Automatic control method and system for intelligent drying rack based on machine vision

Abstract

This application relates to the field of control of drying racks, and particularly to an intelligent drying rack automatic control method and system based on machine vision. The method includes the steps of: during the drying process, controlling the rotation of the rack body of the drying rack to adjust the drying position and angle of the hanging clothes; taking the position where the drying rack is located corresponding to the maximum overall drying efficiency as the optimal position, and controlling the rack body to rotate to the optimal position. This application has the effect of automatically adjusting the position of clothes according to the drying situation of the clothes.

Description

Technical Field

[0001] This application relates to the field of controlling drying racks, and particularly to an automatic control method and system for intelligent drying racks based on machine vision. Background Art

[0002] An intelligent drying rack is a modern household device integrating multiple functions. It not only solves the problems of single function and inconvenient operation of traditional drying racks, but also improves the efficiency and experience of drying clothes.

[0003] Users can use intelligent devices such as remote controls, smartphone apps, or voice control to achieve functions such as raising and lowering the drying rack. For example, the patent application document with the patent publication number CN118584846A discloses a control method, device, equipment, and medium for a drying rack. The method includes: according to the clothes drying instruction issued by the user, obtaining the user's height, where the clothes drying instruction is used to indicate that the user performs a clothes drying operation on the drying rack and to obtain the user's height; obtaining clothes drying scene information, where the clothes drying scene information includes at least the length of at least one piece of clothes to be dried; according to the user's height and the clothes drying scene information, obtaining the target lowering height of the drying rack, and controlling the drying rack to perform a lowering action according to the target lowering height.

[0004] The prior art can also control the moving position of the drying rack. For example, a drying rack control method, device, and storage medium disclosed in the patent document with the authorization announcement number CN110297434B. After the drying rack receives the message notification that the clothes have been washed, it moves to a position close to the clothes. When the drying rack receives the return signal, it moves back to the initial position.

[0005] When users use an intelligent drying rack to dry clothes, the drying speed of the clothes hanging at different positions is different, and it is necessary to manually adjust the drying position on the intelligent drying rack according to the drying situation of the clothes. Therefore, how to automatically adjust the position of the clothes according to the drying situation of the clothes has become an urgent problem to be solved. Summary of the Invention

[0006] To solve the technical problem of how to automatically adjust the position of the clothes according to the drying situation of the clothes, this application provides an automatic control method and system for an intelligent drying rack based on machine vision.

[0007] In a first aspect, this application provides an automatic control method for an intelligent drying rack based on machine vision, adopting the following technical solution:

[0008] The automatic control method for an intelligent drying rack based on machine vision includes the steps of: during the drying process, controlling the frame of the drying rack to rotate to adjust the drying position and angle of the hanging clothes; wherein, the drying rack includes a frame and petals circumferentially distributed on the frame, the frame can rotate around its own axis, and the petals are rotatably connected to the frame to adjust the opening angle of the petals.

[0009] The method for controlling the rotation of the drying rack is as follows: After the initial drying state lasts for a preset period, calculate the drying efficiency of the clothes hanging under each petal within the period. The drying efficiency is the ratio of the change value of the clothes weight within the period to the period. Taking the area of the vertical projection of the petal as one position and any petal as the target petal, move the target petal from the initial position to any other position, and use the sum of the differences in drying efficiency of each petal at different positions as the overall drying efficiency. Let the target petal traverse all positions, and take the position where the target petal with the maximum overall drying efficiency is located as the optimal position, and control the rotation of the rack body to move the target petal to the optimal position.

[0010] The beneficial effect is that after the clothes are hung and dried for a period of time, the drying rack is rotated to move the clothes with lower drying efficiency to the position with higher drying efficiency, achieving a global optimal solution. The overall drying efficiency is obtained by comparing the differences in drying efficiency of each petal at different positions, that is, by adding up the differences in drying efficiency of all petals at different positions to obtain an overall drying efficiency index. Ensure that the clothes can be dried evenly and efficiently during the drying process, especially when environmental factors such as light and wind speed change, it can automatically adjust to adapt to the best drying conditions.

