Nondestructive yield measurement method, device, medium and equipment for sunflower seeds

Abstract

The invention discloses a non-destructive yield measurement method and device for sunflower seeds, a medium and equipment, and relates to the field of agriculture, and the method comprises the steps: obtaining a three-dimensional image of a sunflower seed pile in a granary in real time, carrying out the impurity recognition of the three-dimensional image at each moment, and obtaining the impurity volume in the granary at the corresponding moment; according to the coordinates and geometrical relationship of the feature points of the sunflower seed pile in the three-dimensional image, determining the bottom area of the sunflower seed pile and the height of the sunflower seed pile at the corresponding moment; from the starting moment to the current moment, subtracting the impurity volume from the product of the bottom area and the height, and carrying out time integration to obtain the total volume of the sunflower seed pile at the current moment; the total volume of the sunflower seed heap at the beginning is zero; and determining the difference value between the total volume of the sunflower seed grain heap at the current moment and the total volume of the sunflower seed grain heap at the previous moment as the yield of the sunflower seeds in the current unit time. The method can realize nondestructive yield measurement of sunflower seeds.

Description

Technical Field

[0001] The invention relates to the field of agriculture or oil crop production, and in particular to a non-destructive yield measurement method, device, medium and equipment for sunflower seeds. Background Art

[0002] With the advancement of smart agriculture in my country, the scale of sunflower planting and the degree of mechanization of harvesting are gradually increasing. Real-time acquisition of sunflower seed harvest yield and accurate drawing of real-time sunflower seed yield distribution map are one of the main directions of intelligent development of the sunflower industry.

[0003] At present, the main method to obtain the real-time harvest yield of sunflower seeds is to use impulse sensors to convert the flow of sunflower seeds from the impact force signal. The accuracy of the existing impulse yield measurement method for sunflower seeds is easily affected by mechanical vibration, field conditions, sensor installation angle, seed moisture content, impurity content, seed flow stability, etc., and multiple calibrations are required to ensure the accuracy of seed flow detection. Most importantly, a certain degree of mechanical damage to the sunflower seeds will be caused during the yield acquisition process, which greatly affects the selling price and storage time of sunflower seeds.

[0004] Therefore, there is an urgent need for a method that can achieve non-destructive yield measurement of sunflower seeds. Summary of the invention

[0005] Based on this, it is necessary to provide a non-destructive yield measurement method, device, medium and equipment for sunflower seeds in response to the above technical problems. The method can achieve non-destructive yield measurement of sunflower seeds.

[0006] The present invention adopts the following technical solutions:

[0007] The present invention provides a non-destructive yield measurement method for sunflower seeds, comprising:

[0008] Acquire a three-dimensional image of the sunflower seed pile in the granary in real time, identify impurities in the three-dimensional image at each moment, and obtain the impurity volume in the granary at the corresponding moment;

[0009] According to the coordinates and geometric relationship of the characteristic points of the sunflower seed pile in the three-dimensional image, the bottom area of ​​the sunflower seed pile and the height of the sunflower seed pile at the corresponding moment are determined;

[0010] From the start time to the current time, the product of the bottom area and the height minus the volume of impurities is integrated over time to obtain the total volume of the sunflower seed pile at the current time; the total volume of the sunflower seed pile at the start time is zero;

[0011] The difference between the total volume of the sunflower seed pile at the current moment and the total volume of the sunflower seed pile at the previous moment is determined as the yield of sunflower seeds in the current unit time.

[0012] Preferably, a depth camera is arranged directly above the granary; real-time acquisition of a three-dimensional image of the sunflower seed pile in the granary specifically includes:

[0013] Control the depth camera to collect an initial three-dimensional image of a pile of sunflower seeds in a granary at a preset frequency;

[0014] The initial three-dimensional image collected at each moment is cleaned and feature extracted to obtain a three-dimensional image of the sunflower seed pile in the granary at each moment.

[0015] Preferably, the impurity identification is performed on the three-dimensional image at each moment to obtain the impurity volume in the granary at the corresponding moment, which specifically includes:

[0016] For the 3D image at any moment, the 3D image is input into a pre-trained convolutional neural network to determine the position of the impurities in the granary on the 3D image;

[0017] The volume of the impurities in the granary is determined according to the positions of the impurities in the granary on the three-dimensional image.

