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

Abstract

The application discloses a fan opening degree adjusting method and device in a tea fresh leaf sorting process based on image recognition, equipment, medium and product, relates to the technical field of tea fresh leaf sorting, and the method comprises the following steps: acquiring a first continuous image and a second RGB image in the falling process of target tea fresh leaves at the outlet of a first conveying belt, the first continuous image containing a plurality of first RGB images; target tea fresh leaf regions are extracted from each first RGB image and second RGB image by using a color segmentation method; the physical position and the vertical speed of the target tea fresh leaves are calculated according to the target tea fresh leaf regions of two adjacent first RGB images; the projection area of the target tea fresh leaves is calculated according to the target tea fresh leaf region of the second RGB image; the air flow of the fan outlet is determined according to the physical position, the vertical speed and the projection area, and the fan opening degree is adjusted based on the air flow. The application can adaptively adjust the fan opening degree, so that the impact force received by the target tea fresh leaves when falling onto the conveying belt is reduced, and the tea quality is improved.

Description

TECHNICAL FIELD

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

[0002] In the tea leaf sorting link of tea leaf processing, the traditional air sorting technology is widely used. Its main working principle is to blow tea leaves with different characteristics to the corresponding conveying belt by means of high-pressure air and valve cooperation, so as to realize preliminary sorting. Specifically, the high-pressure air source generates strong airflow, and under the control of the valve, the airflow impacts the falling tea leaves according to the predetermined path and intensity. The selected tea leaves obtain a certain initial speed and move to the conveying belt direction under the push of the airflow.

[0003] Because the tea leaves are soft, when they are blown to the conveying belt by high-pressure air, their speed is often fast, and the edges of the tea leaves are easily damaged due to high-speed collision at the moment of contact with the conveying belt. In the subsequent processing and storage process, the damaged parts will gradually change chemically, initially showing yellowing signs, and will turn red as time further elapses. When the tea leaves are made into finished tea, the edges of the tea leaves that have been damaged will show obvious traces during brewing, greatly affecting the appearance of the tea leaves and reducing their attractiveness in the market. Moreover, the chemical property change of the tea leaves caused by collision affects the original flavor of the tea leaves to some extent, and the subtle changes in taste can be obviously perceived by professional tasting or consumers who have high requirements for tea quality, which significantly hinders the improvement of the overall quality of the tea leaves and is difficult to meet the needs of high-quality tea leaf production and processing. However, the traditional air sorting technology cannot adaptively adjust the fan flow according to the selected tea leaves, so that the tea leaves are damaged when blown to the conveying belt. SUMMARY

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

[0005] To achieve the above-mentioned purpose, the present application provides the following solutions:

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

[0007] acquire a first continuous image and a second RGB image of the target tea fresh leaves in the process of falling from the outlet of the first conveying belt to the second conveying belt, wherein the first continuous image comprises a plurality of first RGB images; the first RGB image is a vertical image of the target tea fresh leaves in the falling process; and the second RGB image is a horizontal image of the target tea fresh leaves in the falling process;

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

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

[0010] calculate the projection area of the target tea fresh leaves according to the target tea fresh leaf region of the second RGB image;

[0011] determine the air flow of the fan outlet according to the physical position, the vertical speed and the projection area, and adjust the fan opening degree based on the air flow.

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

[0013] acquire the first continuous image of the target tea fresh leaves by using a first shooting device arranged at the side of the outlet of the first conveying belt, and determine the scale factor of each first RGB image in the first continuous image as a first scale factor;

[0014] acquire the second RGB image of the target tea fresh leaves by using a second shooting device arranged directly above the outlet of the first conveying belt, and determine the scale factor of the second RGB image as a second scale factor.