[0011] Optionally, in response to the instruction to stop the rotation of the rack body, adjust the petal from the smallest opening angle to the largest opening angle; during this process, calculate the light intensity of the clothes hanging under the petal, and take the petal opening angle corresponding to the maximum light intensity as the optimal opening angle, and adjust the opening angle of the petal to the optimal opening angle.

[0012] The beneficial effect is that in order to optimize the drying plan on each petal, by adjusting the opening angle of the petal, the light intensity of the clothes hanging on the petal is maximized. By optimizing the opening angle of the petal, it can ensure that the clothes receive more uniform and sufficient sunlight during the drying process, thereby accelerating the drying speed of the clothes and improving the drying efficiency.

[0013] Optionally, the calculation method of the light intensity is as follows: , where is the light intensity of the clothes hanging on the th petal; is the total drying area of the clothes dried under the th petal; represents the gray value of the pixel point at

[0014] The beneficial effects are as follows: The grayscale value can be regarded as a quantitative representation of the light intensity received by the pixel. By adding up the grayscale values of all pixels in the clothing image, the total light intensity received by the entire clothing can be obtained. This sum is the accumulation of the light intensities of all parts of the clothing. The introduction of the mean calculation is to ensure consistency when comparing the light intensities of clothes of different sizes, because clothes with a larger area naturally receive more total light, but the average light intensity may be lower.

[0015] Optionally, the calculation method of the total drying area includes the steps of: inputting the collected image of the clothing into a trained target detection model, where the input of the target detection model is the collected image and the output is the range of the clothing in the image; taking the total number of pixels within the range of the clothing as the total drying area.

[0016] The beneficial effects are as follows: Using a target detection model to identify the boundary of the clothing can more accurately measure the actual drying area of the clothing.

[0017] Optionally, the training method of the target detection model is: annotating the clothing image set, determining the main body area of the clothing, taking the minimum external rectangle of the main body area of the clothing as the candidate box, and assigning a class label to the candidate box; using the annotated data to train a preset neural network model until the target detection model is obtained after training is completed.

[0018] Optionally, set the initial height of the clothes hanger. In response to the clothes hanger lowering instruction, obtain an image containing the user, identify the user's identity based on the user image to obtain height information, calculate the optimal clothes hanging height according to the height information, and control the clothes hanger to lower to the optimal clothes hanging height; in response to the clothes hanger raising instruction, control the clothes hanger to raise to the initial height.

[0019] Optionally, the calculation formula for the optimal clothes hanging height is: , where is the optimal clothes hanging height of the user ; is the initial height; is the height of the user ; is the suspension height adjustment parameter.

[0020] The beneficial effects are as follows: The clothes hanger automatically adjusts to the preset optimal height according to the identified height information, ensuring that the user can use it comfortably. If the user is shorter, the clothes hanger may lower to a lower position so that the user can easily hang and pick up clothes.

[0021] In the second aspect, the present application provides an automatic control system for an intelligent clothes hanger based on machine vision, adopting the following technical solutions:

[0022] An automatic control system for an intelligent drying rack based on machine vision, comprising: a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the automatic control method for the intelligent drying rack based on machine vision described above is implemented.

[0023] The beneficial effects are as follows: The automatic control method for the intelligent drying rack based on machine vision described above is generated into a computer program and stored in the memory to be loaded and executed by the processor. Thus, a system is made according to the memory and the processor, which is convenient to use.

[0024] The present application has the following technical effects:

[0025] 1. After the clothes are hung and dried for a period of time, the drying rack is rotated to move the clothes with lower drying efficiency to a position with higher drying efficiency, achieving a global optimal solution. The overall drying efficiency is obtained by comparing the drying efficiency differences of each petal at different positions, that is, adding up the drying efficiency differences of all petals at different positions to obtain an overall drying efficiency index. Ensure that the clothes can be dried evenly and efficiently during the drying process, especially when environmental factors such as light and wind speed change, it can automatically adjust to adapt to the best drying conditions.