[0018] Preferably, determining the volume of impurities in the granary according to the positions of the impurities in the granary on the three-dimensional image includes:

[0019] According to the positions of the impurities in the granary on the three-dimensional image, the three-dimensional image is segmented to obtain the impurity contours of the impurities in the three-dimensional image;

[0020] According to the impurity profile, determine the bottom area of ​​the impurity profile;

[0021] Using the depth information of the impurity in the three-dimensional image information as the thickness of the impurity;

[0022] The product of the bottom area and thickness of the impurity contour is determined as the impurity volume.

[0023] Preferably, determining the volume of impurities in the granary according to the positions of the impurities in the granary on the three-dimensional image specifically includes:

[0024] Performing image segmentation on the three-dimensional image to obtain impurity contours of impurities in the three-dimensional image;

[0025] According to the impurity profile, determine the bottom area of ​​the impurity profile;

[0026] The depth image sampling period is regarded as the thickness of the impurity;

[0027] The product of the bottom area and thickness of the impurity contour is determined as the volume of the impurity.

[0028] Preferably, the total volume of the sunflower seed pile is calculated as follows:

[0029]

[0030] Among them, V km is the total volume of the sunflower seed pile at time m, S k (t) is the change of the bottom area of ​​the sunflower seed pile over time, H k (t) is the change of the height of the sunflower seed pile over time, V z (t) is the change of impurity volume of sunflower seed pile over time, t start is the starting time, t m is the m moment.

[0031] Preferably, the impurity content of sunflower seeds is the ratio of the volume of impurities to the yield of sunflower seeds per unit time.

[0032] The present invention provides a non-destructive yield measurement device for sunflower seeds, comprising:

[0033] An acquisition module is used to acquire a three-dimensional image of the sunflower seed pile in the granary in real time, and to identify impurities in the three-dimensional image at each moment to obtain the impurity volume in the granary at the corresponding moment;

[0034] A first determination module is used to determine the bottom area and height of the sunflower seed pile at a corresponding moment according to the coordinates and geometric relationship of the feature points of the sunflower seed pile in the three-dimensional image;

[0035] A calculation module is used to perform time integration on the product of the bottom area and the height minus the impurity volume from the start time to the current time to obtain the total volume of the sunflower seed pile at the current time; the total volume of the sunflower seed pile at the start time is zero;

[0036] The second determination module is used to determine the difference between the total volume of the sunflower seed pile at the current moment and the total volume of the sunflower seed pile at the previous moment as the yield of sunflower seeds in the current unit time.

[0037] The present invention provides a computer-readable storage medium, wherein the storage medium stores a computer program, and when the computer program is executed by a processor, the above-mentioned non-destructive yield measurement method of sunflower seeds is implemented.

[0038] The present invention provides a computer device, comprising a memory, a processor and a computer program stored in the memory and executable on the processor. When the processor executes the program, the above-mentioned non-destructive yield measurement method of sunflower seeds is implemented.

[0039] At least one of the above technical solutions adopted by the present invention can achieve the following beneficial effects:

[0040] The three-dimensional image can reflect the precise three-dimensional shape and size of the sunflower seeds and their impurities in the granary, which is helpful to accurately identify the volume of the sunflower seeds and the volume of the impurities. Real-time acquisition of the three-dimensional image information of the sunflower seed pile can timely discover the distribution of impurities in the granary and issue an early warning; from the start time to the current time, the product of the bottom area and the height minus the impurity volume is integrated over time to obtain the total volume of the sunflower seed pile at the current time. The total volume of the sunflower seed pile from the start time to the current time can be accurately calculated by the time integration method. The product of the bottom area and the height minus the impurity volume takes into account the change of the volume of the sunflower seed pile over time and the influence of impurities on the volume, and simple instantaneous measurement is more accurate; the total volume of the sunflower seed pile at the current time is subtracted from the total volume of the sunflower seed pile at the previous time to determine the yield of sunflower seeds in the current unit time. This method can achieve non-destructive yield measurement of sunflower seeds. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0042] Figure 1 A schematic diagram of a process flow of a non-destructive yield measurement method for sunflower seeds provided by the present invention;

