CN115751669A

CN115751669A - Air conditioning system and control method thereof

Info

Publication number: CN115751669A
Application number: CN202211372379.XA
Authority: CN
Inventors: 韩海力; 杨晓波; 慕安臻
Original assignee: Qingdao Hisense Hitachi Air Conditioning System Co Ltd
Current assignee: Qingdao Hisense Hitachi Air Conditioning System Co Ltd
Priority date: 2022-11-03
Filing date: 2022-11-03
Publication date: 2023-03-07

Abstract

The application provides an air conditioning system and a control method thereof, relates to the field of air conditioners, and is used for ensuring the accuracy of human body target recognition under the condition that a high-temperature target exists in a thermal imaging image. The control method comprises the following steps: acquiring a thermal imaging image of an infrared detection area; identifying a high-temperature area in the thermal imaging image based on the temperature value of each pixel point in the thermal imaging image, wherein the temperature value of the pixel point in the high-temperature area is above a first temperature threshold; processing a high-temperature area in the thermal imaging image to obtain a processed thermal imaging image, wherein the temperature value of a pixel point of the high-temperature area in the processed thermal imaging image is lower than the temperature value of the same pixel point of the high-temperature area in the thermal imaging image before processing; converting the processed thermal imaging image into a gray image; and carrying out human body identification on the gray level image to obtain the information of the human body target.

Description

Air conditioning system and control method thereof

Technical Field

The application relates to the field of household appliance intellectualization, in particular to an air conditioning system and a control method thereof.

Background

At present, thermal imaging is more and more widely used in various fields, the thermal imaging based on the temperature imaging has unique advantages in the industries of fire prevention monitoring, power inspection, security monitoring and the like, and in addition, the thermal imaging image has no obvious color information relative to a color image, so that the privacy of a user cannot be violated in daily life. After the thermal imaging image is converted into the gray image, various information such as the distance, the direction, the posture, the motion state and the like of the human body are acquired based on the gray image, and a data source can be well provided for the intelligent operation of the air conditioner. However, if a high-temperature object exists in the visible region, effective information is masked due to its temperature sensitivity, so that it becomes extremely difficult to recognize a human body in a grayscale map.

Most of the existing methods for removing or shielding high-temperature targets focus on manual regional shielding, fixed target shielding, shielding based on temperature intervals, shielding based on holder angles and the like, and intelligent, automatic and visual removal of the high-temperature targets cannot be achieved. Therefore, how to ensure the accuracy of human body target identification under the condition that a high-temperature target exists in a thermal imaging image is an urgent problem to be solved.

Disclosure of Invention

The application provides an air conditioning system and a control method thereof, which are used for ensuring the accuracy of human body target recognition under the condition that a high-temperature target exists in a thermal imaging image.

In order to achieve the purpose, the technical scheme is as follows:

in a first aspect, the present application provides an air conditioning system comprising:

an outdoor unit and an indoor unit;

the thermal imaging device is arranged on the indoor unit and is used for acquiring a thermal imaging image of an infrared detection area; and the number of the first and second groups,

a controller configured to:

acquiring a thermal imaging image of the infrared detection area through the thermal imaging device;

identifying a high-temperature area in the thermal imaging image based on temperature values of all pixel points in the thermal imaging image, wherein the temperature values of the pixel points in the high-temperature area are above a first temperature threshold;

processing a high-temperature area in the thermal imaging image to obtain a processed thermal imaging image, wherein the temperature value of a pixel point of the high-temperature area in the processed thermal imaging image is lower than the temperature value of the same pixel point of the high-temperature area in the thermal imaging image before processing;

converting the processed thermal imaging image into a gray image;

and carrying out human body identification on the gray level image to acquire the information of the human body target.

The technical scheme provided by the embodiment of the application at least has the following beneficial effects: after the thermal imaging image of the infrared detection area is obtained, the temperature value of the pixel point of the high-temperature area in the thermal imaging image is processed, so that the temperature value of the pixel point of the high-temperature area in the processed thermal imaging image is lower than the temperature value of the same pixel point of the high-temperature area in the thermal imaging image before processing. It can be understood that the high temperature region is caused by the high temperature target, by reducing the temperature value of the pixel point of the high temperature region, also reduce the temperature value of the pixel point of the high temperature target, the tone scale width of the pixel point of the high temperature target in the gray scale value mapped out in the gray scale image is reduced, also the tone scale width of the pixel point of the non-high temperature target in the gray scale value mapped out in the gray scale image is increased, so that the non-high temperature target, for example, the human body target can be shown in the gray scale image, thereby ensuring the accuracy of the human body target identification under the condition that the high temperature target exists in the infrared detection region.

In some embodiments, the thermal imaging device is further configured to detect a temperature value of the infrared detection area; a controller further configured to: acquiring a temperature value of an infrared detection area through a thermal imaging device; and correcting the second temperature threshold value according to the temperature value of the infrared detection area to obtain a first temperature threshold value.

In some embodiments, the second temperature threshold is above a temperature upper limit value of a pixel point of the human target in the thermal imaging image.

In some embodiments, the controller, when being configured to process a high temperature region in the thermographic image, specifically performs the following steps: compressing and smoothing the temperature values of the pixel points in the high-temperature area in the thermal imaging image to obtain the temperature values after the pixel points in the high-temperature area in the thermal imaging image are processed;

the temperature value after the pixel point processing of the high temperature region in the thermal imaging image is determined according to the following formula:

Y _smooth ＝Y _threshold +(Y _raw -Y _threshold )*a

wherein, Y _smooth The temperature value Y after the pixel point processing of the high temperature region in the thermal imaging image _threshold Is a first temperature threshold, Y _raw The temperature value of a pixel point in a high temperature region in the thermal imaging image is a coefficient of more than 0 and less than 1.

In some embodiments, the controller, when being configured to convert the processed thermal imaging image into a grayscale image, specifically performs the following steps: performing conversion processing on the processed thermal imaging image to obtain a gray level image, wherein the conversion processing comprises at least one of the following steps: the method comprises the following steps of pot cover removing processing, noise reduction processing, filtering processing, enhancement processing and dimming processing, wherein the enhancement processing comprises histogram processing.

In some embodiments, the controller is further configured to: after the processed thermal imaging image is converted into a gray image, human body recognition is carried out on the gray image, and the position information of the human body target is determined, wherein the position information of the human body target comprises at least one of the following items: the distance between the human body target and the indoor unit, the orientation of the human body target, the posture of the human body target and the motion state of the human body target; and adjusting the working mode of the air conditioning system according to the position information of the human body target.

In a second aspect, the present application provides a control method of an air conditioning system, the method including: acquiring a thermal imaging image of an infrared detection area; identifying a high-temperature area in the thermal imaging image based on the temperature value of each pixel point in the thermal imaging image, wherein the temperature value of the pixel point in the high-temperature area is above a first temperature threshold; processing a high-temperature area in the thermal imaging image to obtain a processed thermal imaging image, wherein the temperature value of a pixel point of the high-temperature area in the processed thermal imaging image is lower than the temperature value of the same pixel point of the high-temperature area in the thermal imaging image before processing; converting the processed thermal imaging image into a gray image; and carrying out human body identification on the gray level image to acquire the information of the human body target.

In some embodiments, the method further comprises: acquiring a temperature value of an infrared detection area; and correcting the second temperature threshold value according to the temperature value of the infrared detection area to obtain the first temperature threshold value.

