An Alisma orientale harvesting and cleaning system and method based on machine vision

Abstract

The present invention discloses an Alisma orientale harvesting and cleaning system and method based on machine vision, which relates to the field of Alisma orientale harvesting, and includes a moving module, a positioning module, a digging module, a cutting module and a cleaning module; the positioning module includes a first camera and a second camera, and the first camera and the second camera are used to obtain the first position information, the second position information, the depth information and the size information of the Alisma orientale; the digging module is used to adjust the digging component to dig out the Alisma orientale according to the obtained first position information, depth information and size information; the cutting module is used to adjust the cutting component to cut the withered stems and leaves of the dug-out Alisma orientale according to the obtained second position information and size information; the cleaning module is used to obtain the cut Alisma orientale and clean the Alisma orientale through the cleaning component. The present invention uses machine vision technology to adjust the digging component and the cutting component to quickly and accurately obtain the Alisma orientale.

Description

Technical Field

[0001] The present invention relates to the field of Alisma orientale harvesting, and particularly relates to a harvesting and cleaning system and method for Alisma orientale based on machine vision. Background Art

[0002] The harvesting season of Alisma orientale is in winter. The climate is cold in winter, and there is a lot of accumulated water in the winter paddy fields, which cannot be drained completely. Workers wear thigh boots to work in the fields. When harvesting, first use a knife to draw a circle around the bulb of Alisma orientale to cut off some fibrous roots, then pull up the plant, and then carefully remove the soil and residual roots around the bulb. Except for the central leaves, remove the rest of the leaves (including withered leaves and some non-withered leaves).

[0003] In the existing Alisma orientale harvesting process, an operator holds the upper part of Alisma orientale with one hand and holds a knife with the other hand and inserts it into the mud to cut off the main fibrous roots at the bottom of Alisma orientale. In this process, the thinner small fibrous roots do not need to be cut off. When pulling Alisma orientale out of the mud upwards, the small fibrous roots will break automatically. However, such a harvesting method has low efficiency and the operator is prone to injury. Summary of the Invention

[0004] An object of the present invention is to provide a harvesting and cleaning system and method for Alisma orientale based on machine vision, which obtains the first position information, depth information and size information of Alisma orientale from different angles through a first camera and a second camera, and adjusts a digging module and a cutting module to dig and cut Alisma orientale according to the obtained information.

[0005] This object is achieved by the following technical solutions:

[0006] An Alisma orientale harvesting and cleaning system and method based on machine vision, comprising a moving module, a positioning module, a digging module, a cutting module and a cleaning module; wherein, the moving module comprises a crawler chassis for driving the system to move; the positioning module comprises a first camera and a second camera for obtaining the first position information, second position information, depth information and size information of the Alisma orientale; a first telescopic rod and a second telescopic rod are arranged on the crawler chassis, a first connecting rod is arranged on the first telescopic rod, a digging component and a cutting component are arranged on the first connecting rod, the first camera is connected to the first connecting rod through a third telescopic rod, and the shooting surface of the first camera faces downwards; a second connecting rod is arranged on the second telescopic rod, a sliding rod is arranged on the second connecting rod, the sliding rod can slide on the second telescopic rod, the second camera is arranged on the sliding rod, and the shooting surface of the sliding rod is perpendicular to the shooting surface of the first camera; the digging module is used for adjusting the digging component to dig out the Alisma orientale according to the obtained first position information, depth information and size information; the cutting module is used for adjusting the cutting component to cut the withered stems and leaves of the dug-out Alisma orientale according to the obtained second position information and size information; the cleaning module is used for obtaining the cut Alisma orientale and cleaning the Alisma orientale through a cleaning component.

[0007] When obtaining the Alisma orientale, the first camera and the second camera obtain the first image and the second image of the Alisma orientale in the field, and obtain the first coordinate information of the Alisma orientale according to the first image and the second image, and obtain the first position information and size information according to the first coordinate information;

[0008] The first camera and the second camera obtain the third image and the fourth image of the Alisma orientale on the digging component, and obtain the second coordinate information of the Alisma orientale according to the third image and the fourth image, and obtain the second position information and size information according to the second coordinate information.

