Air conditioner control method and device, air conditioner and storage medium

Abstract

The application provides an air conditioner control method and device, an air conditioner and a storage medium. The air conditioner control method comprises: in response to an air conditioner control request, acquiring initial image information in an air conditioner operating area; performing background analysis on the initial image information to determine foreground object information of the initial image information; performing image processing on the foreground object information according to an object projection curve associated with the foreground object information to obtain target object information; identifying object state information corresponding to the target object information, and adjusting air conditioner operating parameters corresponding to the air conditioner operating area according to the object state information. The technical solution of the application can accurately identify target objects existing in an operating scene that are adhered or blocked by using an air conditioner, improve the identification accuracy of the target objects, and further improve the control accuracy of personalized air conditioner control depending on the target identification result, thereby improving the air conditioner use experience of a user.

Description

Technical Field

[0001] This application relates to the field of air conditioning control technology, specifically to an air conditioning control method, device, air conditioner, and storage medium. Background Technology

[0002] Currently, with the rapid development of air conditioner and image recognition technology, more and more air conditioner devices have object recognition functions. During operation, they use object recognition to detect object information in the working environment for more intelligent control. However, when existing air conditioner devices perform object recognition, abnormal situations such as target loss or misidentification are prone to occur due to image information sticking or being occluded, resulting in poor object recognition accuracy and thus inability to perform corresponding operations more accurately. Summary of the Invention

[0003] This application provides an air conditioning control method, device, air conditioner, and storage medium, aiming to solve the technical problem in the prior art where intelligent devices such as air conditioners suffer from poor recognition accuracy due to abnormal situations such as image information sticking or being occluded, resulting in target loss or misidentification.

[0004] On one hand, embodiments of this application provide an air conditioning control method, which includes the following steps:

[0005] Responding to air conditioning control requests, it acquires initial image information of the air conditioning operating area;

[0006] Background analysis is performed on the initial image information to determine the foreground object information of the initial image information;

[0007] Image processing is performed on the foreground object information based on the object projection curve associated with the foreground object information to obtain the target object information;

[0008] Identify the object status information corresponding to the target object information, and adjust the air conditioning operating parameters corresponding to the air conditioning operating area according to the object status information.

[0009] In one possible implementation of this application, the step of performing background analysis on the initial image information to determine the foreground object information of the initial image information includes:

[0010] The initial image information is modeled using a historical foreground mask to obtain the target background image information of the initial image information;

[0011] Segment the target foreground image information in the initial image information based on the initial image information and the target background image information;

[0012] The target foreground image information is detected using a preset object detection model to determine the foreground object information of the initial image information.

[0013] In one possible implementation of this application, the step of using a historical foreground mask to perform background modeling on the initial image information to obtain the target background image information of the initial image information includes:

[0014] Access the air conditioner image database to obtain the historical foreground mask of the air conditioner operating area;

[0015] The initial image information is modeled according to a preset background recognition model to obtain the initial background image information;

[0016] The initial background image information is updated based on the historical foreground mask and the preset background detection threshold to obtain the target background image information.

[0017] In one possible implementation of this application, updating the initial background image information based on the historical foreground mask and a preset background detection threshold to obtain the target background image information includes:

[0018] Obtain the mask pixels in the historical foreground mask;

[0019] If the mask pixel value of the mask pixel is less than the background detection threshold, then the mask pixel is determined to be a background pixel.

[0020] If the mask pixel value of the mask pixel is greater than the background detection threshold, then the mask pixel is determined to be a foreground pixel.

[0021] The initial background image information is updated based on the background pixels and the foreground pixels to obtain the target background image information.

[0022] In one possible implementation of this application, the step of performing image processing on the foreground object information based on the object projection curve associated with the foreground object information to obtain the target object information includes:

[0023] Morphological processing is performed on the foreground object information to obtain the object feature image of the foreground object information;

[0024] Projection processing is performed on the feature pixel values ​​in the object feature image to obtain the object projection curve of the foreground object information;

[0025] Based on the object projection curve, occlusion detection is performed on the foreground object information to determine the target object information in the foreground object information.

[0026] In one possible implementation of this application, the step of performing projection processing based on the feature pixel values ​​in the object feature image to obtain the object projection curve of the foreground object information includes:

[0027] Obtain feature pixel values ​​from the object feature image, wherein the feature pixel values ​​include horizontal feature pixel values ​​and vertical feature pixel values;

[0028] Pixel projection is performed based on the horizontal feature pixel values ​​to obtain the object projection curve of the foreground object information.

[0029] In one possible implementation of this application, the step of performing occlusion detection on the foreground object information based on the object projection curve to determine the target object information in the foreground object information includes:

[0030] Boundary point detection is performed based on the object projection curve to obtain the target boundary points of the object projection curve, including peak boundary points and trough boundary points.

[0031] Based on the peak boundary points and the trough boundary points, occlusion detection is performed on the foreground object information to determine the object occlusion information in the foreground object information;

[0032] Based on the object occlusion information, the foreground object information is segmented to obtain the target object information in the foreground object information.

[0033] In one possible implementation of this application, the step of identifying the object status information corresponding to the target object information and adjusting the air conditioning operating parameters corresponding to the air conditioning operating area according to the object status information includes:

[0034] Perform state detection on the target object information to obtain the object state information corresponding to the target object information;

[0035] Access the air conditioning operation database to obtain the air conditioning correction parameters associated with the object status information in the air conditioning operation database;

[0036] Adjust the air conditioning operating parameters corresponding to the air conditioning operating area according to the air conditioning correction parameters to obtain the air conditioning correction result.