[0015] Further, the method of extracting the target tea fresh leaf region in each of the first RGB image and the second RGB image by using a color segmentation method specifically comprises:

[0016] preprocess 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 an HSV color space;

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

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

[0020] Further, the physical position and the vertical speed of the target tea fresh leaf are calculated according to the target tea fresh leaf region of the two adjacent first RGB images, specifically including:

[0021] The physical position of the target tea fresh leaf in the two adjacent first RGB images is calculated according to the first scale factor of the two adjacent first RGB images;

[0022] The change distance of the target tea fresh leaf is determined according to the physical position of the target tea fresh leaf in the two adjacent first RGB images;

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

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

[0025] Further, the projection area of the target tea fresh leaf is calculated according to the target tea fresh leaf region of the second RGB image, specifically including:

[0026] The pixel number of the target tea fresh leaf region in the second RGB image is counted;

[0027] The projection area of the target tea fresh leaf is calculated by using the second scale factor and the pixel number.

[0028] Further, the calculation formula of the projection area of the target tea fresh leaf is:

[0029]

[0030] Wherein, B actual is the projection area of the target tea fresh leaf, B pixel is the pixel number of the target tea fresh leaf region, S B is the second scale factor.

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

[0032] An acquisition module is configured to acquire a first continuous image and a second RGB image of a target tea fresh leaf in a falling process at an outlet of the first conveying belt, wherein the first continuous image comprises a plurality of first RGB images; the first RGB image is a vertical image of the target tea fresh leaf in the falling process, and the second RGB image is a horizontal image of the target tea fresh leaf in the falling process;

[0033] An image recognition module is configured to determine a target tea fresh leaf region in each of the first RGB image and the second RGB image by using a color segmentation method;

[0034] The first calculation module is configured to calculate the physical position and the vertical speed of the target tea fresh leaves according to the target tea fresh leaf regions of two adjacent first RGB images.

[0035] The second calculation module is configured to calculate the projection area of the target tea fresh leaves according to the target tea fresh leaf region of the second RGB image.

[0036] The adjusting module is configured to determine the air flow of the fan outlet according to the physical position, the vertical speed and the projection area, and adjust the fan opening degree based on the air flow.

[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 fan opening degree adjusting method in the tea fresh leaf sorting process based on image recognition.

[0038] In a fourth aspect, the present application provides a computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement the fan opening degree adjusting method in the tea fresh leaf sorting process based on image recognition.

[0039] In a fifth aspect, the present application provides a computer program product, which comprises a computer program, and the computer program is executed by a processor to implement the fan opening degree adjusting method in the tea fresh leaf sorting process based on image recognition.

[0040] According to the specific embodiments provided by the present application, the following technical effects are disclosed:

[0041] The present application provides a fan opening degree adjusting method, device, equipment, medium and product in a tea fresh leaf sorting process based on image recognition, adopts a color segmentation method to extract the target tea fresh leaf region in each first RGB image and second RGB image, based on which, the physical position and the vertical speed of the target tea fresh leaves are calculated, and the initial position state of the target tea fresh leaves when starting to decelerate is determined; in order to make the speed of the target tea fresh leaves falling to the second conveying belt tend to zero, the final position state of the target tea fresh leaves is determined, the air resistance received by the target tea fresh leaves in the falling process is calculated through the initial position state and the final position state, and then the projection area of the target tea fresh leaves is used to calculate the air flow of the fan outlet required when the target tea fresh leaves reach the final position state, and then the fan opening degree is adjusted according to the air flow, so that the speed of the target tea fresh leaves falling to the second conveying belt tends to zero, and the impact force received is minimized, which maximally guarantees the integrity of the target tea fresh leaves and improves the quality of the tea leaves. BRIEF DESCRIPTION OF DRAWINGS

[0042] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed in the embodiments. Obviously, the drawings described below only constitute some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained from these drawings without creative labor.

[0043] Figure 1 A working flow diagram of a tea fresh leaf sorting device in an embodiment of the present application is shown in the figure.

[0044] Figure 2 A flow diagram of a fan opening degree adjusting method in a tea fresh leaf sorting process based on image recognition provided by an embodiment of the present application is shown in the figure.

[0045] Figure 3 A physical position diagram of target tea fresh leaves provided by an embodiment of the present application is shown in the figure.

[0046] Figure 4 A functional module diagram of a fan opening degree adjusting device in a tea fresh leaf sorting process based on image recognition provided by another embodiment of the present application is shown in the figure.

