Solar flowerpot device for automatic planting

Abstract

Provided is a solar flowerpot device for automatic planting, comprising an external structure (1), a water storage structure (2), a small water pump (3), a pruning structure (4), a camera device (5), and a processor, wherein the camera device (5) is used for acquiring a plant image. A rhizome position is extracted on the basis of the plant image, and a rhizome image is obtained, wherein the rhizome image is an image in which only the rhizome of a plant exists; color detection is performed on the basis of the rhizome image and the plant image, and a flower position is obtained by means of comparison; and a pruning position is obtained on the basis of the flower position and the rhizome image, and accurate pruning is performed at the rhizome position.

Description

A solar-powered automatic flower pot planting device Technical Field

[0001] This invention relates to the field of computer technology, and more specifically, to a solar-powered automatic flowerpot planting device. Background Technology

[0002] Currently, pruning is necessary during plant growth to prevent excessive growth that could affect aesthetics and to allow the plant to regenerate its energy for optimal growth. However, manual pruning is time-consuming, labor-intensive, and inconvenient, leading to the development of automated pruning methods. However, pruning only at specific locations results in pruning the entire plant up to a certain height, which is not ideal for users who want to preserve the flowers. Therefore, it is necessary to identify the flower locations and prune accurately at the base of the stem.

[0003] Summary of the Invention

[0004] The purpose of this invention is to provide a solar-powered automatic flowerpot planting device to solve the above-mentioned problems existing in the prior art.

[0005] This invention provides a solar-powered automatic flowerpot planting device, including an external structure, a water storage structure, a small water pump, a pruning structure, a camera device, and a processor.

[0006] The camera device is used to acquire plant images; the plant images are images of the side of the plant as detected.

[0007] The processor is used to perform the following methods:

[0008] Based on the plant image, the rootstock is extracted to obtain a rootstock image; the rootstock image is an image containing only the plant's rootstock.

[0009] Based on the root and stem image and the plant image, color detection is performed, and the flower position is obtained by comparison;

[0010] The pruning location is determined based on the flower position and the rootstock image.

[0011] The step of extracting roots and stems from the plant image to obtain a root and stem image includes:

[0012] Based on the plant image, and taking into account the characteristic that the plant roots are connected to the soil, the root location is obtained through target detection.

[0013] Based on the plant image, the position of the stem is determined by the pixels using a histogram to obtain a stem image; the stem image is the position of branches and leaves in the image.

[0014] Based on the root location, adjust the skeleton of the stem location in the stem image to obtain the root and stem image.

[0015] Optionally, the step of predicting the stem position based on the plant image using a histogram to obtain a stem image includes:

[0016] Based on the plant images, a histogram is constructed to obtain a plant array; the plant array is a two-dimensional array; the elements in the plant array are the same as the information in the histogram.

[0017] A color window is created; the color window represents a fixed number of pixel values;

[0018] Based on the color window, slide with a step size of 1 to obtain multiple pixel groups;

[0019] Multiple pixel counts are obtained by summing the number of pixels in multiple pixel groups multiple times.

[0020] By comparing multiple pixel values, the pixel value that is greater than the other pixel values ​​is found to obtain the optimal pixel value;

[0021] The optimal pixel value in the plant image is set to 1, and other positions are set to 0 to obtain the plant stem image.

[0022] Optionally, the step of extracting the skeleton of the location of the plant stem in the plant stem image based on the root location to obtain the root stem image includes:

[0023] The vertical central axis is determined by the location of the root, thus obtaining the root centerline;

[0024] Extend the root centerline by one-eighth of its own length to obtain the extended root centerline;

[0025] The position of the extended stem is obtained by extending the center line of the root in the area of ​​the stem image;

[0026] The left-right ratio is obtained by calculating the quotient of the left and right boundaries of the extended root centerline to the extended stem position.

[0027] The skeleton of the plant stem image is extracted according to the left-right ratio to obtain the root and stem image.

