Fan adjustment method, system, device and storage medium based on machine vision

Abstract

The present invention discloses a fan adjustment method, system, device and storage medium based on machine vision, the method comprising: obtaining first thermal infrared image information of a user; inputting the first thermal infrared image information into a pre-trained human posture recognition model to obtain first human posture information, and determining first position information of multiple human key points according to the first human posture information; inputting the first thermal infrared image information into a pre-trained human temperature recognition model to obtain first human temperature distribution information, and determining first temperature information of each human key point according to the first human temperature distribution information and the first human posture information; and adjusting the fan according to the first position information, the first temperature information and the second temperature information of the indoor environment. The present invention improves the comprehensiveness and accuracy of fan adjustment, avoids the occurrence of discomfort symptoms such as colds and chills to a certain extent, improves the user experience, and can be widely used in the field of smart home technology.

Description

Technical Field

[0001] The present invention relates to the field of smart home technology, and in particular to a fan adjustment method, system, device and storage medium based on machine vision. Background Art

[0002] In the hot summer, people often use fans to cool down, but traditional fans require people to manually control the fan, which is inconvenient to use. With the development of science and technology and the improvement of people's living standards, household products are gradually moving towards automation and intelligence. Some smart temperature-controlled fans have appeared on the market, which can not only automatically adjust the fan speed according to the temperature of the surrounding environment, but also can be remotely controlled through the user's mobile terminal.

[0003] However, most of the existing intelligent temperature-controlled fans can only adjust the wind speed according to the temperature of the surrounding environment, without taking into account the temperature changes of the human body, resulting in inaccurate wind speed adjustment. There are still safety hazards that may cause users to catch colds and other discomfort symptoms, affecting the user experience; in addition, the existing intelligent temperature-controlled fans cannot adjust the fan's wind direction according to the temperature distribution of the human body, affecting the comprehensiveness of the fan adjustment. Summary of the invention

[0004] The purpose of the present invention is to solve one of the technical problems existing in the prior art to at least a certain extent.

[0005] To this end, an object of an embodiment of the present invention is to provide a fan adjustment method based on machine vision, which improves the comprehensiveness and accuracy of fan adjustment, avoids the occurrence of discomfort symptoms such as colds and chills to a certain extent, and improves the user experience.

[0006] Another object of an embodiment of the present invention is to provide a fan adjustment system based on machine vision.

[0007] In order to achieve the above technical objectives, the technical solutions adopted by the embodiments of the present invention include:

[0008] In a first aspect, an embodiment of the present invention provides a fan adjustment method based on machine vision, comprising the following steps:

[0009] Acquire first thermal infrared image information of the user;

[0010] Inputting the first thermal infrared image information into a pre-trained human posture recognition model to obtain first human posture information, and determining first position information of a plurality of human key points according to the first human posture information;

[0011] Inputting the first thermal infrared image information into a pre-trained human body temperature recognition model to obtain first human body temperature distribution information, and determining first temperature information of each of the key points of the human body according to the first human body temperature distribution information and the first human body posture information;

[0012] Acquire second temperature information of the indoor environment, and adjust the fan according to the first position information, the first temperature information, and the second temperature information.

[0013] Furthermore, in one embodiment of the present invention, the fan adjustment method further includes the step of pre-training a human posture recognition model, which specifically includes:

[0014] Obtain a preset human posture heat map data set, wherein the human posture heat map data set includes multiple human posture heat maps and corresponding posture labels;

[0015] Inputting the human posture heat map data set into a pre-built first convolutional neural network to obtain a posture recognition result;

[0016] Determine a first loss value of the first convolutional neural network according to the posture recognition result and the posture label;

[0017] Updating the parameters of the first convolutional neural network through a back propagation algorithm according to the first loss value;

[0018] When the first loss value reaches a preset first threshold value, the number of iterations reaches a preset second threshold value, or the test accuracy reaches a preset third threshold value, the training is stopped to obtain a trained human posture recognition model.