[0047] Figure 5 A structural diagram of a computer device provided by an embodiment of the present application is shown in the figure. DETAILED DESCRIPTION

[0048] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments only constitute some embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.

[0049] In order to make the purposes, features and advantages of the present application more obvious and easy to understand, the present application will be further described in detail below with reference to the drawings and specific embodiments.

[0050] The fan opening degree adjusting method in a tea fresh leaf sorting process based on image recognition provided by the present embodiment application is applied to a tea fresh leaf sorting device, as shown in the figure. Figure 1 The tea fresh leaf sorting device includes a first conveying belt 1, a second conveying belt 2 and a fan 3. The tea fresh leaves have a certain initial speed and fly out under the action of the first conveying belt 1. The target tea fresh leaves to be selected are changed in flight trajectory by the high-pressure air flow sprayed by the downward air nozzle 4, and obtain a certain vertical speed, so that the target tea fresh leaves fall onto the second conveying belt 2. The fan 3 provides upward deceleration air flow to change the air resistance received by the target tea fresh leaves during the falling process, and reduce the vertical speed of the target tea fresh leaves.

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

[0052] Step 101, acquiring the first continuous image and the second RGB image of the target tea fresh leaf during the falling process from the outlet of the first conveying belt to the second conveying belt, wherein the first continuous image contains multiple first RGB images; the first RGB image is the vertical image of the target tea fresh leaf during the falling process, and the second RGB image is the horizontal image of the target tea fresh leaf during the falling process.

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

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

[0055] Step 104, calculating the projection area of the target tea fresh leaf according to the target tea fresh leaf area of the second RGB image.

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

[0057] By implementing steps 101 to 105, the fan 3 opening degree can be adaptively adjusted, the air flow rate is changed, the air resistance received by the target tea fresh leaf during the falling process from the first conveying belt 1 to the second conveying belt 2 is changed, the falling speed of the target tea fresh leaf to the second conveying belt 2 tends to be 0, the damage to the target tea fresh leaf is minimized, and the tea quality is improved.

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

[0059] Step 1001, using the first shooting device arranged on the outlet side of the first conveying belt to shoot the first continuous image of the target tea fresh leaf, and determining 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 outlet side of the first conveying belt is used to shoot the vertical image of the target tea fresh leaf during the falling process from the first conveying belt to the second conveying belt. Specifically, the first shooting device is an RGB camera. As Figure 1As shown, region A is the region where the target tea fresh leaves are accelerated downward by the high-pressure airflow, and region B is the region covered by the first shooting device, i.e., the deceleration region of the target tea fresh leaves, in which the target tea fresh leaves are subjected to air resistance and are not subjected to 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 uses the first shooting device, the light source, and shoots a square block with a known projection area A actual , which has a simple surface texture, to obtain a reference image, so as to accurately identify and measure in the image.

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

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

[0065] Step 1.4: Use region filling to calculate the number n of pixels inside the boundaries of the square block in the reference image, and obtain the area A pixel of each pixel.

[0066] Step 1.5: Use the formula: to obtain the scale factor of the image pixels of the reference image to the actual physical coordinates, and take this scale factor as the first scale factor S A of the first RGB image.

[0067] Step 1002: Shoot a second RGB image of the target tea fresh leaves using a second shooting device arranged directly above the outlet of the first conveying belt, and determine the 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 B is determined according to the method of determining the first scale factor, which is not described herein.

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

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

[0070] Specifically, to improve processing speed, the resolution of the first RGB image and the second RGB image is compressed, so that the resolution of the first RGB image and the second RGB image is a preset value, which can be 800*800 or other values, and is not limited in the present embodiment.

[0071] Gaussian blurring is applied to the first RGB image and the second RGB image at a preset resolution to reduce noise in the images, resulting in preprocessed first RGB image and second RGB image.

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

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

[0074] Multiple images of the target fresh tea leaves were captured at a color temperature of 6000K, and their average HSV (hue, saturation, brightness) color space range was obtained. The upper and lower boundaries of the HSV color space were determined based on the average HSV color space range.