In some embodiments, processing a high temperature region in a thermographic image comprises: compressing and smoothing the temperature values of the pixel points in the high-temperature area in the thermal imaging image to obtain the temperature values after the pixel points in the high-temperature area in the thermal imaging image are processed; the temperature value after the pixel point processing of the high temperature region in the thermal imaging image is determined according to the following formula:

Y _smooth ＝Y _threshold +(Y _raw -Y _threshold )*a

In some embodiments, converting the processed thermographic image to a grayscale image comprises: performing conversion processing on the processed thermal imaging image to obtain a gray level image, wherein the conversion processing comprises at least one of the following steps: the method comprises the following steps of pot cover removing processing, noise reduction processing, filtering processing, enhancement processing and dimming processing, wherein the enhancement processing comprises histogram processing.

In some embodiments, the information of the human target comprises at least one of: the distance between the human body target and the indoor unit, the orientation of the human body target, the posture of the human body target and the motion state of the human body target; and adjusting the working mode of the air conditioning system according to the information of the human body target.

In a third aspect, an embodiment of the present application provides a controller, including: one or more processors; one or more memories; wherein the one or more memories are configured to store computer program code comprising computer instructions, and the controller is configured to perform any one of the control methods of the air conditioning system provided by the second aspect when the one or more processors execute the computer instructions.

In a fourth aspect, embodiments of the present application provide a computer-readable storage medium, where the computer-readable storage medium includes computer instructions, and when the computer instructions are executed on a computer, the computer is caused to execute any one of the control methods of the air conditioning system provided in the second aspect.

In a fifth aspect, embodiments of the present invention provide a computer program product, which is directly loadable into a memory and contains software codes, and which, when loaded and executed by a computer, is capable of implementing any one of the control methods of the air conditioning system as provided in the second aspect.

It should be noted that all or part of the computer instructions may be stored on the computer readable storage medium. The computer readable storage medium may be packaged with or separately from a processor of the controller, which is not limited in this application.

For the beneficial effects of the second aspect to the fifth aspect in the present application, reference may be made to the beneficial effect analysis of the first aspect, and details are not described here.

Drawings

The accompanying drawings are included to provide a further understanding of the present invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the example serve to explain the principles of the invention and are not intended to limit the invention.

Fig. 1 is a schematic composition diagram of an air conditioning system according to an embodiment of the present disclosure;

fig. 2 is a schematic view of an application scenario of a thermal imaging apparatus according to an embodiment of the present disclosure;

fig. 3 is a schematic diagram illustrating a temperature measurement of a thermal imager according to an embodiment of the present application;

fig. 4 is a schematic composition diagram of an intelligent home system provided in the embodiment of the present application;

fig. 5 is a schematic flowchart of a control method of an air conditioning system according to an embodiment of the present disclosure;

fig. 6 is a flowchart illustrating another control method for an air conditioning system according to an embodiment of the present disclosure;

fig. 7 is a schematic flowchart of another control method for an air conditioning system according to an embodiment of the present disclosure;

fig. 8 is a schematic flowchart of another control method for an air conditioning system according to an embodiment of the present disclosure;

fig. 9 is a schematic flowchart of another control method for an air conditioning system according to an embodiment of the present disclosure;

fig. 10 is a schematic flowchart of another control method for an air conditioning system according to an embodiment of the present application;

FIG. 11 is a schematic flow chart illustrating a process for thermal imaging according to an embodiment of the present disclosure;

FIG. 12 is a schematic flow chart illustrating a process for thermal imaging according to an embodiment of the present disclosure;

fig. 13 is a schematic diagram illustrating comparison between effects of a gray scale image according to an embodiment of the present application;

fig. 14 is a schematic hardware structure diagram of a controller according to an embodiment of the present disclosure.

Detailed Description

The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.

It should be noted that all directional indicators (such as up, down, left, right, front, back \8230;) in the embodiments of the present invention are only used to explain the relative positional relationship between the components, the motion situation, etc. in a specific posture (as shown in the attached drawings), and if the specific posture is changed, the directional indicator is changed accordingly.

The terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of the present application, "a plurality" means two or more unless otherwise specified.

In the description of the present application, it is to be noted that the terms "connected" and "connected" are to be interpreted broadly, and may be, for example, fixedly connected, detachably connected, or integrally connected, unless explicitly stated or limited otherwise. The specific meaning of the above terms in the present application can be understood in a specific case by those of ordinary skill in the art. In addition, when a pipeline is described, the terms "connected" and "connected" are used in this application to have a meaning of conducting. The specific meaning is to be understood in conjunction with the context.

In the embodiments of the present application, words such as "exemplary" or "for example" are used to mean serving as an example, instance, or illustration. Any embodiment or design described herein as "exemplary" or "such as" is not necessarily to be construed as preferred or advantageous over other embodiments or designs. Rather, use of the word "exemplary" or "such as" is intended to present relevant concepts in a concrete fashion.

The thermal imaging image is generated based on different temperatures of different objects in the infrared detection area, various information such as the distance, the direction, the posture, the motion state and the like of a human body can be accurately identified based on the thermal imaging image, and the information can well provide data sources for intelligent operation of an air conditioner, such as intelligent operation of the air conditioner including human startup, unmanned shutdown, intelligent air supply and the like. However, if a high-temperature object exists in the infrared detection area, effective information is masked due to its temperature sensitivity, so that it becomes abnormally difficult to identify a human body in a grayscale image of a thermal imager.

Based on this, an embodiment of the present application provides a control method of an air conditioning system, where a high-temperature target in a high-temperature region in a thermal imaging image is processed, so that a processed temperature value of the high-temperature target is lower than a pre-processing temperature value, it can be understood that, based on a certain mapping relationship, a color gradation width of the temperature value of the high-temperature target in a mapped gray scale value is smaller, that is, a color gradation width of the temperature value of a non-high-temperature target in the mapped gray scale value is larger, so that the non-high-temperature target, for example, a human body target can be displayed in the gray scale image, thereby ensuring accuracy of human body identification.

Fig. 1 is a schematic composition diagram of an air conditioning system according to an embodiment of the present disclosure. It should be noted that the air conditioning system according to the embodiment of the present application may be a common air conditioning system composed of one indoor unit and one outdoor unit, or may be a multi-split air conditioning system. For convenience of description, different types of air conditioning systems are illustrated by taking the schematic structural diagram of the air conditioning system shown in fig. 1 as an example.

As shown in fig. 1, the air conditioning system 10 includes an outdoor unit 11, a thermal imaging device 12 (not shown in fig. 1), an indoor unit 13, and a controller 14 (not shown in fig. 1).

In some embodiments, the outdoor unit 11 is generally disposed outdoors for exchanging heat with an indoor environment. In the illustration of fig. 1, the outdoor unit 11 is indicated by a broken line because the outdoor unit 11 is located outdoors on the opposite side of the indoor unit 13 with respect to the wall surface.

In some embodiments, the indoor unit 13 is an indoor unit (shown in fig. 1) which is typically mounted on an indoor wall surface or the like. For another example, an indoor cabinet (not shown in fig. 1) is also an indoor unit configuration of the indoor unit.

In some embodiments, as shown in fig. 2, the thermal imaging device 12 is disposed on the indoor unit 13, or may be integrated on the indoor unit 13, and is configured to acquire a thermal imaging image of an infrared detection area and also acquire a temperature value of the infrared detection area.

In the embodiment of the present application, the thermal imaging device 12 is an electronic apparatus that performs target detection using infrared radiation, such as: thermopiles, thermal imagers, etc.

In some embodiments of the present application, the thermal imaging device 12 employs a thermal imager with high resolution and good imaging effect.

In some embodiments, infrared radiation may be referred to as infrared light, and refers to electromagnetic waves having wavelengths of approximately 0.75 microns to 120 microns.