[0019] Further, in one embodiment of the present invention, the step of determining first position information of a plurality of human body key points according to the first human body posture information specifically includes:

[0020] Marking a plurality of key points of the human body on the first thermal infrared image according to the first human body posture information;

[0021] The first position information of each of the key points of the human body is determined according to the position of each of the key points of the human body on the first thermal infrared image and the shooting angle of the first thermal infrared image.

[0022] Furthermore, in one embodiment of the present invention, the fan adjustment method further includes the step of pre-training a human body temperature recognition model, which specifically includes:

[0023] Acquire a preset human body temperature heat map data set, wherein the human body temperature heat map data set includes a plurality of human body temperature heat maps and corresponding temperature distribution labels;

[0024] Inputting the human body posture thermal map data set into a pre-built second convolutional neural network to obtain a temperature distribution recognition result;

[0025] Determine a second loss value of the second convolutional neural network according to the temperature distribution recognition result and the temperature distribution label;

[0026] Updating the parameters of the second convolutional neural network through a back propagation algorithm according to the second loss value;

[0027] When the second loss value reaches a preset fourth threshold value, or the number of iterations reaches a preset fifth threshold value, or the test accuracy reaches a preset sixth threshold value, the training is stopped to obtain a trained human posture recognition model.

[0028] Further, in one embodiment of the present invention, the step of determining the first temperature information of each of the key points of the human body according to the first human body temperature distribution information and the first human body posture information specifically includes:

[0029] Marking a plurality of key points of the human body on the first thermal infrared image according to the first human body posture information;

[0030] The first temperature information of each of the key points of the human body is determined according to the first human body temperature distribution information and the position of each of the key points of the human body on the first thermal infrared image.

[0031] Further, in an embodiment of the present invention, the step of adjusting the fan according to the first position information, the first temperature information and the second temperature information specifically includes:

[0032] Determine a plurality of areas to be cooled according to the first position information and the first temperature information, and adjust the wind direction of the fan so that the fan supplies air to the areas to be cooled;

[0033] A first temperature difference is determined according to the first temperature information corresponding to the area to be cooled and the second temperature information, and a rotation speed of the fan is adjusted according to the first temperature difference.

[0034] Furthermore, in one embodiment of the present invention, the fan adjustment method further comprises the following steps:

[0035] When the second temperature information is less than or equal to a preset temperature threshold, the fan is controlled to stop rotating.

[0036] In a second aspect, an embodiment of the present invention provides a fan adjustment system based on machine vision, comprising:

[0037] An acquisition module, used to acquire first thermal infrared image information of a user;

[0038] a posture recognition module, configured to input the first thermal infrared image information into a pre-trained human posture recognition model to obtain first human posture information, and determine first position information of a plurality of human key points according to the first human posture information;

[0039] a temperature recognition module, configured to input the first thermal infrared image information into a pre-trained human body temperature recognition model to obtain first human body temperature distribution information, and determine first temperature information of each of the key points of the human body according to the first human body temperature distribution information and the first human body posture information;

[0040] The fan adjustment module is used to obtain second temperature information of the indoor environment and adjust the fan according to the first position information, the first temperature information and the second temperature information.

[0041] In a third aspect, an embodiment of the present invention provides a fan adjustment device based on machine vision, comprising:

[0042] at least one processor;

[0043] at least one memory for storing at least one program;

[0044] When the at least one program is executed by the at least one processor, the at least one processor implements the above-mentioned fan adjustment method based on machine vision.

[0045] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, which stores a program executable by a processor. When the program executable by the processor is executed by the processor, it is used to execute the above-mentioned fan adjustment method based on machine vision.