[0009] Slide the sliding rod on the second telescopic rod so that the distances between the second camera and the crawler chassis are X1, X2, X3, X4 and X5 respectively, where X1 < X2 < X3 < X4 < X5, and X1 = 0. The second camera obtains the first height image, second height image, third height image, fourth height image and fifth height image of the Alisma orientale in the field when the distances between the second camera and the crawler chassis are X1, X2, X3, X4 and X5 respectively. The repair module repairs the missing parts of the Alisma orientale in the first height image - fifth height image, obtains the average height of the missing parts of the Alisma orientale, and obtains the depth information.

[0010] Obtain the first coordinate information and the second coordinate information of the Alisma orientale through the first camera and the second camera, and adjust the digging component to dig the Alisma orientale according to the first coordinate information and the second coordinate information, and cut the dug-out Alisma orientale through the cutting component.

[0011] This system uses machine vision to obtain Alisma orientale, a technology that uses machines to replace human eyes for measurement and judgment. It converts the captured target into an image signal through machine vision products (i.e., image capture devices, including CMOS and CCD types), transmits it to a dedicated image processing system, obtains the morphological information of the captured target, and converts it into a digital signal according to information such as pixel distribution, brightness, and color; the image system performs various operations on these signals to extract the features of the target, and then controls the actions of on-site equipment according to the discrimination results.

[0012] Existing Alisma orientale is dug manually, with low operation efficiency and being time-consuming and laborious. This system can automatically obtain Alisma orientale through the first camera and the second camera. Compared with existing systems using machine vision, the first camera and the second camera of this system obtain images of Alisma orientale from different directions and angles, and determine the coordinate information of Alisma orientale in a preset coordinate system through the images of Alisma orientale from two angles. The coordinate information obtained by this system is more accurate. At the same time, in the preset coordinate system, the plane where the crawler chassis is located is the X and Z axes, and the straight line where the third telescopic rod is located is the Y axis. When obtaining coordinate information from the graphics obtained by the first camera and the second camera, the preset coordinate system can be faster and more accurate. Therefore, when this system obtains Alisma orientale, it can process it more quickly and accurately.

[0013] At the same time, the third telescopic rod focuses the first camera by stretching to ensure that the captured image is clear and accurate.

[0014] Preferably, both the first connecting rod and the second connecting rod are connected with stabilizing chains, and a support rod is connected to the stabilizing chains. The stabilizing chains can rotate circumferentially around the support rod. Support frames are arranged at both ends of the support rod, and the lower ends of the support frames are connected to the ground. The support rod can further stabilize the first connecting rod and the second connecting rod to prevent them from falling off.

[0015] Furthermore, the cleaning module includes a conveyor belt connected to the crawler chassis. One end of the conveyor belt connected to the crawler chassis is provided with a telescopic plate. The telescopic plate is located inside the conveyor belt or below the excavation component through stretching. The telescopic plate is used to obtain the Alisma orientale clamped by the excavation component and convey it into the conveyor belt. A number of spray heads and water tanks are arranged on the crawler chassis. The spray heads spray the water in the water tank to clean the Alisma orientale on the conveyor belt.

[0016] On the other hand, a method for harvesting and cleaning Alisma orientale based on machine vision includes the following steps:

[0017] The crawler chassis moves to the location of Alisma orientale in the field;

[0018] Obtain the first position information, depth information, and size information of Alisma orientale through the first camera and the second camera;

[0019] The excavation component adjusts the excavation position and angle of the excavation component according to the first position information, depth information, and size information, and digs out the alisma in the field;

[0020] The first camera and the second camera obtain the second position information and size information of the alisma in the excavation component;

[0021] The cutting component adjusts the position information of the cutting component according to the second position information and size information, and rotates the cutting component at the position of the alisma to cut the withered stems and leaves;

[0022] The cleaning module obtains the cut alisma and cleans the alisma through the cleaning component.