[0037] On the other hand, this application provides an air conditioning control device, the air conditioning control device comprising:

[0038] The image acquisition module is configured to acquire initial image information of the air conditioning operating area in response to an air conditioning control request.

[0039] An image segmentation module is configured to perform background analysis on the initial image information to determine the foreground object information of the initial image information;

[0040] The image processing module is configured to perform image processing on the foreground object information based on the object projection curve associated with the foreground object information to obtain target object information;

[0041] The air conditioning control module is configured to identify the object status information corresponding to the target object information and adjust the air conditioning operating parameters corresponding to the air conditioning operating area according to the object status information.

[0042] On the other hand, this application also provides an air conditioner, the air conditioner comprising:

[0043] One or more processors;

[0044] Memory; and

[0045] 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.

[0046] On the other hand, this application also provides a computer-readable storage medium having a computer program stored thereon, the computer program being loaded by a processor to execute the steps in the air conditioning control method.

[0047] This application acquires initial image information of the air conditioning operating area in response to an air conditioning control request; performs background analysis on the initial image information to determine foreground object information; processes the foreground object information based on the object projection curve associated with the foreground object information to obtain target object information; identifies the object state information corresponding to the target object information; and adjusts the air conditioning operating parameters corresponding to the air conditioning operating area according to the object state information. This enables the air conditioner to extract foreground object information containing user objects from the image information when acquiring image information in the air conditioning operating area. Furthermore, it utilizes the object projection curve associated with the foreground object information to determine whether the foreground image information is stuck or occluded, processes the foreground object information to obtain separated target object information, and corrects the air conditioner parameters based on the object state information of the target object information. This allows for accurate identification of stuck or occluded target objects in the operating scene by the air conditioner, improving the accuracy of target object identification and thus enhancing the control accuracy of personalized air conditioning control based on target identification results, ultimately improving the user's air conditioning experience. Attached Figure Description

[0048] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used 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 effort.

[0049] Figure 1 This is a schematic diagram of a scenario for the air conditioning control method according to an embodiment of this application;

[0050] Figure 2 This is a flowchart illustrating one embodiment of the air conditioning control method in this application.

[0051] Figure 3 This is a schematic diagram of an embodiment of the air conditioning control method provided in this application, which generates an object feature image by performing morphological processing on the information of the adhered foreground object.

[0052] Figure 4 This is a flowchart illustrating an embodiment of the air conditioning control method for determining target background image information provided in this application.

[0053] Figure 5 A flowchart illustrating an embodiment of the air conditioning control method provided in this application for occlusion detection;

[0054] Figure 6 A schematic diagram of the structure of one embodiment of the air conditioning control device provided in this application;

[0055] Figure 7 This is a schematic diagram of the structure of one embodiment of the air conditioner provided in this application. Detailed Implementation

[0056] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0057] In the description of this invention, it should be understood that the terms "center," "longitudinal," "lateral," "length," "width," "thickness," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," and "outer," etc., indicating orientation or positional relationships based on the orientation or positional relationships shown in the accompanying drawings, are only for the convenience of describing the invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the invention. Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, features defined with "first" and "second" may explicitly or implicitly include one or more of the stated features. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0058] In this application, the term "exemplary" is used to mean "serving as an example, illustration, or description." Any embodiment described as "exemplary" in this application is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is provided to enable any person skilled in the art to make and use the invention. Details are set forth in the following description for purposes of explanation. It should be understood that those skilled in the art will recognize that the invention can be made without using these specific details. In other instances, well-known structures and processes will not be described in detail to avoid obscuring the description of the invention with unnecessary detail. Therefore, the invention is not intended to be limited to the embodiments shown, but is consistent with the broadest scope of the principles and features disclosed in this application.

[0059] Currently, with the rapid development of air conditioner and image recognition technology, more and more air conditioner devices have object recognition functions. During operation, they use object recognition to detect object information in the working environment for more intelligent control. However, when existing air conditioner devices perform object recognition, abnormal situations such as target loss or misidentification are prone to occur due to image information sticking or being occluded, resulting in poor object recognition accuracy and thus inability to perform corresponding operations more accurately.

[0060] Based on this, this application proposes an air conditioning control method, apparatus, device, and computer-readable storage medium to solve the technical problem in the prior art where intelligent devices such as air conditioners suffer from poor recognition accuracy due to abnormal situations such as target loss or misidentification caused by image information adhesion or occlusion during image recognition.

[0061] The air conditioning control method in this embodiment of the invention is applied to an air conditioning control device, which is installed in an air conditioner. The air conditioner is equipped with one or more processors, a memory, and one or more application programs. The one or more application programs are stored in the memory and configured to be executed by the processor to implement the air conditioning control method. The air conditioner can be a smart terminal, such as a mobile phone, tablet computer, network device, and smart computer. Optionally, the air conditioner can also be a server or a service cluster composed of multiple servers.

[0062] like Figure 1 As shown, Figure 1 This is a schematic diagram of a scenario for an air conditioning control method according to an embodiment of the present application. The air conditioning control scenario in this embodiment includes an air conditioner 100 (the air conditioner 100 integrates an air conditioning control device), and the air conditioner 100 has a computer-readable storage medium corresponding to the air conditioning control method running in it to execute the steps of the air conditioning control method.