[0026] 2. In order to optimize the drying solution on each petal, by adjusting the opening angle of the petal, the light intensity on the clothes hanging on the petal is maximized. By optimizing the opening angle of the petal, it can ensure that the clothes receive more uniform and sufficient sunlight during the drying process, thereby accelerating the drying speed of the clothes and improving the drying efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] By referring to the following detailed description with reference to the accompanying drawings, the above and other objects, features, and advantages of the exemplary embodiments of the present application will become readily understandable. In the drawings, several embodiments of the present application are shown in an exemplary rather than restrictive manner, and the same or corresponding reference numerals represent the same or corresponding parts.

[0028] Figure 1 It is a flowchart of the method for the automatic control method of the intelligent drying rack based on machine vision in an embodiment of the present application.

[0029] Figure 2 It is a schematic structural diagram of the drying rack in the automatic control method of the intelligent drying rack based on machine vision in an embodiment of the present application.

[0030] Figure 3 It is a flowchart of the method for controlling the rotation of the drying rack in the automatic control method of the intelligent drying rack based on machine vision in an embodiment of the present application.

[0031] Reference numerals: 1, clothes drying component; 2, storage slot; 3, hook; 4, second motor. Specific embodiments

[0032] The following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are some, but not all, of the embodiments of the present application. All other embodiments obtained by those skilled in the art based on the embodiments in the present application without creative efforts fall within the protection scope of the present application.

[0033] It should be understood that when terms such as "first" and "second" are used in the claims, the description, and the drawings of the present application, they are only used to distinguish different objects and not to describe a specific order. The terms "including" and "comprising" used in the description and claims of the present application indicate the presence of the described features, wholes, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or their combinations.

[0034] The embodiments of the present application disclose an automatic control method for an intelligent clothes hanger based on machine vision, as Figure 1 shown, the method includes steps S1 - S3:

[0035] S1: Set the initial height of the clothes hanger. In response to the clothes hanger lowering instruction, obtain an image containing the user, identify the user's identity based on the user image to obtain height information, calculate the optimal clothes hanging height according to the height information, and control the clothes hanger to lower to the optimal clothes hanging height; in response to the clothes hanger rising instruction, control the clothes hanger to rise to the initial height.

[0036] In one embodiment, a lifting component is provided on the clothes hanger. The lifting component can be a telescopic frame or a hanging rope on the clothes hanger in the prior art to control the lifting of the clothes hanger. The clothes hanger can receive voice instructions or remote control instructions from a remote controller to perform lifting.

[0037] Referring to Figure 2 , the clothes hanger includes a disc-shaped frame body and a plurality of clothes hanging parts 1. The plurality of clothes hanging parts 1 are distributed along the circumference of the frame body and can be unfolded in a petal shape. The clothes hanging part 1 can be a plate-shaped structure or a rod-shaped structure. For the convenience of description, the clothes hanging part 1 will be referred to as a petal hereinafter. One end of the petal is rotatably connected to the frame body through a hinge shaft. A storage groove 2 is provided on the frame body, and a first motor is fixedly placed in the storage groove 2. The output shaft of the first motor is coaxially fixed to the hinge shaft, and the first motor can drive the petal to rotate to adjust the opening angle of the petal.

[0038] Below the petals, there are multiple hooks 3 hanging. The hooks 3 are hinged to the petals, and the multiple hooks 3 are arranged at intervals and evenly along the length direction of the petals. A housing is fixedly arranged on the disc. A second motor 4 is arranged on the upper surface of the housing. The output shaft of the second motor 4 is fixedly connected to the frame body, and the output shaft of the second motor 4 is coaxial with the output shaft of the frame body. The lifting assembly is connected to the second motor 4. Exemplarily, when the lifting assembly is a suspension rope, a hanging ring can be welded on the casing of the second motor 4 to connect the suspension rope. When the lifting assembly is a telescopic frame, the moving and extending end of the telescopic frame is welded to the casing of the second motor 4.

