3 × X3 Formula (36)

[0269] In some embodiments of the present disclosure, if it is determined that the target object in the target thermal imaging image is a human body, the controller 102 of the air-conditioning system 10 is further configured to: obtain the ambient temperature; and adjust the operating parameters of the air-conditioning system 10 according to the actual temperature of the human body and the ambient temperature, wherein the operating parameters of the air-conditioning system 10 include at least at least one of the air supply direction, air supply temperature, air supply humidity, and air supply volume.

[0270] For example, the controller 102 obtains the ambient temperature and human body temperature of the infrared detection area from the target thermal imaging image. Assuming that the temperature set by the user is 26°C, the controller 102 can adjust the air supply temperature, humidity and air volume of the air-conditioning system 10, and perform body temperature control with the area where the human body is located as the center, so that the user can get a better user experience.

[0271] In this way, when the temperature measurement technology of the thermal imaging device 101 is applied to the intelligent control of the air-conditioning system 10, the temperature measurement accuracy of the thermal imaging device 101 is improved, and the intelligent control of the air-conditioning system 10 can also meet user needs more accurately, so that users can get a better user experience.

[0272] In some embodiments of the present disclosure, a user may determine an area in a target thermal imaging image that exceeds a target temperature threshold as a dangerous area. Then, when the controller 102 detects an image area in the target thermal imaging image whose temperature exceeds the target temperature threshold, the controller 102 may determine the image area as a dangerous area and send an alarm to the terminal device used by the user through the communication device 105 to prompt the user to check whether there is any dangerous situation in the infrared detection area.

[0273] Figure 23 is a structural diagram of a controller according to some embodiments. As shown in Figure 23, the controller 102 includes a processor 301, and the processor 301 is configured to execute computer program code stored in the memory 302, thereby implementing the control method of the air-conditioning system 10 provided in some embodiments of the present disclosure.

[0274] In some embodiments of the present disclosure, the controller 102 further includes a memory 302 and a communication interface 303 connected to the processor 301. The processor 301, the memory 302, and the communication interface 303 are connected via a bus 304.

[0275] Those skilled in the art will understand that the scope of the present disclosure is not limited to the above specific embodiments, and that certain elements of the embodiments may be modified and replaced without departing from the spirit of the present disclosure. The scope of the present disclosure is limited by the appended claims.

Claims

1. An air conditioning system, comprising: Outdoor unit; an indoor unit connected to the outdoor unit; an infrared device configured to perform thermal imaging of a target object to detect position information of the target object; and The controller is configured as: Determine a preset lower viewing angle of the target quantity from a preset angle range; wherein the preset angle range is the installation angle range of the infrared device; According to the correspondence between the lower viewing angle and the first distance, each first target distance corresponding to the target pixel point at each preset lower viewing angle is determined; wherein the first distance is the distance between the image pixel point of the infrared device and the infrared device; the target pixel point is the image pixel point of the infrared device imaging the target object in the target area; the first target distance is the predicted distance between the target pixel point and the infrared device; Determine, from each of the first target distances, a first target distance having the smallest absolute value of the distance difference with the second target distance; wherein the second target distance is the actual distance between the target pixel point and the infrared device; and The preset lower viewing angle corresponding to the first target distance having the smallest absolute value of the distance difference with the second target distance is used as the installation angle of the infrared device.

2. The air conditioning system according to claim 1, wherein: The controller is also configured to: Determining each first target distance according to the correspondence between the downward viewing angle, the parameters of the infrared device and the first distance; The infrared device parameters include: first parameters, the first parameters including a pitch angle of the infrared device in a first direction of the target area and a first resolution of an image formed by the infrared device in the first direction; and second parameters, the second parameters comprising a horizontal field angle of the infrared device in a second direction of the target area and a second resolution of an image formed by the infrared device in the second direction; The first direction is perpendicular to the second direction.

3. The air conditioning system according to claim 2, wherein: The controller is also configured to: Determine a first target pitch angle of the target pixel point according to the corresponding relationship between the lower viewing angle, the first parameter, the position information of the image pixel point in the first direction and the first pitch angle of the image pixel point; wherein the first pitch angle is the pitch angle of the target pixel point in the first direction; Determine a second target pitch angle of the target pixel point according to the lower viewing angle, the second parameter, the position information of the image pixel point in the second direction, and the corresponding relationship between the second pitch angle of the image pixel point; wherein the second pitch angle is the pitch angle of the target pixel point in the second direction; The distances of each first target are determined according to the second distance, the first target pitch angle and the second target pitch angle; wherein the second distance is the distance between the infrared device and the target area plane.

4. The air conditioning system according to any one of claims 1 to 3, wherein: The preset angle range is an angle interval formed by a first preset angle and a second preset angle; wherein the first preset angle is smaller than the second preset angle; The controller is further configured to: divide the preset angle range into the target number of preset lower viewing angles according to the target angle interval from the preset angle range; The target angle interval is the average angle difference after dividing the target angle difference into equal parts of the target number; the target angle difference is the angle difference between the second preset angle and the first preset angle.

