Air conditioner control method, device and equipment and storage medium

By collecting and processing scene image sequences of air conditioning operating areas in the air conditioning control system, the problem of inaccurate user image information recognition under complex background is solved, and more accurate air conditioning control is achieved.

CN119649211AActive Publication Date: 2025-03-18TCL AIR CONDITIONER ZHONGSHAN CO LTD
View PDF 4 Cites 0 Cited by

Patent Information

Application Number
CN202411623294.3
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-11-13
Publication Date
2025-03-18
Estimated Expiration
2044-11-13

AI Technical Summary

Technical Problem

The prior art cannot accurately identify user image information under complex backgrounds or backgrounds with large changes, resulting in inaccurate air conditioning control.

Method used

By collecting the scene image sequence of the air conditioner running area, using pixel grayscale values ​​for mode background modeling, obtaining the initial reference background, and obtaining local scene operators through block smoothing processing, updating the target scene background, and finally air conditioning control is performed according to the target scene background.

Benefits of technology

It improves the recognition accuracy and the recognition accuracy of target objects in complex scenarios, thereby improving the accuracy of air conditioning interaction.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119649211A_ABST
    Figure CN119649211A_ABST
Patent Text Reader

Abstract

The invention provides an air conditioner control method and device, equipment and a storage medium, and the method comprises the steps that in response to an air conditioner control request, a scene image sequence corresponding to an air conditioner operation area is collected; performing mode background modeling on the scene image sequence according to the pixel gray value of the scene image sequence to obtain an initial reference background of the scene image sequence; obtaining a local scene operator of the target image block according to the initial reference background and block smoothing processing in the scene image sequence, and determining a target scene background of the scene image sequence according to the local scene operator; target object information is determined according to the target scene background and the scene image sequence, air conditioner control is conducted according to the target object information, and an air conditioner control result is obtained. According to the invention, background modeling can be carried out without depending on prior information, the interference influence of most dynamic background transformation and illumination conditions on image recognition can be eliminated, and the accuracy of target object recognition in a subsequent complex environment is improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the technical field of air conditioners, and in particular to an air conditioning control method, device, equipment and storage medium. Background Art

[0002] At present, with the rapid development of the field of air conditioner technology, more and more air conditioners are installed in various indoor places. More and more users choose to install air conditioners in indoor places with higher temperatures such as kitchens for temperature control, and existing air conditioners can detect users and perform corresponding control operations. However, in scenes such as kitchens, the background environment is relatively complex and there are large background changes, which makes it impossible to effectively recognize user image information, resulting in inaccurate air conditioner control and failure to meet existing air conditioner control needs. Summary of the invention

[0003] The embodiments of the present application provide an air conditioning control method, apparatus, device and storage medium, which are intended to solve the technical problem in the prior art that user image information cannot be accurately recognized in complex backgrounds or backgrounds with large changes, resulting in abnormal air conditioning control.

[0004] In one aspect, an embodiment of the present application provides an air conditioning control method, the air conditioning control method comprising the following steps:

[0005] In response to the air conditioning control request, a scene image sequence corresponding to the air conditioning operation area is collected;

[0006] Performing mode background modeling on the scene image sequence according to the pixel grayscale values ​​of the scene image sequence to obtain an initial reference background of the scene image sequence;

[0007] Determine a target scene background of the scene image sequence according to the initial reference background and a target image block obtained by block smoothing in the scene image sequence;

[0008] Target object information is determined according to the target scene background and the scene image sequence, and air-conditioning control is performed according to the target object information to obtain an air-conditioning control result.

[0009] In a possible implementation of the present application, performing mode background modeling on the scene image sequence according to the pixel grayscale values ​​of the scene image sequence to obtain an initial reference background of the scene image sequence includes:

[0010] Determining a first pixel of a first scene image frame, a first grayscale value of the first pixel, and a first statistical quantity of the first grayscale value based on a scene image histogram corresponding to the scene image sequence;

[0011] Acquire a second pixel of a second scene image frame in the scene image sequence, as well as a second grayscale value of the second pixel and a second statistical quantity corresponding to the second grayscale value;

[0012] If the second statistical quantity is less than or equal to the first statistical quantity, performing mode modeling on the scene image sequence according to the first grayscale value to obtain an initial reference background;

[0013] If the second statistical quantity is greater than the first statistical quantity, mode modeling is performed on the scene image sequence according to the second grayscale value to obtain an initial reference background.

[0014] In a possible implementation of the present application, determining a first pixel point of a first scene image frame, a first grayscale value of the first pixel point, and a first statistical quantity of the first grayscale value based on a scene image histogram corresponding to the scene image sequence includes:

[0015] Obtaining a scene image histogram corresponding to the scene image sequence;

[0016] Determining a pixel grayscale value of a first pixel in the scene image sequence according to the scene image histogram;

[0017] Obtaining the statistical frequency of the pixel grayscale value in the scene image histogram to obtain the grayscale statistical quantity of the pixel grayscale value;

[0018] The grayscale value of the pixel with the largest grayscale statistical quantity is determined as the first grayscale value of the first pixel, and the grayscale statistical quantity is determined as the first statistical quantity of the first grayscale value.

[0019] In a possible implementation of the present application, determining the target scene background of the scene image sequence according to the initial reference background and the target image block obtained by block smoothing in the scene image sequence includes:

[0020] The initial reference background is processed by dividing into blocks to obtain reference background image blocks, and the scene image sequence is processed by dividing into blocks to obtain target image blocks;

[0021] Obtaining a reference grayscale average value corresponding to the reference background image block and a scene grayscale average value of the target image block;

[0022] The scene image sequence is updated according to the reference grayscale average value and the scene grayscale average value to obtain an updated image sequence;

[0023] A local scene operator corresponding to a target image block in an updated scene image sequence is calculated, and a target scene background of the updated image sequence is generated according to the local scene operator.

[0024] In a possible implementation of the present application, updating the scene image sequence according to the reference grayscale average value and the scene grayscale average value to obtain an updated image sequence includes:

[0025] Calculating the absolute value of the difference between the reference grayscale average value and the scene grayscale average value;

[0026] If the absolute value of the difference is less than a preset difference threshold, the target image block in the scene image sequence is updated using the reference grayscale average value to obtain an updated image sequence;

[0027] If the absolute value of the difference is greater than a preset difference threshold, the target image block in the scene image sequence is updated based on the neighborhood grayscale value of the target image block to obtain an updated image sequence.