[0063] Understandable, Figure 1 The air conditioner in the air conditioning control method scenario shown, or the device contained in the air conditioner, does not constitute a limitation on the embodiments of the present invention. That is, the number or type of air conditioner in the air conditioning control method scenario, or the number or type of device contained in each device, does not affect the overall implementation of the technical solution in the embodiments of the present invention, and can all be considered as equivalent substitutions or derivatives of the technical solutions claimed in the embodiments of the present invention.

[0064] In this embodiment of the invention, the air conditioner 100 is mainly used to: respond to an air conditioning control request and obtain initial image information of the air conditioning operating area;

[0065] Background analysis is performed on the initial image information to determine the foreground object information of the initial image information;

[0066] Image processing is performed on the foreground object information based on the object projection curve associated with the foreground object information to obtain the target object information;

[0067] Identify the object status information corresponding to the target object information, and adjust the air conditioning operating parameters corresponding to the air conditioning operating area according to the object status information.

[0068] In this embodiment of the invention, the air conditioner 100 can be an independent air conditioner, such as a portable air conditioner, a window air conditioner, a wall-mounted air conditioner, and a cabinet air conditioner, or it can be an air conditioning control network or an air conditioning control cluster composed of multiple air conditioners.

[0069] This application provides an air conditioning control method, apparatus, device, and computer-readable storage medium, which will be described in detail below.

[0070] It will be understood by those skilled in the art that Figure 1 The application environment shown is only one application scenario related to the solution of this application and does not constitute a limitation on the application scenario of this application. Other application environments may include more than one application scenario. Figure 1 The number of more or fewer air conditioners shown, or the air conditioning control network connections, for example Figure 1 Only one air conditioner is shown in the image. It is understood that the scenario of the air conditioning control method may also include one or more air conditioners, which is not limited here. The air conditioner 100 may also include a memory for storing image data and other data.

[0071] It should be noted that, Figure 1 The schematic diagram of the air conditioning control method shown is merely an example. The scenarios of the air conditioning control method described in the embodiments of the present invention are intended to more clearly illustrate the technical solutions of the embodiments of the present invention and do not constitute a limitation on the technical solutions provided in the embodiments of the present invention.

[0072] Based on the scenarios described above for air conditioning control methods, various embodiments of the air conditioning control method disclosed in this invention are proposed.

[0073] like Figure 2 As shown, Figure 2 This is a flowchart illustrating one embodiment of the air conditioning control method in this application. The air conditioning control method includes the following steps 201 to 204:

[0074] 201. Respond to the air conditioning control request and obtain initial image information of the air conditioning operating area;

[0075] The air conditioning control method in this embodiment is applied to an air conditioner. The type and number of air conditioners are not specifically limited. That is, the air conditioner can be any one of various intelligent air conditioners such as one or more portable air conditioners, window air conditioners, wall-mounted air conditioners, and floor-standing air conditioners.

[0076] Specifically, during operation, the air conditioner can respond to air conditioning control requests. These requests involve the air conditioner collecting information about target objects within the air conditioning operating area and using this information to execute personalized air conditioning control events. The triggering method for these control requests is not specifically limited here; they can be triggered by the user, such as clicking the control button on the air conditioner's control panel or a remote control connected to the air conditioner. Optionally, in other embodiments, the air conditioning control requests can also be triggered by the air conditioner itself. For example, if the air conditioner has a human image control process, it can trigger the control request when a target user object is detected in the air conditioning operating area.

[0077] Specifically, when the air conditioner receives an air conditioning control request, it also collects initial image information of the air conditioning operating area associated with the air conditioner. This air conditioning operating area represents the area where the air conditioner regulates air and temperature. The initial image information is obtained by the air conditioner using a preset image acquisition module to capture images of the air conditioning operating area, and may include information about target objects such as users. This preset image acquisition module can be an optical imaging module such as an infrared acquisition module or a depth camera module. For example, in one specific embodiment, the air conditioner can collect the initial image information of the air conditioning operating area using an infrared image module installed on the air conditioner or installed in a distance from the air conditioner and located within the air conditioning operating area. Optionally, in other embodiments, the image acquisition module can also be installed in other smart home appliances within the air conditioning operating area, and the air conditioner obtains the initial image information of the air conditioning operating area through a communication connection with these smart home appliances.

[0078] Specifically, after acquiring the initial image information of the air-conditioning operating area, the air conditioner performs image processing on the initial image information to determine the user object appearing in the air-conditioning operating area, and then uses the object status information of the user object to perform personalized control of the air conditioner in subsequent steps.

[0079] 202. Perform background analysis on the initial image information to determine the foreground object information of the initial image information;

[0080] Specifically, after acquiring the initial image information of the air-conditioning operating area, the air conditioner performs background analysis on the initial image information to determine the foreground image information in the initial image information, so that subsequent steps can determine the target object information in the initial image information that represents the user or other specific objects that can instruct the air conditioner to adjust its operating status based on the foreground image information.

[0081] Specifically, the air conditioner also has a pre-set background recognition model. After acquiring the initial image information, the background recognition model is used to model the background of the initial image information, thereby obtaining the initial background image information corresponding to the initial image information. The pre-set background recognition model can be a neural network model that uses median filtering to model the background of the initial image information.

[0082] Specifically, after the air conditioner uses the background recognition model to perform noise removal and other operations on the initial image information, it also uses the median filtering algorithm to model the background of the initial image information. That is, the background recognition model obtains the filtered image information by replacing each pixel value in the initial image information with the median value of the pixel values ​​in the neighborhood, and obtains the initial background image information of the initial image information by taking the median value of each pixel in the filtered image information as the sequence pixel value in the filtered image information.