[0028] Optionally, the step of extracting the skeleton from the stem image according to the left-right ratio to obtain the rootstock image includes:

[0029] Based on the stated left-right ratio, the number of left corrosion cycles and the number of right corrosion cycles are obtained;

[0030] The erosion boundary algorithm is used to erode the left boundary of the stem position in the stem image multiple times according to the number of left erosions.

[0031] The erosion boundary algorithm is used to erode the right boundary of the stem position in the stem image multiple times based on the number of right erosions.

[0032] The rootstock image was obtained by repeatedly alternating between left and right erosion.

[0033] Optionally, the step of performing color detection based on the rootstock image and the plant image, and obtaining the flower position by comparison, includes:

[0034] The plant image is detected to obtain the initial flower position and initial flower color;

[0035] Based on the initial detection of flower color and the color corresponding to the pixel count when acquiring the stem image, determine whether the colors are similar;

[0036] If the colors of the initially detected flower position and the color position are not similar, the flower position is obtained; the flower position is the initially detected flower position.

[0037] Optionally, determining the pruning location based on the flower position and rootstock image includes:

[0038] The trimming position includes the trimming height position and the trimming horizontal position;

[0039] Obtain the pruning height; the pruning height represents the preset height of the branches and leaves after pruning.

[0040] The height of the flower is determined by its vertical position.

[0041] If the trimming height is less than the flower height, set the trimming height position to the flower height; if the trimming height is greater than or equal to the flower height, set the trimming height position to the trimming height.

[0042] Based on the rootstock image at the pruning height position, locate the rootstock position and set it as the pruning horizontal position.

[0043] Optionally, the external structure includes an uncovered flowerpot structure and a flowerpot lid.

[0044] The uncovered flowerpot structure is a cylinder with one open side; the flowerpot lid can be fastened to the uncovered flowerpot structure.

[0045] The water storage structure is located at the bottom of the uncovered flowerpot structure; the water storage structure is pull-out; and a screen is located above the water storage structure.

[0046] Soil and plants are present above the screen;

[0047] The camera device is fixed to the side edge of the uncovered flowerpot structure;

[0048] A small water pump is fixed to the side edge of an uncovered flowerpot structure opposite the camera equipment; the small water pump is used to periodically spray water from the water storage structure onto the surface of the soil layer.

[0049] The pruning structure is fixed inside the flowerpot lid; the processor is built into the pruning structure.

[0050] Optionally, a solar panel is fixedly placed on the outside of the flowerpot cover; the solar panel is connected to the motor.

[0051] Optionally, the pruning structure includes a motor, blades, and support rods.

[0052] The processor is built into the motor;

[0053] The motor is connected to the support rod; the motor can control the support rod to extend downwards.

[0054] The center point of the blade is fixedly connected to the support rod.

[0055] Optionally, the pump structure includes a suction component and a discharge component.

[0056] The suction part of the small water pump is located in the water storage structure; the discharge part of the small water pump is located above the soil.

[0057] Compared with the prior art, the embodiments of the present invention achieve the following beneficial effects:

[0058] This invention also provides a solar-powered automatic flowerpot planting device, comprising: a camera device for acquiring plant images; the plant images being images of the side of the plant detected by monitoring; and a processor for executing the following methods: extracting roots and stems based on the plant images to obtain root and stem images; the root and stem images being images containing only the plant's roots and stems; performing color detection based on the root and stem images and comparing them to determine the flower positions; and determining the pruning positions based on the flower positions and the root and stem images.

[0059] The approximate location of branches and leaves is determined by color discrimination from plant images. The root and stem structure is corrected by adjusting its left-right proportions, and the structure is extracted to obtain the root and stem image. A neural network is then used to identify flower locations and perform precise pruning at these locations. Controlled pruning avoids accidental flower cutting during detection by recognizing flowers. Simultaneously, the location of connected branches and leaves is detected for accurate automatic pruning, preventing pruning that misses branches and leaves. In addition, a water pump automatically waters the plants, and solar panels charge the batteries. A water storage structure allows for easy replenishment of water and nutrient solution. A sieve facilitates the return of excess water from the soil layer to the bottom without removing soil. Attached Figure Description

[0060] Figure 1 is a flowchart of a method for obtaining the pruning position in a solar-powered automatic flowerpot planting device provided by an embodiment of the present invention.