[0023] The first camera and the second camera obtain the first image and the second image of the alisma in the field, and obtain the first coordinate information of the alisma in the preset coordinate system according to the first image and the second image;

[0024] The second camera slides on the second telescopic rod through the sliding rod, and the second camera respectively obtains the first height image, the second height image, the third height image, the fourth height image, and the fifth height image of the alisma in the field when the distances between the second camera and the crawler chassis are X1, X2, X3, X4, and X5 respectively. The repair module repairs the missing parts of the alisma in the first height image - the fifth height image, obtains the average height of the missing parts of the alisma, and obtains the depth information;

[0025] Adjust the excavation depth information and excavation position information of the excavation component according to the first coordinate information and depth information;

[0026] Obtain the size information according to the first coordinate information and depth information, and adjust the excavation angle information of the excavation component through the size information.

[0027] Compared with the prior art, the present invention has the following advantages and beneficial effects:

[0028] The present invention relates to an alisma harvesting and cleaning system and method based on machine vision. The present invention uses machine vision technology to adjust the excavation component and the cutting component, quickly and accurately obtain the alisma, and the first camera and the second camera of the present invention obtain images of the alisma from different direction angles, and determine the coordinate information of the alisma in the preset coordinate system through the alisma images of the two angles. The coordinate information obtained by this system is more accurate;

[0029] Moreover, the first camera and the second camera of the present invention obtain images of the alisma from different direction angles, obtain the depth and size of the alisma, and thus obtain the alisma more accurately. Brief Description of the Drawings

[0030] The accompanying drawings described herein are used to provide a further understanding of the embodiments of the present invention, form a part of this application, and do not limit the embodiments of the present invention. In the drawings:

[0031] Figure 1 It is a schematic structural diagram of the mobile module, positioning module, excavation module, cutting module, and cleaning module of this system;

[0032] Figure 2 It is a schematic structural diagram of this system;

[0033] Figure 3 It is a schematic diagram of a preset coordinate system in this system;

[0034] Figure 4 It is a schematic diagram of coordinates A1, A2, A3, and A4;

[0035] Figure 5 It is a schematic diagram of the conveyor belt in this system.

[0036] Markings and corresponding component names in the drawings:

[0037] 1 - First connecting rod, 2 - First telescopic rod, 3 - Crawler chassis, 4 - Excavation component, 5 - Cutting component, 6 - Third telescopic rod, 7 - First camera, 8 - Second connecting rod, 9 - Second telescopic rod, 10 - Sliding rod, 11 - Second camera, 12 - Conveyor belt, 13 - Stabilizing chain, 14 - Support rod. Detailed implementation manners

[0038] To make the objectives, technical solutions, and advantages of the present invention clearer and more understandable, the present invention will be further described in detail below in conjunction with the embodiments and the accompanying drawings. The illustrative embodiments and descriptions thereof of the present invention are only used to explain the present invention and do not limit the present invention.

[0039] In the description of the present invention, it should be understood that the orientation or positional relationships indicated by the terms "front", "rear", "left", "right", "up", "down", "vertical", "horizontal", "high", "low", "inner", "outer", etc. are based on the orientation or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus should not be construed as limiting the protection scope of the present invention.

[0040] Embodiment 1

[0041] As Figure 1 shown, this system includes a mobile module, a positioning module, an excavation module, a cutting module, and a cleaning module.

[0042] Among them, the mobile module is used to drive the system to move in the field. During the movement, when the system is located at the alisma plantago, the positioning module acquires the first position information, depth information, and size information of the alisma plantago, and sends the first position information, depth information, and size information to the excavation module. The excavation module excavates the alisma plantago according to the acquired first position information, depth information, and size information. After the alisma plantago is dug out, the positioning module acquires the second position information and size information of the alisma plantago, and sends the second position information and size information to the cutting module. The cutting module removes the remaining leaves of the alisma plantago except the central leaf according to the acquired second position information and size information. The remaining leaves include withered leaves and some non-withered leaves. The cleaning module is used to acquire the cut alisma plantago and clean the alisma plantago through the cleaning component.