[0083] Specifically, after acquiring the initial background image information of the initial image information, the air conditioner, considering that the operating area is a user's home environment and is greatly affected by environmental factors such as lighting, also uses a historical foreground mask to update the background information of the initial image information, thereby obtaining the target background image information of the initial image. This historical foreground mask is a foreground mask image representing the foreground information of the historical image information, obtained by background segmentation based on historical image information of a preset duration preceding the initial image information. The preset duration can be a custom duration of the previous frame or several previous frames.

[0084] Specifically, the air conditioner accesses a pre-set air conditioner image database that stores image information of the air conditioner's operating area at different time points. It then obtains a historical foreground mask associated with the initial image information within that operating area. Based on the historical foreground mask and a preset background detection threshold, it determines the background region to be updated in the initial background image information and updates this region to obtain the target background image information. The background detection threshold is a pixel value threshold corresponding to the air conditioner's operating area, used to detect whether an image is a background image.

[0085] Specifically, after determining the target background image information in the initial image information, the air conditioner further segments the target foreground information in the initial image information based on the initial image information and the target background image information. That is, after determining the target background image information, the air conditioner uses the target background image information to perform image segmentation on the initial image information, thereby extracting the target foreground image information from the initial image information. Specifically, the air conditioner subtracts the initial image information and the target foreground image information pixel-by-pixel to obtain the difference image information, and then uses a foreground detection threshold to perform threshold segmentation on the difference image information to obtain the foreground image information corresponding to the difference image information.

[0086] Specifically, after determining the target foreground image information in the initial image information, the air conditioner also uses a preset object detection model to perform object detection on the target foreground image information, thereby determining the foreground object information contained in the target foreground image information. This foreground object information refers to object image information representing the user or other objects present in the initial image information.

[0087] 203. Perform image processing on the foreground object information based on the object projection curve associated with the foreground object information to obtain the target object information;

[0088] Specifically, after determining the foreground object information present in the initial image information, the air conditioner further performs image processing on the foreground object information based on the object projection curve associated with the foreground object information to obtain the target object information.

[0089] Specifically, since the initial image information captured in the air conditioner's operating area may contain multiple user objects that are stuck together, or a specific user may be obscured by another user, or a specific user may be obscured by furniture or other objects, resulting in target loss or target recognition errors, the air conditioner further performs morphological processing on each foreground object information after acquiring the foreground image information corresponding to the initial image information, generating object feature images of each foreground object information that may be stuck together or obscured in the initial image information.

[0090] That is, the air conditioner selects information from each foreground object and generates a geometric feature image that covers the foreground object information. This geometric feature image can be a rectangle or other geometric shape. For example... Figure 3 As shown, Figure 3 This is a schematic diagram of an embodiment of the air conditioning control method provided in this application, which generates an object feature image by performing morphological processing on information of adhered foreground objects. For example... Figure 3 As shown, the Figure 3 The image shows a foreground image containing a combination of foreground object information with overlapping features. The air conditioner performs morphological processing on this combination of foreground object information with overlapping features to generate an object feature image representing the foreground object information as a combination of two partially overlapping rectangular features. In one specific embodiment, this morphological processing can be to mask the foreground object information and determine the mask bounding box corresponding to the foreground object information as the object feature image of the foreground object information.

[0091] Specifically, after acquiring the object feature image of the foreground object information, the air conditioner performs projection processing based on the feature pixel values ​​in the object feature image to obtain the object projection curve of the foreground object information. That is, after acquiring each object feature image, the air conditioner also acquires the feature pixel values ​​in the object feature image. These feature pixel values ​​include horizontal feature pixel values ​​and vertical feature pixel values. The horizontal feature pixel values ​​are the pixel values ​​located in the horizontal direction of the object feature image, and the vertical feature pixel values ​​are the pixel values ​​located in the vertical direction of the object feature image.

[0092] Specifically, after acquiring the feature pixel values ​​of the object's feature image, the air conditioner sums the horizontal feature pixel values ​​along the horizontal direction to obtain the total horizontal pixel value, and sums the vertical feature pixel values ​​along the vertical direction to obtain the total vertical pixel value. These total horizontal and vertical pixel values ​​are then projected onto the horizontal and vertical directions respectively to obtain the object projection curves of the foreground object information. These object projection curves include a horizontal projection curve and a vertical projection curve. The horizontal projection curve is the pixel projection curve obtained by projecting along the horizontal direction, and the vertical projection curve is the pixel projection curve obtained by projecting along the vertical direction.

[0093] Specifically, after obtaining the object projection curve of the foreground object information, the air conditioner also performs occlusion detection on the foreground object information based on the object projection curve to determine whether the foreground object information is occluded or stuck, and identifies the target object information to be guided for the operation control of the air conditioner.

[0094] 204. Identify the object status information corresponding to the target object information, and adjust the air conditioning operating parameters corresponding to the air conditioning operating area according to the object status information.

[0095] Specifically, after identifying the target object information in the foreground object information, the air conditioner also identifies the object status information corresponding to the target object information and adjusts the air conditioner operating parameters corresponding to the air conditioner operating area according to the object status information. Here, the target object information refers to image information representing user objects or other objects that can affect the operating status of the air conditioner.

[0096] Specifically, after determining the target object information, the air conditioner can further perform object recognition to determine the object's state information. This state information can be state parameters representing the target object's attributes, posture, and other states. For example, the object state information may include object identity information, object posture information, and object physiological state information.

