Fan opening degree adjusting method, device and equipment in fresh tea leaf sorting process based on image recognition, medium and product

Abstract

The invention discloses a fan opening degree adjusting method, device and equipment in the fresh tea leaf sorting process based on image recognition, a medium and a product, and relates to the technical field of fresh tea leaf sorting. The method comprises the steps that a first continuous image and a second RGB image of target fresh tea leaves in the falling process at an outlet of a first conveying belt are obtained, the first continuous image comprises a plurality of first RGB images; extracting a target fresh tea leaf area from each first RGB image and each second RGB image by adopting a color segmentation method; calculating the physical position and the vertical speed of the target fresh tea leaf according to the target fresh tea leaf areas of the two adjacent first RGB images; calculating the projection area of the target fresh tea leaf according to the target fresh tea leaf area of the second RGB image; and determining the air flow of the fan outlet according to the physical position, the vertical speed and the projection area, and adjusting the opening degree of the fan based on the air flow. The opening degree of the fan can be adjusted in a self-adaptive mode, so that impact force borne by target fresh tea leaves when the target fresh tea leaves fall onto the conveying belt is reduced, and the tea leaf quality is improved.

Description

Technical Field

[0001] The present application relates to the technical field of fresh tea leaf sorting, and in particular to a method, device, equipment, medium and product for adjusting the opening of a fan in a fresh tea leaf sorting process based on image recognition. Background Art

[0002] In the process of sorting fresh tea leaves in tea processing, traditional air sorting technology is widely used. Its main working principle is to use the synergy of high-pressure air and valves to blow fresh tea leaves with different characteristics to the corresponding conveyor belt to achieve preliminary sorting. Specifically, the high-pressure air source generates a strong airflow, and under the control of the valve, the airflow impacts the falling fresh tea leaves according to the predetermined path and intensity. Driven by the airflow, the selected fresh tea leaves obtain a certain initial velocity and move towards the conveyor belt.

[0003] Since fresh tea leaves are soft in texture, they are often blown to the conveyor belt by high-pressure air at a high speed. At the moment of contact with the conveyor belt, the edges of the fresh tea leaves are easily damaged due to high-speed collision. During the subsequent processing and storage process, the damaged parts will gradually undergo chemical changes, initially showing signs of yellowing, and turning red as time goes on. When the tea leaves are made into finished tea, obvious marks will appear on the edges of the damaged tea leaves when brewing, which greatly affects the appearance of the tea leaves and reduces their appeal in the market. In addition, the changes in the chemical properties of the tea leaves caused by the collision also affect the original flavor of the tea leaves to a certain extent. The subtle changes in taste can be clearly detected by professional tasting or consumers with high requirements for tea quality. This has formed a significant obstacle to the improvement of the overall quality of the tea leaves and is difficult to meet the needs of high-quality tea production and processing. However, traditional air selection technology cannot adaptively adjust the fan flow according to the selected fresh tea leaves, causing the fresh tea leaves to be damaged when they are blown to the conveyor belt. Summary of the invention

[0004] The purpose of this application is to provide a method, device, equipment, medium and product for adjusting the fan opening in the process of fresh tea leaf sorting based on image recognition, which can adaptively adjust the fan opening to reduce the impact force on the target fresh tea leaves when they fall onto the conveyor belt, thereby improving the quality of the tea.

[0005] To achieve the above objectives, this application provides the following solutions:

[0006] In a first aspect, the present application provides a method for adjusting fan opening in a fresh tea leaf sorting process based on image recognition, comprising:

[0007] Acquire a first continuous image and a second RGB image of the target fresh tea leaves falling from the exit of the first conveyor belt to the second conveyor belt, wherein the first continuous image includes a plurality of first RGB images; the first RGB image is an image in the vertical direction of the target fresh tea leaves falling, and the second RGB image is an image in the horizontal direction of the target fresh tea leaves falling;

[0008] Extracting the target fresh tea leaf area in each of the first RGB image and the second RGB image using a color segmentation method;

[0009] Calculating the physical position and vertical speed of the target fresh tea leaves according to the target fresh tea leaf regions of the two adjacent first RGB images;

[0010] Calculating the projection area of ​​the target fresh tea leaves according to the target fresh tea leaves area of ​​the second RGB image;

[0011] The air flow rate at the fan outlet is determined according to the physical position, the vertical speed, and the projected area, and the fan opening is adjusted based on the air flow rate.