[0043] In some embodiments, as Figure 2 shown, the mobile module includes a crawler chassis 3. The crawler chassis 3 includes two mutually parallel mobile chassis. The mobile chassis is used to move in the field, and the crawler chassis 3 is used to drive the system to move; the positioning module includes a first camera 7 and a second camera 11. The first camera 7 and the second camera 11 are used to acquire the first position information, second position information, depth information, and size information of the alisma plantago; first telescopic rods 2 and second telescopic rods 9 are arranged on both mobile chassis. A first connecting rod 1 is arranged on the two first telescopic rods 2. An excavation component 4 and a cutting component 5 are arranged on the first connecting rod 1. The first camera 7 is connected to the first connecting rod 1 through a third telescopic rod 6, and the shooting surface of the first camera 7 faces downward;

[0044] A second connecting rod 8 is arranged on the two second telescopic rods 9. A sliding rod 10 is arranged on the second connecting rod 8. The sliding rod 10 can slide on the second telescopic rod 9. The second camera 11 is arranged on the sliding rod 10, and the shooting surface of the sliding rod 10 is perpendicular to the shooting surface of the first camera 7.

[0045] In this embodiment, the first position information, second position information, depth information, and size information of the alisma plantago are acquired through the first camera 7 and the second camera 11.

[0046] Embodiment 2

[0047] On the basis of the above embodiment, a method for harvesting and cleaning alisma plantago based on machine vision includes the following steps:

[0048] Step 1, the crawler chassis 3 moves to the alisma plantago in the field, so that the first camera 7 is located directly above the alisma plantago to be acquired;

[0049] Step 2, acquire the first position information, depth information, and size information of the alisma plantago through the first camera 7 and the second camera 11;

[0050] Step 2.1, the first camera 7 obtains the first image of the alisma plantago in the field with the shooting surface facing downwards, and the second camera 11 obtains the second image of the alisma plantago in the field with the shooting surface facing forwards. In this embodiment, the direction with the shooting surface facing forwards is the direction in which the plane where the two second telescopic rods 9 are located faces the plane where the two first telescopic rods 2 are located; the first camera 7 and the second camera 11 respectively obtain the first image and the second image of the alisma plantago in the field, and obtain the first coordinate information of the alisma plantago in the preset coordinate system; the preset coordinate system takes the upper end surface of the crawler chassis 3 as the X and Z axes, and the straight line where the third telescopic rod 6 is located as the Y axis, as Figure 3 shown, where the Z axis is parallel to the straight line where the mobile chassis is located; the first coordinate information of the alisma plantago in the preset coordinate system is obtained through the first image and the second image taken at two angles; among them, the excavation assembly 4 is located on the plane where the Y and X axes are located;

[0051] Step 2.2, the second camera 11 slides on the second telescopic rod 9 through the sliding rod 10, so that the second camera 11 respectively obtains the first height image, the second height image, the third height image, the fourth height image and the fifth height image of the alisma plantago in the field when the distances between the second camera 11 and the crawler chassis 3 are X1, X2, X3, X4 and X5 respectively. The repair module repairs the missing parts of the alisma plantago in the first height image - the fifth height image to obtain the average height of the missing parts of the alisma plantago, and obtains the depth information;

[0052] Among them, as Figure 4 shown, the first coordinate information includes the coordinates A3 of the uppermost part of the alisma plantago when it is in the field, the coordinates A1 and A2 of the uppermost part of the alisma plantago in the field on the plane where the Y and X axes are located, and the depth information is the coordinate A4 of the lowermost part of the alisma plantago on the plane where the Y and X axes are located;