[0046] The advantages and beneficial effects of the present invention will be partly given in the following description, partly become apparent from the following description, or be understood through the practice of the present invention:

[0047] The embodiment of the present invention obtains thermal infrared image information of the user, inputs the thermal infrared image information into a pre-trained human posture recognition model and human temperature recognition model, obtains human posture information and human temperature distribution information, determines the first position information of multiple human key points according to the human posture information, determines the first temperature information of each human key point according to the human temperature distribution information and the human posture information, and then obtains the second temperature information of the indoor environment, so that the fan can be controlled and adjusted according to the first position information, the first temperature information and the second temperature information. The embodiment of the present invention performs human posture recognition and human temperature recognition on the thermal infrared image information, and can determine the position information and temperature information of each human key point, and then can determine the position information of the human key point that needs to be cooled to adjust the wind direction, and can also combine the ambient temperature and the temperature information of the human key point to adjust the wind speed, thereby improving the comprehensiveness and accuracy of fan adjustment, avoiding the occurrence of discomfort symptoms such as colds and chills to a certain extent, and improving the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the technical solution in the embodiments of the present invention, the following introduction is made to the drawings required for use in the embodiments of the present invention. It should be understood that the drawings introduced below are only for the convenience of clearly describing some embodiments of the technical solution of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0049] Figure 1 A flowchart of a fan adjustment method based on machine vision provided by an embodiment of the present invention;

[0050] Figure 2 A structural block diagram of a fan adjustment system based on machine vision provided by an embodiment of the present invention;

[0051] Figure 3 A structural block diagram of a fan adjustment device based on machine vision provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0052] The embodiments of the present invention are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and are not to be construed as limitations of the present invention. For the step numbers in the following embodiments, they are only provided for the convenience of explanation, and the order between the steps is not limited in any way, and the execution order of each step in the embodiment can be adaptively adjusted according to the understanding of those skilled in the art.

[0053] In the description of the present invention, the meaning of "a plurality" is two or more than two. If there is a description of "a first" or "a second", it is only used for the purpose of distinguishing technical features, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features or implicitly indicating the order of the indicated technical features. In addition, unless otherwise defined, all technical and scientific terms used in this document have the same meaning as those commonly understood by those skilled in the art.

[0054] Reference Figure 1 The embodiment of the present invention provides a fan adjustment method based on machine vision, which specifically includes the following steps:

[0055] S101. Acquire first thermal infrared image information of a user.

[0056] Specifically, when sleeping, users often use very weak lights for lighting, in which case it is impossible to obtain a clear visible light image, so the embodiment of the present invention obtains thermal infrared images for subsequent human posture recognition and human temperature recognition. The embodiment of the present invention uses a thermal infrared camera to obtain thermal infrared image information of the user when sleeping.

[0057] S102: input the first thermal infrared image information into a pre-trained human posture recognition model to obtain first human posture information, and determine first position information of a plurality of human body key points according to the first human posture information.

[0058] As an optional implementation, the fan adjustment method further includes the step of pre-training a human posture recognition model, which specifically includes:

[0059] A1. Obtain a preset human posture heat map dataset, where the human posture heat map dataset includes multiple human posture heat maps and corresponding posture labels;

[0060] A2. Input the human posture heat map dataset into the pre-built first convolutional neural network to obtain the posture recognition result;

[0061] A3, determining a first loss value of the first convolutional neural network according to the posture recognition result and the posture label;

[0062] A4. Update the parameters of the first convolutional neural network through a back propagation algorithm according to the first loss value;

[0063] A5. When the first loss value reaches a preset first threshold value, the number of iterations reaches a preset second threshold value, or the test accuracy reaches a preset third threshold value, the training is stopped to obtain a trained human posture recognition model.