[0012] Furthermore, before acquiring the first continuous image and the second RGB image of the target fresh tea leaves at the outlet of the first conveyor belt, the method further includes:

[0013] Using a first shooting device disposed on the exit side of the first conveyor belt to shoot first continuous images of the target fresh tea leaves, and determining a scale factor of each first RGB image in the first continuous images as a first scale factor;

[0014] A second shooting device disposed just above the exit of the first conveyor belt is used to shoot a second RGB image of the target fresh tea leaves, and a scale factor of the second RGB image is determined as a second scale factor.

[0015] Furthermore, a color segmentation method is used to extract a target fresh tea leaf region in each of the first RGB image and the second RGB image, specifically including:

[0016] Preprocessing the first RGB image and the second RGB image;

[0017] Convert the RGB color space of the preprocessed first RGB image and the second RGB image into the HSV color space;

[0018] Creating a binary mask in the preprocessed first RGB image and the second RGB image according to a preset upper bound and a lower bound of an HSV color space;

[0019] The target fresh tea leaf region in each of the first RGB image and the second RGB image is extracted using the binary mask.

[0020] Further, calculating the physical position and vertical speed of the target fresh tea leaves according to the target fresh tea leaf regions of two adjacent first RGB images specifically includes:

[0021] Calculating the physical position of the target fresh tea leaves in the two adjacent first RGB images according to the first scale factor of the two adjacent first RGB images;

[0022] Determine the change distance of the target fresh tea leaves according to the physical positions of the target fresh tea leaves in two adjacent first RGB images;

[0023] Determine the time interval according to the shooting time of two adjacent first RGB images;

[0024] The vertical speed of the target fresh tea leaves is calculated based on the change distance and the time interval.

[0025] Further, calculating the projection area of ​​the target fresh tea leaves according to the target fresh tea leaf area of ​​the second RGB image specifically includes:

[0026] Counting the number of pixels occupied by the target fresh tea leaf area in the second RGB image;

[0027] The projection area of ​​the target fresh tea leaves is calculated using the second scale factor and the number of pixels.

[0028] Furthermore, the calculation formula of the projected area of ​​the target fresh tea leaves is:

[0029]

[0030] Among them, B actual is the projection area of ​​the target fresh tea leaves, B pixel is the number of pixels occupied by the target fresh tea leaf area, S B is the second scaling factor.

[0031] In a second aspect, the present application provides a fan opening adjustment device in a fresh tea leaf sorting process based on image recognition, comprising:

[0032] an acquisition module, used to acquire a first continuous image and a second RGB image of the target fresh tea leaves in the process of falling at the exit of the first conveyor belt, wherein the first continuous image includes a plurality of first RGB images; the first RGB image is an image in the vertical direction of the target fresh tea leaves in the process of falling, and the second RGB image is an image in the horizontal direction of the target fresh tea leaves in the process of falling;

[0033] An image recognition module, used for determining a target fresh tea leaf region in each of the first RGB image and the second RGB image by using a color segmentation method;

[0034] A first calculation module, used for calculating the physical position and vertical speed of the target fresh tea leaves according to the target fresh tea leaf regions of two adjacent first RGB images;

[0035] A second calculation module, used for calculating the projection area of ​​the target fresh tea leaves according to the target fresh tea leaf area of ​​the second RGB image;

[0036] The regulating module is used to determine the air flow rate at the fan outlet according to the physical position, the vertical speed, and the projected area, and adjust the fan opening based on the air flow rate.

[0037] In a third aspect, the present application provides a computer device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the above-mentioned method for adjusting the fan opening in the fresh tea leaf sorting process based on image recognition.

[0038] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the above-mentioned method for adjusting the fan opening in the fresh tea leaf sorting process based on image recognition.

[0039] In a fifth aspect, the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the above-mentioned method for adjusting the fan opening in the fresh tea leaf sorting process based on image recognition.