[0039] To identify the height information of a person, the user needs to manually set the initial height and input the face. When the user first uses the clothes dryer, the user needs to manually input their height information and input the face data. This can be done through an application or control panel connected to the clothes dryer. A camera is set on the clothes dryer. When the user issues a lowering command (which may be through a voice command, remote control or application button), the clothes dryer starts to lower, takes a video of the user, and identifies the user's identity through face recognition, and retrieves the height information associated with the user from the database.

[0040] The calculation formula for the optimal clothes drying height is: , where is the optimal clothes drying height for the user ; is the initial height; is the height of the user ; is the suspension height adjustment parameter. Exemplarily, , which can be adjusted by the user according to the actual application scenario.

[0041] The clothes dryer automatically adjusts to the preset optimal height according to the identified height information to ensure that the user can use it comfortably. If the user is relatively short, the clothes dryer may lower to a lower position so that the user can easily hang and pick up clothes.

[0042] In other embodiments, the lifting assembly may not be provided, and the second motor 4 of the clothes dryer is fixed on the storage rack, and the storage rack is placed on the ground.

[0043] S2: During the drying process, control the rotation of the frame of the clothes dryer to adjust the drying position and angle of the hanging clothes.

[0044] Referring to Figure 3 , the method for controlling the rotation of the clothes dryer includes steps S20 - step S22, which are as follows:

[0045] S20: After the initial drying state lasts for a preset period, calculate the drying efficiency of the clothes hanging below each petal within the period. The drying efficiency is the ratio of the change value of the clothes weight within the period to the period.

[0046] Exemplarily, after hanging the clothes, the user can send a command indicating that hanging is complete through a voice command or by pressing a button on the remote control. At this time, the first period starts to be calculated. A period can be 1 hour. 1 hour is a hyperparameter that can be adjusted by the user according to the actual application scenario. The clothes drying state in the first period is the initial drying state.

[0047] Gravity sensors are installed on each petal. During the process of drying the clothes, the weight change of the clothes is collected through the gravity sensors. After one period, calculate the drying efficiency of the clothes hanging below each petal within the period. The calculation formula for the drying efficiency is: , where is the weight change rate of the clothes hanging below the th petal within the period. The greater the change rate, the more conducive the position where the petal is located is to drying the clothes; is the initial weight of the clothes hanging below the th petal; is the weight of the clothes hanging below the th petal after the period .

[0048] S21: Take the area of the vertical projection of the petal as one position, take any petal as the target petal, move the target petal from the initial position to any other position, and use the sum of the differences in drying efficiency of each petal at different positions as the overall drying efficiency.

[0049] The rotation here is not an actual rotation. The purpose is to calculate the overall drying efficiency under each rotation scheme to find the scheme with the highest drying efficiency. The angle that the turntable can rotate is determined by the number of petals. When the number of petals is 4, the angles that the turntable can rotate are 90°, 180°, 270°, and 360°.

[0050] S22: Let the target petal traverse all positions, take the position where the target petal is located corresponding to the maximum value of the overall drying efficiency as the optimal position, and control the frame to rotate to move the target petal to the optimal position.

[0051] Calculate the overall drying efficiency. This efficiency is obtained by comparing the differences in drying efficiency of each petal at different positions, that is, by adding up the differences in drying efficiency of all petals at different positions to obtain an overall drying efficiency index. Ensure that the clothes can be dried evenly and efficiently during the drying process, especially when environmental factors such as light and wind speed change, it can automatically adjust to adapt to the best drying conditions.

[0052] S3: In response to the instruction for the rack to stop rotating, adjust the petals from the minimum opening angle to the maximum opening angle; during this process, calculate the illumination intensity of the clothes hanging under the petals, and use the petal opening angle corresponding to the maximum illumination intensity as the optimal opening angle, and adjust the opening angle of the petals to the optimal opening angle.

[0053] After receiving the instruction for the rack to stop rotating, the system will start the process of adjusting the opening angle of the petals. This step is the trigger point of the entire optimization process, ensuring that the drying rack is in a stationary state for subsequent adjustment operations.