[0053] Step 2.3, according to the coordinates A1, A2, A3 and A4, adjust the position of the excavation assembly 4. The excavation assembly 4 includes two excavation rods, and both excavation rods are located on the plane where the Y and X axes are located. When adjusting the position of the excavation assembly 4, after the two excavation rods are inserted into the field, the lower ends of the two excavation rods are located below the coordinate A4; the two excavation rods are respectively located on both sides of the coordinates A1 and A2, and then the distance between the two excavation rods is shortened so that the two excavation rods are in contact with both sides of the alisma plantago, and the alisma plantago is dug out;

[0054] Step 2.4, before digging out the alisma orientale, obtain the coordinates B1 and B2 of the topmost position of the alisma orientale in the plane where the Y and z axes are located in the field; obtain the height and width of the alisma orientale based on the coordinates A1, A2, A3, A4, B1, and B2, and estimate the volume size information of the alisma orientale through the height and width. When the volume size information of the alisma orientale is less than the preset volume size Q, when the two digging rods are inserted into the field, the distance between the lower ends of the two digging rods and the coordinate A4 on the Y axis is less than 5 cm, and the upper ends of the two digging rods do not need to rotate. When the two digging rods clamp the alisma orientale, they are parallel to each other; when the volume size information of the alisma orientale is greater than or equal to the preset volume size Q, when the two digging rods are inserted into the field, the distance between the lower ends of the two digging rods and the coordinate A4 on the Y axis is greater than 10 cm; and the upper ends of the two digging rods rotate. When the two digging rods clamp the alisma orientale, the included angle between the two digging rods is greater than 60 degrees; where the preset volume size Q is the average volume size of the alisma orientale in this area.

[0055] Step 2.5, the two digging rods clamp the alisma orientale and lift it upward to dig out the alisma orientale.

[0056] Step 3, the first camera 7 and the second camera 11 obtain the second position information and size information of the alisma orientale in the digging component 4.

[0057] Step 3.1, the first camera 7 obtains the third image of the dug-out alisma orientale with the shooting surface facing downward, and the second camera 11 obtains the fourth image of the dug-out alisma orientale with the shooting surface facing forward. Obtain the second coordinate information of the alisma orientale in the preset coordinate system based on the third image and the fourth image; the second coordinate information includes the coordinates C3 and C4 of the topmost and bottommost positions of the alisma orientale, and the coordinates C1 and C2 of the two ends of the alisma orientale in the X-axis direction on the plane where the Y and X axes are located.

[0058] Step 3.2, a number of spray nozzles and a water tank are arranged on the crawler chassis 3. The spray nozzles spray the water in the water tank to wash the alisma orientale on the conveyor belt 12. Obtain the center point of the alisma orientale based on the coordinates C1, C2, C3, and C4, and adjust the angle of the spray nozzles on the crawler chassis 3 according to the center point so that the spraying direction of the spray nozzles passes through the center point of the alisma orientale.

[0059] Step 3.3, obtain the height and width of the alisma orientale based on the coordinates C1, C2, C3, and C4, and estimate the actual volume size information of the alisma orientale through the height and width; when the actual volume size information of the alisma orientale is less than the preset volume size Q, the water spraying amount of the spray nozzles is less than the preset value M. When the actual volume size information of the alisma orientale is greater than or equal to the preset volume size Q, the water spraying amount of the spray nozzles is greater than or equal to the preset value M. The preset value M is the water spraying amount when several spray nozzles wash the alisma orientale with the volume size Q and wash it clean.

[0060] Step 4: The cutting assembly 5 adjusts its position according to the second position information and size information, and rotates the cutting assembly 5 at the alisma plantago to cut the withered stems and leaves.

[0061] Step 5: As Figure 5 shown, the cleaning module includes a conveyor belt 12 connected to the crawler chassis 3. One end of the conveyor belt 12 connected to the crawler chassis 3 is provided with a telescopic plate. The telescopic plate is located inside the conveyor belt 12 or below the excavation assembly 4 through telescoping. The telescopic plate is used to obtain the alisma plantago clamped by the excavation assembly 4 and convey it into the conveyor belt 12. After Step 4, the telescopic plate extends and is located below the excavation assembly 4. The alisma plantago moves onto the telescopic plate, and the telescopic plate shortens to place the alisma plantago on the conveyor belt 12 for conveying.