[0040] According to the specific embodiments provided in this application, this application discloses the following technical effects:

[0041] The present application provides a method, device, equipment, medium and product for adjusting the fan opening in a tea leaf sorting process based on image recognition. The color segmentation method is used to extract the target tea leaf area in each first RGB image and the second RGB image. Based on this, the physical position and vertical speed of the target tea leaf are calculated, and the initial position state of the target tea leaf when starting to decelerate is determined; in order to make the speed of the target tea leaf falling to the second conveyor belt approach zero, the final position state of the target tea leaf is determined, and the air resistance encountered by the target tea leaf during the falling process is calculated through the initial position state and the final position state. Then, the projected area of ​​the target tea leaf can be used to calculate the air flow rate at the fan outlet required when the target tea leaf reaches the final position state, and then the fan opening is adjusted according to the air flow rate, so that the speed of the target tea leaf when falling to the second conveyor belt approaches zero, the impact force is minimized, the integrity of the target tea leaf is guaranteed to the greatest extent, and the quality of the tea leaves is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0043] Figure 1 This is a schematic diagram of the working process of a fresh tea leaf sorting device in one embodiment of the present application;

[0044] Figure 2 A schematic flow chart of a method for adjusting fan opening in a fresh tea leaf sorting process based on image recognition provided in an embodiment of the present application;

[0045] Figure 3 A schematic diagram of the physical location of target fresh tea leaves provided in one embodiment of the present application;

[0046] Figure 4 A schematic diagram of the functional modules of a fan opening adjustment device in a fresh tea leaf sorting process based on image recognition provided in another embodiment of the present application;

[0047] Figure 5 A schematic diagram of the structure of a computer device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0048] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0049] In order to make the purpose, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below with reference to the accompanying drawings and specific implementation methods.

[0050] The fan opening adjustment method in the fresh tea leaf sorting process based on image recognition provided in this embodiment is applied to a fresh tea leaf sorting device, such as Figure 1 As shown, the fresh tea leaf sorting device includes a first conveyor belt 1, a second conveyor belt 2 and a fan 3. The fresh tea leaves fly out horizontally with a certain initial velocity under the action of the first conveyor belt 1. The fresh leaves to be selected, that is, the target fresh tea leaves, are changed in flight trajectory by the high-pressure airflow sprayed from the downward air nozzle 4, and obtain a certain vertical speed, so that the target fresh tea leaves fall onto the second conveyor belt 2, and the fan 3 provides a decelerating airflow upward to change the air resistance encountered by the target fresh tea leaves during the falling process, thereby reducing the vertical speed of the target fresh tea leaves.

[0051] like Figure 2 As shown, the method for adjusting the fan opening in the fresh tea leaf sorting process based on image recognition includes the following steps 101 to 105. Among them:

[0052] Step 101, obtaining a first continuous image and a second RGB image of a target fresh tea leaf falling from the exit of the first conveyor belt to the second conveyor belt, wherein the first continuous image includes multiple first RGB images; the first RGB image is an image in the vertical direction of the target fresh tea leaf falling, and the second RGB image is an image in the horizontal direction of the target fresh tea leaf falling.

[0053] Step 102: extracting the target fresh tea leaf region in each of the first RGB image and the second RGB image using a color segmentation method.

[0054] Step 103: calculating the physical position and vertical speed of the target fresh tea leaves according to the target fresh tea leaf regions in two adjacent first RGB images.

[0055] Step 104: Calculate the projection area of ​​the target fresh tea leaves according to the target fresh tea leaf region of the second RGB image.

[0056] Step 105, determining the air flow rate at the fan outlet according to the physical position, the vertical speed, and the projected area, and adjusting the fan opening based on the air flow rate.

[0057] By implementing steps 101 to 105, the opening of the fan 3 can be adaptively adjusted to change the air flow rate, thereby changing the air resistance encountered by the target fresh tea leaves in the process of leaving the first conveyor belt 1 and falling to the second conveyor belt 2, so that the speed at which the target fresh tea leaves fall to the second conveyor belt 2 approaches 0, thereby minimizing damage to the target fresh tea leaves and thereby improving the quality of the tea leaves.

[0058] In an exemplary embodiment, before step 101, steps 1001-1002 are also included:

[0059] Step 1001: Use a first shooting device arranged on the exit side of the first conveyor belt to shoot first continuous images of target fresh tea leaves, and determine the scale factor of each first RGB image in the first continuous image as the first scale factor.