[0054] In one embodiment, the end point values of the petal opening angle range are the maximum and minimum angles at which the petals can open. Exemplarily, taking the horizontal plane as zero degrees, the petals can open to positions 60° below the horizontal plane and 120° above the horizontal plane. For the convenience of description, the angles below the horizontal plane are recorded as negative numbers, and the angles above the horizontal plane are recorded as positive numbers. After the rack stops rotating, the petals will start from 60° below the horizontal plane and gradually adjust to 120° above the horizontal plane. Taking 10° as an interval, record the illumination intensities corresponding to -60°, -50°, … 0°, … 120° respectively.

[0055] Calculate the total drying area and then according to the illumination intensity of the total drying area.

[0056] In one embodiment, the calculation method of the total drying area is as follows: input the collected image of the clothes into the trained target detection model. The input of the target detection model is the collected image, and the output is the range of clothes in the image; use the total number of pixel points within the range of clothes as the total drying area.

[0057] The camera for collecting images here can be the same as the camera for identifying the user's identity above, or can be set separately. The installation position of the camera can be on one side of the petal, used to capture the collected image of the clothes hanging on the vector petal. This installation method can reduce the occlusion between clothes because the camera shoots from the side and can capture the contour and details of each piece of clothing, but can only shoot the side of the clothes. It can also be set at the outer end of the petal to obtain the collected image of the clothes hanging on this petal. However, under the collection angle of this scheme, there is more occlusion between clothes, but the front of the clothes can be shot, especially the front of the relatively outer clothes, and the light-receiving area of this part of the clothes is larger. The shadow and occlusion of the clothes are an inevitable part of the drying process. Therefore, these factors are considered when designing the shooting angle to obtain the actual illumination area relatively accurately.

[0058] The training method of the object detection model is as follows: annotate the clothing image set, determine the main body area of the clothing, and use the minimum external rectangle of the main body area of the clothing as the candidate box, and assign a class label to the candidate box; use the annotated data to train the preset neural network model until the object detection model is obtained after the training is completed.

[0059] The model can be selected from neural network models such as CNN (Convolutional Neural Networks) model or YOLO that can be applied to identify objects. The model and the process of model training are prior arts and will not be elaborated here.

[0060] In one embodiment, the calculation method of the illumination intensity is as follows: , where is the illumination intensity of the th petal hanging the clothing; is the total drying area of the clothing dried under the th petal; represents the gray value of the pixel at the position.

[0061] In image processing, the gray value is usually used to represent the brightness of each pixel in the image. The range of the gray value is usually from 0 to 255, where 0 represents black (no light) and 255 represents white (the brightest). Therefore, the gray value can be regarded as a quantitative representation of the illumination intensity received by the pixel. Adding up the gray values of all pixels in the clothing image can obtain the total illumination intensity received by the entire clothing. This sum is the accumulation of the illumination intensities of all parts of the clothing. The introduction of the mean calculation is to ensure the consistency when comparing the illumination intensities of clothes of different sizes, because clothes with a larger area naturally receive more total light, but the average illumination intensity may be lower.

[0062] In one embodiment, the drying angles between the petals may be the same. When they are the same, it will affect the overall ventilation efficiency of clothing drying. Therefore, when the drying angles of the petals are the same, fix the drying angle of one petal and adjust the drying angle of the other petal to the angle with the maximum illumination intensity among other angles except the fixed angle.

[0063] The embodiment of the present application also discloses an automatic control system for an intelligent clothes hanger based on machine vision, including a processor and a memory. The memory stores computer program instructions, and when the computer program instructions are executed by the processor, the automatic control method for the intelligent clothes hanger based on machine vision according to the present application is implemented.

[0064] The above system also includes other components well-known to those skilled in the art such as a communication bus and a communication interface. Their settings and functions are known in the art, so they will not be elaborated here.