[0028] In a possible implementation of the present application, the calculating a local scene operator corresponding to a target image block in an updated scene image sequence, and generating a target scene background of the updated image sequence according to the local scene operator, includes:

[0029] Obtaining the grayscale value of the central pixel and the grayscale values ​​of the neighboring pixels of the target image block;

[0030] Thresholding the grayscale value of the neighborhood pixels according to the grayscale value of the central pixel to obtain an initial scene operator;

[0031] Performing base conversion on the initial scene operator to obtain a local scene operator corresponding to the target image block;

[0032] A local operator histogram corresponding to an updated scene sequence is generated according to the local scene operator, and mode background modeling is performed on the updated image sequence according to the local operator histogram to obtain a target scene background.

[0033] In a possible implementation of the present application, performing air conditioning control according to the target object information to obtain an air conditioning control result includes:

[0034] Performing target detection based on the target scene background and the scene image sequence to obtain target object information in the scene image sequence;

[0035] An air-conditioning control instruction corresponding to the target object information is identified, and air-conditioning control is performed based on the air-conditioning control instruction to obtain an air-conditioning control result.

[0036] On the other hand, the present application provides an air conditioning control device, the air conditioning control device comprising:

[0037] An image acquisition module is configured to respond to an air conditioning control request and collect a scene image sequence corresponding to an air conditioning operation area;

[0038] A background reference module is configured to perform mode background modeling on the scene image sequence according to the pixel grayscale values ​​of the scene image sequence to obtain an initial reference background of the scene image sequence;

[0039] A background updating module, configured to determine a target scene background of the scene image sequence according to the initial reference background and a target image block obtained by block smoothing in the scene image sequence;

[0040] The air conditioning control module is configured to determine target object information according to the target scene background and the scene image sequence, perform air conditioning control according to the target object information, and obtain an air conditioning control result.

[0041] On the other hand, the present application also provides an air conditioning control device, the air conditioning control device comprising:

[0042] one or more processors;

[0043] Memory; and

[0044] One or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the processor to implement the steps of the air conditioning control method.

[0045] On the other hand, the present application also provides a computer-readable storage medium on which a computer program is stored, and the computer program is loaded by a processor to execute the steps in the air conditioning control method.

[0046] In the present application, by responding to the air-conditioning control request, the scene image sequence corresponding to the air-conditioning operation area is collected; the scene image sequence is subjected to mode background modeling according to the pixel grayscale value of the scene image sequence to obtain the initial reference background of the scene image sequence; the local scene operator of the target image block is obtained by block smoothing according to the initial reference background and the scene image sequence, and the target scene background of the scene image sequence is determined according to the local scene operator; the target object information is determined according to the target scene background and the scene image sequence, and the air-conditioning control is performed according to the target object information to obtain the air-conditioning control result. After obtaining the scene image sequence collected by the air conditioner, the scene image sequence is subjected to background modeling, thereby obtaining the initial reference background obtained by the initial modeling, and the scene image sequence is subjected to block smoothing according to the initial reference background, and the local scene operator after the block smoothing is obtained, and the target scene background of the scene line graphic sequence is updated according to the local scene operator, thereby improving the recognition accuracy in complex scenes, and then improving the recognition accuracy of subsequent target objects, thereby improving the accuracy of air-conditioning interaction. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0048] Figure 1 A schematic diagram of a scenario of an air conditioning control method according to an embodiment of the present application;

[0049] Figure 2 A flowchart of an embodiment of an air conditioning control method in an embodiment of the present application;

[0050] Figure 3 A flowchart of an embodiment of the air conditioning control method provided in the embodiment of the present application, in which the scene image sequence is updated according to the reference grayscale average value and the scene grayscale average value to obtain an updated image sequence;

[0051] Figure 4 A flow chart of an embodiment of determining a target scene background of a scene image sequence by using a local scene operator in an air conditioning control method provided in an embodiment of the present application;

[0052] Figure 5 A schematic diagram of the structure of an embodiment of an air conditioning control device provided in an embodiment of the present application;

[0053] Figure 6A schematic structural diagram of an embodiment of an air conditioning control device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0054] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0055] In the description of the present invention, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside" and the like indicate positions or positional relationships based on the positions or positional relationships shown in the accompanying drawings, which are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, the terms "first" and "second" are only used for descriptive purposes, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, the meaning of "multiple" is two or more, unless otherwise clearly and specifically defined.

[0056] In this application, the word "exemplary" is used to mean "serving as an example, illustration, or illustration." Any embodiment described in this application as "exemplary" is not necessarily to be construed as being preferred or advantageous over other embodiments. The following description is given to enable any person skilled in the art to implement and use the invention. In the following description, details are listed for the purpose of explanation. It should be understood that a person of ordinary skill in the art can recognize that the invention can be implemented without using these specific details. In other instances, well-known structures and processes are not elaborated in detail to avoid obscuring the description of the invention with unnecessary details. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles and features disclosed in this application.

[0057] At present, with the rapid development of the field of air conditioner technology, more and more air conditioners are installed in various indoor places. More and more users choose to install air conditioners in indoor places with higher temperatures such as kitchens for temperature control, and existing air conditioners can detect users and perform corresponding control operations. However, in scenes such as kitchens, the background environment is relatively complex and there are large background changes, which makes it impossible to effectively recognize user image information, resulting in inaccurate air conditioner control and failure to meet existing air conditioner control needs.

[0058] Based on this, the present application proposes an air conditioning control method, device, equipment and computer-readable storage medium to solve the technical problem in the prior art that user image information cannot be accurately identified in complex backgrounds or backgrounds with large changes, resulting in abnormal air conditioning control.

[0059] The air conditioning control method in the embodiment of the present invention is applied to an air conditioning control device, and the air conditioning control device is arranged in an air conditioning control device, and the air conditioning control device is provided with one or more processors, memories, and one or more applications, wherein the one or more applications are stored in the memories and are configured to be executed by the processor to implement the air conditioning control method; wherein the air conditioning control device can be an intelligent terminal, such as a mobile phone, a tablet computer, a network device, and a smart computer, etc.; optionally, the air conditioning control device can also be a server, or a service cluster composed of multiple servers.

[0060] like Figure 1 As shown, Figure 1 The following is a scene diagram of the air conditioning control method of the embodiment of the present application. The air conditioning control scene in the embodiment of the present invention includes an air conditioning control device 100 (an air conditioning control device is integrated in the air conditioning control device 100) and an air conditioner 200. The air conditioning control device 100 runs a computer-readable storage medium corresponding to the air conditioning control method to execute the steps of the air conditioning control method. The air conditioner 200 is an intelligent air conditioner that is connected to the air conditioning control device 100 for communication and can respond to the control interaction of the air conditioning control device. Optionally, in a specific embodiment, the air conditioning control device can also be an air conditioning main control module inside the air conditioner.