[0064] Specifically, the human posture heat map is a human body heat map of multiple different human postures, and its posture labels can be manually annotated. After the human posture heat map data set is input into the initialized first convolutional neural network, the posture recognition result output by the model can be obtained. The accuracy of the human posture recognition model can be evaluated according to the posture recognition result and the posture label, so as to update the parameters of the model. For the human posture recognition model, the accuracy of the posture recognition result can be measured by the loss function. The loss function is defined on a single training data and is used to measure the prediction error of a training data. Specifically, the loss value of the training data is determined by the label of a single training data and the prediction result of the model for the training data. In actual training, a training data set has a lot of training data, so the cost function is generally used to measure the overall error of the training data set. The cost function is defined on the entire training data set and is used to calculate the average value of the prediction error of all training data, which can better measure the prediction effect of the model. For general machine learning models, based on the aforementioned cost function, plus the regularization term that measures the complexity of the model, it can be used as the objective function of the training, and the loss value of the entire training data set can be calculated based on the objective function. There are many types of commonly used loss functions, such as 0-1 loss function, square loss function, absolute loss function, logarithmic loss function, cross entropy loss function, etc., which can all be used as loss functions of machine learning models, which will not be elaborated here one by one. In an embodiment of the present invention, any loss function can be selected to determine the loss value of training. Based on the loss value of training, the back propagation algorithm is used to update the parameters of the model, and a trained human posture recognition model can be obtained by iterating several rounds. Specifically, the number of iterations can be pre-set, or the training is considered to be completed when the test set meets the accuracy requirements.

[0065] Further as an optional implementation manner, the step of determining first position information of a plurality of human body key points according to the first human body posture information specifically includes:

[0066] B1. marking a plurality of key points of the human body on the first thermal infrared image according to the first human body posture information;

[0067] B2. Determine first position information of each key point of the human body according to the position of each key point of the human body on the first thermal infrared image and the shooting angle of the first thermal infrared image.

[0068] Specifically, the COCO dataset represents the key points of the human body as 17 joints, namely the nose, left and right eyes, left and right ears, left and right shoulders, left and right elbows, left and right wrists, left and right hips, left and right knees, and left and right ankles. In an embodiment of the present invention, the first human posture information obtained by identification can be used to mark these key points of the human body on the first thermal infrared image, and then the position of each key point of the human body can be determined in combination with information such as the shooting angle of the thermal infrared camera.

[0069] In some optional embodiments, key points of the human body may be divided and selected according to actual needs, such as being divided into the head, neck, chest, abdomen, buttocks, and limbs.

[0070] S103, inputting the first thermal infrared image information into a pre-trained human body temperature recognition model to obtain first human body temperature distribution information, and determining first temperature information of each human body key point according to the first human body temperature distribution information and the first human body posture information.

[0071] As an optional implementation, the fan adjustment method further includes the step of pre-training a human body temperature recognition model, which specifically includes:

[0072] C1. Obtain a preset human body temperature heat map dataset, where the human body temperature heat map dataset includes multiple human body temperature heat maps and corresponding temperature distribution labels;

[0073] C2, input the human posture heat map dataset into the pre-built second convolutional neural network to obtain the temperature distribution recognition result;

[0074] C3, determining a second loss value of the second convolutional neural network according to the temperature distribution recognition result and the temperature distribution label;

[0075] C4, updating the parameters of the second convolutional neural network through a back propagation algorithm according to the second loss value;

[0076] C5. When the second loss value reaches the preset fourth threshold or the number of iterations reaches the preset fifth threshold or the test accuracy reaches the preset sixth threshold, stop training to obtain a trained human posture recognition model.

[0077] Specifically, the human body temperature heat map is a human body heat map with multiple different temperature distribution conditions. Its temperature distribution label can be manually annotated. It is necessary to annotate the temperature label of each pixel area of ​​the human body temperature heat map to form a set of "pixel area-temperature label", which is the temperature distribution label. The annotated human body temperature heat map data set is input into the second convolutional neural network for training to obtain a human posture recognition model. The specific training process is not described in detail.

[0078] Further as an optional implementation manner, the step of determining the first temperature information of each key point of the human body according to the first human body temperature distribution information and the first human body posture information specifically includes:

[0079] D1. marking a plurality of key points of the human body on the first thermal infrared image according to the first human body posture information;

[0080] D2. Determine the first temperature information of each key point of the human body according to the first human body temperature distribution information and the position of each key point of the human body on the first thermal infrared image.