The principle of infrared thermography can be understood as follows: due to the existence of black body radiation, electromagnetic wave radiation is carried out on any object according to different temperatures, and if the surface temperature of the object exceeds absolute zero, the electromagnetic wave can be radiated. Along with the temperature change, the radiation intensity and the wavelength distribution characteristic of the electromagnetic wave are changed. The portion with a wavelength of 2.0 microns to 120 microns is called "thermal infrared" while the "visible light" that is visible to humans is between 0.4 microns to 0.75 microns. Infrared thermal imaging uses a photoelectric technology to detect infrared specific waveband signals of object thermal radiation, converts the signals into images and graphs which can be distinguished by human vision, and can further calculate temperature values. The human body is beyond the visual barrier, so that the temperature distribution of the surface of the object can be seen.

Fig. 3 is a schematic diagram of temperature measurement of a thermal imager according to an embodiment of the present application, and as shown in fig. 3, infrared rays emitted by a target converge to a detector through a lens, and the detector converts received heat energy into an electrical signal and outputs the electrical signal. The data sent between the detector and the main control board comprise original data (raw 14 bit), blocking piece temperature and detector temperature, thermal imaging can be achieved through the original data, and temperature measurement can be achieved through the original data, the blocking piece temperature and the detector temperature. The specific temperature measurement formula (1) is as follows:

Δraw14＝bT ₀ ⁴ –cT ₁ ⁴ formula (1)

Wherein, T ₀ Target temperature value T calculated by temperature measurement formula ₁ Representing the temperature value detected by the detector. b and c areThe preset coefficient is preset when the thermal imager leaves a factory.

In some embodiments, the controller 14 refers to a device that can generate an operation control signal according to the command operation code and the timing signal, and instruct the air conditioning system 10 to execute the control command. Illustratively, the controller 14 may be a Central Processing Unit (CPU), a general purpose processor Network Processor (NP), a Digital Signal Processor (DSP), a Programmable Logic Device (PLD), a microprocessor, a microcontroller, or any combination thereof. The controller may also be other devices with processing functions, such as a circuit, a device, or a software module, which is not limited in any way by the embodiments of the present application.

In some embodiments, the controller 14 may acquire the temperature value of the infrared detection area through the thermal imaging device 12.

It is to be understood that fig. 1 is an exemplary architectural diagram, and the air conditioning system shown in fig. 1 includes an unlimited number of devices (e.g., the number of indoor units, the number of outdoor units, and the number of thermal imaging devices disposed on the indoor units). The air conditioning system may include other devices besides the device shown in fig. 1, which is not limited thereto.

For further description of the scheme of the present application, as shown in fig. 4, a schematic composition diagram of an intelligent home system provided in the embodiment of the present application is shown. As shown in fig. 4, the smart home system includes an air conditioning system 10, a server 15, a terminal device 16, and the internet 17.

The internet (17), also called internet or internet, internet (transliteration), is a huge network formed by connecting networks in series, and these networks are connected by a set of common protocols to form a logically single huge international network. In the present embodiment, the internet 17 may be used to provide a network.

After the air conditioning system 10 and the terminal device 16 access the internet 17, the air conditioning system 10 and the terminal device 16 can communicate with the server 15 on the network side through the internet 17. Meanwhile, the air conditioning system 10 and the terminal device 16 may communicate with each other through the internet 17.

The terminal device 16 is used for sending a control instruction to the air conditioning system 10 and receiving a detection result of the thermal imaging device 12 of the air conditioning system 10 on the infrared detection area. The terminal device 16 in the embodiment of the present application may be, for example, a mobile phone, a tablet computer, a desktop computer, a laptop computer, a handheld computer, a notebook computer, an ultra-mobile personal computer (UMPC), a netbook, a cellular phone, a Personal Digital Assistant (PDA), an Augmented Reality (AR) \ Virtual Reality (VR) device, and the like. The present application is not limited to the specific form of the terminal device 16. The system can be used for man-machine interaction with a user through one or more modes of a keyboard, a touch pad, a touch screen, a remote controller, voice interaction or handwriting equipment and the like. Taking the terminal device 16 as a mobile phone, the user may use the mobile phone to send a control command to the thermal imaging device 12 of the air conditioning system 10.

For example, a user may download an intelligent home APP on a mobile phone, and the intelligent home APP may be used to manage an intelligent home device, which is exemplified by the air conditioning system 10 configured with the thermal imaging device 12 in this embodiment of the application. Further, the user may select an online device of the air conditioning system 10 in which the thermal imaging device 12 is disposed, and select a control function to be performed on the thermal imaging device 12 of the air conditioning system 10 among management options of the air conditioning system 10. Such as control functions to start, shut down, switch modes (e.g., monitor mode), etc. If it is detected that the user clicks a start button for the thermal imaging device 12 of the air conditioning system 10 in the smart home APP, the mobile phone may send a start instruction for the thermal imaging device 12 of the air conditioning system 10 to the internet 17. Further, the internet 17 may send the start instruction to the thermal imaging device 12 of the air conditioning system 10, so that the thermal imaging device 12 of the air conditioning system 10 starts up in response to the start instruction.

The server 15 is configured to receive and store the grayscale image of the infrared detection area sent by the thermal imaging device 12 of the air conditioning system 10, and transmit the grayscale image of the infrared detection area at that moment to the terminal device 16.

The server 15 may be a single server, or may be a server cluster including a plurality of servers. In some embodiments, the server cluster may also be a distributed cluster. The present application is not limited to a specific form of the server 15.

In some embodiments of the present application, the thermal imaging device 12 of the air conditioning system 10 transmits the grayscale image of the infrared detection area to the server 15 through a network provided by the internet 17 according to the grayscale image of the infrared detection area.

The server 15 receives the grayscale image of the infrared detection region sent by the thermal imaging device 12 of the air conditioning system 10, and transmits the grayscale image of the infrared detection region to the terminal device 16, so that a user of the terminal device 16 can view the grayscale image in real time.

As a possible implementation manner, a one-key checking and downloading function is configured on the smart home APP, and when a user wants to check a grayscale image picture of a certain time period, the user can check the grayscale image picture through the one-key checking function and download the grayscale image of the infrared detection region to the terminal device 16.

It is to be understood that fig. 4 is an exemplary architecture diagram, and the number of devices included in the smart home system shown in fig. 4 is not limited (e.g., the number of thermal imaging devices and the number of terminal devices configured in the air conditioning system 10). It is noted that the present invention is not limited to the device shown in fig. 4, and other devices may be included.

In some embodiments, the thermal imaging apparatus may be deployed on other furniture devices, such as smart televisions or smart door locks.

The embodiments provided in the present application will be described in detail below with reference to the accompanying drawings.

The embodiment of the application provides a control method of an air conditioning system, which is applied to a controller, which may be the controller 14 shown in fig. 1. As shown in fig. 5, the method comprises the steps of:

and S101, acquiring a thermal imaging image of the infrared detection area.

In some embodiments, the controller acquires a thermal imaging image of the infrared detection area through the thermal imaging device after receiving the instruction of the human target detection function.

For example, the above instruction to start human target detection may be triggered by a user operating on the air conditioning system.

For example, the instruction for turning on the human target detection may be from an electronic device. Specifically, the air conditioning system may be connected to the terminal device by means of a wired connection (e.g., signal line) or a wireless connection (e.g., bluetooth, wi-Fi). When a user is at home, the air conditioning system is instructed to start the human body target detection function through the terminal equipment. And the terminal equipment responds to the operation of starting the human body target detection function by the user and sends an instruction of starting the human body target detection function to the air conditioning system.

As another possible implementation manner, when the preset time is reached, the air conditioning system automatically starts the human body target detection function, and controls the thermal imaging device to detect the infrared detection area, so as to obtain a thermal imaging image of the infrared detection area. Therefore, the user can automatically start the human body target detection function at regular time through one timing operation, so that the operation of the user is saved, and the use of the user is facilitated.