[0061] Figure 2 is a schematic diagram of the structure of a solar-powered automatic flowerpot planting device provided in an embodiment of the present invention.

[0062] The diagram is labeled as follows: External structure 1, Uncovered flowerpot structure 102, Flowerpot lid 101, Water storage structure 2, Small water pump 3, Suction component 301, Discharge component 302, Pruning structure 4, Motor 402, Blade 401, Support rod 403, Camera equipment 5, Screen 6, Solar panel 7. Detailed Implementation

[0063] The present invention will now be described in detail with reference to the accompanying drawings.

[0064] Example

[0065] As shown in Figure 1, this embodiment of the invention provides a solar-powered automatic flowerpot planting device, including an external structure 1, a water storage structure 2, a small water pump 3, a pruning structure 4, a camera device 5, and a processor:

[0066] The camera device 5 is used to acquire plant images. The plant images are images of the side views of the monitored plants.

[0067] The processor is used to perform the following methods:

[0068] S101: Based on the plant image, extract the rhizome to obtain a rhizome image. The rhizome image is an image containing only the plant's rhizome.

[0069] S102: Based on the root and stem image and the plant image, perform color detection and obtain the flower position by comparison.

[0070] Among these steps, color detection is performed, and objects that differ from branches and leaves are identified through comparison.

[0071] S103: Based on the flower position and rootstock image, obtain the pruning position.

[0072] The pruning position is transmitted to the pruning structure.

[0073] The step of extracting roots and stems from the plant image to obtain a root and stem image includes:

[0074] Based on the plant image, and taking advantage of the characteristic that plant roots are connected to the soil, the location of the roots is obtained through target detection.

[0075] Among them, based on the fact that plant roots are connected to the soil, plant images are represented by images with different shapes and colors.

[0076] In this embodiment, the YOLOv5 algorithm is used for target detection. Multiple plant images are used as training images, and the corresponding plant root positions are used as annotations for training, resulting in a target detection algorithm that can detect root positions.

[0077] Based on the plant image, the position of the stem is determined by the pixels using a histogram to obtain a stem image; the stem image is the position of branches and leaves in the image.

[0078] Based on the root location, adjust the skeleton of the stem location in the stem image to obtain the root and stem image.

[0079] Using the above method, the position of the bottom rootstock is found based on the two-dimensional image, and the rootstock position is adjusted from bottom to top.

[0080] Optionally, the step of predicting the stem position based on the plant image using a histogram to obtain a stem image includes:

[0081] Based on the plant images, a histogram is constructed to obtain a plant array. The plant array is a two-dimensional array; the elements in the plant array have the same information as those in the histogram.

[0082] The histogram and plant array are arranged in ascending order of color pixel values.

[0083] In the histogram, the value in the image represents the number of pixels corresponding to each pixel value.

[0084] In this case, judging pixels based on histograms is equivalent to judging colors, since the colors of branches and leaves have a fixed range.

[0085] Create a color window. The color window represents a fixed number of pixel values.

[0086] The color window refers to grouping the colors in the histogram, i.e., the plant array.

[0087] In this embodiment, the number of color windows is 4.

[0088] Based on the color window, slide with a step size of 1 to obtain multiple pixel groups.

[0089] Here, the pixel group represents adjacent positions, i.e., adjacent colors.

[0090] The number of pixels is obtained by adding the number of pixels in multiple pixel groups separately.

[0091] The number of pixels refers to the number of similar colors, such as the amount of green in the leaves.

[0092] By comparing multiple pixel values, the pixel value that is greater than the others is found to obtain the optimal pixel value.

[0093] The optimal pixel value in the plant image is set to 1, and other positions are set to 0 to obtain the plant stem image.

[0094] The plant stem image is an image that roughly shows the location of the plant's branches and leaves.