[0075] Step 204: Use the binary mask to extract the target tea leaf region from each of the first RGB image and the second RGB image.

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

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

[0078] Step 301: Calculate the physical location of the target tea leaves in two adjacent first RGB images based on the first scaling factor of the two adjacent first RGB images. Specifically, this includes steps 3.1-3.3:

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

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

[0081] like Figure 3 As shown, X 像素 Y represents 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The pixel number of the image boundary of the first RGB image in the vertical direction from the midpoint of the target tea fresh leaf.

[0082] Step 3.3: Combine X 实际 and Y 实际 The physical position of the target tea fresh leaf is obtained.

[0083] The physical positions of the target tea fresh leaf in the adjacent two first RGB images are calculated respectively according to steps 3.1-3.3.

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

[0085] For example, Y1 and Y2 are calculated by the method of step 3.2; wherein Y1 and Y2 are the actual longitudinal coordinates of the target tea fresh leaf in the adjacent two first RGB images.

[0086] The displacement of the target tea fresh leaf in the vertical direction, that is, the change distance ΔY of the target tea fresh leaf, is calculated by the formula: ΔY=Y1-Y2.

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

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

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

[0090] The vertical speed is calculated by the formula: to obtain the vertical speed V 垂直 of the target tea fresh leaf.

[0091] In the specific implementation process, X1 and X2 can also be calculated by the method of step 3.1, X1 and X2 being the actual horizontal coordinates of the target tea fresh leaf in the adjacent two first RGB images.

[0092] The displacement ΔX of the target tea fresh leaf in the horizontal direction is calculated by the formula: ΔX=X1-X2, and on this basis, the horizontal speed V 水平 of the target tea fresh leaf is calculated by the formula:

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

[0094] The formula for calculating the projected area of the target tea fresh leaf is:

[0095]

[0096] wherein B actual is the projected area of the target tea fresh leaf, B pixel is the number of pixels occupied by the target tea fresh leaf region, S B is the second scale factor.

[0097] In one exemplary embodiment, step 105 specifically comprises steps 4.1-4.7:

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

[0099] In a room temperature environment with a temperature of 25°C, the air density is approximately: p≈1.184 kg / m 3 ; the acceleration of gravity is: g≈9.81 m / s 2 ; the air flow rate of the fan 3 at the rated speed is: Q=2000 m 3 / h; when the throttle valve of the fan 3 is opened to 100%, Q=2000 m 3 / h, and when the throttle valve is opened to 50%, Q=1000 m 3 / h; the outlet size of the fan is: A outlet =0.0162 m 2 ; the mass of each target tea fresh leaf is m=1 g; the air resistance coefficient of the target tea fresh leaf is: C d =1.2; and the projected area of the target tea fresh leaf is S 鲜叶 =B actual .

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

[0101] Step 4.3: Calculate the required deceleration a of the target tea fresh leaf.

[0102] In order to make the target tea fresh leaf stop in the target tea fresh leaf sorting device, the target tea fresh leaf needs to be decelerated from the vertical velocity V 垂直That is, the speed of the initial position is reduced to zero, and the deceleration is completed within the height h, which is the distance from the initial position to the second conveyor belt, and the height h changes with the distance between the target tea fresh leaves and the second conveyor belt 2, wherein the initial position is Figure 1 The position where the area A and the area B are in contact, therefore, using the kinematic formula: It is known that when the speed of the target tea fresh leaves falling on the second conveyor belt 2 approaches 0 m / s infinitely, that is, V takes the value of 0, the acceleration a of the target tea fresh leaves falling to the second conveyor belt:

[0103] Step 4.4: According to the force on the target tea fresh leaves during the process of falling to the second conveyor belt, the air resistance on the target tea fresh leaves is calculated.

[0104] F d = m x a + m x g = F a +F g ;

[0105] Where F a is the force required for the target tea fresh leaves to decelerate, F d is the air resistance, and F g is the gravity of the target tea fresh leaves.

[0106] Step 4.5: Calculate the air flow speed at the outlet of the fan.