[0061] Understandably, Figure 1 The air-conditioning control equipment in the air-conditioning control method scenario shown, or the devices included in the air-conditioning control equipment, does not constitute a limitation on the embodiments of the present invention, that is, the number and type of air-conditioning control equipment included in the air-conditioning control method scenario, or the number and type of devices included in each device, do not affect the overall implementation of the technical solution in the embodiments of the present invention, and can all be regarded as equivalent replacements or derivatives of the technical solution claimed to be protected by the embodiments of the present invention.

[0062] The air conditioning control device 100 in the embodiment of the present invention is mainly used for: responding to an air conditioning control request, collecting a scene image sequence corresponding to an air conditioning operation area; performing mode background modeling on the scene image sequence according to the pixel grayscale values ​​of the scene image sequence to obtain an initial reference background of the scene image sequence; obtaining a local scene operator of a target image block according to the initial reference background and block smoothing in the scene image sequence, and determining a target scene background of the scene image sequence according to the local scene operator; determining target object information according to the target scene background and the scene image sequence, performing air conditioning control according to the target object information, and obtaining an air conditioning control result.

[0063] The air conditioning control device 100 in the embodiment of the present invention can be an independent air conditioning control device, such as a smart terminal such as a mobile phone, tablet computer, network equipment, server and smart computer that is connected to the air conditioner for communication. Optionally, in other embodiments, the air conditioning control device can also be an air conditioning main control module inside the air conditioner.

[0064] The embodiments of the present application provide an air conditioning control method, apparatus, device, and computer-readable storage medium, which are described in detail below.

[0065] It can be understood by those skilled in the art that Figure 1 The application environment shown in is only one of the application scenarios related to the present application solution and does not constitute a limitation on the application scenario of the present application solution. Other application environments may also include Figure 1 More or fewer air conditioning control devices, or air conditioning control network connection relationships shown, such as Figure 1 Only one air conditioning control device is shown. It can be understood that the scenario of the air conditioning control method can also include one or more air conditioning control devices, which is not specifically limited here. The air conditioning control device 100 can also include a memory for storing image data and other data.

[0066] It should be noted that Figure 1 The scene diagram of the air-conditioning control method shown is only an example. The scene of the air-conditioning control method described in the embodiment of the present invention is to more clearly illustrate the technical solution of the embodiment of the present invention, and does not constitute a limitation on the technical solution provided by the embodiment of the present invention.

[0067] Based on the scenario of the above air-conditioning control method, various embodiments of the air-conditioning control method disclosed in the present invention are proposed.

[0068] like Figure 2 As shown, Figure 2 This is a flow chart of an embodiment of an air conditioning control method in an embodiment of the present application. The air conditioning control method includes the following steps 201 to 204:

[0069] 201. In response to an air conditioning control request, a scene image sequence corresponding to an air conditioning operation area is collected;

[0070] The air conditioning control method in this embodiment is applied to air conditioning control equipment, and the type and number of air conditioning control equipment are not specifically limited, that is, the air conditioning control equipment can be one or more intelligent terminals such as mobile phones, tablet computers, network equipment, servers and intelligent computers that are connected to the air conditioner for communication. Optionally, in other embodiments, the air conditioning control equipment can also be an air conditioning main control module inside the air conditioner. Among them, the air conditioner can be a mobile air conditioner, an air conditioning window unit, an air conditioning wall unit, an air conditioning cabinet unit, and other intelligent air conditioners with image acquisition functions.

[0071] Specifically, the air conditioner and the air conditioner control device can respond to the air conditioner control request during operation, wherein the air conditioner control request is a control event that drives the air conditioner to collect a scene image sequence in the air conditioner operation area, and identifies the target object information after modeling the scene image sequence to perform personalized air conditioner control. The triggering method of the air conditioner control request is not specifically limited here, that is, the triggering method of the air conditioner control request can be actively triggered by the user, for example, the user actively triggers the air conditioner control request by clicking the air conditioner control panel or the air conditioner control button in the remote control connected to the air conditioner. Optionally, in other embodiments, the air conditioner control request can also be actively triggered by the air conditioner, for example, an object control process is set in the air conditioner, and the air conditioner control request is actively triggered when the target user object is detected in the air conditioner operation area.

[0072] Specifically, when the air conditioner obtains the air conditioning control request, it also collects the scene image sequence in the air conditioning operation area associated with the air conditioner. Among them, the air conditioning operation area is the air conditioning working area that represents the air conditioning for air and temperature regulation of the air conditioner. In a specific embodiment, the air conditioning operation area can be a kitchen area with a complex background. The scene image sequence is the image information obtained by the air conditioner using a preset image acquisition module to shoot the air conditioning operation area, which may contain target object information associated with the user object. Among them, the preset image acquisition module can be an optical camera module such as an infrared acquisition module and a depth camera module. For example, in a specific embodiment, the air conditioner can collect the scene image sequence in the air conditioning operation area through an infrared image module that is set on the air conditioner or separated from the air conditioner and is in the air conditioning operation area. Optionally, in other embodiments, the image acquisition module can also be set in other smart home appliances in the air conditioning operation area, and the air conditioner is connected to the smart home appliance by communication to obtain the scene image sequence of the air conditioning operation area. Among them, the target object information is the specific action information (such as gesture action information or somatosensory action information) associated with the user object or other target object, which can be associated with the intelligent control of the air conditioner. For example, the target object information may be a specified interaction action being performed by the user object and including specific interaction information.

[0073] 202. Performing mode background modeling on the scene image sequence according to the pixel grayscale values ​​of the scene image sequence to obtain an initial reference background of the scene image sequence;

[0074] Specifically, since the air-conditioning operating area corresponding to the air conditioner may be an indoor operating area with a complex and changeable environment, and the scene image sequence is easily affected by factors such as lighting changes, actor movements and occlusion, it will cause a large impact on the target detection of the scene image sequence in subsequent steps. Therefore, before the air-conditioning control device obtains the air conditioner to determine the target object information, it also performs majority background modeling on the scene image sequence to obtain the initial reference background of the scene image sequence.

[0075] Specifically, after obtaining the pixel grayscale value, the air conditioning control device counts the number of grayscale statistics of the pixel grayscale value in the scene image histogram, sets the pixel grayscale value with the highest statistical number as the reference grayscale value of the scene image sequence, and constructs the initial reference background of the scene image sequence based on each reference grayscale value. The generation formula of the reference grayscale value is as follows:

[0076] B (x,y),f (n)=Max[F (x,y),f (n)]

[0077] Among them, B (x,y),f(n) is the reference gray value, F (x,y),f (n) is the grayscale statistical number of pixel grayscale values.