Optionally, the predetermined time may be adjusted by a user according to a use requirement, which is not limited in this embodiment of the application. For example, if the user presets at 18:00 to 8:00, the time period is at home, the thermal imaging device is required to start the human body target detection function to detect the infrared detection area, and then the thermal imaging device is in a state of 18:00, automatically starting a human body target detection function, and in 18:00 to 8: and keeping the human body target detection function in an on state in the 00 time period.

In the embodiment of the present application, the infrared detection area is an area where human body target detection is required, such as a living room, a bedroom, a study room, and the like, which is not limited herein.

S102, identifying a high-temperature area in the thermal imaging image based on the temperature value of each pixel point in the thermal imaging image.

The high temperature area is an area with a temperature value above a first temperature threshold, that is, the high temperature area is an area with a temperature value of each pixel point above the first temperature threshold.

In some embodiments, the high temperature region may be identified in the following manner.

In the mode 1, whether a high-temperature area exists in the thermal imaging image is judged according to the temperature value of each pixel point in the thermal imaging image.

Illustratively, the temperature values of all pixel points in the thermal imaging image are traversed, and N connected regions are determined.

The temperature value of each pixel point in the connected region is above the first temperature threshold, N is a natural number, and the connected region is a region containing pixel points with the temperature values above the first temperature threshold.

Wherein the high temperature region may be caused by a high temperature target, for example, the high temperature target may be a lit candle, a fire point, or the like.

It is understood that if there is no high temperature target in the infrared detection area, the temperature of various articles in the infrared detection area is close to room temperature, and the temperature of some electrical products in operation may be higher than room temperature but out of a certain range. If a high-temperature target exists in the infrared detection area, the temperature value of the high-temperature target and the temperature value around the high-temperature target are greatly higher than the room temperature.

Since the high-temperature target is associated with the high-temperature region in the thermal imaging image, if the temperature value of each pixel point constituting a connected region is greater than or equal to the first temperature threshold, the probability that the connected region is a high-temperature target (e.g., an ignition region) in the real world is high, and thus the region can be used as the high-temperature region.

It should be noted that if the temperature value of each pixel in the thermal imaging image is below the first temperature threshold, N is 0, that is, it is determined that there is no high-temperature region in the thermal imaging image.

And 2, inputting the thermal imaging image into the high-temperature region identification model to obtain the identification result of the high-temperature region.

Illustratively, the high temperature region identification model may be trained in advance according to a machine learning algorithm. And inputting the thermal imaging image into a high-temperature region identification model trained in advance so as to obtain the identification result of the high-temperature region. The recognition result indicates whether a high temperature region exists in the thermal imaging image.

In some embodiments, the detection using the high temperature region identification model based on the machine learning algorithm can have a plurality of different detection forms and implementation methods. For example, a conventional high-temperature region recognition model based on a machine learning algorithm is obtained by using a Support Vector Machine (SVM) algorithm, a gradient boosting iterative decision tree (GBDT) algorithm, a random forest algorithm (RF) algorithm, and the like, or a high-temperature region recognition model based on deep learning is obtained by using a Convolutional Neural Network (CNN) algorithm, a Recurrent Neural Network (RNN) algorithm, and a long-term short-memory network (LSTM) algorithm.

It is easy to understand that the deep convolutional neural network can automatically extract and learn more essential features in the image from massive training data, and the deep convolutional neural network is applied to the high-temperature target detection based on the thermal imaging image, so that the classification effect is remarkably enhanced, and the accuracy of human target detection is further improved under the condition that the high-temperature target exists in the thermal imaging image.

Optionally, if it is determined that the thermal imaging image does not have the high temperature region according to the mode 1 or the mode 2, the thermal imaging device continues to perform human target detection on the infrared detection region.

If it is determined that a high-temperature region exists in the thermal imaging image according to the mode 1 or the mode 2, the thermal imaging apparatus processes the high-temperature region in the thermal imaging image.

S103, processing the high-temperature area in the thermal imaging image to obtain a processed thermal imaging image.

It can be understood that the high-temperature target in the high-temperature region in the thermal imaging image occupies the bright spot, which causes the human body target to tend to be in the background color in the gray scale image, so that it is difficult to identify the human body in the subsequent human body identification based on the gray scale image, and therefore the high-temperature region in the thermal imaging image needs to be processed.

Illustratively, as shown in fig. 6, step S103 may be embodied as the following steps:

and S1031, compressing and smoothing the temperature values of the pixel points in the high-temperature region in the thermal imaging image to obtain the temperature values after the pixel points in the high-temperature region in the thermal imaging image are processed.

In some embodiments, the processed temperature value of the pixel points of the high temperature region in the thermal imaging image is determined according to the following formula (2):

Y _smooth ＝Y _threshold +(Y _raw -Y _threshold ) A formula (2)

Illustratively, assume a first temperature threshold Y _threshold The temperature value Y is 40 ℃, and the temperature value Y is the pixel point of the high temperature region in the thermal imaging image _raw The temperature is 50 ℃, the coefficient a is 0.4, and the temperature value Y processed by the pixel points in the high temperature region in the thermal imaging image can be obtained according to a calculation formula _smooth The temperature value is 44 ℃, namely after compression smoothing processing, the temperature value of the pixel points in the high-temperature region in the thermal imaging image is reduced to 44 ℃ from 50 ℃, and the difference value with the first temperature threshold is reduced to 4 ℃ from 10 ℃, namely the temperature value of the pixel points in the high-temperature region is reduced, so that the temperature values of the pixel points in the thermal imaging image tend to be balanced.

And S104, converting the processed thermal imaging image into a gray image.

Illustratively, as shown in fig. 7, step S104 may be embodied as the following steps:

and S1041, converting the processed thermal imaging image to obtain a gray image.

Wherein the conversion process comprises at least one of: the method comprises the following steps of pot cover removing processing, noise reduction processing, filtering processing, enhancement processing and dimming processing, wherein the enhancement processing comprises histogram processing.

The following specifically describes the conversion process of the processed thermal imaging image.

1. And (5) removing the pot cover.

In some embodiments, after obtaining the processed thermographic image, the controller may also perform decapping on the processed thermographic image.

For thermal imaging devices, system response non-uniformity defects introduced by the optics, detector, and post-processing circuitry together are often well compensated for by a single reference radiation source based calibration. However, due to the influence of factors such as field switching and focusing of the thermal imaging device, ambient temperature, and impact vibration, the nonuniformity introduced by the optical system may be significantly changed, which often causes the thermal imaging image output by the thermal imaging device to have black center, bright edges and four corners, i.e. the pan cover effect. The pot-cover effect is a result of non-uniformity introduced by the optical system of the thermal imaging device not being effectively compensated, and is a special optical system introducing noise.

The purpose of carrying out pan cover removing treatment on the processed thermal imaging image is to avoid the phenomenon that the thermal imaging image has black center, bright edges and four corners, and improve the uniformity of the thermal imaging image.

2. And (5) noise reduction processing.

The noise reduction processing on the processed thermal imaging image can be divided into temporal noise reduction and spatial noise reduction.

Optionally, the time denoising adopts a multi-frame filtering manner, and low-pass filtering processing is performed on pixels at the same positions corresponding to consecutive frames. Here, temporal noise reduction may also be understood as a noise reduction operation.

The low-pass filtering is a filtering method, and the rule is that low-frequency signals can normally pass through, and high-frequency signals exceeding a set critical value are blocked and weakened. But the magnitude of the blocking and attenuation will vary depending on the frequency and filtering procedure (purpose). Low-pass filtering can be simply thought of as: a frequency point is set which cannot pass when the signal frequency is higher than this frequency, which is the cut-off frequency in the digital signal, and all values are assigned to 0 when the frequency is higher than this cut-off frequency. In the processing process, the low-frequency signals are all passed through, and the high-frequency signals are limited to pass through, so that the purpose of eliminating noise and interference information and textures is achieved.