[0097] For example, after determining the target object information, the air conditioner can also identify the target object information to determine the object's identity information. Then, the air conditioner can read the air conditioning correction parameters corresponding to the object's identity information and adjust the air conditioner's operating parameters according to the air conditioning correction parameters to guide the air conditioner to operate in a personalized manner according to the object's identity information.

[0098] For example, after determining the target object information, the air conditioner can also perform posture recognition on the target object to determine its posture information, thereby judging the current behavioral state of the target object. Based on this behavioral state, appropriate air conditioning correction parameters are selected to adjust the air conditioner's operating parameters, guiding the air conditioner to operate in a personalized manner according to the object's posture information. In one specific embodiment, the object's posture information can be posture information that can characterize user behavior activities, such as sitting posture information, movement posture information, and sleeping posture information.

[0099] In this embodiment, the air conditioner acquires initial image information in the air-conditioning operating area in response to an air-conditioning control request; performs background analysis on the initial image information to determine the foreground object information; processes the foreground object information based on the object projection curve associated with the foreground object information to obtain target object information; identifies the object state information corresponding to the target object information; and adjusts the air-conditioning operating parameters corresponding to the air-conditioning operating area according to the object state information. This enables the air conditioner to extract foreground object information containing user objects from the image information when acquiring image information in the air-conditioning operating area, and to determine whether the foreground image information is stuck or occluded using the object projection curve associated with the foreground object information. Image processing is then performed on the foreground object information to obtain separated target object information, and the air conditioner parameters are corrected based on the object state information of the target object information. This allows for accurate identification of stuck or occluded target objects in the operating scene when objects are stuck or occluded, improving the accuracy of target object identification and thus improving the control accuracy of personalized air-conditioning control based on target identification results, ultimately enhancing the user's air-conditioning experience.

[0100] like Figure 4 As shown, Figure 4 This is a flowchart illustrating an embodiment of the air conditioning control method for determining target background image information provided in this application. Specifically, in this embodiment, the air conditioning control method further includes steps 301 to 304:

[0101] 301. Obtain the mask pixels in the historical foreground mask;

[0102] 302. If the mask pixel value of the mask pixel is less than the background detection threshold, then the mask pixel is determined to be a background pixel.

[0103] 303. If the mask pixel value of the mask pixel is greater than the background detection threshold, then the mask pixel is determined to be a foreground pixel.

[0104] 304. Update the initial background image information based on the background pixels and the foreground pixels to obtain the target background image information.

[0105] Based on the above embodiments, in this embodiment, the air conditioner can obtain the historical foreground mask corresponding to the initial image information, and determine the background area to be updated in the initial background image information according to the historical foreground mask and the preset background detection threshold, and update the background area to be updated in the initial background image information to obtain the target background image information.

[0106] Specifically, after obtaining the historical foreground mask, the air conditioner uses the historical foreground mask as a priori indicator and obtains the mask pixels in the historical foreground mask. By comparing the mask pixels with the background detection threshold, the background area to be updated in the initial background image information is determined.

[0107] Optionally, if the mask pixel value of a mask pixel in the historical foreground mask is less than the background detection threshold, the air conditioner determines that the mask pixel is a background pixel.

[0108] Optionally, if the mask pixel value of a mask pixel in the historical foreground mask is greater than the background detection threshold, the air conditioner determines that the mask pixel is a foreground pixel.

[0109] Specifically, after obtaining the background pixels in the historical foreground mask, the air conditioner determines the background update region based on these background pixels, and updates the corresponding pixels in the initial background image information according to the background update region to obtain the target background image information. The pixel update formula is as follows:

[0110]

[0111] Among them, P t (x,y) represents the pixel value of point (x,y) in the initial background image information; P t+1 (x,y) represents the pixel value of point (x,y) in the target background image information; I t (x,y) represents the pixel value of the midpoint (x,y) in the historical foreground image information; Mask(x,y) represents the pixel value of the midpoint (x,y) in the historical foreground mask; α is a weight between 0 and 1.

[0112] Specifically, after determining the target foreground image information in the initial image information, the air conditioner also uses a preset object detection model to perform object detection on the target foreground image information, thereby determining the foreground object information contained in the target foreground image information. This foreground object information refers to object image information representing the user or other objects present in the initial image information.

[0113] In this embodiment, the air conditioner acquires mask pixels from the historical foreground mask. If the mask pixel value is less than the background detection threshold, the mask pixel is determined to be a background pixel; if the mask pixel value is greater than the background detection threshold, the mask pixel is determined to be a foreground pixel. The initial background image information is updated based on the background and foreground pixels to obtain the target background image information. This achieves updating the initial background image information based on the historical foreground image and historical foreground mask to obtain the target background image information, thereby reducing interference from environmental factors on subsequent object recognition and improving recognition accuracy.

[0114] like Figure 5 As shown, Figure 5 This is a flowchart illustrating an embodiment of the air conditioning control method for occlusion detection provided in this application. Specifically, in this embodiment, the air conditioning control method further includes steps 401 to 403:

[0115] 401. Based on the object projection curve, perform boundary point detection to obtain the target boundary points of the object projection curve, wherein the target boundary points include peak boundary points and trough boundary points;

[0116] 402. Based on the peak boundary points and the trough boundary points, perform occlusion detection on the foreground object information to determine the object occlusion information in the foreground object information;

[0117] 403. Perform object segmentation on the foreground object information based on the object occlusion information to obtain the target object information in the foreground object information.