[0078] Optionally, in order to reduce the modeling complexity of majority background modeling based on pixel grayscale values, the air conditioning control device also performs majority modeling based on the first grayscale value and the second grayscale value in the pixel grayscale value to obtain an initial reference background, thereby reducing the modeling complexity and computational complexity of the initial reference background.

[0079] Specifically, after acquiring the scene image sequence, the air conditioning control device also collects the pixel grayscale value of each scene image frame in the scene image sequence, and counts the pixel grayscale values ​​of each scene image frame to generate a scene image histogram corresponding to the scene image sequence. The pixel grayscale value includes a first grayscale value and a second grayscale value.

[0080] Specifically, after acquiring the scene image histogram corresponding to the scene image sequence, the air conditioning control device also determines the first pixel point of the first scene image frame, the first grayscale value of the first pixel point, and the first statistical quantity of the first grayscale value according to the scene image histogram corresponding to the scene image sequence. The first scene image frame is any image frame other than the current image frame in the scene image sequence. The first pixel point is any pixel point in the first scene image frame. The first grayscale value is the pixel grayscale value with the largest grayscale statistical quantity corresponding to the first pixel point in the image sequence. The first statistical quantity is the statistical quantity of the number of times the first grayscale value appears in the scene image sequence.

[0081] Specifically, the air conditioning control device obtains a scene image histogram corresponding to the scene image sequence, and determines the pixel grayscale value of the first pixel point in the scene image sequence in each scene image frame based on the scene image histogram, and obtains the statistical frequency of the pixel grayscale value in the scene image histogram, determines the grayscale statistical quantity of the pixel grayscale value, and determines the pixel grayscale value with the largest grayscale statistical quantity as the first grayscale value of the first pixel point, and determines the grayscale value statistical quantity as the first statistical quantity of the first grayscale value.

[0082] Specifically, the air conditioning control device also obtains the second pixel point of the second scene image frame in the scene image sequence, as well as the second grayscale value of the second pixel point, and the second statistical quantity corresponding to the second grayscale value. The second scene image frame is the next scene image frame corresponding to the first scene image frame in the scene image sequence. The second pixel point is the image pixel point corresponding to the first pixel point in the second scene image frame. The second grayscale value is the pixel grayscale value of the second pixel point with the largest statistical quantity in the scene image. The second statistical quantity is the statistical quantity of the number of times the second grayscale value appears in the scene image sequence.

[0083] Specifically, after obtaining the first grayscale value and the first statistical quantity of the first grayscale value, the air conditioning control device also obtains the second grayscale value and the second statistical quantity of the second grayscale value, and determines the reference grayscale value by comparing the first statistical quantity and the second statistical quantity, and constructs the initial reference background of the scene image sequence according to each reference grayscale value.

[0084] Optionally, if the second statistical number is less than or equal to the first statistical number, the air conditioning control device determines the reference grayscale values ​​corresponding to the first pixel and the second pixel using the first grayscale value corresponding to the first statistical number, and performs majority modeling on the scene image sequence according to the reference grayscale value to obtain an initial reference background.

[0085] Optionally, if the second statistical number is greater than the first statistical number, the air conditioning control device determines the second grayscale value corresponding to the second statistical number as the reference grayscale value corresponding to the first pixel and the second pixel, and performs majority modeling on the scene image sequence according to the reference grayscale value to obtain an initial reference background.

[0086] 203. A local scene operator of a target image block obtained by block smoothing processing in the initial reference background and the scene image sequence is obtained, and a target scene background of the scene image sequence is determined according to the local scene operator;

[0087] Specifically, after obtaining the initial reference background corresponding to the scene image sequence, the air conditioning control device also performs block smoothing on the scene image sequence according to the initial reference background, thereby obtaining a stable local scene operator of the target image block, and performs secondary modeling based on the local scene operator to determine the target scene background of the scene image sequence. This eliminates most of the interference of dynamic background changes and changes in lighting conditions on the scene background, thereby improving the accuracy of subsequent background recognition.

[0088] Specifically, after acquiring the initial reference background, the air conditioning control device performs block processing on the initial reference background to obtain a reference background image block, and performs block processing on the scene image sequence according to the same block rule to obtain a target image block. That is, in a specific embodiment, the air conditioning control device divides the initial reference background into 9*9 rectangular image blocks, and then divides the rectangular image blocks into 3*3 regional image blocks to obtain reference background image blocks. Similarly, the air conditioning control device divides each scene image frame in the scene image sequence into 9*9 target image blocks, and then divides the target image blocks into 3*3 scene sub-image blocks to obtain target image blocks.

[0089] Specifically, after obtaining the reference background image block and the corresponding target image block, the air conditioning control device further obtains the reference grayscale average value corresponding to the reference background image block and the scene grayscale average value of the target image block, and updates the scene image sequence according to the reference grayscale average value and the scene grayscale average value to obtain an updated image sequence. That is, the air conditioning control device compares the reference grayscale average value with the scene grayscale average value, and then smoothes the target image blocks of the scene image sequence according to the comparison result, thereby obtaining each smoothed target image block, and generates an updated image sequence according to each smoothed target image block.

[0090] Specifically, after acquiring the update image sequence, the air conditioning control device also calculates the local scene operator corresponding to the smoothed target image block in the update scene image sequence, and generates the target scene background of the update image sequence according to the local scene operator. That is, the air conditioning control device performs mode modeling again according to the local scene operator corresponding to each target image block to obtain the target scene background of the update image sequence. Among them, the local scene operator is an LBP (Local Binary Patterns, binary pattern texture) operator.

[0091] 204. Determine target object information according to the target scene background and the scene image sequence, perform air conditioning control according to the target object information, and obtain an air conditioning control result.

[0092] Specifically, after the air-conditioning control device performs multiple background modeling using the grayscale statistics of the scene image sequence and the local scene operator to obtain the target scene background, it also determines the target object information based on the target scene background and the scene image sequence, and performs air-conditioning control based on the target object information to obtain the air-conditioning control result.

[0093] Specifically, after acquiring the target scene background, the air conditioning control device performs target detection on the air conditioning operation area according to the scene image sequence and the target scene background, thereby determining the target object corresponding to the scene image sequence in the air conditioning operation area, and the target object information of the target object. The target object may be a designated user in the air conditioning operation area. The target object information is gesture interaction information or somatosensory interaction information associated with a specific air conditioning control instruction.

[0094] Specifically, after acquiring the target object information, the air-conditioning control device parses the target object information, identifies the air-conditioning control instructions associated with the target object information, and controls the air conditioner through the air-conditioning control instructions, driving the air conditioner to operate according to the operating parameters corresponding to the air-conditioning control instructions, and obtaining the air-conditioning operation results, thereby improving the intelligent control accuracy of the air conditioner and avoiding misoperation of the air conditioner due to incorrect identification of the target object information.