[0060] The first shooting device on the exit side of the first conveyor belt is used to shoot the vertical image of the target fresh tea leaves in the process of leaving the first conveyor belt and falling to the second conveyor belt. Specifically, the first shooting device is an RGB camera. Figure 1As shown, area A is the area where the target tea leaves are accelerated downward by the high-pressure airflow, and area B is the area covered by the first shooting device, that is, the area where the target tea leaves are decelerated. In area B, the target tea leaves are affected by air resistance and are not affected by the downward force formed by the high-pressure airflow.

[0061] The process of determining the first scale factor includes steps 1.1 to 1.5:

[0062] Step 1.1 Use the first shooting device and light source to shoot a projection area A actual , a block with simple surface texture is used to obtain a reference image to facilitate accurate identification and measurement in the image.

[0063] Step 1.2: Convert the reference image to grayscale to simplify processing and apply Gaussian filtering to reduce noise.

[0064] Step 1.3: Use Canny edge detection to identify the boundaries of the blocks in the reference image.

[0065] Step 1.4: Use area filling to calculate the number of pixels n inside the block boundary in the reference image and get the area A of each pixel pixel .

[0066] Step 1.5: Use the formula: Obtain the scale factor between the image pixels of the reference image and the actual physical coordinates, and use the scale factor as the first scale factor S of the first RGB image. A .

[0067] Step 1002: Use a second shooting device disposed just above the exit of the first conveyor belt to shoot a second RGB image of the target fresh tea leaves, and determine a scale factor of the second RGB image as a second scale factor. Specifically, the second shooting device is an RGB camera. At the same time, the second scale factor S is determined according to the method for determining the first scale factor. B , which will not be elaborated here.

[0068] In an exemplary embodiment, step 102 specifically includes steps 201 to 204:

[0069] Step 201: preprocess the first RGB image and the second RGB image.

[0070] Specifically, to improve the processing speed, the resolutions of the first RGB image and the second RGB image are compressed so that the resolutions of the first RGB image and the second RGB image are preset values, which may be 800*800 or other values, and are not limited in this embodiment.

[0071] Gaussian blur processing is performed on the first RGB image and the second RGB image with preset resolution to reduce noise in the images, thereby obtaining the preprocessed first RGB image and the second RGB image.

[0072] Step 202: Convert the RGB color space of the preprocessed first RGB image and the second RGB image into an HSV color space.

[0073] Step 203: Create a binary mask in the preprocessed first RGB image and the second RGB image according to the upper and lower bounds of the preset HSV color space.

[0074] At a color temperature of 6000K, multiple images of target fresh tea leaves are taken, and their average HSV (hue, saturation, value) color space range is obtained. The upper and lower bounds of the HSV color space are determined according to the average HSV color space range.

[0075] Step 204: extracting the target fresh tea leaf region in each of the first RGB image and the second RGB image using the binary mask.

[0076] In the specific implementation process, after creating the binary mask, a closing operation is used to fill the holes inside the target fresh tea leaf area, and the filled binary mask is used to extract the target fresh tea leaf area in each of the first RGB image and the second RGB image.

[0077] In an exemplary embodiment, step 103 specifically includes steps 301 to 304:

[0078] Step 301, calculating the physical position of the target fresh tea leaves in two adjacent first RGB images according to the first scale factor of the two adjacent first RGB images. Specifically including steps 3.1 to 3.3:

[0079] Step: 3.1: Calculate the actual position of the target tea leaf on the horizontal coordinate X in the first RGB image, using the formula: 实际 =X 像素 ×S A get.

[0080] Step 3.2: Calculate the actual position of the target tea leaf on the ordinate Y in the first RGB image, using the formula: 实际 =Y 像素 ×S A get.

[0081] like Figure 3 As shown, X 像素 Y is the number of pixels in the horizontal direction from the image boundary of the first RGB image to the midpoint of the target fresh tea leaf; 像素is the number of pixels in the vertical direction from the image boundary of the first RGB image to the midpoint of the target fresh tea leaf.

[0082] Step 3.3: Combine X 实际 With Y 实际 Get the physical location of the target fresh tea leaves.

[0083] According to steps 3.1 to 3.3, the physical positions of the target fresh tea leaves in two adjacent first RGB images are calculated respectively.

[0084] Step 302: determining a change distance of the target fresh tea leaves according to the physical positions of the target fresh tea leaves in two adjacent first RGB images.