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

[0108] Therefore, according to the F d calculated in step 4.4, combined with the expression of the air flow speed v air , the air flow speed at the outlet of the fan is calculated.

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

[0110] Using the formula: Q = v air x A outlet , and the air flow speed at the outlet of the fan obtained in step 4.5, the air flow at the outlet of the fan is calculated, where Q is the air flow.

[0111] Step 4.7: The calculated air flow adjusts the fan opening.

[0112] The air volume of the fan is determined by the fan rotating speed and the throttle opening, wherein the fan reaches the rated working rotating speed after starting and keeps the rotating speed unchanged; the air flow can be controlled by adjusting the opening of the throttle, and in the embodiment, the fan opening refers to the opening of the throttle.

[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 adjusting device in an image recognition based tea fresh leaf sorting process for implementing the fan opening adjusting method in the image recognition based tea fresh leaf sorting process as described above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme described in the above method, and therefore the specific limitations in one or more fan opening adjusting device embodiments in the image recognition based tea fresh leaf sorting process provided below can refer to the limitations of the image recognition based tea fresh leaf sorting process in the fan opening adjusting method described above, which will not be described here again.

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

[0116] The acquisition module 41 is configured to acquire the first RGB image as a vertical direction image in the falling process of the target tea fresh leaf, and acquire the second RGB image as a horizontal direction image in the falling process of the target tea fresh leaf.

[0117] The image recognition module 42 is configured to determine the target tea fresh 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 configured to calculate the physical position and the vertical speed of the target tea fresh leaf according to the target tea fresh leaf areas of two adjacent first RGB images.

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

[0120] The adjusting module 45 is configured to determine the air flow of the fan outlet according to the physical position, the vertical speed and the projection area, and adjust the fan opening based on the air flow.

[0121] In an exemplary embodiment, a computer device can be provided, which can be a server or a terminal, and the internal structure diagram thereof can be as shown in Figure 5As shown in the figure. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. Among them, the processor, the memory and the input / output interface are connected through the system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capability. 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 tea fresh leaf in the falling process at the outlet of the first conveying belt. The input / output interface of the computer device is used to exchange information between the processor and the external device. The communication interface of the computer device is used to communicate with the terminal outside through the network connection. The computer program is executed by the processor to realize a fan opening adjustment method in a tea fresh leaf sorting process based on image recognition.

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

[0123] In one exemplary embodiment, a computer device is also provided, including a memory and a processor, the memory storing a computer program, and the processor executing the computer program to realize the steps in the above method embodiments.

[0124] In one exemplary embodiment, a computer readable storage medium is provided, storing a computer program, which is executed by a processor to realize the steps in the above method embodiments.

[0125] In one exemplary embodiment, a computer program product is provided, including a computer program, which is executed by a processor to realize the steps in the above method embodiments.

[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 for analysis, stored data, displayed data, etc.) involved in the present application are all information and data authorized by the user or authorized by all parties, and the collection, use and processing of related data need to comply with relevant regulations.

[0127] Those skilled 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. The computer program can be stored in a non-volatile computer readable storage medium, and when the computer program is executed, the processes of the above-mentioned embodiments of the methods can be included. Any reference to 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 storage, high-density embedded non-volatile memory, resistive memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration but not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc.

[0128] The database involved in the embodiments provided in the present application can include at least one of a relational database and a non-relational database. The non-relational database can include a distributed database based on a blockchain, etc., without being limited thereto. The processor involved in the embodiments provided in the present application can be a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., without being limited thereto.

[0129] The technical features of the above embodiments can be combined arbitrarily. In order to make the description concise, all possible combinations of the technical features in the above embodiments are not described, but as long as the combinations of the technical features do not exist, they should be considered as the scope of the present application.

[0130] The principles and implementation modes of the present application are described by applying specific examples herein. The above description of the embodiments is only used to help understand the method and its core idea of the present application; meanwhile, for those skilled in the art, according to the idea of the present application, the specific implementation mode and application range can be changed. In conclusion, the content of the present application should not be understood as a limitation.