5. The air conditioning system according to any one of claims 1 to 3, wherein: The controller is also configured to: Determine at least one target pixel point from the target area; When the determined target pixel point is one, the first target distance is determined by the one target pixel point; When the determined target pixel points are multiple, under a preset viewing angle, the multiple target pixel points correspond to the first target distance; and the multiple target pixel points correspond to the second target distance.

6. The air conditioning system according to any one of claims 1 to 5, wherein: The controller is also configured to: Determine the plurality of first target distances corresponding to the plurality of target pixel points under each of the preset lower viewing angles as a first target distance group; Determine the first target distance group with the smallest sum of the absolute values ​​of the distance differences between the plurality of first target distances and the corresponding plurality of second target distances in each first target distance group as the target distance group; The preset lower viewing angle corresponding to the target distance group is determined as the installation angle of the infrared device.

7. The air conditioning system according to any one of claims 1 to 6, wherein: The controller is also configured to: The position information of the target object corresponding to the target pixel point is determined according to the installation angle of the infrared device. 8 . The air conditioning system according to claim 1 , further comprising a distance detection device configured to determine the second target distance.

9. The air conditioning system according to any one of claims 1 to 8, wherein: The infrared device comprises: A thermal imaging device, disposed in the indoor unit and configured to collect thermal imaging images of the infrared detection area; The controller is also configured to: Acquire a target thermal imaging image of the infrared detection area by the thermal imaging device, wherein the target thermal imaging image includes the measured temperature of each pixel point; Identifying a target image area corresponding to the target object from the target thermal imaging image; Determine temperature measurement parameters of the target object in the target thermal imaging image according to a target image area corresponding to the target object in the target thermal imaging image and an installation height of the thermal imaging device, wherein the temperature measurement parameters include a pitch angle and a heading angle of the target object in the target thermal imaging image relative to the thermal imaging device; Based on the temperature measurement parameters, the preset correction values ​​and the preset weight coefficients corresponding to the temperature measurement parameters, the measured temperature of the target object in the target image area is corrected to obtain the actual temperature of the target object.

10. The air conditioning system according to claim 9, wherein: The controller is also configured to: Determining a reference pixel point for indicating the position of the target object from a target image area corresponding to the target object; According to the horizontal coordinate of the reference pixel point in the preset rectangular coordinate system and the installation height of the thermal imaging device, the ratio of the horizontal coordinate of the reference pixel point to the installation height of the thermal imaging device is used as the tangent value of the heading angle of the target object relative to the thermal imaging device, and the heading angle of the target object relative to the thermal imaging device is determined based on the tangent value of the heading angle; wherein the preset rectangular coordinate system is a rectangular coordinate system established in the target thermal imaging image, with the vertical projection point of the thermal imaging device on the target thermal imaging image as the origin and a straight line passing through the origin and parallel to the width of the target thermal imaging image as the horizontal axis; Determine a first distance based on the Pythagorean theorem according to the horizontal coordinate of the reference pixel point in the preset rectangular coordinate system and the installation height of the thermal imaging device; wherein the first distance is the distance between the projection point of the reference pixel point on the horizontal axis and the thermal imaging device; According to the ordinate of the reference pixel point in the preset rectangular coordinate system and the first distance, a ratio of the ordinate of the reference pixel point to the first distance is used as a tangent value of the pitch angle of the target object relative to the thermal imaging device, and the pitch angle of the target object relative to the thermal imaging device is determined based on the tangent value.

11. The air conditioning system according to claim 9 or 10, wherein: The controller is also configured to: Acquire a plurality of thermal imaging image samples by means of the thermal imaging device, wherein the plurality of thermal imaging image samples are thermal imaging images of the target object at different positions in the infrared detection area, and each of the plurality of thermal imaging image samples includes a measured temperature of each pixel point; Obtaining a measured temperature of the target object in each thermal imaging image sample; Determining the temperature measurement parameter of the target object in each thermal imaging image sample according to the target image area corresponding to the target object in each thermal imaging image sample and the installation height of the thermal imaging device; According to the temperature measurement parameters of the target object in each thermal imaging image sample, a preset correction value and a preset weight coefficient corresponding to the temperature measurement parameter are determined based on a linear regression algorithm, wherein the preset correction value and the preset weight coefficient are configured to indicate the measured temperature of the target object and the relationship between the temperature measurement parameter and the actual temperature.

12. The air conditioning system according to claim 11, wherein: The controller is also configured to: The product of the preset weight coefficient, the temperature measurement parameter of the target object in the target thermal imaging image corresponding to the preset weight coefficient, the measured temperature of the target object in the target thermal imaging image and the preset correction value is taken as the actual temperature of the target object.

13. The air conditioning system according to claim 9 or 10, wherein: The temperature measurement parameters also include: the distance between the target object and the thermal imaging device in the horizontal direction in the target thermal imaging image; The controller is also configured to: According to the abscissa and ordinate of the reference pixel point in the preset rectangular coordinate system, based on the Pythagorean theorem, the distance between the target object in the target thermal imaging image and the thermal imaging device in the horizontal direction is determined.