Optionally, the spatial noise reduction adopts gaussian filtering to ensure smoothness of the image. Wherein spatial noise reduction may also be understood as a vertical striping operation.

The gaussian filtering is a linear smooth filtering, is suitable for eliminating gaussian noise, and is widely applied to a noise reduction process of image processing. Generally speaking, gaussian filtering is a process of performing weighted average on the whole image, and the value of each pixel point is obtained by performing weighted average on the value of each pixel point and other pixel values in the neighborhood.

The specific operation of gaussian filtering is to scan each pixel in the thermal imaging image with a template (or convolution, mask), and to replace the value of the pixel in the center of the template with the weighted average gray value of the pixels in the neighborhood determined by the template.

The processed thermal imaging image is subjected to low-pass filtering and Gaussian filtering, so that the signal-to-noise ratio of the thermal imaging image can be improved, and the processed thermal imaging image is easy to extract.

3. And (5) filtering.

After the noise reduction processing is performed on the processed thermal imaging image, further, the filtering processing may be performed on the processed thermal imaging image.

Optionally, the filtering process includes a bilateral filtering (bilateral filter) process.

The bilateral filtering processing is a nonlinear filtering method, is compromise processing combining spatial proximity and pixel value similarity of an image, simultaneously considers spatial domain information and gray scale similarity, achieves the purpose of edge protection and denoising, and has the characteristics of simplicity, non-iteration and locality. And after bilateral filtering processing is carried out on the thermal imaging image, a base layer image of the thermal imaging image can be obtained.

The bilateral filtering process has the advantages that edge preservation (edge preservation) can be performed, and due to the adoption of the Gaussian filtering process for denoising, edges can be blurred obviously, and the protection effect on high-frequency details is not obvious. The bilateral filter has a Gaussian variance sigma-d higher than Gaussian filter as the name suggests, and is a Gaussian filter function based on spatial distribution, so that pixels far away from the edge do not influence the pixel value on the edge too much near the edge, and the storage of the pixel value near the edge is ensured.

However, due to the fact that too much high-frequency information is stored, bilateral filtering processing cannot be used for filtering out high-frequency noise in an image cleanly, and only good filtering can be conducted on low-frequency information. Therefore, after the thermal imaging image is subjected to bilateral filtering processing to obtain a base layer image of the thermal imaging image, enhancement processing needs to be performed on the base layer image.

4. And (6) enhancing treatment.

After the noise reduction processing and the filtering processing are performed on the processed thermal imaging image to obtain the base layer image of the processed thermal imaging image, further, the enhancement processing can be performed on the base layer image of the processed thermal imaging image.

Enhancing the base layer image of the processed thermographic image may include the following two aspects:

on one hand, the difference processing can be performed on the base layer image of the processed thermal imaging image, and the high-frequency data in the base layer image is separated to obtain the detail layer image of the processed thermal imaging image. And further, the detail layer image of the processed thermal imaging image can be subjected to high-frequency amplification processing to obtain the detail layer image of the enhanced thermal imaging image.

In another aspect, a histogram processing may be performed on the base layer image of the processed thermographic image to improve the contrast of the thermographic image to obtain an enhanced base layer image of the thermographic image.

The histogram processing is to process the contrast of the thermal imaging image, and the image noise of the thermal imaging image is reduced by performing the noise reduction processing on the thermal imaging image, but the details of the image cannot be visually observed, so that the histogram processing needs to be performed on the base layer image of the thermal imaging image.

Histogram processing is an image enhancement method that expands the dynamic display range of an image and enhances contrast by making the probability of the input image gray-scale value as uniformly distributed as possible. The histogram processing reduces the original information of the image from a certain angle, mainly representing the gray scale information, but from the observation angle, the full gray scale information is unfavorable for observation, at this time, the interested gray scale information can be stretched through the histogram processing, and the uninteresting gray scale information is compressed, so that the contrast improvement effect is achieved.

In the embodiment of the application, the histogram processing adopts the conversion from 14bit to 8bit, removes the area with less compression gray level, stretches the area with more gray level, obtains the corresponding stretching coefficient by utilizing the gray data of the previous frame, and applies the stretching coefficient to the image of the next frame. The stretching coefficients are replaced in real time, and the stretching effect is ensured.

Because the background and the noise occupy a large number of gray levels, and the gray level of the target is less, the contrast of the background and the noise is improved after histogram equalization, and the contrast of the target is reduced. In this case, a flat histogram equalization algorithm may be employed. The platform histogram equalization algorithm modifies the image histogram by selecting an appropriate platform threshold, thereby suppressing the background and noise moderately.

It should be noted that when the thermal imaging image is processed by using the platform histogram equalization algorithm, a main peak smoothing parameter may be added, the tensile strength of the image is changed by changing the main peak suppression width, and smoothing and multi-frame processing are adopted when the main peak of the image is obtained, so as to avoid image oscillation caused by the drastic change of the main peak. Therefore, the image contrast can be better improved, and meanwhile, the uniform picture and the image flicker are avoided.

5. And (6) dimming processing.

In some embodiments, the gray scale homogenization algorithm can be used for improving the image brightness of the processed thermal imaging image, and the contrast of the image is maintained through the linear dimming stretching of the homogenized image.

After the processed thermal imaging image is subjected to the conversion processing, a clear gray image of the infrared detection area can be obtained.

And S105, carrying out human body recognition on the gray level image to acquire the information of the human body target.

In some embodiments, after obtaining the grayscale image, human body recognition may be performed on the grayscale image to determine information of human body targets in the infrared detection region. Wherein the information of the human target comprises at least one of: the distance between the human body target and the indoor unit, the orientation of the human body target, the posture of the human body target and the motion state of the human body target.

Optionally, the human body recognition model is stored in the controller in advance. After the gray level image is obtained, the gray level image can be input into the human body recognition model, and a human body recognition result is output, wherein the human body recognition result indicates whether a human body target exists in the infrared detection area.

And under the condition that the human body target identification result indicates that the human body target exists in the infrared detection area, the human body position of the detected human body target can be tracked by utilizing a tracking algorithm, so that the position information of the human body target is determined. The gesture recognition of the human body target in the gray level image can be performed according to a detection algorithm based on key points or an algorithm based on neural network feature extraction, and the gesture recognition result of the human body target in the gray level image is determined. The gray level image can be processed by using a method for improving the motion history map based on the combination of a Gaussian kernel function and equal-interval frame interval sampling, each frame image is not required to be analyzed, the gray level value change in the motion history map can be effectively smoothed to enable the motion history map to have strong robustness, image features are extracted through a direction gradient histogram, and then a neural network classifier is used for detecting whether an action state label is changed or not and extracting an action key frame according to the change of the action state label, so that the motion state of the human body target is determined.

Alternatively, the human recognition model may be implemented by various algorithms. For example, a traditional human body recognition model based on a machine learning algorithm is obtained by using a Support Vector Machine (SVM) algorithm, a gradient boosting iterative decision tree (GBDT) algorithm, a random forest algorithm (RF) algorithm, and the like, or a deep learning-based human body recognition model is obtained by using a Convolutional Neural Network (CNN) algorithm, a Recurrent Neural Network (RNN) algorithm, and a long-term short-memory network (LSTM) algorithm, which are not limited in this embodiment.

In some embodiments, the grayscale image may also be transmitted and displayed or developed by other application algorithms, for example, grayscale image data may be input into an AI algorithm, an area where a human body target is located may be framed, and when it is detected that the human body target is located in a preset area, an alarm prompt is sent out, so as to implement functions such as anti-theft alarm. The preset area may be preset by the user through the terminal device.