[0062] In the above embodiments, the structures of the excavation assembly and the cutting assembly are both existing structures, as long as they can achieve the effects of excavation and cutting. The inventor does not make specific limitations here. At the same time, when adjusting the position of the excavation assembly 4, the two excavation rods slide on the first connecting rod, and the positions of the two excavation rods on the first connecting rod are adjusted. When adjusting the position of the cutting assembly, the cutting assembly slides on the first connecting rod, and the position of the cutting assembly on the first connecting rod is adjusted.

[0063] Embodiment 3

[0064] Based on the above embodiments, before the first camera 7 and the second camera 11 acquire images, the third telescopic rod 6 telescopes to focus the first camera 7, and the sliding rod 10 slides on the second telescopic rod 9 to focus the second camera 11.

[0065] In some embodiments, stabilizing chains 13 are connected to both the first connecting rod 1 and the second connecting rod 8. A support rod 14 is connected to the stabilizing chains 13. The stabilizing chains 13 can rotate circumferentially around the support rod 14. Both ends of the support rod 14 are provided with support frames, and the lower ends of the support frames are connected to the ground. The support rod 14 can further stabilize the first connecting rod 1 and the second connecting rod 8 to prevent them from falling off.

[0066] The "first", "second", "third", etc. used herein are only for distinguishing the corresponding components clearly and do not aim to limit any order or emphasize importance, etc. In addition, the term "connected" used herein, without special explanation, can be directly connected or indirectly connected via other components.

[0067] The specific embodiments described above further elaborate on the objective, technical solution, and beneficial effects of the present invention. It should be understood that the above description is only for the specific embodiments of the present invention and is not intended to limit the protection scope of the present invention. Any modifications, equivalent replacements, improvements, etc., made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. An Alisma orientale harvesting and cleaning system based on machine vision, characterized in that, It includes a moving module, a positioning module, a digging module, a cutting module and a cleaning module; The moving module includes a crawler chassis (3), and the crawler chassis (3) is used to drive the system to move; The positioning module includes a first camera (7) and a second camera (11), and the first camera (7) and the second camera (11) are used to obtain the first position information, second position information, depth information and size information of the alisma orientale; A first telescopic rod (2) and a second telescopic rod (9) are arranged on the crawler chassis (3). A first connecting rod (1) is arranged on the first telescopic rod (2). A digging assembly (4) and a cutting assembly (5) are arranged on the first connecting rod (1). The first camera (7) is connected to the first connecting rod (1) through a third telescopic rod (6), and the shooting surface of the first camera (7) faces downward; A second connecting rod (8) is arranged on the second telescopic rod (9). A sliding rod (10) is arranged on the second connecting rod (8). The sliding rod (10) can slide on the second telescopic rod (9). The second camera (11) is arranged on the sliding rod (10), and the shooting surface of the sliding rod (10) is perpendicular to the shooting surface of the first camera (7); The digging module is used to adjust the digging assembly (4) to dig out the alisma orientale according to the obtained first position information, depth information and size information; The cutting module is used to adjust the cutting assembly (5) to cut the withered stems and leaves of the dug-out alisma orientale according to the obtained second position information and size information; The cleaning module is used to obtain the cut alisma orientale and clean the alisma orientale through a cleaning assembly.

2. The harvesting and cleaning system of Alisma orientale based on machine vision according to claim 1, characterized in that, The first camera (7) and the second camera (11) obtain the first image and the second image of the alisma orientale in the field, and obtain the first coordinate information of the alisma orientale according to the first image and the second image. The first position information and size information are obtained according to the first coordinate information; The first camera (7) and the second camera (11) obtain the third image and the fourth image of the alisma orientale on the digging assembly (4), and obtain the second coordinate information of the alisma orientale according to the third image and the fourth image. The second position information and size information are obtained according to the second coordinate information.