[0095] Optionally, the step of extracting the skeleton of the location of the plant stem in the plant stem image based on the root location to obtain the root stem image includes:

[0096] Extend the root by one-eighth of its length to obtain an extended rootstock.

[0097] The left-right ratio is obtained by calculating the quotient of the left and right boundaries of the extended root centerline to the extended stem position.

[0098] The left-right ratio is obtained by subtracting the left-right coordinate of the extended stem position from the horizontal coordinate of the root centerline and dividing by the vertical coordinate of the extended stem position from the horizontal coordinate of the root centerline.

[0099] The skeleton of the plant stem image is extracted according to the left-right ratio to obtain the root and stem image.

[0100] By matching the root location with the stem image using the above method, the skeleton of the stem can be obtained more accurately during skeleton extraction.

[0101] Optionally, the step of extracting a portion of the skeleton from the plant image using a histogram to obtain a plant stem image includes:

[0102] Based on the stated left-right ratio, the number of left corrosion cycles and the number of right corrosion cycles are obtained;

[0103] The erosion boundary algorithm is used to erode the left boundary of the stem position in the stem image multiple times based on the number of left erosions.

[0104] The erosion boundary algorithm is used to erode the right boundary of the stem position in the stem image multiple times based on the number of right erosions.

[0105] In this embodiment, the erosion boundary algorithm is the K3M algorithm.

[0106] The rootstock image was obtained by repeatedly alternating between left and right erosion.

[0107] The above method generally involves eroding the boundary at the same time as the boundary itself. However, due to the proportion issue, the right side is eroded only after the left side has been eroded a certain number of times.

[0108] Optionally, the step of performing color detection based on the rootstock image and the plant image, and obtaining the flower position by comparison, includes:

[0109] The plant image is then inspected to obtain the initial flower location and initial flower color.

[0110] In this embodiment, the YOLOv5 object detection model, trained by using multiple flower images, is used to detect the flower positions.

[0111] The flower colors are categorized into seven groups: red, orange, yellow, green, cyan, blue, and purple, and labeled as 1, 2, 3, 4, 5, 6, and 7, respectively. 1 corresponds to red, 2 to orange, 3 to yellow, 4 to green, 5 to cyan, 6 to blue, and 7 to purple.

[0112] Based on the initial detection of flower color and the color corresponding to the pixel count when acquiring the stem image, it is determined whether the colors are similar.

[0113] In this process, based on the pixel values ​​corresponding to the number of pixels when the plant stem image is acquired, i.e., the RGB values, the colors are classified according to the color reference table into red, orange, yellow, green, cyan, blue, and purple, and it is determined whether the category is the same as the category of the flower color initially detected.

[0114] If the colors of the initially detected flower position and color position are not similar, the flower position is obtained. This flower position is the initially detected flower position.

[0115] Sometimes, misjudgments can occur due to the similarity between the shape of the branches and leaves and the flowers. It is better to use color comparison and alignment to make a judgment.

[0116] Optionally, determining the pruning location based on the flower position and rootstock image includes:

[0117] The trimming position includes the trimming height position and the trimming horizontal position;

[0118] Obtain the pruning height. The pruning height represents the preset height of the branches and leaves after pruning.

[0119] In this embodiment, the pruning height is set to 1 / 10 of the flowerpot height, which is 5cm in this embodiment.

[0120] The height of the flower is determined by its vertical position.

[0121] The center point and height of the flower are obtained. The height of the flower is obtained by adding half its height to the center point.

[0122] The flower height refers to the height of the tallest flower among a group of flowers.

[0123] If the trimming height is less than the flower height, set the trimming height position to the flower height; if the trimming height is greater than or equal to the flower height, set the trimming height position to the trimming height.

[0124] Based on the rootstock image at the pruning height position, locate the rootstock position and set it as the pruning horizontal position.

[0125] Optionally, the external structure 1 includes an uncovered flowerpot structure 102 and a flowerpot lid 101.