[0081] Specifically, in an embodiment of the present invention, the first human body posture information obtained by identification can be used to mark multiple human body key points on the first thermal infrared image, and the first human body temperature distribution information obtained by identification can be used to mark the temperature information of each area on the first thermal infrared image. By comparing the results of the two markings, the first temperature information of each human body key point can be obtained.

[0082] S104: Acquire second temperature information of the indoor environment, and adjust the fan according to the first position information, the first temperature information, and the second temperature information.

[0083] Specifically, the second temperature information can be obtained through a temperature sensor. In the embodiment of the present invention, the wind direction and the speed of the fan can be automatically adjusted according to the first position information, the first temperature information and the second temperature information.

[0084] As an optional implementation, the step of adjusting the fan according to the first position information, the first temperature information, and the second temperature information specifically includes:

[0085] E1. Determine a plurality of areas to be cooled according to the first position information and the first temperature information, and adjust the wind direction of the fan so that the fan supplies air to the areas to be cooled;

[0086] E2. Determine a first temperature difference according to the first temperature information and the second temperature information corresponding to the area to be cooled, and adjust the rotation speed of the fan according to the first temperature difference.

[0087] Specifically, several key points of the human body with higher temperatures are determined based on the first temperature information, and then several areas to be cooled are determined based on the first position information of these key points of the human body, and then the wind direction of the fan is adjusted so that the fan supplies air to the areas to be cooled; the first temperature difference is determined based on the first temperature information of the key points of the human body in the areas to be cooled and the second temperature information of the indoor environment. When the first temperature difference is large, the speed of the fan can be increased, and when the first temperature difference is small, the speed of the fan can be reduced.

[0088] In some optional embodiments, when there are multiple areas to be cooled, the fan can change the wind direction by swinging to supply air to the multiple areas to be cooled. At the same time, the fan can also be controlled not to continuously supply air to the human head and abdomen.

[0089] As an optional implementation, the fan adjustment method further includes the following steps:

[0090] When the second temperature information is less than or equal to a preset temperature threshold, the fan is controlled to stop rotating.

[0091] Specifically, in areas with a large temperature difference between day and night, when the ambient temperature is detected to be too low at night, the fan can be directly stopped from supplying air to prevent users from catching a cold.

[0092] The above is a description of the method steps of the embodiment of the present invention. It can be understood that the embodiment of the present invention performs human posture recognition and human temperature recognition on thermal infrared image information, and can determine the position information and temperature information of each key point of the human body, and then determine the position information of the key point of the human body that needs to be cooled to adjust the wind direction, and can also adjust the wind speed in combination with the ambient temperature and the temperature information of the key point of the human body, thereby improving the comprehensiveness and accuracy of fan adjustment, avoiding the occurrence of discomfort symptoms such as colds and chills to a certain extent, and improving the user experience.

[0093] Reference Figure 2 , an embodiment of the present invention provides a fan adjustment system based on machine vision, comprising:

[0094] An acquisition module, used to acquire first thermal infrared image information of a user;

[0095] A posture recognition module, used for inputting the first thermal infrared image information into a pre-trained human posture recognition model to obtain first human posture information, and determining first position information of a plurality of human key points according to the first human posture information;

[0096] A temperature recognition module, used to input the first thermal infrared image information into a pre-trained human body temperature recognition model to obtain first human body temperature distribution information, and determine first temperature information of each key point of the human body according to the first human body temperature distribution information and the first human body posture information;

[0097] The fan adjustment module is used to obtain second temperature information of the indoor environment and adjust the fan according to the first position information, the first temperature information and the second temperature information.

[0098] The contents of the above method embodiments are all applicable to the present system embodiments. The functions specifically implemented by the present system embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0099] Reference Figure 3 , an embodiment of the present invention provides a fan adjustment device based on machine vision, comprising:

[0100] at least one processor;

[0101] at least one memory for storing at least one program;

[0102] When the at least one program is executed by the at least one processor, the at least one processor implements the above-mentioned fan adjustment method based on machine vision.