3. The Alisma orientale harvesting and cleaning system based on machine vision according to claim 2, characterized in that, The sliding rod (10) is made to slide on the second telescopic rod (9) so that the distances between the second camera (11) and the crawler chassis (3) are X1, X2, X3, X4 and X5 respectively, where X1 < X2 < X3 < X4 < X5, and X1 = 0. The second camera (11) obtains the first height image, second height image, third height image, fourth height image and fifth height image of the alisma orientale in the field when the distances from the crawler chassis (3) are X1, X2, X3, X4 and X5 respectively. The missing parts of the alisma orientale in the first height image - fifth height image are repaired through a repair module, and the average height of the missing parts of the alisma orientale is obtained to obtain the depth information.

4. A water plantain harvesting and cleaning system based on machine vision according to claim 1, characterized in that, The third telescopic rod (6) focuses the first camera (7) by telescoping.

5. A water plantain harvesting and cleaning system based on machine vision according to claim 1, characterized in that, The cleaning module includes a conveyor belt (12) connected to a crawler chassis (3). One end of the conveyor belt (12) connected to the crawler chassis (3) is provided with a telescopic plate. The telescopic plate is located inside the conveyor belt (12) or below the excavation component (4) by telescoping, and the telescopic plate is used to obtain the alisma orientale clamped by the excavation component (4) and convey it into the conveyor belt (12).

6. The harvesting and cleaning system of Alisma orientale based on machine vision according to claim 5, characterized in that, A number of spray heads and a water tank are arranged on the crawler chassis (3). The spray heads spray the water in the water tank to clean the alisma orientale on the conveyor belt (12).

7. A water plantain harvesting and cleaning system based on machine vision according to claim 1, characterized in that, Stabilizing chains (13) are connected to both the first connecting rod (1) and the second connecting rod (8). A support rod (14) is connected to the stabilizing chains (13), and the stabilizing chains (13) can rotate circumferentially around the support rod (14).

8. A harvesting and cleaning system for Alisma orientale based on machine vision according to claim 7, characterized in that, Both ends of the support rod (14) are provided with support frames, and the lower ends of the support frames are connected to the ground.

9. A harvesting and cleaning method of Alisma orientale based on machine vision, characterized in that, Including the system according to any one of claims 1-8, comprising the following steps: The crawler chassis (3) moves to the alisma orientale in the field; The first position information, depth information and size information of the alisma orientale are obtained through the first camera (7) and the second camera (11); The excavation component (4) adjusts the excavation position and angle of the excavation component (4) according to the first position information, depth information and size information, and digs out the alisma orientale in the field; The first camera (7) and the second camera (11) obtain the second position information and size information of the alisma orientale in the excavation component (4); The cutting component (5) adjusts the position information of the cutting component (5) according to the second position information and size information, and rotates the cutting component (5) at the position of the alisma orientale to cut the withered stems and leaves; The cleaning module obtains the cut alisma orientale and cleans the alisma orientale through the cleaning component.

10. A method for harvesting and cleaning alisma orientale based on machine vision according to claim 9, characterized in that The first camera (7) and the second camera (11) obtain the first image and the second image of the alisma orientale in the field, and obtain the first coordinate information of the alisma orientale in a preset coordinate system according to the first image and the second image; The second camera (11) slides on the second telescopic rod (9) through the sliding rod (10), so that the second camera (11) obtains the first height image, the second height image, the third height image, the fourth height image and the fifth height image of the alisma orientale in the field at distances X1, X2, X3, X4 and X5 from the crawler chassis (3) respectively. The missing parts of the alisma orientale in the first height image - the fifth height image are repaired through the repair module, and the average height of the missing parts of the alisma orientale is obtained to obtain the depth information; Adjust the excavation depth information and excavation position information of the excavation component (4) according to the first coordinate information and the depth information; Obtain the size information according to the first coordinate information and the depth information, and adjust the excavation angle information of the excavation component (4) through the size information.

Images