[0118] Based on the above embodiments, in this embodiment, after the air conditioner obtains the object projection curve of the foreground object information, it also performs occlusion detection on the foreground object information according to the object projection curve to determine whether the foreground object information is occluded or stuck, and identifies the target object information to be guided to perform operation control of the air conditioner.

[0119] Specifically, the air conditioner performs boundary point detection on the object's projected curve to obtain the target boundary points of the object's projected curve. That is, the air conditioner searches for boundary points in the peaks and their neighborhoods of the object's projected curve, which means calculating the first derivative within the interval of the peaks and their neighborhoods of the object's projected curve to obtain the first step function associated with the object's projected curve, and obtaining the jump discontinuities of the step function to determine the peak boundary points in the direction corresponding to the peak.

[0120] Specifically, the air conditioner also searches for boundary points in the valleys and their neighborhoods of the object projection curve. That is, it calculates the first derivative of the valleys and their neighborhoods in the object projection curve, obtains the second step function associated with the object projection curve, and obtains the jump discontinuities of the step function to determine the valley boundary points in the direction corresponding to the valley.

[0121] Specifically, after obtaining the peak and trough boundary points, the air conditioner determines these peak and trough boundary points as the target boundary points of the object projection curve.

[0122] Specifically, after acquiring the target boundary points of the projection curves of each object, the air conditioner also performs occlusion detection on the foreground object information based on the peak and trough boundary points within these target boundary points. That is, the air conditioner determines the target boundary region of each object's projection curve based on the peak and trough boundary points, and judges whether the target boundary region has peaks or troughs based on the peak and trough boundary points. If the target boundary region has peaks, it means that the foreground object information is occluded in the corresponding direction of the object's projection curve, causing the target boundary regions to overlap. If the target boundary region has troughs, it means that the target boundary region is not occluded and there is no overlap, thus generating object occlusion information in the foreground object information.

[0123] Specifically, after determining the object's occlusion information, the air conditioner segments the foreground object information based on the object's occlusion information, thereby obtaining the target object information in the foreground object information that can guide the operation of the air conditioner.

[0124] In this embodiment, the air conditioner performs boundary point detection based on the object projection curve to obtain the target boundary points of the object projection curve, including peak boundary points and trough boundary points. Based on the peak and trough boundary points, occlusion detection is performed on the foreground object information to determine object occlusion information. Based on the object occlusion information, object segmentation is performed on the foreground object information to obtain the target object information. This achieves occlusion detection and segmentation of object images using projection curves, thereby accurately identifying adhered or occluded target objects in the operating scene when objects are stuck together or occluded, improving object recognition accuracy.

[0125] To better implement the air conditioning control method in the embodiments of this application, an air conditioning control device is also provided in the embodiments of this application, such as... Figure 6 As shown, Figure 6 This is a schematic diagram of the structure of the air conditioning control device provided in the embodiments of this application. Specifically, the air conditioning control device 500 includes:

[0126] The image acquisition module 501 is configured to acquire initial image information in the air conditioning operating area in response to an air conditioning control request.

[0127] Image segmentation module 502 is configured to perform background analysis on the initial image information to determine the foreground object information of the initial image information;

[0128] Image processing module 503 is configured to perform image processing on the foreground object information based on the object projection curve associated with the foreground object information to obtain target object information;

[0129] The air conditioning control module 504 is configured to identify the object status information corresponding to the target object information and adjust the air conditioning operating parameters corresponding to the air conditioning operating area according to the object status information.

[0130] In one possible implementation of this embodiment, the air conditioning control device performs background analysis on the initial image information to determine the foreground object information of the initial image information, including:

[0131] The initial image information is modeled using a historical foreground mask to obtain the target background image information of the initial image information;

[0132] Segment the target foreground image information in the initial image information based on the initial image information and the target background image information;

[0133] The target foreground image information is detected using a preset object detection model to determine the foreground object information of the initial image information.

[0134] In one possible implementation of this embodiment, the air conditioning control device uses a historical foreground mask to perform background modeling on the initial image information to obtain target background image information of the initial image information, including:

[0135] Access the air conditioner image database to obtain the historical foreground mask of the air conditioner operating area;

[0136] The initial image information is modeled according to a preset background recognition model to obtain the initial background image information;

[0137] The initial background image information is updated based on the historical foreground mask and the preset background detection threshold to obtain the target background image information.

[0138] In one possible implementation of this embodiment, the air conditioning control device updates the initial background image information based on the historical foreground mask and a preset background detection threshold to obtain target background image information, including:

[0139] Obtain the mask pixels in the historical foreground mask;

[0140] If the mask pixel value of the mask pixel is less than the background detection threshold, then the mask pixel is determined to be a background pixel.

[0141] If the mask pixel value of the mask pixel is greater than the background detection threshold, then the mask pixel is determined to be a foreground pixel.

[0142] The initial background image information is updated based on the background pixels and the foreground pixels to obtain the target background image information.

[0143] In one possible implementation of this embodiment, the air conditioning control device performs image processing on the foreground object information based on the object projection curve associated with the foreground object information to obtain target object information, including:

[0144] Morphological processing is performed on the foreground object information to obtain the object feature image of the foreground object information;

[0145] Projection processing is performed on the feature pixel values ​​in the object feature image to obtain the object projection curve of the foreground object information;

[0146] Based on the object projection curve, occlusion detection is performed on the foreground object information to determine the target object information in the foreground object information.