[0103] The contents of the above method embodiments are all applicable to the present device embodiments. The functions specifically implemented by the present device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0104] An embodiment of the present invention further provides a computer-readable storage medium, in which a program executable by a processor is stored. When the program executable by the processor is executed by the processor, it is used to execute the above-mentioned fan adjustment method based on machine vision.

[0105] A computer-readable storage medium according to an embodiment of the present invention can execute a fan adjustment method based on machine vision provided by an embodiment of the method of the present invention, can execute any combination of implementation steps of the method embodiment, and has the corresponding functions and beneficial effects of the method.

[0106] The embodiment of the present invention also discloses a computer program product or a computer program, wherein the computer program product or the computer program includes computer instructions, and the computer instructions are stored in a computer-readable storage medium. A processor of a computer device can read the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes Figure 1 The method shown.

[0107] In some selectable embodiments, the function / operation mentioned in the block diagram may not occur in the order mentioned in the operation diagram. For example, depending on the function / operation involved, the two boxes shown in succession can actually be executed substantially simultaneously or the above-mentioned boxes can sometimes be executed in reverse order. In addition, the embodiment presented and described in the flow chart of the present invention is provided by way of example, for the purpose of providing a more comprehensive understanding of technology. The disclosed method is not limited to the operation and logic flow presented herein. Selectable embodiments are expected, wherein the order of various operations is changed and the sub-operation of a part for which is described as a larger operation is performed independently.

[0108] In addition, although the present invention is described in the context of functional modules, it should be understood that, unless otherwise specified to the contrary, one or more of the above-mentioned functions and / or features can be integrated into a single physical device and / or software module, or one or more functions and / or features can be implemented in a separate physical device or software module. It is also understood that a detailed discussion of the actual implementation of each module is unnecessary for understanding the present invention. More specifically, in view of the properties, functions and internal relationships of the various functional modules in the device disclosed herein, the actual implementation of the module will be understood within the conventional skills of the engineer. Therefore, those skilled in the art can implement the present invention set forth in the claims without excessive experimentation using ordinary techniques. It is also understood that the specific concepts disclosed are merely illustrative and are not intended to limit the scope of the present invention, which is determined by the full scope of the appended claims and their equivalents.

[0109] If the above functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the above methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0110] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0111] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and editable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the above-mentioned program is printed, since the above-mentioned program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or processing in other suitable ways as necessary, and then stored in a computer memory.

[0112] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0113] In the above description of this specification, the description with reference to the terms "one embodiment / example", "another embodiment / example" or "certain embodiments / examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0114] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the claims and their equivalents.

[0115] The above is a specific description of the preferred implementation of the present invention, but the present invention is not limited to the above embodiments. Those skilled in the art may make various equivalent modifications or substitutions without violating the spirit of the present invention. These equivalent modifications or substitutions are all included in the scope defined by the claims of this application.

Claims

1. A fan adjustment method based on machine vision, characterized in that: The following steps are involved: Acquire first thermal infrared image information of the user; Inputting the first thermal infrared image information into a pre-trained human posture recognition model to obtain first human posture information, and determining first position information of a plurality of human key points according to the first human posture information; Inputting the first thermal infrared image information into a pre-trained human body temperature recognition model to obtain first human body temperature distribution information, and determining first temperature information of each of the key points of the human body according to the first human body temperature distribution information and the first human body posture information; Acquire second temperature information of the indoor environment, and adjust the fan according to the first position information, the first temperature information, and the second temperature information; The step of adjusting the fan according to the first position information, the first temperature information, and the second temperature information specifically includes: Determine a plurality of areas to be cooled according to the first position information and the first temperature information, and adjust the wind direction of the fan so that the fan supplies air to the areas to be cooled; A first temperature difference is determined according to the first temperature information corresponding to the area to be cooled and the second temperature information, and a rotation speed of the fan is adjusted according to the first temperature difference.