[0095] In this embodiment, the air conditioning control device collects the scene image sequence corresponding to the air conditioning operation area by responding to the air conditioning control request; performs mode background modeling on the scene image sequence according to the pixel grayscale value of the scene image sequence to obtain the initial reference background of the scene image sequence; obtains the local scene operator of the target image block by block smoothing in the initial reference background and the scene image sequence, and determines the target scene background of the scene image sequence according to the local scene operator; determines the target object information according to the target scene background and the scene image sequence, and performs air conditioning control according to the target object information to obtain the air conditioning control result. After obtaining the scene image sequence collected by the air conditioner, background modeling is performed on the scene image sequence to obtain the initial reference background obtained by the initial modeling, and the scene image sequence is subjected to block smoothing according to the initial reference background, and the local scene operator after the block smoothing is obtained, and the target scene background of the scene line graphic sequence is updated according to the local scene operator, thereby improving the recognition accuracy in complex scenes, and then improving the recognition accuracy of subsequent target objects, thereby improving the accuracy of air conditioning interaction.

[0096] like Figure 3 As shown, Figure 3 In the air conditioning control method provided in the embodiment of the present application, the scene image sequence is updated according to the reference grayscale average value and the scene grayscale average value to obtain a flow chart of an embodiment of the updated image sequence. Specifically, in this embodiment, the air conditioning control method further includes steps 301 to 302:

[0097] 301. Calculate the absolute value of the difference between the reference grayscale average value and the scene grayscale average value;

[0098] 302. If the absolute value of the difference is less than a preset difference threshold, update the target image block in the scene image sequence using the reference grayscale average value to obtain an updated image sequence.

[0099] Based on the above embodiments, in this embodiment, after obtaining the reference background image block and the corresponding target image block, the air conditioning control device further obtains the reference grayscale average value corresponding to the reference background image block and the scene grayscale average value of the target image block, and updates the scene image sequence according to the reference grayscale average value and the scene grayscale average value to obtain an updated image sequence.

[0100] Specifically, after acquiring the background image block and the target image block, the air conditioning control device also acquires the background grayscale corresponding to each image pixel in the background image block, and calculates the average value corresponding to each background grayscale in the background image block to obtain the reference grayscale average value of the background image block. In addition, the air conditioning control device also acquires the pixel grayscale corresponding to each image pixel in the target image block, and calculates the average value corresponding to each pixel grayscale in the target image block to obtain the scene grayscale average value of the target image block.

[0101] Specifically, after obtaining the parameter grayscale average value and the scene grayscale average value, the air-conditioning control device also calculates the absolute value of the difference between the reference grayscale average value and the scene grayscale average value, and compares the absolute value of the difference with a preset difference threshold value, thereby updating the target image block in the scene image sequence according to the comparison result, thereby obtaining a smoothed target image block, and updating the scene image sequence based on each smoothed target image block to obtain an updated image sequence.

[0102] Optionally, if the absolute value of the difference is less than a preset difference threshold, the air conditioning control device uses the reference grayscale average value to update the target image block in the scene image sequence, that is, the air conditioning control device sets the reference grayscale average value to the updated scene grayscale average value of the target image block to obtain a smoothed target image block, and updates the scene image sequence according to the smoothed target image block to obtain an updated image sequence.

[0103] Optionally, if the absolute value of the difference is greater than a preset difference threshold, the air conditioning control device obtains the neighborhood grayscale value of the target image block, uses the neighborhood grayscale value to update the target image block to obtain a smoothed target image block, and updates the scene image sequence according to the smoothed target image block to obtain an updated image sequence.

[0104] Specifically, after acquiring the update image sequence, the air conditioning control device also calculates the local scene operator corresponding to the smoothed target image block in the update scene image sequence, and generates the target scene background of the update image sequence according to the local scene operator. That is, the air conditioning control device performs mode modeling again according to the local scene operator corresponding to each target image block to obtain the target scene background of the update image sequence.

[0105] In this embodiment, the air conditioning control device calculates the absolute value of the difference between the reference grayscale average value and the scene grayscale average value; if the absolute value of the difference is less than the preset difference threshold, the reference grayscale average value is used to update the target image block in the scene image sequence to obtain an updated image sequence; if the absolute value of the difference is greater than the preset difference threshold, the target image block in the scene image sequence is updated based on the neighborhood grayscale value of the target image block to obtain an updated image sequence. Before calculating the local scene operator to determine the target scene background, the target image block is smoothed using neighborhood feature information such as the reference grayscale average value and the scene grayscale average value, thereby improving the anti-noise performance during subsequent modeling.

[0106] like Figure 4 As shown, Figure 4 This is a flow chart of an embodiment of determining a target scene background of a scene image sequence by using a local scene operator in the air conditioning control method provided in the embodiment of the present application. Specifically, in this embodiment, the air conditioning control method further includes steps 401 to 404:

[0107] 401. Obtain the grayscale value of the central pixel and the grayscale values ​​of the neighboring pixels of the target image block;

[0108] 402. Perform thresholding processing on the grayscale value of the neighborhood pixels according to the grayscale value of the central pixel to obtain an initial scene operator;

[0109] 403. Performing base conversion on the initial scene operator to obtain a local scene operator corresponding to the target image block;

[0110] 404. Generate a local operator histogram corresponding to an updated scene sequence according to the local scene operator, and perform mode background modeling on the updated image sequence according to the local operator histogram to obtain a target scene background.

[0111] Based on the above embodiment, in this embodiment, after acquiring the update image sequence, the air conditioning control device further calculates the local scene operator corresponding to the smoothed target image block in the update scene image sequence, and generates the target scene background of the update image sequence according to the local scene operator. That is, the air conditioning control device performs mode modeling again according to the local scene operator corresponding to each target image block to obtain the target scene background of the update image sequence.

[0112] Specifically, the air conditioning control device obtains the central grayscale value and the neighborhood grayscale value of the target image block in the updated image sequence. The central grayscale value is the pixel grayscale value corresponding to the central pixel of the target image block. The neighborhood grayscale value is the pixel grayscale value corresponding to the remaining pixels adjacent to the central pixel in the target image block. For example, in a specific embodiment, the target image block is a nine-square grid image block with a specification of 3*3 pixels. For example, the pixel schematic diagram of the target image block is as follows:

[0113]

[0114] Among them, 1 to 9 correspond to a pixel point in the target image block respectively, pixel point 5 is the central pixel point of the target image block, and the remaining pixel points in the target image block are all neighborhood pixel points of pixel point 5. The air conditioning control device determines the pixel grayscale value corresponding to pixel point 5 as the central pixel grayscale value of the target image block, and the pixel grayscale values ​​corresponding to the remaining pixel points are determined as the neighborhood pixel grayscale values ​​of the target image block.