Based on the embodiment shown in fig. 5, at least the following advantages are brought: and after the thermal imaging image of the infrared detection area is obtained, processing the temperature value of the pixel point of the high-temperature area in the thermal imaging image, so that the temperature value of the pixel point of the high-temperature area in the processed thermal imaging image is lower than the temperature value of the same pixel point of the high-temperature area in the thermal imaging image before processing. It can be understood that the high temperature region is caused by the high temperature target, by reducing the temperature value of the pixel point of the high temperature region, also reduce the temperature value of the pixel point of the high temperature target, the tone scale width of the pixel point of the high temperature target in the gray scale value mapped out in the gray scale image is reduced, also the tone scale width of the pixel point of the non-high temperature target in the gray scale value mapped out in the gray scale image is increased, so that the non-high temperature target, for example, the human body target can be shown in the gray scale image, thereby ensuring the accuracy of the human body target identification under the condition that the high temperature target exists in the infrared detection region.

In some embodiments, as shown in fig. 8, after step S105, the method further comprises the steps of:

s201, adjusting the working mode of the air conditioning system according to the information of the human body target.

In some embodiments, after obtaining the information of the human target, the controller may adjust an operation mode of the air conditioning system according to the information of the human target.

Illustratively, the air conditioning system is controlled to start working under the condition that the human body target exists in the infrared detection area. And under the condition that no human body target exists in the infrared detection area, controlling the air conditioning system to stop working.

Optionally, the air volume of the air conditioning system is adjusted according to the distance between the identified human body target and the indoor unit. The distance between the human body target and the indoor unit can be in a positive correlation relationship, that is, the closer the distance between the human body target and the indoor unit is, the smaller the air volume of the air conditioning system is, and the farther the distance between the human body target and the indoor unit is, the larger the air volume of the air conditioning system is.

Optionally, the wind direction of the air conditioning system may be adjusted according to the recognized posture of the human target. For example, when the posture of the human body target is recognized as standing, the air volume of the air conditioning system is increased. And when the posture of the human body target is recognized as lying, reducing the air volume of the air conditioning system.

Optionally, as shown in fig. 9, the step S101 may be implemented as the following steps:

and S1011, acquiring an original thermal imaging image of the infrared detection area.

In some embodiments, the controller obtains level data received from detection of the infrared detection zone by the thermal imaging device.

Wherein, the level data refers to: the thermal imaging device receives a 16-Bit (Bit) level signal obtained by converting an optical signal, which is reflected by electromagnetic waves emitted by the thermal imaging device after the electromagnetic waves contact an article in an infrared detection area, and the optical signal is received by the thermal imaging device. It should be understood that since the thermal imaging apparatus can emit electromagnetic waves for a long time, the above-described level data may have a plurality of frames, that is, the original thermal imaging image may have a plurality of frames.

In some embodiments, after the controller acquires the level data, the level data at the current time is restored to an image size matrix with the same resolution as that of the thermal imaging device according to the resolution of the thermal imaging device, so as to obtain an original thermal imaging image of the infrared detection area.

And S1012, carrying out non-uniform correction processing and bad point removal processing on the original thermal imaging image to obtain a thermal imaging image of the infrared detection area.

After obtaining the original thermographic image of the infrared detection area, the controller may perform non-uniform correction processing and bad point removal processing on the original thermographic image, so as to generate a clearer infrared thermographic image. The processing operation of the raw thermographic image is described in detail below.

1. Non-uniformity correction processing

Due to the limitation of the current process level and the software level, the thermal imaging device cannot automatically adjust the self detection parameters according to the external temperature and humidity. Therefore, after the thermal imaging device is opened for a period of time or after a user observes that the external temperature or humidity changes, the lens needs to be shielded by the blocking piece, and the detection parameters of the thermal imaging device are corrected according to the existing environment so as to achieve a proper detection effect. If the detection parameters of the thermal imaging device are not corrected through the baffle, irregular gray bottom or horizontal and vertical stripes can appear during detection of the thermal imaging device, so that the original thermal imaging image needs to be corrected.

In some embodiments, the non-uniformity correction process uses a two-point correction method to process the raw thermographic image. The two-point correction method is to convert the response characteristic curves of all the detection units into the same response characteristic curve through rotation and translation. After correction, under the condition of uniform radiation input, the output electric signals of all the detection units are the same, so that the non-uniform noise of the original thermal imaging image is eliminated, the gain coefficient of the thermal imaging device is compensated, and the offset coefficient is corrected.

In some embodiments, the process of the two-point correction method described above may satisfy the following formula (3):

y = A (X-B) formula (3)

Wherein Y is the corrected thermal imaging image, X is the original thermal imaging image, B is the baffle original data, and A is the sensitivity correction coefficient.

After the original thermal imaging image is corrected, the original thermal imaging image is relatively uniform.

2. Bad point removal process

It can be understood that, since the thermal imaging image is different from other images (e.g. color images), there is relatively large noise, where the relatively significant noise is called a dead pixel, which means that the gray value of a pixel point in the thermal imaging image is significantly different from the points of the pixel points around the pixel point, and if the dead pixel is not identified and removed, the denoising effect on the thermal imaging image is affected, so that the dead pixel removal processing needs to be performed on the original thermal imaging image.

In some embodiments, the bad point removal process is processed in an average value of neighboring 9 non-bad points around the bad point instead.

After the non-uniform correction processing and the dead pixel removing processing, a more uniform thermal imaging image of the infrared detection area can be obtained.

In some embodiments, as shown in fig. 10, the first temperature threshold may be determined by:

s301, acquiring a temperature value of the infrared detection area.

The calculation method of the temperature value of the infrared detection area is specifically explained as follows.

The detector of the thermal imaging device can convert received thermal radiation energy of an infrared band into an electric signal, and the electric signal is amplified, shaped and converted into a digital signal through analog-to-digital conversion, so that a thermal imaging image is generated. The grey value of each point in the thermal imaging image corresponds to the radiant energy emitted by the point on the object to be measured and reflected to the thermal imaging device. But the temperature value read from the thermographic image is the radiation temperature T of the object surface _r Not the true temperature T ₀ True temperature T ₀ Equal to the true temperature of a black body radiating the same energy. Therefore, in actual detection, if the real temperature is adopted, the thermal imaging device is calibrated by using the high-precision black body, and the temperature of the black body and the output voltage (represented as gray on a thermal imaging image) of the photoelectric conversion device of the thermal imaging device are found outDegree) of the image.

By blackbody is meant an object that absorbs radiation of any wavelength at any temperature.

In some embodiments, the black body is used to perform temperature correction for the thermal imaging device to ensure the temperature measurement accuracy of the thermal imaging device.

For example, the temperature of the black body is 37 degrees celsius, the thermal imaging device detects the temperature of the black body, and the obtained temperature value is 37.1 degrees celsius, which may indicate that the temperature measurement of the thermal imaging device has an error of 0.1 degrees celsius.

Stefan-boltzmann's law states that the degree of radiation of a black body satisfies the following equation (4):

E _b ＝σT ⁴ formula (4)

Wherein E is _b The radiation power of a black body is the radiation degree of the black body, sigma is the total radiation power of the black body, and T is the thermodynamic temperature of the black body, namely the total radiation power of various emitted wavelengths on the surface unit area of the black body is in direct proportion to the fourth power of the thermodynamic temperature T.