[0065] In the present application, the foregoing memory may be any tangible medium that contains or stores a program, which can be used by or in conjunction with an instruction execution system, apparatus, or device. For example, a computer-readable storage medium may be any suitable magnetic storage medium or magneto-optical storage medium, such as a resistive random access memory (RRAM), a dynamic random access memory (DRAM), a static random access memory (SRAM), an enhanced dynamic random access memory (EDRAM), a high bandwidth memory (HBM), a hybrid memory cube (HMC), etc., or any other medium that can be used to store the required information and can be accessed by an application program, a module, or both. Any such computer storage medium may be part of the device or accessible or connectable to the device.

[0066] Although this specification has shown and described multiple embodiments of the present application, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Those skilled in the art will think of many changes, alterations, and alternative ways without departing from the spirit and scope of the present application. It should be understood that various alternatives to the embodiments of the present application described herein may be employed in the practice of the present application.

[0067] The above are all preferred embodiments of the present application, and the protection scope of the present application is not limited thereby. Therefore, all equivalent changes made according to the structure, shape, and principle of the present application shall be covered within the protection scope of the present application.

Claims

1. An automatic control method for an intelligent clothes drying rack based on machine vision, characterized in that: Includes steps: Setting the initial height of the clothes rack, responding to the clothes rack lowering instruction, obtaining a user image, identifying the user identity according to the user image to obtain height information, calculating the optimal clothes drying height according to the height information, and controlling the clothes rack to descend to the optimal clothes drying height; responding to the clothes rack raising instruction, controlling the clothes rack to rise to the initial height; During the drying process, the frame of the clothes drying rack is controlled to rotate to adjust the drying position and angle of the hung clothes; wherein the clothes drying rack comprises a frame and petals circumferentially distributed on the frame, the frame can rotate around its own axis, and the petals are rotatably connected to the frame to adjust the opening angle of the petals; The method to control the rotation of the clothes drying rack is: In response to the initial drying state continuing for a preset period, the drying efficiency of the clothes hung under each petal in the period is calculated, where the drying efficiency is the ratio of the change value of the clothes weight in the period to the period; The vertical projection area of ​​the petals is taken as a position, and any petal is taken as the target petal. The target petal is moved from the initial position to any other position, and the cumulative sum of the differences in the drying efficiencies of the petals at different positions is taken as the overall drying efficiency; The target petals are made to traverse all positions, and the position of the target petals corresponding to the maximum overall drying efficiency is taken as the optimal position, and the frame is controlled to rotate so that the target petals are moved to the optimal position; The method also includes the following steps: in response to an instruction to stop rotating the frame, adjusting the petals from a minimum opening angle to a maximum opening angle; in this process, calculating the light intensity of the clothes hung under the petals, taking the petals opening angle corresponding to the maximum light intensity as the optimal opening angle, and adjusting the petals opening angle to the optimal opening angle.

2. The method for automatically controlling an intelligent clothes drying rack based on machine vision according to claim 1, characterized in that: The method for calculating the total drying area includes the following steps: The collected image of the clothes is input into the trained target detection model. The input of the target detection model is the collected image, and the output is the range of the clothes in the image. The total number of pixels in the range of the clothes is taken as the total drying area.

3. The automatic control method of the intelligent clothes drying rack based on machine vision according to claim 2 is characterized in that: The training method of the target detection model is as follows: annotate the clothing image set, determine the main area of ​​the clothing, and use the minimum outer rectangle of the main area of ​​the clothing as the candidate box, and label the candidate box with a category; use the annotated data to train the preset neural network model until the target detection model is obtained after the training is completed.

4. The automatic control method of the intelligent clothes drying rack based on machine vision according to claim 1 is characterized in that: The formula for calculating the optimal height of clothes drying is: , where For users The optimal height for drying clothes; is the initial height; For users height; Adjustment parameters for suspension height.

5. An intelligent clothes drying rack automatic control system based on machine vision, characterized in that: include: A processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the automatic control method of the intelligent clothes drying rack based on machine vision according to any one of claims 1 to 4 is implemented.

Images