[0115] Specifically, after obtaining the grayscale value of the central pixel and the grayscale value of the neighboring pixels, the air conditioning control device also performs threshold processing according to the grayscale value of the central pixel and the grayscale value of the neighboring pixels to obtain an initial scene operator, that is, the air conditioning control device performs local binary pattern processing on the grayscale value of the central pixel and the grayscale value of the neighboring pixels to obtain an initial scene operator, wherein the calculation formula corresponding to the initial scene operator is as follows:

[0116]

[0117] Among them, h C is the gray value of the center pixel, h N is the gray value of the neighborhood pixels.

[0118] That is, after obtaining the grayscale value of the center pixel and the grayscale value of the neighborhood pixel, the air conditioning control device also performs differential processing based on the grayscale value of the center pixel and the grayscale value of the neighborhood pixel. If the grayscale value of the neighborhood pixel is greater than the grayscale value of the center pixel, the grayscale value of the neighborhood pixel is recorded as 1, and if the grayscale value of the neighborhood pixel is less than the grayscale value of the center pixel, the grayscale value of the neighborhood pixel is recorded as 0, so as to generate a binary initial scene operator. In a specific embodiment, the target image block is a scene image block with a specification of 3*3 pixels, and the corresponding initial scene operator is an eight-bit binary parameter.

[0119] Specifically, after acquiring the initial scene operator, the air conditioning control device also performs base conversion on the initial scene operator, converting the initial scene operator into a decimal number to obtain a local scene operator corresponding to the target image block.

[0120] Specifically, after obtaining the local scene operator corresponding to each target image block, the air conditioning control device generates a local operator histogram corresponding to the local scene operator, and performs mode background modeling on the updated image sequence according to the local operator histogram to obtain the target scene background. That is, the air conditioning control device reads the local scene operator corresponding to any target pixel in the updated image sequence in different scene image frames according to the local operator histogram, determines the scene local operator with the largest number of occurrences as the background scene operator corresponding to the target pixel, summarizes the background scene operator of each target pixel, and obtains the target scene background of the updated image sequence.

[0121] In this embodiment, the air conditioning control device obtains the grayscale value of the central pixel and the grayscale value of the neighboring pixels of the target image block; performs thresholding on the grayscale value of the neighboring pixels according to the grayscale value of the central pixel to obtain the initial scene operator; performs base conversion on the initial scene operator to obtain the local scene operator corresponding to the target image block; generates a local operator histogram corresponding to the updated scene sequence according to the local scene operator, performs mode background modeling on the updated image sequence according to the local operator histogram, and obtains the target scene background. This achieves background modeling without relying on prior information, and can eliminate most of the interference effects of dynamic background changes and lighting conditions on image recognition, thereby improving the accuracy of target object recognition in subsequent complex environments.

[0122] In order to better implement the air conditioning control method in the embodiment of the present application, based on the air conditioning control method, an air conditioning control device is also provided in the embodiment of the present application, such as Figure 5 As shown, Figure 5 The structure diagram of the air conditioning control device provided in the embodiment of the present application is as follows. Specifically, the air conditioning control device 500 includes:

[0123] The image acquisition module 501 is configured to respond to the air conditioning control request and collect a scene image sequence corresponding to the air conditioning operation area;

[0124] A background reference module 502 is configured to perform mode background modeling on the scene image sequence according to the pixel grayscale values ​​of the scene image sequence to obtain an initial reference background of the scene image sequence;

[0125] A background updating module 503 is configured to determine a target scene background of the scene image sequence according to the initial reference background and a target image block obtained by block smoothing in the scene image sequence;

[0126] The air conditioning control module 504 is configured to determine target object information according to the target scene background and the scene image sequence, perform air conditioning control according to the target object information, and obtain an air conditioning control result.

[0127] In a possible implementation of this embodiment, the air conditioning control device performs mode background modeling on the scene image sequence according to the pixel grayscale values ​​of the scene image sequence to obtain an initial reference background of the scene image sequence, including:

[0128] Determining a first pixel of a first scene image frame, a first grayscale value of the first pixel, and a first statistical quantity of the first grayscale value based on a scene image histogram corresponding to the scene image sequence;

[0129] Acquire a second pixel of a second scene image frame in the scene image sequence, as well as a second grayscale value of the second pixel and a second statistical quantity corresponding to the second grayscale value;

[0130] If the second statistical quantity is less than or equal to the first statistical quantity, performing mode modeling on the scene image sequence according to the first grayscale value to obtain an initial reference background;

[0131] If the second statistical quantity is greater than the first statistical quantity, mode modeling is performed on the scene image sequence according to the second grayscale value to obtain an initial reference background.

[0132] In a possible implementation of this embodiment, the air conditioning control device determines a first pixel point of a first scene image frame, a first grayscale value of the first pixel point, and a first statistical quantity of the first grayscale value based on a scene image histogram corresponding to the scene image sequence, including:

[0133] Obtaining a scene image histogram corresponding to the scene image sequence;

[0134] Determining a pixel grayscale value of a first pixel in the scene image sequence according to the scene image histogram;

[0135] Obtaining the statistical frequency of the pixel grayscale value in the scene image histogram to obtain the grayscale statistical quantity of the pixel grayscale value;

[0136] The grayscale value of the pixel with the largest grayscale statistical quantity is determined as the first grayscale value of the first pixel, and the grayscale statistical quantity is determined as the first statistical quantity of the first grayscale value.

[0137] In a possible implementation of this embodiment, the air conditioning control device obtains a local scene operator of a target image block by block smoothing processing in the initial reference background and the scene image sequence, and determines the target scene background of the scene image sequence according to the local scene operator, including:

[0138] The initial reference background is processed by dividing into blocks to obtain reference background image blocks, and the scene image sequence is processed by dividing into blocks to obtain target image blocks;

[0139] Obtaining a reference grayscale average value corresponding to the reference background image block and a scene grayscale average value of the target image block;

[0140] The scene image sequence is updated according to the reference grayscale average value and the scene grayscale average value to obtain an updated image sequence;

[0141] A local scene operator corresponding to a target image block in an updated scene image sequence is calculated, and a target scene background of the updated image sequence is generated according to the local scene operator.