[0126] The uncovered flowerpot structure 102 is a cylinder with one open side; the flowerpot lid 101 can be fastened to the uncovered flowerpot structure 102.

[0127] The water storage structure 2 is located at the bottom of the uncovered flowerpot structure 102; the water storage structure 2 is pull-out; and the screen 6 is located above the water storage structure 2.

[0128] Soil and plants are present above the screen 6.

[0129] The camera device 5 is fixed to the side edge of the uncovered flowerpot structure 102.

[0130] The small water pump 3 is fixed to the side edge of the uncovered flowerpot structure 102 opposite the camera equipment 5; the small water pump 3 is used to spray water from the water storage structure 2 onto the surface of the soil layer at regular intervals.

[0131] The pruning structure 4 is fixed inside the flowerpot cover 101; the processor is built into the pruning structure 4.

[0132] Optionally, a right solar panel 7 is fixedly placed on the outside of the flowerpot cover 101; the solar panel 7 is connected to the motor 402.

[0133] Optionally, the pruning structure includes a motor 402, a blade 401, and a support rod 403.

[0134] The processor is built into motor 402.

[0135] The motor 402 is connected to the support rod 403; the motor 402 can control the support rod 403 to extend downward.

[0136] The center point of the blade 401 is fixedly connected to the support rod 403.

[0137] Among them, the motor 402 and the blade 401 form the pruning structure 4, which is similar to the ceiling fan of the early years.

[0138] Upon contact with the top cover, the pruning structure 4 begins operation, extending downwards from the pot cover 101 to the pruning height to trim branches and leaves. A solar panel 7 is located on the exterior of the pot cover 101 to charge the battery. The battery can also be powered by a battery-powered appliance.

[0139] The motor battery is the same as the small water pump 3 battery and can be used interchangeably.

[0140] Optionally, the water pump structure includes a suction component 301 and a discharge component 302.

[0141] The suction component 301 of the small water pump 3 is located in the water storage structure 2; the discharge component 302 of the small water pump 3 is located above the soil.

[0142] The water pump is powered by a rechargeable battery, and a solar panel surrounds the soil layer to power the battery. Alternatively, battery-powered electrical appliances can also be used to power the battery.

[0143] Optionally, it consists of three layers. The bottom layer is a pull-out water storage device, which, being made of glass, allows for easy monitoring of the water level. The pull-out design makes it convenient to add water and nutrient solution as needed.

[0144] The middle layer is the soil layer, and the soil layer and the bottom layer are separated by a dense sieve, which allows excess water in the soil layer to flow back to the bottom layer without taking away the soil.

[0145] The top layer is the plant growth layer, which provides space for plant growth.

[0146] The flowerpot has a small water pump on its side, which is used to periodically spray water from the bottom layer onto the surface of the soil.

[0147] The water pump is powered by a rechargeable battery. A solar panel surrounds the soil layer to power the battery, or it can be powered by a battery-powered appliance.

[0148] The device features a top cover with a pruning device (similar to an old-fashioned ceiling fan) inside. Once the top of the plant touches the cover, the pruning device activates, extending 3-5 cm down from the cover, or to a predetermined length, to trim branches and leaves. The pruning device is powered by a rechargeable battery, which is charged by a solar panel on the outside of the top cover. It can also be powered by a battery-powered appliance. This battery is the same as the one used in the water pump and is interchangeable.

[0149] The specific ways in which each module performs operations in the system described in the above embodiments have been described in detail in the relevant embodiments, and will not be elaborated here.

[0150] This invention also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the aforementioned solar-powered automatic flowerpot planting device and the data mentioned above.

[0151] The algorithms and displays provided herein are not inherently related to any particular computer, virtual system, or other device. Various general-purpose systems can also be used in conjunction with the teachings herein. The required structure for constructing such systems is apparent from the above description. Furthermore, this invention is not directed to any particular programming language. It should be understood that the contents of the invention described herein can be implemented using various programming languages, and the above description of specific languages ​​is for the purpose of disclosing the best mode of implementation of the invention.