[0043] Figure 2 A schematic diagram of a non-destructive yield measurement device for sunflower seeds provided by the present invention;

[0044] Figure 3 A schematic diagram of a computer device for implementing a non-destructive yield measurement method for sunflower seeds provided by the present invention. DETAILED DESCRIPTION

[0045] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the specific embodiments of the present invention and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0046] Devices such as desktop computers, servers, and notebook computers that implement the solution of the present invention. For the sake of convenience, the following description will only take the server as the execution subject.

[0047] The technical solutions provided by various embodiments of the present invention are described in detail below in conjunction with the accompanying drawings.

[0048] Figure 1 The present invention is a schematic flow chart of a non-destructive yield measurement method for sunflower seeds, which specifically includes the following steps:

[0049] S101: Acquire a three-dimensional image of a pile of sunflower seeds in a granary in real time, perform impurity identification on the three-dimensional image at each moment, and obtain the impurity volume in the granary at the corresponding moment.

[0050] In an exemplary embodiment, a depth camera is arranged directly above the granary; a three-dimensional image of the pile of sunflower seed grains in the granary is obtained in real time, specifically including: controlling the depth camera to collect initial three-dimensional images of the pile of sunflower seed grains in the granary at a preset frequency; cleaning and feature extraction are performed on the initial three-dimensional images collected at each moment to obtain a three-dimensional image of the pile of sunflower seed grains in the granary at each moment.

[0051] Specifically, the preset frequency is set according to specific engineering practices, for example, 1 Hz. By setting the depth camera directly above the granary, real-time 3D image acquisition of the sunflower seed pile in the granary can be achieved. The depth camera works at a frequency of 1 Hz, constantly capturing the surface shape and distribution state of the sunflower seeds in the granary, thereby generating initial 3D image data. This process is an important manifestation of the modernization of sunflower seed yield management. With the help of advanced sensing technology and image processing technology, the process improves the accuracy of sunflower seed yield measurement.

[0052] Next, the initial 3D images collected at each moment are cleaned and feature extracted. The cleaning process aims to remove noise and irrelevant information in the initial 3D images and retain the true morphology and distribution characteristics of the sunflower seeds. Feature extraction is to extract key information of the sunflower seeds, such as size, shape, and position, from the cleaned images for subsequent analysis and processing. Through these processes, accurate 3D images of the sunflower seeds in the granary at each moment are obtained. By analyzing the accurate 3D images, the volume of the sunflower seeds can be estimated more accurately.

[0053] In an exemplary embodiment, impurity identification is performed on the three-dimensional image at each moment to obtain the impurity volume in the granary at the corresponding moment, specifically including: for the three-dimensional image at any moment, the three-dimensional image is input into a pre-trained convolutional neural network to determine the position of the impurities in the granary on the three-dimensional image; according to the position of the impurities in the granary on the three-dimensional image, the impurity volume in the granary is determined.

[0054] Specifically, for the three-dimensional image of sunflower seeds in the granary obtained at any time, it is first input into a pre-trained convolutional neural network (CNN) to determine the impurity position. The convolutional neural network extracts and classifies the input three-dimensional image, and finally outputs the position information of the impurity in the three-dimensional image. The position information includes the coordinates or bounding box of the impurity, which is used to identify which parts of the three-dimensional image are impurities. The impurity position information output by the trained convolutional neural network is processed to obtain the impurity volume.

[0055] In an exemplary embodiment, the volume of impurities in the granary is determined based on the positions of impurities in the granary on the three-dimensional image, including: performing image segmentation on the three-dimensional image based on the positions of impurities in the granary on the three-dimensional image to obtain impurity contours of impurities in the three-dimensional image; determining the contour bottom area of ​​the impurities based on the impurity contours; using the depth information of the impurities in the three-dimensional image information as the thickness of the impurities; and determining the impurity volume as the product of the contour bottom area and the thickness of the impurities.