[0085] For example, calculate Y by the method in step 3.2 1 and Y 2 ; Among them, Y 1 and Y 2 is the actual vertical coordinate of the target fresh tea leaf in the two adjacent first RGB images.

[0086] Using the formula: ΔY=Y 1 -Y 2 The vertical displacement of the target fresh tea leaves in two adjacent first RGB images, that is, the change distance ΔY of the target fresh tea leaves is calculated.

[0087] Step 303: determine the time interval according to the shooting time of two adjacent first RGB images.

[0088] Specifically, the time interval Δt between the shooting of two adjacent first RGB images is calculated. It is known that the first shooting device shoots at a speed of 60 images per second. Therefore, the time interval between the shooting of two adjacent first RGB images is:

[0089] Step 304: Calculate the vertical speed of the target fresh tea leaves based on the change distance and time interval.

[0090] Using the formula: Calculate the vertical velocity and obtain the vertical velocity V of the target fresh tea leaves 垂直 .

[0091] In the specific implementation process, the method in step 3.1 can also be used to calculate X 1 and X 2 , X 1 and X 2 is the actual horizontal coordinate of the target fresh tea leaf in the two adjacent first RGB images.

[0092] Use the formula: ΔX=X 1 -X 2Calculate the horizontal displacement ΔX of the target fresh tea leaves in two adjacent first RGB images, and on this basis, use the formula: Calculate the horizontal speed V of the target tea leaves 水平 .

[0093] In an exemplary embodiment, step 104 specifically includes: counting the number of pixels occupied by the target fresh tea leaf area in the second RGB image; and calculating the projection area of ​​the target fresh tea leaf using a second scale factor and the number of pixels.

[0094] The calculation formula of the projected area of ​​the target fresh tea leaves is:

[0095]

[0096] Among them, B actual is the projection area of ​​the target fresh tea leaves, B pixel is the number of pixels occupied by the target fresh tea leaf area, S B is the second scaling factor.

[0097] In an exemplary embodiment, step 105 specifically includes steps 4.1 to 4.7:

[0098] Step 4.1: Calibrate the environment of the fresh tea leaf sorting device, the fan in the fresh tea leaf sorting device, and the parameters of the target fresh tea leaves.

[0099] The room temperature is 25℃, and the air density is about: ρ≈1.184kg / m 3 ; Gravitational acceleration: g≈9.81m / s 2 ; Air flow of fan 3 at rated speed: Q = 2000m 3 / h; when the throttle valve of fan 3 is opened to 100%, Q = 2000m 3 / h, when the throttle valve is opened 50%, Q = 1000m 3 / h; fan outlet size: A outlet =0.0162m 2 ; The mass of each target fresh tea leaf is m = 1g; The air resistance coefficient of the target fresh tea leaf is: C d =1.2; the projected area of ​​the target fresh tea leaves is S 鲜叶 =B actual .

[0100] Step 4.2: Obtain the physical position of the target fresh tea leaves obtained in step 301, and obtain the vertical velocity V of the target fresh tea leaves in step 304 垂直 Step 104 obtains the projection area B of the target fresh tea leaves. actual .

[0101] Step 4.3: Calculate the deceleration a required for the target fresh tea leaves.

[0102] In order to make the target tea leaves move from the vertical speed V 垂直 That is, the speed at the initial position is decelerated to zero, and the deceleration is completed within a height h, where the height h is the distance from the initial position to the second conveyor belt, and the height h changes with the distance between the target fresh tea leaves and the second conveyor belt 2, wherein the initial position is Figure 1 The position where area A and area B touch each other, therefore, using the kinematic formula: It is known that when the target fresh tea leaves fall on the second conveyor belt 2, the speed is infinitely close to 0m / s, that is, V is 0, then the acceleration a of the target fresh tea leaves falling to the second conveyor belt is:

[0103] Step 4.4: Calculate the air resistance experienced by the target fresh tea leaves based on the force experienced by the target fresh tea leaves in the process of falling onto the second conveyor belt.

[0104] F d =m×a+m×g=F a +F g ;

[0105] Among them, F a is the force required to decelerate the target fresh tea leaves, F d is the air resistance, F g The target is the gravity exerted on fresh tea leaves.

[0106] Step 4.5: Calculate the air velocity at the fan outlet.