[0152] Numerous specific details are set forth in the specification provided herein. However, it will be understood that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures, and techniques have not been shown in detail so as not to obscure the understanding of this specification.

[0153] Similarly, it should be understood that, in order to simplify this disclosure and aid in understanding one or more of the various aspects of the invention, in the above description of exemplary embodiments of the invention, various features of the invention are sometimes grouped together in a single embodiment, figure, or description thereof. However, this method of disclosure should not be construed as reflecting an intention that the claimed invention requires more features than are expressly recited in each claim. Rather, as reflected in the following claims, inventive aspects lie in fewer than all features of a single foregoing disclosed embodiment. Therefore, the claims following the detailed description are hereby expressly incorporated into this detailed description, wherein each claim itself is a separate embodiment of the invention.

[0154] Those skilled in the art will understand that modules in the device of the embodiments can be adaptively changed and placed in one or more devices different from that embodiment. Modules, units, or components in the embodiments can be combined into a single module, unit, or component, and further, they can be divided into multiple sub-modules, sub-units, or sub-components. Except where at least some of such features and / or processes or units are mutually exclusive, any combination can be used to combine all features disclosed in this specification (including the accompanying claims, abstract, and drawings) and all processes or units of any method or device so disclosed. Unless expressly stated otherwise, each feature disclosed in this specification (including the accompanying claims, abstract, and drawings) may be replaced by an alternative feature that serves the same, equivalent, or similar purpose.

[0155] Furthermore, those skilled in the art will understand that although some embodiments herein include certain features included in other embodiments but not others, combinations of features from different embodiments are intended to be within the scope of the invention and form different embodiments. For example, in the following claims, any of the claimed embodiments can be used in any combination.

[0156] The various component embodiments of the present invention can be implemented in hardware, or as software modules running on one or more processors, or a combination thereof. Those skilled in the art will understand that microprocessors or digital signal processors (DSPs) can be used in practice to implement some or all of the functions of some or all of the components in the apparatus according to embodiments of the present invention. The present invention can also be implemented as a device or apparatus program (e.g., a computer program and computer program product) for performing part or all of the methods described herein. Such programs implementing the present invention can be stored on a computer-readable medium or can be in the form of one or more signals. Such signals can be downloaded from an Internet website, provided on a carrier signal, or provided in any other form.

[0157] It should be noted that the above embodiments are illustrative of the invention and not restrictive, and that those skilled in the art can devise alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses should not be construed as limiting the claims. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention can be implemented by means of hardware comprising several different elements and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by the same item of hardware. The use of the words first, second, and third, etc., does not indicate any order. These words can be interpreted as names.

Claims

1. A solar-powered automatic flowerpot planting device, characterized in that, Includes external structure, water storage structure, small water pump, pruning structure, camera equipment, and processor: The camera device is used to acquire plant images; the plant images are images of the side of the plant as detected. The processor is used to perform the following methods: Based on the plant image, the rootstock is extracted to obtain a rootstock image; the rootstock image is an image containing only the plant's rootstock. Based on the root and stem image and the plant image, color detection is performed, and the flower position is obtained by comparison; The pruning location is determined based on the flower position and rootstock image; The step of extracting roots and stems from the plant image to obtain a root and stem image includes: Based on the plant image, and taking into account the characteristic that the plant roots are connected to the soil, the root location is obtained through target detection. Based on the plant image, the position of the stem is determined by the pixels using a histogram to obtain a stem image; the stem image is the position of branches and leaves in the image. Based on the root location, adjust the skeleton of the stem location in the stem image to obtain the root and stem image; The step of predicting the stem position based on the plant image using a histogram to obtain a stem image includes: Based on the plant images, a histogram is constructed to obtain a plant array; the plant array is a two-dimensional array; the elements in the plant array are the same as the information in the histogram. A color window is created; the color window represents a fixed number of pixel values; Based on the color window, slide with a step size of 1 to obtain multiple pixel groups; Multiple pixel counts are obtained by summing the number of pixels in multiple pixel groups multiple times. By comparing multiple pixel values, the pixel value that is greater than the other pixel values ​​is found to obtain the optimal pixel value; The optimal pixel value in the plant image is set to 1, and other positions are set to 0 to obtain the plant stem image.