[0147] In one possible implementation of this embodiment, the air conditioning control device performs projection processing based on the feature pixel values ​​in the object feature image to obtain the object projection curve of the foreground object information, including:

[0148] Obtain feature pixel values ​​from the object feature image, wherein the feature pixel values ​​include horizontal feature pixel values ​​and vertical feature pixel values;

[0149] Pixel projection is performed based on the horizontal feature pixel values ​​to obtain the object projection curve of the foreground object information.

[0150] In one possible implementation of this embodiment, the air conditioning control device performs occlusion detection on the foreground object information based on the object projection curve to determine the target object information in the foreground object information, including:

[0151] Boundary point detection is performed based on the object projection curve to obtain the target boundary points of the object projection curve, including peak boundary points and trough boundary points.

[0152] Based on the peak boundary points and the trough boundary points, occlusion detection is performed on the foreground object information to determine the object occlusion information in the foreground object information;

[0153] Based on the object occlusion information, the foreground object information is segmented to obtain the target object information in the foreground object information.

[0154] In one possible implementation of this embodiment, the air conditioning control device identifies the object status information corresponding to the target object information and adjusts the air conditioning operating parameters corresponding to the air conditioning operating area according to the object status information, including:

[0155] Perform state detection on the target object information to obtain the object state information corresponding to the target object information;

[0156] Access the air conditioning operation database to obtain the air conditioning correction parameters associated with the object status information in the air conditioning operation database;

[0157] Adjust the air conditioning operating parameters corresponding to the air conditioning operating area according to the air conditioning correction parameters to obtain the air conditioning correction result.

[0158] In this embodiment, the air conditioning control device acquires initial image information in the air conditioning operating area in response to an air conditioning control request; performs background analysis on the initial image information to determine the foreground object information; processes the foreground object information based on the object projection curve associated with the foreground object information to obtain target object information; identifies the object state information corresponding to the target object information; and adjusts the air conditioning operating parameters corresponding to the air conditioning operating area according to the object state information. This enables the air conditioner to extract foreground object information containing user objects from the image information when acquiring image information in the air conditioning operating area, and to determine whether the foreground image information is stuck or occluded using the object projection curve associated with the foreground object information. Image processing is then performed on the foreground object information to obtain separated target object information, and the air conditioner parameters are corrected based on the object state information of the target object information. This ensures accurate identification of target objects even when objects are stuck or occluded, improving the accuracy of target object identification and thus improving the control accuracy of personalized air conditioning control based on target identification results, ultimately enhancing the user's air conditioning experience.

[0159] This invention also provides an air conditioner, such as... Figure 7 As shown, Figure 7 This is a schematic diagram of an embodiment of the air conditioner provided in this application.

[0160] The air conditioner integrates any one of the air conditioning control devices provided in the embodiments of the present invention, and the air conditioner includes:

[0161] One or more processors;

[0162] Memory; and

[0163] One or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the processor in the steps of the air conditioning control method described in any of the embodiments of the above-described air conditioning control method.

[0164] Specifically, an air conditioner may include components such as a processor 601 with one or more processing cores, a memory 602 with one or more computer-readable storage media, a power supply 603, and an input unit 604. Those skilled in the art will understand that... Figure 7 The air conditioner structure shown does not constitute a limitation on the air conditioner and may include more or fewer components than shown, or combine certain components, or have different component arrangements. Wherein:

[0165] The processor 601 is the control center of the air conditioner. It connects to various parts of the air conditioner via various interfaces and lines. By running or executing software programs and / or modules stored in the memory 602, and by calling data stored in the memory 602, it performs various functions and processes data, thereby providing overall monitoring of the air conditioner. 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 handles the operating system, user interface, and applications, and the modem processor mainly handles wireless communication. It is understood that the modem processor may not be integrated into the processor 601.

[0166] 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. The program storage area may store the operating system, application programs required for at least one function (such as sound playback function, image playback function, etc.), etc.; the data storage area may store data created based on the use of the air conditioner, etc. In addition, the memory 602 may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device. Accordingly, the memory 602 may also include a memory controller to provide the processor 601 with access to the memory 602.

[0167] The air conditioner also includes a power supply 603 that supplies power to the various components. Preferably, the power supply 603 can be logically connected to the processor 601 through a power management system, thereby enabling functions such as charging, discharging, and power consumption management through the power management system. The power supply 603 may also include one or more DC or AC power supplies, a recharging system, a power fault detection circuit, a power converter or inverter, a power status indicator, or any other components.

[0168] The air conditioner may also include an input unit 604, which can be used to receive input digital or character information, and generate keyboard, mouse, joystick, optical or trackball signal inputs related to user settings and function control.

[0169] Although not shown, the air conditioner may also include a display unit, etc., which will not be described in detail here. Specifically, in this embodiment, the processor 601 in the air conditioner loads 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 runs the application programs stored in the memory 602 to realize various functions, as follows:

[0170] Responding to air conditioning control requests, it acquires initial image information of the air conditioning operating area;

[0171] Background analysis is performed on the initial image information to determine the foreground object information of the initial image information;

[0172] Image processing is performed on the foreground object information based on the object projection curve associated with the foreground object information to obtain the target object information;

[0173] Identify the object status information corresponding to the target object information, and adjust the air conditioning operating parameters corresponding to the air conditioning operating area according to the object status information.