[0056] Specifically, first, the three-dimensional image is segmented using image processing techniques, such as threshold segmentation, region growing or edge detection, with the goal of identifying and separating the impurity part and obtaining the contour of the impurity in the three-dimensional image. Secondly, after obtaining the contour in the three-dimensional image, the bottom area of ​​the impurity contour can be obtained by calculating the area of ​​the plane area enclosed by the contour. Thirdly, the three-dimensional image information of the impurity contains depth information. By analyzing this depth information, the thickness of the impurity, that is, the size of the impurity in the vertical direction, is determined. Finally, the bottom area of ​​the impurity contour is multiplied by the thickness to obtain the volume of the impurity.

[0057] In an exemplary embodiment, the volume of impurities in the granary is determined based on the positions of impurities in the granary on the three-dimensional image, specifically including: performing image segmentation on the three-dimensional image to obtain the impurity contour of the impurities in the three-dimensional image; determining the contour bottom area of ​​the impurity based on the impurity contour; using the depth image sampling period as the thickness of the impurity; and determining the volume of the impurity as the product of the contour bottom area and the thickness of the impurity.

[0058] Specifically, first, the three-dimensional image is segmented using image processing techniques, such as threshold segmentation, region growing or edge detection, with the goal of identifying and separating the impurity part and obtaining the contour of the impurity in the three-dimensional image. Secondly, after obtaining the contour in the three-dimensional image, the bottom area of ​​the impurity contour can be obtained by calculating the area of ​​the plane area enclosed by the contour. Thirdly, the depth image sampling period is used as the thickness of the impurity. Finally, the bottom area of ​​the impurity contour is multiplied by the thickness to obtain the volume of the impurity.

[0059] S102: Determine the bottom area and height of the sunflower seed pile at a corresponding moment according to the coordinates and geometric relationships of the feature points of the sunflower seed pile in the three-dimensional image.

[0060] Specifically, first, the coordinates of the feature points of the sunflower seed pile are extracted from the three-dimensional image. The feature points may be the vertices, edge points or other points that can represent the shape of the seed pile. Secondly, assuming that the bottom of the sunflower seed pile is approximately a polygon (such as a rectangle, ellipse, etc.), the area of ​​the polygon is calculated according to the coordinates of the bottom feature points, which is the bottom area S of the sunflower seed pile. K . Again, if the bottom is a regular geometric shape (such as a rectangle), the corresponding area formula is used directly. If it is an irregular shape, a more complex algorithm may need to be used, such as a polygon area formula or summation after triangulation. Finally, the height of the sunflower seed pile is determined by comparing the depth coordinates of the bottom and top feature points, finding the point with the smallest z coordinate among the bottom feature points and the point with the largest z coordinate among the top feature points. The difference between the two is the height H of the sunflower seed pile. K .

[0061] S103: from the start time to the current time, the product of the bottom area and the height minus the impurity volume is time-integrated to obtain the total volume of the sunflower seed pile at the current time; the total volume of the sunflower seed pile at the start time is zero.

[0062] Specifically, assuming that the total volume of the sunflower seed pile at the start time is zero, the product of the bottom area and the height minus the impurity volume is integrated from the start time to the current time to obtain the total volume of the sunflower seed pile at the current time.

[0063] In an exemplary embodiment, the total volume of the sunflower seed pile is calculated as shown in formula (1):

[0064]

[0065] Among them, V km is the total volume of the sunflower seed pile at time m, S k (t) is the change of the bottom area of ​​the sunflower seed pile over time, H k (t) is the change of the height of the sunflower seed pile over time, V z (t) is the change of impurity volume of sunflower seed pile over time, t start is the starting time, t m is the m moment.

[0066] S104: Determine the difference between the total volume of the sunflower seed pile at the current moment and the total volume of the sunflower seed pile at the previous moment as the yield of sunflower seeds in the current unit time.

[0067] Specifically, the calculation method of the output of sunflower seeds per unit time is as shown in formula (2):

[0068] V k n =V k m -V k( m - 1) (2);

[0069] Among them, V k n is the output of sunflower seeds per unit time, V k m is the total volume of the sunflower seed pile at time m, V k( m - 1) is the total volume of the sunflower seed pile at time m-1.