2. The solar-powered automatic planting flowerpot device according to claim 1, characterized in that, The step of extracting the skeleton of the plant stem location from the plant stem image based on the root location to obtain the root stem image includes: The vertical central axis is determined by the location of the root, thus obtaining the root centerline; Extend the root centerline by one-eighth of its own length to obtain the extended root centerline; The position of the extended stem is obtained by extending the center line of the root in the area of ​​the stem image; The left-right ratio is obtained by calculating the quotient of the left and right boundaries of the extended root centerline to the extended stem position. The skeleton of the plant stem image is extracted according to the left-right ratio to obtain the root and stem image.

3. The solar-powered automatic planting flowerpot device according to claim 2, characterized in that, The step of extracting the skeleton from the stem image according to the left-right ratio to obtain the root and stem image includes: Based on the stated left-right ratio, the number of left corrosion cycles and the number of right corrosion cycles are obtained; The erosion boundary algorithm is used to erode the left boundary of the stem position in the stem image multiple times according to the number of left erosions. The erosion boundary algorithm is used to erode the right boundary of the stem position in the stem image multiple times based on the number of right erosions. The rootstock image was obtained by repeatedly alternating between left and right erosion.

4. The solar-powered automatic planting flowerpot device according to claim 1, characterized in that, The step of performing color detection based on the rootstock image and the plant image, and obtaining the flower position by comparison, includes: The plant image is detected to obtain the initial flower position and initial flower color; Based on the initial detection of flower color and the color corresponding to the pixel count when acquiring the stem image, determine whether the colors are similar; If the colors of the initially detected flower position and the color position are not similar, the flower position is obtained; the flower position is the initially detected flower position.

5. A solar-powered automatic planting flowerpot device according to claim 1, characterized in that, The process of determining the pruning location based on the flower position and rootstock image includes: The trimming position includes the trimming height position and the trimming horizontal position; Obtain the pruning height; the pruning height represents the preset height of the branches and leaves after pruning. The height of the flower is determined by its vertical position. If the trimming height is less than the flower height, set the trimming height position to the flower height; if the trimming height is greater than or equal to the flower height, set the trimming height position to the trimming height. Based on the rootstock image at the pruning height position, locate the rootstock position and set it as the pruning horizontal position.

6. A solar-powered automatic planting flowerpot device according to claim 1, characterized in that, The external structure includes an uncovered flowerpot structure and a flowerpot lid. The uncovered flowerpot structure is a cylinder with one open side; the flowerpot lid can be fastened to the uncovered flowerpot structure. The water storage structure is located at the bottom of the uncovered flowerpot structure; the water storage structure is pull-out; and a screen is located above the water storage structure. Soil and plants are present above the screen; The camera device is fixed to the side edge of the uncovered flowerpot structure; A small water pump is fixed to the side edge of an uncovered flowerpot structure opposite the camera equipment; the small water pump is used to periodically spray water from the water storage structure onto the surface of the soil layer. The pruning structure is fixed inside the flowerpot lid; the processor is built into the pruning structure.

7. A solar-powered automatic planting flowerpot device according to claim 1, characterized in that, A solar panel is fixedly placed on the outside of the flowerpot cover; the solar panel is connected to the motor.

8. A solar-powered automatic planting flowerpot device according to claim 7, characterized in that, The pruning structure includes a motor, blades, and support rods. The motor is connected to the support rod; the motor can control the support rod to extend downwards. The center point of the blade is fixedly connected to the support rod.

9. A solar-powered automatic planting flowerpot device according to claim 8, characterized in that, The processor is built into the motor.

10. A solar-powered automatic planting flowerpot device according to claim 7, characterized in that, The water pump structure includes a suction component and a discharge component. The suction part of the small water pump is located in the water storage structure; the discharge part of the small water pump is located above the soil.

Images