[0174] Therefore, embodiments of the present invention provide a computer-readable storage medium, which may include: read-only memory (ROM), random access memory (RAM), a magnetic disk, or an optical disk, etc. A computer program is stored thereon, which 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 loaded by the processor can execute the following steps:

[0175] Responding to air conditioning control requests, it acquires initial image information of the air conditioning operating area;

[0176] Background analysis is performed on the initial image information to determine the foreground object information of the initial image information;

[0177] Image processing is performed on the foreground object information based on the object projection curve associated with the foreground object information to obtain the target object information;

[0178] Identify the object status information corresponding to the target object information, and adjust the air conditioning operating parameters corresponding to the air conditioning operating area according to the object status information.

[0179] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the detailed descriptions of other embodiments above, which will not be repeated here.

[0180] In practice, each of the above units or structures can be implemented as an independent entity or can be arbitrarily combined to be implemented as the same or several entities. For the specific implementation of each of the above units or structures, please refer to the previous method embodiments, which will not be repeated here.

[0181] For details on the implementation of each of the above operations, please refer to the previous examples, which will not be repeated here.

[0182] The above provides a detailed description of an air conditioning control method provided by the embodiments of this application. Specific embodiments have been used to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only for the purpose of helping to understand the method and core ideas of the present invention. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of the present invention. Therefore, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. An air conditioning control method, characterized in that, The air conditioning control method includes: Responding to air conditioning control requests, it acquires initial image information of the air conditioning operating area; Background analysis is performed on the initial image information to determine the foreground object information of the initial image information; Morphological processing is performed on the foreground object information to obtain an object feature image of the foreground object information, and feature pixel values ​​in the object feature image are obtained, the feature pixel values ​​including horizontal feature pixel values ​​and vertical feature pixel values; Pixel projection is performed based on the horizontal and vertical feature pixel values ​​to obtain the object projection curve of the foreground object information. Occlusion detection is performed on the foreground object information based on the object projection curve to determine the target object information in the foreground object information. Identify the object status information corresponding to the target object information, and adjust the air conditioning operating parameters corresponding to the air conditioning operating area according to the object status information.

2. The air conditioning control method according to claim 1, characterized in that, The step of performing background analysis on the initial image information to determine the foreground object information of the initial image information includes: The initial image information is modeled using a historical foreground mask to obtain the target background image information of the initial image information; Segment the target foreground image information in the initial image information based on the initial image information and the target background image information; The target foreground image information is detected using a preset object detection model to determine the foreground object information of the initial image information.

3. The air conditioning control method according to claim 2, characterized in that, The step of using a historical foreground mask to perform background modeling on the initial image information to obtain the target background image information of the initial image information includes: Access the air conditioner image database to obtain the historical foreground mask of the air conditioner operating area; The initial image information is modeled according to a preset background recognition model to obtain the initial background image information; The initial background image information is updated based on the historical foreground mask and the preset background detection threshold to obtain the target background image information.

4. The air conditioning control method according to claim 3, characterized in that, The step of updating the initial background image information based on the historical foreground mask and a preset background detection threshold to obtain the target background image information includes: Obtain the mask pixels in the historical foreground mask; If the mask pixel value of the mask pixel is less than the background detection threshold, then the mask pixel is determined to be a background pixel. If the mask pixel value of the mask pixel is greater than the background detection threshold, then the mask pixel is determined to be a foreground pixel. The initial background image information is updated based on the background pixels and the foreground pixels to obtain the target background image information.

5. The air conditioning control method according to claim 1, characterized in that, The step of performing occlusion detection on the foreground object information based on the object projection curve to determine the target object information in the foreground object information includes: Boundary point detection is performed based on the object projection curve to obtain the target boundary points of the object projection curve, including peak boundary points and trough boundary points. Based on the peak boundary points and the trough boundary points, occlusion detection is performed on the foreground object information to determine the object occlusion information in the foreground object information; Based on the object occlusion information, the foreground object information is segmented to obtain the target object information in the foreground object information.

6. The air conditioning control method according to any one of claims 1-5, characterized in that, The step of identifying the object status information corresponding to the target object information and adjusting the air conditioning operating parameters corresponding to the air conditioning operating area according to the object status information includes: Perform state detection on the target object information to obtain the object state information corresponding to the target object information; Access the air conditioning operation database to obtain the air conditioning correction parameters associated with the object status information in the air conditioning operation database; Adjust the air conditioning operating parameters corresponding to the air conditioning operating area according to the air conditioning correction parameters to obtain the air conditioning correction result.

7. An air conditioning control device, characterized in that, The air conditioning control device includes: The image acquisition module is configured to acquire initial image information of the air conditioning operating area in response to an air conditioning control request. An image segmentation module is configured to perform background analysis on the initial image information to determine the foreground object information of the initial image information; An image processing module is configured to perform morphological processing on the foreground object information to obtain an object feature image of the foreground object information; acquire feature pixel values ​​in the object feature image, the feature pixel values ​​including horizontal feature pixel values ​​and vertical feature pixel values; perform pixel projection based on the horizontal feature pixel values ​​and vertical feature pixel values ​​to obtain an object projection curve of the foreground object information; and perform occlusion detection on the foreground object information based on the object projection curve to determine the target object information in the foreground object information. The air conditioning control module is configured to identify the object status information corresponding to the target object information and adjust the air conditioning operating parameters corresponding to the air conditioning operating area according to the object status information.

8. An air conditioner, characterized in that, The air conditioner includes: One or more processors; Memory; and 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 according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, It stores a computer program, which is loaded by a processor to execute the steps of the air conditioning control method according to any one of claims 1 to 6.

Images