At the same temperature, the power radiated by an actual object in the same wavelength range is always less than that radiated by a black body. That is, the single-color emissivity E (λ, T) of the actual object is smaller than that of the black body _b (lambda, T). We compare E (. Lamda., T) with E _b The ratio of (λ, T) is called the monochromatic blackness e (λ) of the object, which represents how close the radiation of the actual object is to the black body, and the following equation (5) can be obtained:

converting the formula (5) to obtain the following formula (6):

E(λ，T)＝ε(λ)E _b (lambda, T) formula (6)

Integrating the two ends of equation (6) yields the following equation (7):

an object is said to be a gray body if its monochromatic blackness epsilon (lambda) is a constant that does not vary with the wavelength lambda, i.e. epsilon (lambda) = epsilon. Combining the following equation (8) and equation (9):

the following formula (10) can be obtained:

E(T)＝εE _b (T) formula (10)

Equation (10) in combination with equation (4) above, the following equation (11) can be derived:

E _b ＝εσT ⁴ formula (11)

The thermal radiation of a real object is in the infrared wavelength range and can be approximately seen as grey body radiation. ε is defined as the emissivity of the object, which represents the ratio of the radiation power of the object to the black body radiation power at the same temperature and under the same measurement conditions.

The illuminance of the radiation acting on the thermal imaging device can be obtained by the following equation (12):

E _λ ＝A ₀ d ^-2 [τ _αλ ε _λ L _bλ (T ₀ )+τ _αλ (1-α _λ )L _bλ (T _u )+ε _αλ L _bλ (T _a )]formula (12)

Wherein epsilon _λ Is surface emissivity, alpha lambda is surface absorptivity, tau _αλ Is the spectral transmission of the atmosphere, ε _αλ To atmospheric emissivity, T ₀ Is the surface temperature, T, of the object to be measured _u Is ambient temperature, T _a Is the atmospheric temperature and d is the distance between the target and the thermal imaging device. In the usual case, A ₀ d ^-2 Is a constant value, A ₀ For the target corresponding to the smallest spatial opening angle of the thermal imaging deviceThe visible area of (a). Thermal imaging devices typically operate within a narrow band, e.g., 8um-14um or 3um-5um _λ 、αλ、τ _αλ Generally considered independent of λ. The response voltage of the thermal imaging apparatus can be obtained by the following formula (13):

wherein A is _R As the area of the lens of the thermal imaging device, let K be represented by the following formula (14):

K＝A _R A ₀ d ^-2 formula (14)

Combining the following equation (15):

then equation (13) can be transformed to equation (16) below:

V _S ＝K{τ _a [εf(T ₀ )+(1-α)f(T _u )]+ε _a f(T _a ) Equation (16)

According to planck's law of radiation, the following equation (17) is obtained:

the true temperature of the surface of the measured object can be obtained from the following equation (18):

when thermal imaging devices with different wave bands are used, the value of n is different, and for an InSb (3-5 mu m) detector, the value of n is 8.68; for the HgCdTe (6-9 μm) detector, the n value is 5.33; for the HgCdTe (8-14 μm) detector, the n value is 4.09.

When the measured surface satisfies the gray body approximation,i.e. epsilon = alpha, and if considered atmospheric epsilon _a ＝α _a ＝1-τ _a Then equation (17) can be transformed to equation (19) below:

equation (18) can be transformed to equation (20) below:

the formula (20) is a calculation formula of the real temperature of the surface of the ash body.

Neglecting the effect of atmospheric transmittance, i.e. τ, when measuring temperature at close range _a =1, then equation (17) may be transformed to equation (21) below:

in summary, if the emissivity of the surface of the measured object is obtained, the real temperature of the surface of the measured object, that is, the temperature value of the infrared detection region, can be calculated through the above formula (20) or formula (21), and the detected radiation temperature and the ambient temperature.

It should be noted that, due to different influence factors, certain deviation may exist in the detection results obtained by different temperature measurement methods, and the influence of the certain deviation on the detection results may be ignored.

S302, correcting the second temperature threshold value according to the temperature value of the infrared detection area to obtain a first temperature threshold value.

The second temperature threshold may be preset when the air conditioning system leaves the factory.

It should be noted that the second temperature threshold is higher than the upper limit of the temperature of the pixel point corresponding to the human body target in the thermal imaging image. And assuming that the upper limit value of the temperature of the pixel point corresponding to the human body target in the thermal imaging image is 42 ℃, the second temperature threshold value is higher than 42 ℃.

Illustratively, the first temperature threshold may be determined by the following equation (22):

Y _threshold ＝mT ₃ ⁴ -nT ₄ ⁴ formula (22)

Wherein, T ₃ Is a second temperature threshold, T ₄ The temperature values of the infrared detection area are m and n are preset coefficients and are preset when the air conditioner leaves a factory, and the values of m and n are related to the distance between the human body target and the indoor unit and the temperature of a baffle plate or the temperature of a focal plane of the thermal imaging device to form a three-dimensional matrix.

As a possible implementation manner, the m and n may also be determined according to a blackbody temperature calibration curve or a temperature formula.

The embodiment based on fig. 10 brings at least the following advantages: revise the second temperature threshold value based on the temperature value of infrared detection region, also revise the temperature upper limit value of the pixel point that human target corresponds in the thermal imaging image according to the current temperature value of infrared detection region, obtain first temperature threshold value, so that discern the high temperature region according to first temperature threshold value, promoted the precision to the high temperature region discernment, and then can be accurate after the temperature value to the pixel point of high temperature region is handled, make the human target can be accurate appear in the grey level image, help promoting the precision to human target discernment.

The following will exemplify the compression smoothing process of the thermal imaging image in the embodiment of the present application with reference to the thermal imaging image processing flowchart shown in fig. 11.

Illustratively, after the temperature value of each pixel point of the thermal imaging image at the current time of the infrared detection area is obtained, whether a high-temperature area exists in the thermal imaging image is judged according to the temperature value of each pixel point of the thermal imaging image at the current time of the infrared detection area, if the high-temperature area exists, the high-temperature area in the thermal imaging image is compressed and smoothed to obtain a processed thermal imaging image, and then the process is finished. If no high temperature region exists in the thermal imaging image, the process is finished.

The following describes the processing procedure of the thermal imaging image in the embodiment of the present application with reference to a general flowchart of the thermal imaging image processing shown in fig. 12.

Illustratively, after the original 16-bit level data of the infrared detection region at the current moment is acquired, the original 16-bit level data is converted into an image size matrix with equal resolution according to the resolution of the thermal imaging device, so as to obtain an original thermal imaging image of the infrared detection region at the current moment.

Furthermore, the original thermal imaging image is subjected to non-uniform correction processing and dead pixel removal processing, so that a uniform thermal imaging image is obtained.

Furthermore, the temperature value of each pixel point in the original thermal imaging image is obtained through the temperature measuring module, the high-temperature area in the thermal imaging image is identified, and the high-temperature area is compressed and smoothed to obtain the processed thermal imaging image.

And performing high-temperature target compression smoothing on the relatively uniform original thermal imaging image to obtain a processed thermal imaging image.

Further, the thermal imaging image subjected to high-temperature compression smoothing is subjected to pan cover removing treatment, so that a more uniform thermal imaging image is obtained.

Further, the more uniform thermal imaging image is subjected to temporal noise reduction and spatial noise reduction to obtain a thermal imaging image with a high signal-to-noise ratio. The time noise reduction adopts a multi-frame filtering mode, and the space noise reduction adopts a Gaussian filtering mode.

Further, bilateral filtering processing is carried out on the thermal imaging image with high signal-to-noise ratio, and a base layer image of the thermal imaging image is obtained.

Further, enhancement processing may be performed on the base layer image of the thermographic image. Enhancing the base layer image of the thermographic image may include two aspects.

On one hand, the platform histogram processing can be carried out on the basic layer image of the thermal imaging image, the contrast of the thermal imaging image is improved, and the basic layer image of the enhanced thermal imaging image can be obtained.

On the other hand, the difference processing can be carried out on the basic layer image of the thermal imaging image, high-frequency data is separated, and the detail layer image of the thermal imaging image is obtained. And further, the detail layer image of the thermal imaging image can be subjected to high-frequency amplification processing to obtain the detail layer image of the enhanced thermal imaging image.