[0107] Using the formula: The air flow velocity at the fan outlet is derived, where A is the projected area of ​​the target fresh tea leaves; the expression of the air flow velocity is:

[0108] Therefore, the F calculated according to step 4.4 is d , combined with the air velocity v air The air velocity at the fan outlet is calculated using the expression

[0109] Step 4.6: Calculate the fan outlet air flow rate.

[0110] Using the formula: Q = v air ×A outlet The air flow rate at the fan outlet is calculated using the air flow velocity at the fan outlet obtained in step 4.5, where Q is the air flow rate.

[0111] Step 4.7: Adjust the fan opening according to the calculated air flow.

[0112] The wind force of the fan is determined by the fan speed and the throttle valve opening, wherein the fan reaches the rated operating speed and maintains the speed unchanged after starting; the air flow can be controlled by adjusting the throttle valve opening. In this embodiment, the adjusted fan opening refers to the throttle valve opening.

[0113] Therefore, after the required air flow is calculated in step 4.6, the fan opening can be adjusted according to the required air flow.

[0114] Based on the same inventive concept, the embodiment of the present application also provides a fan opening adjustment device in the process of fresh tea leaves sorting based on image recognition for realizing the fan opening adjustment method in the process of fresh tea leaves sorting based on image recognition mentioned above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in the embodiments of one or more fan opening adjustment devices in the process of fresh tea leaves sorting based on image recognition provided below can refer to the limitations of the fan opening adjustment method in the process of fresh tea leaves sorting based on image recognition above, and will not be repeated here.

[0115] In an exemplary embodiment, Figure 4 As shown, a fan opening adjustment device in a fresh tea leaf sorting process based on image recognition is provided, comprising:

[0116] The acquisition module 41 is used for the first RGB image to be an image in the vertical direction of the target fresh tea leaves during the falling process, and the second RGB image to be an image in the horizontal direction of the target fresh tea leaves during the falling process.

[0117] The image recognition module 42 is used to determine the target fresh tea leaf area in each of the first RGB image and the second RGB image by using a color segmentation method.

[0118] The first calculation module 43 is used to calculate the physical position and vertical speed of the target fresh tea leaves according to the target fresh tea leaf regions of two adjacent first RGB images.

[0119] The second calculation module 44 is used to calculate the projection area of ​​the target fresh tea leaves according to the target fresh tea leaf area of ​​the second RGB image.

[0120] The regulating module 45 is used to determine the air flow rate at the fan outlet according to the physical position, the vertical speed, and the projected area, and adjust the fan opening based on the air flow rate.

[0121] In an exemplary embodiment, a computer device is provided. The computer device may be a server or a terminal. The internal structure diagram thereof may be as follows: Figure 5As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store the first continuous image and the second RGB image of the target fresh tea leaves falling at the exit of the first conveyor belt. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a fan opening adjustment method in a fresh tea leaf sorting process based on image recognition is implemented.

[0122] Those skilled in the art will understand that Figure 5 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0123] In an exemplary embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above-mentioned method embodiments when executing the computer program.

[0124] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0125] In an exemplary embodiment, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0126] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0127] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM may be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0128] The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. The non-relational database may include a distributed database based on blockchain, etc., but is not limited thereto. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but is not limited thereto.

[0129] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0130] This article uses specific examples to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the method and core ideas of this application. At the same time, for those skilled in the art, according to the ideas of this application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. A method for adjusting the fan opening in a fresh tea leaf sorting process based on image recognition, applied to a fresh tea leaf sorting device, the fresh tea leaf sorting device comprising a first conveyor belt, a second conveyor belt and a fan, characterized in that: The method for adjusting the fan opening in the fresh tea leaf sorting process based on image recognition includes: Acquire a first continuous image and a second RGB image of the target fresh tea leaves falling from the exit of the first conveyor belt to the second conveyor belt, wherein the first continuous image includes a plurality of first RGB images; the first RGB image is an image in the vertical direction of the target fresh tea leaves falling, and the second RGB image is an image in the horizontal direction of the target fresh tea leaves falling; Extracting the target fresh tea leaf area in each of the first RGB image and the second RGB image using a color segmentation method; Calculating the physical position and vertical speed of the target fresh tea leaves according to the target fresh tea leaf regions of the two adjacent first RGB images; Calculating the projection area of ​​the target fresh tea leaves according to the target fresh tea leaves area of ​​the second RGB image; The air flow rate at the fan outlet is determined according to the physical position, the vertical speed, and the projected area, and the fan opening is adjusted based on the air flow rate.