[0070] In an exemplary embodiment, the impurity content of sunflower seeds is a ratio of the volume of impurities to the yield of sunflower seeds per unit time.

[0071] Specifically, the calculation formula for the impurity content of sunflower seeds is shown in formula (3):

[0072]

[0073] Among them, f is the impurity content of sunflower seeds, V z is the impurity volume per unit time, V k n is the output of sunflower seeds in the current unit time.

[0074] In an exemplary embodiment, the present invention draws a distribution diagram of sunflower seed yield in real time based on the sunflower seed yield obtained in the current unit time, and the present invention also includes a human-computer interaction system, which allows the user to view the harvest yield and impurity content of sunflower seeds in real time when clicking on the touch screen.

[0075] Specifically, the invention can obtain the yield of sunflower seeds in the current unit time in real time, which is an important basis for realizing precision agricultural management, and helps to understand the production status in a timely manner and discover potential problems. Based on the collected data, the system can automatically draw a distribution map of sunflower seed yields. This visual display method allows users to intuitively see the yield differences in different time periods or different regions, providing a basis for production decisions. Through interactive devices such as touch screens, users can not only view real-time yield data, but also further understand key quality indicators such as the impurity content of sunflower seeds. This instant feedback mechanism enhances the user's control over the production process, making it easier to adjust production parameters or take corrective measures in a timely manner.

[0076] When applying the non-destructive yield measurement method for sunflower seeds provided by the present invention, it is not necessary to Figure 1 The steps are executed in the order shown. The specific execution order of the steps can be determined according to needs, and the present invention does not limit this.

[0077] The above is a non-destructive yield measurement method for sunflower seeds provided by one or more embodiments of the present invention. Based on the same idea, the present invention also provides a corresponding non-destructive yield measurement device for sunflower seeds, such as Figure 2 shown.

[0078] Figure 2 A schematic diagram of a non-destructive yield measurement device for sunflower seeds provided by the present invention, comprising:

[0079] The acquisition module 201 is used to acquire the three-dimensional image of the sunflower seed pile in the granary in real time, and perform impurity recognition on the three-dimensional image at each moment to obtain the impurity volume in the granary at the corresponding moment.

[0080] The first determination module 202 is used to determine the bottom area and height of the sunflower seed pile at a corresponding moment according to the coordinates and geometric relationships of the feature points of the sunflower seed pile in the three-dimensional image;

[0081] The calculation module 203 is used to perform time integration on the product of the bottom area and the height minus the impurity volume from the start time to the current time to obtain the total volume of the sunflower seed pile at the current time; the total volume of the sunflower seed pile at the start time is zero;

[0082] The second determining module 204 is used to determine the difference between the total volume of the sunflower seed pile at the current moment and the total volume of the sunflower seed pile at the previous moment as the yield of sunflower seeds in the current unit time.

[0083] For the specific definition of a non-destructive yield measurement device for sunflower seeds, please refer to the definition of a non-destructive yield measurement method for sunflower seeds in the above text, which will not be repeated here. Each module in the above-mentioned non-destructive yield measurement device for sunflower seeds can be implemented in whole or in part by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0084] The present invention also provides a computer-readable storage medium, which stores a computer program, which can be used to execute the above Figure 1 The invention provides a non-destructive yield measurement method for sunflower seeds.

[0085] The present invention also provides Figure 3 The structural diagram of the computer device shown in FIG. Figure 3As shown in the figure, at the hardware level, the computer device includes a processor, an internal bus, a network interface, a memory, and a non-volatile memory, and may also include other hardware required for the business. The processor reads the corresponding computer program from the non-volatile memory into the memory and then runs it to achieve the above Figure 1 The invention provides a non-destructive yield measurement method for sunflower seeds.

[0086] 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, 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 memory, storage, database or other media used in the embodiments provided by the present invention 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 or optical memory, etc. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0087] The technical features of the above embodiments may be arbitrarily combined. 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 the present invention.