Furthermore, the basic layer image of the enhanced thermal imaging image and the detail layer image of the enhanced thermal imaging image are combined, and then dimming processing is carried out, so that a gray level image with a clear infrared detection area can be obtained.

For example, as shown in fig. 13 (a), the human body object in the gray-scale image is not clear enough, and as shown in fig. 13 (b), the human body object in the gray-scale image is clear.

After obtaining the grayscale image, human target recognition may be performed based on the grayscale image.

It can be seen that the foregoing describes the solution provided by the embodiments of the present application primarily from a methodological perspective. In order to implement the functions described above, the embodiments of the present application provide corresponding hardware structures and/or software modules for performing the respective functions. Those of skill in the art will readily appreciate that the various illustrative modules and algorithm steps described in connection with the embodiments disclosed herein may be implemented as hardware or combinations of hardware and computer software. Whether a function is performed as hardware or computer software drives hardware depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.

As shown in fig. 14, the controller 3000 includes a processor 3001, and optionally, a memory 3002 and a communication interface 3003, which are connected to the processor 3001. The processor 3001, memory 3002, and communication interface 3003 are connected by a bus 3004.

The processor 3001 may be a Central Processing Unit (CPU), a general purpose processor Network Processor (NP), a Digital Signal Processor (DSP), a microprocessor, a microcontroller, a Programmable Logic Device (PLD), or any combination thereof. The processor 3001 may also be any other means having processing functionality such as a circuit, device, or software module. The processor 3001 may include a plurality of CPUs, and the processor 3001 may be a single-core (single-CPU) processor or a multi-core (multi-CPU) processor. A processor herein may refer to one or more devices, circuits, or processing cores that process data (e.g., computer program instructions).

The memory 3002 may be a read-only memory (ROM) or other types of static storage devices that may store static information and instructions, a Random Access Memory (RAM) or other types of dynamic storage devices that may store information and instructions, an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compact disc, laser disc, optical disc, digital versatile disc, blu-ray disc, etc.), a magnetic disc storage medium or other magnetic storage device, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer, which are not limited by the embodiments of the present application. The memory 3002 may be separate or integrated with the processor 3001. The memory 3002 may contain, among other things, computer program code. The processor 3001 is configured to execute the computer program code stored in the memory 3002, thereby implementing the methods provided by the embodiments of the present application.

Communication interface 3003 may be used to communicate with other devices or communication networks (e.g., ethernet, radio Access Network (RAN), wireless Local Area Networks (WLAN), etc.). Communication interface 3003 may be a module, circuitry, transceiver, or any device capable of enabling communication.

The bus 3004 may be a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The bus 3004 may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is shown in FIG. 14, but this is not intended to represent only one bus or type of bus.

The embodiment of the present application further provides a computer-readable storage medium, which includes computer-executable instructions, and when the computer-readable storage medium runs on a computer, the computer is caused to execute any one of the methods provided by the foregoing embodiments.

Embodiments of the present application further provide a computer program product containing instructions for executing a computer, which when executed on a computer, causes the computer to perform any one of the methods provided in the foregoing embodiments.

An embodiment of the present application further provides a chip, including: a processor coupled to the memory through the interface, and an interface, when the processor executes the computer program or the computer execution instructions in the memory, the processor causes any one of the methods provided by the above embodiments to be performed.

In the above embodiments, the implementation may be wholly or partially realized by software, hardware, firmware, or any combination thereof. When implemented using a software program, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer-executable instructions. The processes or functions described in accordance with the embodiments of the present application occur, in whole or in part, when computer-executable instructions are loaded and executed on a computer. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable device. The computer executable instructions may be stored on a computer readable storage medium or transmitted from one computer readable storage medium to another, for example, the computer executable instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wire (e.g., coaxial cable, fiber optic, digital Subscriber Line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.). Computer-readable storage media can be any available media that can be accessed by a computer or data storage device including one or more available media integrated servers, data centers, and the like. The usable medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a magnetic tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a Solid State Disk (SSD)), among others.

While the present application has been described in connection with various embodiments, other variations to the disclosed embodiments can be understood and effected by those skilled in the art in practicing the claimed application, from a review of the drawings, the disclosure, and the appended claims. In the claims, the word "comprising" does not exclude other elements or steps, and the word "a" or "an" does not exclude a plurality. A single processor or other unit may fulfill the functions of several items recited in the claims. The mere fact that certain measures are recited in mutually different dependent claims does not indicate that a combination of these measures cannot be used to advantage.

Although the present application has been described in conjunction with specific features and embodiments thereof, it will be evident that various modifications and combinations can be made thereto without departing from the spirit and scope of the application. Accordingly, the specification and drawings are merely illustrative of the present application as defined in the appended claims and are intended to cover any and all modifications, variations, combinations, or equivalents within the scope of the application. It will be apparent to those skilled in the art that various changes and modifications may be made in the present application without departing from the spirit and scope of the application. Thus, if such modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is intended to include such modifications and variations as well.

The above description is only an embodiment of the present application, but the scope of the present application is not limited thereto, and any changes or substitutions within the technical scope of the present disclosure should be covered by the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims

1. An air conditioning system, comprising:

an outdoor unit and an indoor unit;

a controller configured to:

converting the processed thermal imaging image into a gray image;

and carrying out human body identification on the gray level image to obtain the information of the human body target.

2. The air conditioning system of claim 1, wherein the thermal imaging device is further configured to detect a temperature value of the infrared detection area;

the controller further configured to:

acquiring a temperature value of the infrared detection area through the thermal imaging device;

and correcting a second temperature threshold value according to the temperature value of the infrared detection area to obtain the first temperature threshold value.

3. The air conditioning system of claim 2, wherein the second temperature threshold is above an upper temperature limit of a corresponding pixel of the human target in the thermal imaging image.

4. The air conditioning system of claim 3, wherein the controller is configured to perform the following steps in processing a high temperature region in the thermographic image:

compressing and smoothing the temperature values of the pixel points in the high-temperature area in the thermal imaging image to obtain the temperature values after the pixel points in the high-temperature area in the thermal imaging image are processed;

Y _smooth ＝Y _threshold +(Y _raw -Y _threshold )*a

wherein, Y _smooth The temperature value Y after the pixel point processing of the high temperature area in the thermal imaging image _threshold Is the first temperature threshold, Y _raw And a is a coefficient which is larger than 0 and smaller than 1, and is the temperature value of the pixel point of the high temperature region in the thermal imaging image.

5. The air conditioning system as claimed in claim 4, wherein the controller is configured to specifically perform the following steps when converting the processed thermographic image into a grayscale image:

performing conversion processing on the processed thermal imaging image to obtain the gray level image, wherein the conversion processing comprises at least one of the following steps: the method comprises the following steps of pot cover removing processing, noise reduction processing, filtering processing, enhancement processing and dimming processing, wherein the enhancement processing comprises histogram processing.

6. The air conditioning system according to any one of claims 1 to 5, wherein the information of the human target includes at least one of: the distance between the human body target and the indoor unit, the orientation of the human body target, the posture of the human body target and the motion state of the human body target;

the controller further configured to:

and adjusting the working mode of the air conditioning system according to the information of the human body target.

7. A method of controlling an air conditioning system, the method comprising:

acquiring a thermal imaging image of an infrared detection area;

converting the processed thermal imaging image into a gray image;

8. The method of claim 7, further comprising:

acquiring a temperature value of the infrared detection area;

9. The method of claim 8, wherein the second temperature threshold is above an upper temperature limit of corresponding pixels of the human target in the thermographic image.

10. The method of claim 9, wherein the processing of high temperature regions in the thermographic image comprises:

Y _smooth ＝Y _threshold +(Y _raw -Y _threshold )*a