[0142] In a possible implementation of this embodiment, the air conditioning control device updates the scene image sequence according to the reference grayscale average value and the scene grayscale average value to obtain an updated image sequence, including:

[0143] Calculating the absolute value of the difference between the reference grayscale average value and the scene grayscale average value;

[0144] If the absolute value of the difference is less than a preset difference threshold, the target image block in the scene image sequence is updated using the reference grayscale average value to obtain an updated image sequence; if the absolute value of the difference is greater than the preset difference threshold, the target image block in the scene image sequence is updated based on the neighborhood grayscale value of the target image block to obtain an updated image sequence.

[0145] In a possible implementation of this embodiment, the air conditioning control device obtains a local scene operator of a target image block by block smoothing processing in the initial reference background and the scene image sequence, and determines the target scene background of the scene image sequence according to the local scene operator, including:

[0146] Obtaining the grayscale value of the central pixel and the grayscale values ​​of the neighboring pixels of the target image block;

[0147] Thresholding the grayscale value of the neighborhood pixels according to the grayscale value of the central pixel to obtain an initial scene operator;

[0148] Performing base conversion on the initial scene operator to obtain a local scene operator corresponding to the target image block;

[0149] A local operator histogram corresponding to an updated scene sequence is generated according to the local scene operator, and mode background modeling is performed on the updated image sequence according to the local operator histogram to obtain a target scene background.

[0150] In a possible implementation of this embodiment, the air conditioning control device performs air conditioning control according to the target object information to obtain an air conditioning control result, including:

[0151] Performing target detection based on the target scene background and the scene image sequence to obtain target object information in the scene image sequence;

[0152] An air-conditioning control instruction corresponding to the target object information is identified, and air-conditioning control is performed based on the air-conditioning control instruction to obtain an air-conditioning control result.

[0153] In this embodiment, the air conditioning control device collects the scene image sequence corresponding to the air conditioning operation area by responding to the air conditioning control request; performs mode background modeling on the scene image sequence according to the pixel grayscale value of the scene image sequence to obtain the initial reference background of the scene image sequence; obtains the local scene operator of the target image block by block smoothing in the initial reference background and the scene image sequence, and determines the target scene background of the scene image sequence according to the local scene operator; determines the target object information according to the target scene background and the scene image sequence, and performs air conditioning control according to the target object information to obtain the air conditioning control result. After obtaining the scene image sequence collected by the air conditioner, background modeling is performed on the scene image sequence to obtain the initial reference background obtained by the initial modeling, and the scene image sequence is subjected to block smoothing according to the initial reference background, and the local scene operator after the block smoothing is obtained, and the target scene background of the scene line graphic sequence is updated according to the local scene operator, thereby improving the recognition accuracy in complex scenes, and then improving the recognition accuracy of subsequent target objects, thereby improving the accuracy of air conditioning interaction.

[0154] The embodiment of the present invention also provides an air conditioning control device, such as Figure 6 As shown, Figure 6 This is a schematic diagram of the structure of an embodiment of the air conditioning control device provided in the embodiments of the present application.

[0155] The air conditioning control device integrates any one of the air conditioning control devices provided in the embodiments of the present invention, and the air conditioning control device includes:

[0156] one or more processors;

[0157] Memory; and

[0158] One or more applications, wherein the one or more applications are stored in the memory and are configured so that the processor executes the steps of the air conditioning control method described in any of the above air conditioning control method embodiments.

[0159] Specifically, the air conditioning control device may include one or more processing core processors 601, one or more computer-readable storage media memories 602, a power supply 603, an input unit 604 and other components. Those skilled in the art will understand that Figure 6 The air conditioning control device structure shown in the figure does not constitute a limitation on the air conditioning control device, and may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently. Among them:

[0160] The processor 601 is the control center of the air conditioning control device. It uses various interfaces and lines to connect various parts of the entire air conditioning control device. By running or executing software programs and / or modules stored in the memory 602, and calling data stored in the memory 602, it performs various functions of the air conditioning control device and processes data, thereby monitoring the air conditioning control device as a whole. Optionally, the processor 601 may include one or more processing cores; preferably, the processor 601 may integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, user interface, and application programs, and the modem processor mainly processes wireless communications. It is understandable that the above-mentioned modem processor may not be integrated into the processor 601.

[0161] The memory 602 can be used to store software programs and modules. The processor 601 executes various functional applications and data processing by running the software programs and modules stored in the memory 602. The memory 602 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area may store data created according to the use of the air conditioning control device, etc. In addition, the memory 602 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage devices. Accordingly, the memory 602 may also include a memory controller to provide the processor 601 with access to the memory 602.

[0162] The air conditioning control device also includes a power supply 603 for supplying power to various components. Preferably, the power supply 603 can be logically connected to the processor 601 through a power management system, so as to realize functions such as management of charging, discharging, and power consumption management through the power management system. The power supply 603 can also include any components such as one or more DC or AC power supplies, recharging systems, power failure detection circuits, power converters or inverters, and power status indicators.

[0163] The air conditioning control device may further include an input unit 604, which may be used to receive input digital or character information and generate keyboard, mouse, joystick, optical or trackball signal input related to user settings and function control.

[0164] Although not shown, the air conditioning control device may further include a display unit, etc., which will not be described in detail herein. Specifically in this embodiment, the processor 601 in the air conditioning control device will load the executable files corresponding to the processes of one or more application programs into the memory 602 according to the following instructions, and the processor 601 will run the application programs stored in the memory 602, thereby realizing various functions, as follows:

[0165] In response to the air conditioning control request, a scene image sequence corresponding to the air conditioning operation area is collected;

[0166] Performing mode background modeling on the scene image sequence according to the pixel grayscale values ​​of the scene image sequence to obtain an initial reference background of the scene image sequence;

[0167] A local scene operator of a target image block obtained by block smoothing processing in the initial reference background and the scene image sequence, and a target scene background of the scene image sequence is determined according to the local scene operator;

[0168] Target object information is determined according to the target scene background and the scene image sequence, and air-conditioning control is performed according to the target object information to obtain an air-conditioning control result.

[0169] To this end, an embodiment of the present invention provides a computer-readable storage medium, which may include: a read-only memory (ROM), a random access memory (RAM), a disk or an optical disk, etc. A computer program is stored thereon, and the computer program is loaded by a processor to execute the steps in any of the air conditioning control methods provided in the embodiments of the present invention. For example, the computer program can be loaded by the processor to execute the following steps:

[0170] In response to the air conditioning control request, a scene image sequence corresponding to the air conditioning operation area is collected;

[0171] Performing mode background modeling on the scene image sequence according to the pixel grayscale values ​​of the scene image sequence to obtain an initial reference background of the scene image sequence;

[0172] A local scene operator of a target image block obtained by block smoothing processing in the initial reference background and the scene image sequence, and a target scene background of the scene image sequence is determined according to the local scene operator;

[0173] Target object information is determined according to the target scene background and the scene image sequence, and air-conditioning control is performed according to the target object information to obtain an air-conditioning control result.