14. The air conditioning system according to claim 13, wherein: The target object in the target thermal imaging image is a human body; The controller is also configured to: Get the ambient temperature; According to the actual temperature of the human body and the ambient temperature, the operating parameters of the air conditioning system are adjusted, and the operating parameters of the air conditioning system include at least one of air supply direction, air supply temperature, air supply humidity or air supply volume.

15. A method for controlling an air conditioning system, wherein: The air conditioning system comprises: Outdoor unit and indoor unit; an infrared device configured to perform thermal imaging of a target object to detect position information of the target object; a controller coupled to the outdoor unit, the indoor unit and the infrared device; The control method comprises: Determine a preset lower viewing angle of the target quantity from a preset angle range; wherein the preset angle range is the installation angle range of the infrared device; According to the correspondence between the lower viewing angle and the first distance, determine each first target distance corresponding to each preset lower viewing angle of the target pixel point in the lower viewing angle of the target number; wherein the first distance is the distance between the image pixel point of the infrared device and the infrared device; the target pixel point is the image pixel point of the infrared device imaging the target object in the target area; the first target distance is the predicted distance between the target pixel point and the infrared device; From each of the first target distances, determine the first target distance having the smallest absolute value of the distance difference with the second target distance; wherein the second target distance is the actual distance between the target pixel point and the infrared device; The preset lower viewing angle corresponding to the first target distance having the smallest absolute value of the distance difference with the second target distance is used as the installation angle of the infrared device; The position information of the target object corresponding to the target pixel point is determined according to the installation angle of the infrared device.

16. The control method according to claim 15, wherein: The step of determining, according to the correspondence between the lower viewing angle and the first distance, each first target distance corresponding to each of the preset lower viewing angles in the lower viewing angles of the target number of the target pixel points further includes: Determining each first target distance according to the correspondence between the downward viewing angle, the parameters of the infrared device and the first distance; The infrared device parameters include: first parameters, the first parameters including a pitch angle of the infrared device in a first direction of the target area and a first resolution of an image formed by the infrared device in the first direction; second parameters, the second parameters comprising a horizontal field angle of the infrared device in a second direction of the target area and a second resolution of an image formed by the infrared device in the second direction; The first direction is perpendicular to the second direction.

17. The control method according to claim 16, wherein: The determining of each first target distance according to the correspondence between the downward viewing angle, the parameter of the infrared device and the first distance also includes: Determine a first target pitch angle of the target pixel point according to the corresponding relationship between the lower viewing angle, the first parameter, the position information of the image pixel point in the first direction and the first pitch angle of the image pixel point; wherein the first pitch angle is the pitch angle of the target pixel point in the first direction; Determine a second target pitch angle of the target pixel point according to the lower viewing angle, the second parameter, the position information of the image pixel point in the second direction, and the corresponding relationship between the second pitch angle of the image pixel point; wherein the second pitch angle is the pitch angle of the target pixel point in the second direction; The distances of each first target are determined according to the second distance, the first target pitch angle and the second target pitch angle; wherein the second distance is the distance between the infrared device and the target area plane.

18. The control method according to any one of claims 15 to 17, further comprising: The preset angle range is an angle interval formed by a first preset angle and a second preset angle; wherein the first preset angle is smaller than the second preset angle; The control method also includes: from a preset angle range, dividing the preset angle range into the target number of preset lower viewing angles according to a target angle interval; wherein the target angle interval is the average angle difference after the target angle difference is evenly divided into the target number of equal parts; the target angle difference is the angle difference between the second preset angle and the first preset angle.

19. The control method according to any one of claims 15 to 18, wherein: The control method further comprises: Determine at least one target pixel point from the target area; When the determined target pixel point is one, the first target distance is determined by the one target pixel point; When the determined target pixel points are multiple, under a preset viewing angle, the multiple target pixel points correspond to the first target distance; and the multiple target pixel points correspond to the second target distance.

20. A method for controlling an air conditioning system, wherein: The air conditioning system comprises: Outdoor unit, an indoor unit connected to the outdoor unit; An infrared device is configured to perform thermal imaging of a target object to detect position information of the target object; the infrared device includes a thermal imaging device, which is disposed on the indoor unit and is configured to collect a thermal imaging image of an infrared detection area; a controller coupled to the outdoor unit, the indoor unit, the infrared device and the thermal imaging device; The control method comprises: Acquire a target thermal imaging image of the infrared detection area by a thermal imaging device, wherein the target thermal imaging image includes the measured temperature of each pixel point; Identifying a target image area corresponding to the target object from the target thermal imaging image; Determine, according to a target image area corresponding to the target object in the target thermal imaging image and an installation height of the thermal imaging device, a temperature measurement parameter of the target object in the target thermal imaging image, wherein the temperature measurement parameter includes at least a pitch angle and a heading angle of the target object in the target thermal imaging image relative to the thermal imaging device; Based on the temperature measurement parameters, the preset correction values ​​and the preset weight coefficients corresponding to the temperature measurement parameters, the measured temperature of the target object in the target image area is corrected to obtain the actual temperature of the target object.

Images