2. The method for adjusting fan opening in the process of fresh tea leaf sorting based on image recognition according to claim 1, characterized in that: Before acquiring the first continuous image and the second RGB image of the target fresh tea leaves at the exit of the first conveyor belt, the method further includes: Using a first shooting device disposed on the exit side of the first conveyor belt to shoot first continuous images of the target fresh tea leaves, and determining a scale factor of each first RGB image in the first continuous images as a first scale factor; A second shooting device disposed just above the exit of the first conveyor belt is used to shoot a second RGB image of the target fresh tea leaves, and a scale factor of the second RGB image is determined as a second scale factor.

3. The method for adjusting fan opening in the process of fresh tea leaf sorting based on image recognition according to claim 2, characterized in that: The target fresh tea leaf area is extracted from each of the first RGB image and the second RGB image using a color segmentation method, specifically including: Preprocessing the first RGB image and the second RGB image; Convert the RGB color space of the preprocessed first RGB image and the second RGB image into the HSV color space; Creating a binary mask in the preprocessed first RGB image and the second RGB image according to a preset upper bound and a lower bound of an HSV color space; The target fresh tea leaf region in each of the first RGB image and the second RGB image is extracted using the binary mask.

4. The method for adjusting fan opening in the process of fresh tea leaf sorting based on image recognition according to claim 2, characterized in that: Calculating the physical position and vertical speed of the target fresh tea leaves according to the target fresh tea leaf regions of two adjacent first RGB images specifically includes: Calculating the physical position of the target fresh tea leaves in the two adjacent first RGB images according to the first scale factor of the two adjacent first RGB images; Determine the change distance of the target fresh tea leaves according to the physical positions of the target fresh tea leaves in two adjacent first RGB images; Determine the time interval according to the shooting time of two adjacent first RGB images; The vertical speed of the target fresh tea leaves is calculated based on the change distance and the time interval.

5. The method for adjusting fan opening in the process of fresh tea leaf sorting based on image recognition according to claim 2, characterized in that: Calculating the projection area of ​​the target fresh tea leaves according to the target fresh tea leaves region of the second RGB image specifically includes: Counting the number of pixels occupied by the target fresh tea leaf area in the second RGB image; The projection area of ​​the target fresh tea leaves is calculated using the second scale factor and the number of pixels.

6. The method for adjusting fan opening in the process of fresh tea leaf sorting based on image recognition according to claim 5, characterized in that: The calculation formula of the projected area of ​​the target fresh tea leaves is: Among them, B actual is the projection area of ​​the target fresh tea leaves, B pixel is the number of pixels occupied by the target fresh tea leaf area in the second RGB image, S B is the second scaling factor.

7. A fan opening adjustment device in the process of fresh tea leaf sorting based on image recognition, characterized in that: The device for adjusting the fan opening in the fresh tea leaf sorting process based on image recognition comprises: an acquisition module, used to acquire a first continuous image and a second RGB image of the target fresh tea leaves in the process of falling at the exit of the first conveyor belt, wherein the first continuous image includes a plurality of first RGB images; the first RGB image is an image in the vertical direction of the target fresh tea leaves in the process of falling, and the second RGB image is an image in the horizontal direction of the target fresh tea leaves in the process of falling; An image recognition module, used for determining a target fresh tea leaf region in each of the first RGB image and the second RGB image by using a color segmentation method; A first calculation module, used for calculating the physical position and vertical speed of the target fresh tea leaves according to the target fresh tea leaf regions of two adjacent first RGB images; A second calculation module, used for calculating the projection area of ​​the target fresh tea leaves according to the target fresh tea leaf area of ​​the second RGB image; The regulating module is used to determine the air flow rate at the fan outlet according to the physical position, the vertical speed, and the projected area, and adjust the fan opening based on the air flow rate.

8. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the method for adjusting the fan opening in the fresh tea leaf sorting process based on image recognition as described in any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for adjusting the fan opening in the fresh tea leaf sorting process based on image recognition as described in any one of claims 1 to 6 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the method for adjusting the fan opening in the fresh tea leaf sorting process based on image recognition as described in any one of claims 1 to 6 is implemented.

Images