[0174] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, please refer to the detailed description of other embodiments above, and will not be repeated here.

[0175] In specific implementation, the above units or structures can be implemented as independent entities, or can be arbitrarily combined to be implemented as the same or several entities. The specific implementation of the above units or structures can refer to the previous method embodiments, which will not be repeated here.

[0176] The specific implementation of the above operations can be found in the previous embodiments, which will not be described in detail here.

[0177] The above is a detailed introduction to an air conditioning control method provided in an embodiment of the present application. Specific embodiments are used herein to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea. At the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims

1. An air conditioning control method, characterized in that: The air conditioning control method comprises: In response to the air conditioning control request, a scene image sequence corresponding to the air conditioning operation area is collected; Performing mode background modeling on the scene image sequence according to the pixel grayscale values ​​of the scene image sequence to obtain an initial reference background of the scene image sequence; A local scene operator of a target image block obtained by block smoothing processing in the initial reference background and the scene image sequence, and a target scene background of the scene image sequence is determined according to the local scene operator; Target object information is determined according to the target scene background and the scene image sequence, and air-conditioning control is performed according to the target object information to obtain an air-conditioning control result.

2. The air conditioning control method according to claim 1, characterized in that: The pixel grayscale value includes a first grayscale value and a second grayscale value; The performing mode background modeling on the scene image sequence according to the pixel grayscale values ​​of the scene image sequence to obtain an initial reference background of the scene image sequence includes: Determining a first pixel of a first scene image frame, a first grayscale value of the first pixel, and a first statistical quantity of the first grayscale value based on a scene image histogram corresponding to the scene image sequence; Acquire a second pixel of a second scene image frame in the scene image sequence, as well as a second grayscale value of the second pixel and a second statistical quantity corresponding to the second grayscale value; If the second statistical quantity is less than or equal to the first statistical quantity, performing mode modeling on the scene image sequence according to the first grayscale value to obtain an initial reference background; If the second statistical quantity is greater than the first statistical quantity, mode modeling is performed on the scene image sequence according to the second grayscale value to obtain an initial reference background.

3. The air conditioning control method according to claim 2, characterized in that: The determining, based on the scene image histogram corresponding to the scene image sequence, a first pixel point of the first scene image frame, a first grayscale value of the first pixel point, and a first statistical quantity of the first grayscale value, comprises: Obtaining a scene image histogram corresponding to the scene image sequence; Determining a pixel grayscale value of a first pixel in the scene image sequence according to the scene image histogram; Obtaining the statistical frequency of the pixel grayscale value in the scene image histogram to obtain the grayscale statistical quantity of the pixel grayscale value; The grayscale value of the pixel with the largest grayscale statistical quantity is determined as the first grayscale value of the first pixel, and the grayscale statistical quantity is determined as the first statistical quantity of the first grayscale value.

4. The air conditioning control method according to claim 1, characterized in that: The method of obtaining a local scene operator of a target image block by block smoothing according to the initial reference background and the scene image sequence, and determining a target scene background of the scene image sequence according to the local scene operator comprises: The initial reference background is processed by dividing into blocks to obtain reference background image blocks, and the scene image sequence is processed by dividing into blocks to obtain target image blocks; Obtaining a reference grayscale average value corresponding to the reference background image block and a scene grayscale average value of the target image block; The scene image sequence is updated according to the reference grayscale average value and the scene grayscale average value to obtain an updated image sequence; A local scene operator corresponding to a target image block in an updated scene image sequence is calculated, and a target scene background of the updated image sequence is generated according to the local scene operator.

5. The air conditioning control method according to claim 4, characterized in that: The updating of the scene image sequence according to the reference grayscale average value and the scene grayscale average value to obtain an updated image sequence includes: Calculating the absolute value of the difference between the reference grayscale average value and the scene grayscale average value; If the absolute value of the difference is less than a preset difference threshold, the target image block in the scene image sequence is updated using the reference grayscale average value to obtain an updated image sequence; If the absolute value of the difference is greater than a preset difference threshold, the target image block in the scene image sequence is updated based on the neighborhood grayscale value of the target image block to obtain an updated image sequence.

6. The air conditioning control method according to claim 4, characterized in that: The method of obtaining a local scene operator of a target image block by block smoothing according to the initial reference background and the scene image sequence, and determining a target scene background of the scene image sequence according to the local scene operator comprises: Obtaining the grayscale value of the central pixel and the grayscale values ​​of the neighboring pixels of the target image block; Thresholding the grayscale value of the neighborhood pixels according to the grayscale value of the central pixel to obtain an initial scene operator; Performing base conversion on the initial scene operator to obtain a local scene operator corresponding to the target image block; A local operator histogram corresponding to an updated scene sequence is generated according to the local scene operator, and mode background modeling is performed on the updated image sequence according to the local operator histogram to obtain a target scene background.

7. The air conditioning control method according to any one of claims 1 to 6, characterized in that: The performing air conditioning control according to the target object information to obtain an air conditioning control result includes: Performing target detection based on the target scene background and the scene image sequence to obtain target object information in the scene image sequence; An air-conditioning control instruction corresponding to the target object information is identified, and air-conditioning control is performed based on the air-conditioning control instruction to obtain an air-conditioning control result.

8. An air conditioning control device, characterized in that: The air conditioning control device comprises: An image acquisition module is configured to respond to an air conditioning control request and collect a scene image sequence corresponding to an air conditioning operation area; A background reference module is configured to perform mode background modeling on the scene image sequence according to the pixel grayscale values ​​of the scene image sequence to obtain an initial reference background of the scene image sequence; A background updating module, configured to determine a target scene background of the scene image sequence according to the initial reference background and a target image block obtained by block smoothing in the scene image sequence; The air conditioning control module is configured to determine target object information according to the target scene background and the scene image sequence, perform air conditioning control according to the target object information, and obtain an air conditioning control result.

9. An air conditioning control device, characterized in that: The air conditioning control device comprises: one or more processors; Memory; and One or more applications, wherein the one or more applications are stored in the memory and are configured to be executed by the processor to implement the steps of the air conditioning control method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and the computer program is loaded by a processor to execute the steps of the air conditioning control method according to any one of claims 1 to 7.

Citation Information

Patent Citations

  • Gesture verification method and device for controlling air conditioners

    CN106569600A

  • Background difference and iteration searching-based status recognition method of high-voltage isolation switch

    CN108334824A

  • Moving target detection method and system combined with foreground contour extraction

    CN116071392A

  • Method of recognizing object based on pattern matching and medium for recording computer program having same

    US7058221B1