2. The fan adjustment method based on machine vision according to claim 1, characterized in that: The fan adjustment method further includes the step of pre-training a human posture recognition model, which specifically includes: Obtain a preset human posture heat map data set, wherein the human posture heat map data set includes multiple human posture heat maps and corresponding posture labels; Inputting the human posture heat map data set into a pre-built first convolutional neural network to obtain a posture recognition result; Determine a first loss value of the first convolutional neural network according to the posture recognition result and the posture label; Updating the parameters of the first convolutional neural network through a back propagation algorithm according to the first loss value; When the first loss value reaches a preset first threshold value, the number of iterations reaches a preset second threshold value, or the test accuracy reaches a preset third threshold value, the training is stopped to obtain a trained human posture recognition model.

3. The fan adjustment method based on machine vision according to claim 1, characterized in that: The step of determining first position information of a plurality of human body key points according to the first human body posture information specifically includes: Marking a plurality of key points of the human body on the first thermal infrared image according to the first human body posture information; The first position information of each of the key points of the human body is determined according to the position of each of the key points of the human body on the first thermal infrared image and the shooting angle of the first thermal infrared image.

4. The fan adjustment method based on machine vision according to claim 1, characterized in that: The fan adjustment method further includes the step of pre-training a human body temperature recognition model, which specifically includes: Acquire a preset human body temperature heat map data set, wherein the human body temperature heat map data set includes a plurality of human body temperature heat maps and corresponding temperature distribution labels; Inputting the human body temperature thermal map data set into a pre-built second convolutional neural network to obtain a temperature distribution recognition result; Determine a second loss value of the second convolutional neural network according to the temperature distribution recognition result and the temperature distribution label; Updating the parameters of the second convolutional neural network through a back propagation algorithm according to the second loss value; When the second loss value reaches the preset fourth threshold or the number of iterations reaches the preset fifth threshold or the test accuracy reaches the preset sixth threshold, the training is stopped to obtain a trained human body temperature recognition model.

5. The fan adjustment method based on machine vision according to claim 1, characterized in that: The step of determining the first temperature information of each key point of the human body according to the first human body temperature distribution information and the first human body posture information specifically includes: Marking a plurality of key points of the human body on the first thermal infrared image according to the first human body posture information; The first temperature information of each of the key points of the human body is determined according to the first human body temperature distribution information and the position of each of the key points of the human body on the first thermal infrared image.

6. A fan adjustment method based on machine vision according to any one of claims 1 to 5, characterized in that: The fan adjustment method further comprises the following steps: When the second temperature information is less than or equal to a preset temperature threshold, the fan is controlled to stop rotating.

7. A fan adjustment system based on machine vision, characterized in that: include: An acquisition module, used to acquire first thermal infrared image information of a user; a posture recognition module, configured to input the first thermal infrared image information into a pre-trained human posture recognition model to obtain first human posture information, and determine first position information of a plurality of human key points according to the first human posture information; a temperature recognition module, configured to input the first thermal infrared image information into a pre-trained human body temperature recognition model to obtain first human body temperature distribution information, and determine first temperature information of each of the key points of the human body according to the first human body temperature distribution information and the first human body posture information; a fan adjustment module, configured to obtain second temperature information of the indoor environment, and adjust the fan according to the first position information, the first temperature information, and the second temperature information; The step of adjusting the fan according to the first position information, the first temperature information, and the second temperature information specifically includes: Determine a plurality of areas to be cooled according to the first position information and the first temperature information, and adjust the wind direction of the fan so that the fan supplies air to the areas to be cooled; A first temperature difference is determined according to the first temperature information corresponding to the area to be cooled and the second temperature information, and a rotation speed of the fan is adjusted according to the first temperature difference.

8. A fan adjustment device based on machine vision, characterized in that: include: at least one processor; at least one memory for storing at least one program; When the at least one program is executed by the at least one processor, the at least one processor implements the fan adjustment method based on machine vision as described in any one of claims 1 to 6.

9. A computer-readable storage medium storing a program executable by a processor, characterized in that: The program executable by the processor is used to execute a fan adjustment method based on machine vision as claimed in any one of claims 1 to 6 when executed by the processor.

Images