Claims

1. A method for adjusting the fan opening in the tea leaf sorting process based on image recognition, applied to a tea leaf sorting device, the 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 during the image recognition-based tea leaf sorting process includes: Acquire a first continuous image and a second RGB image of the target fresh tea leaves as they fall from the exit of the first conveyor belt to the second conveyor belt. The first continuous image contains multiple first RGB images. The first RGB image is a vertical image of the target fresh tea leaves as they fall, and the second RGB image is a horizontal image of the target fresh tea leaves as they fall. The target fresh tea leaf region is extracted from each of the first RGB image and the second RGB image using a color segmentation method; The physical position and vertical velocity of the target tea leaf are calculated based on the target tea leaf region in two adjacent first RGB images. Calculate the projected area of ​​the target tea leaves based on the target tea leaf region of the second RGB image; The airflow rate at the fan outlet is determined based on the physical location, vertical speed, and projected area, and the fan opening is adjusted based on the airflow rate; this ensures that the speed of the target tea leaves falling onto the second conveyor belt is close to zero, minimizing the impact force and maximizing the integrity of the target tea leaves.

2. The method for adjusting the fan opening during the tea leaf sorting process based on image recognition according to claim 1, characterized in that, Before acquiring the first consecutive image and the second RGB image of the target fresh tea leaves at the exit of the first conveyor belt, the method further includes: A first continuous image of the target fresh tea leaves is captured using a first imaging device located on the side of the exit of the first conveyor belt, and the scaling factor of each first RGB image in the first continuous image is determined as the first scaling factor. A second RGB image of the target fresh tea leaves is captured using a second imaging device positioned directly above the exit of the first conveyor belt, and the scaling factor of the second RGB image is determined as the second scaling factor.

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

4. The method for adjusting the fan opening during the tea leaf sorting process based on image recognition according to claim 2, characterized in that, The physical position and vertical velocity of the target tea leaf are calculated based on the target tea leaf region in two adjacent first RGB images, specifically including: The physical location of the target fresh tea leaves in the two adjacent first RGB images is calculated based on the first scaling factor of the two adjacent first RGB images. The change distance of the target tea leaves is determined based on the physical position of the target tea leaves in two adjacent first RGB images; The time interval is determined based on the capture time of two adjacent first RGB images; The vertical velocity of the target fresh tea leaves is calculated based on the changed distance and time interval.

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

6. The method for adjusting the fan opening during the tea leaf sorting process based on image recognition according to claim 5, characterized in that, The formula for calculating the projected area of ​​the target fresh tea leaves is: ； in, The projected area of ​​the target tea leaves The number of pixels occupied by the target fresh tea leaf area in the second RGB image. This is the second scaling factor.

7. A fan opening adjustment device in the process of sorting fresh tea leaves based on image recognition, characterized in that, The fan opening adjustment device in the image recognition-based fresh tea leaf sorting process includes: The acquisition module is used to acquire a first continuous image and a second RGB image of the target fresh tea leaves during their fall at the exit of the first conveyor belt. The first continuous image includes multiple first RGB images. The first RGB image is a vertical image of the target fresh tea leaves during their fall, and the second RGB image is a horizontal image of the target fresh tea leaves during their fall. The image recognition module is used to determine the target fresh tea leaf region in each of the first RGB image and the second RGB image using a color segmentation method; The first calculation module is used to calculate the physical position and vertical velocity of the target tea leaf based on the target tea leaf region in two adjacent first RGB images. The second calculation module is used to calculate the projected area of ​​the target tea leaves based on the target tea leaf region of the second RGB image. The adjustment module is used to determine the airflow at the fan outlet based on the physical location, the vertical speed, and the projected area, and to adjust the fan opening based on the airflow; so that the speed of the target tea leaves falling onto the second conveyor belt approaches zero, the impact force is minimized, and the integrity of the target tea leaves is guaranteed to the greatest extent.

8. A computer device, comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that the processor executes the computer program to implement the fan opening adjustment method in the image recognition-based tea leaf sorting process according to any one of claims 1-6.

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

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

Images