Claims

1. A non-destructive yield measurement method for sunflower seeds, characterized in that: include: Acquire a three-dimensional image of the sunflower seed pile in the granary in real time, identify impurities in the three-dimensional image at each moment, and obtain the impurity volume in the granary at the corresponding moment; According to the coordinates and geometric relationship of the characteristic points of the sunflower seed pile in the three-dimensional image, the bottom area of ​​the sunflower seed pile and the height of the sunflower seed pile at the corresponding moment are determined; From the start time to the current time, the product of the bottom area and the height minus the volume of impurities is integrated over time to obtain the total volume of the sunflower seed pile at the current time; the total volume of the sunflower seed pile at the start time is zero; The difference between the total volume of the sunflower seed pile at the current moment and the total volume of the sunflower seed pile at the previous moment is determined as the yield of sunflower seeds in the current unit time.

2. The method according to claim 1, characterized in that A depth camera is set up directly above the granary to obtain a three-dimensional image of the sunflower seed pile in the granary in real time, including: Control the depth camera to collect an initial three-dimensional image of a pile of sunflower seeds in a granary at a preset frequency; The initial three-dimensional image collected at each moment is cleaned and feature extracted to obtain a three-dimensional image of the sunflower seed pile in the granary at each moment.

3. The method according to claim 1, characterized in that The impurity recognition is performed on the three-dimensional image at each moment to obtain the impurity volume in the granary at the corresponding moment, including: For the 3D image at any moment, the 3D image is input into a pre-trained convolutional neural network to determine the position of the impurities in the granary on the 3D image; The volume of the impurities in the granary is determined according to the positions of the impurities in the granary on the three-dimensional image.

4. The method according to claim 3, characterized in that According to the position of the impurities in the granary on the three-dimensional image, the volume of the impurities in the granary is determined, including: According to the positions of the impurities in the granary on the three-dimensional image, the three-dimensional image is segmented to obtain the impurity contours of the impurities in the three-dimensional image; According to the impurity profile, determine the bottom area of ​​the impurity profile; Using the depth information of the impurity in the three-dimensional image information as the thickness of the impurity; The product of the bottom area and thickness of the impurity contour is determined as the impurity volume.

5. The method according to claim 3, characterized in that According to the position of the impurities in the granary on the three-dimensional image, the volume of the impurities in the granary is determined, specifically including: Performing image segmentation on the three-dimensional image to obtain impurity contours of impurities in the three-dimensional image; According to the impurity profile, determine the bottom area of ​​the impurity profile; The depth image sampling period is regarded as the thickness of the impurity; The product of the bottom area and thickness of the impurity contour is determined as the volume of the impurity.

6. The method according to claim 1, characterized in that The total volume of a pile of sunflower seeds is calculated as: Among them, V km is the total volume of the sunflower seed pile at time m, S k (t) is the change of the bottom area of ​​the sunflower seed pile over time, H k (t) is the change of the height of the sunflower seed pile over time, V z (t) is the change of impurity volume of sunflower seed pile over time, t start is the starting time, t m is the m moment.

7. The method according to claim 1, characterized in that The impurity content of sunflower seeds is the ratio of the volume of impurities to the output of sunflower seeds per unit time.

8. A non-destructive yield measurement device for sunflower seeds, characterized in that: include: An acquisition module is used to acquire a three-dimensional image of the sunflower seed pile in the granary in real time, and to identify impurities in the three-dimensional image at each moment to obtain the impurity volume in the granary at the corresponding moment; A first determination module is used to determine the bottom area and height of the sunflower seed pile at a corresponding moment according to the coordinates and geometric relationship of the feature points of the sunflower seed pile in the three-dimensional image; A calculation module is used to perform time integration on the product of the bottom area and the height minus the impurity volume from the start time to the current time to obtain the total volume of the sunflower seed pile at the current time; the total volume of the sunflower seed pile at the start time is zero; The second determination module is used to determine the difference between the total volume of the sunflower seed pile at the current moment and the total volume of the sunflower seed pile at the previous moment as the yield of sunflower seeds in the current unit time.

9. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

10. A computer device, characterized in that: The invention comprises a memory, a processor and a computer program stored in the memory and executable on the processor, and when the processor executes the program, a method as claimed in any one of claims 1 to 7 is implemented.

Images