Chinese cabbage harvesting machine based on machine vision and control method

Abstract

The application provides a Chinese cabbage row-harvesting machine based on machine vision and a control method, which comprises a chassis, a row-harvesting mechanism, a cabbage-harvesting and conveying mechanism, a visual detection module, a motion control module and an edge computing module; the cabbage-harvesting and conveying mechanism is used for harvesting and conveying cabbages; the cabbage-harvesting and conveying mechanism is installed on the chassis, and the row-harvesting mechanism is used for adjusting the row-harvesting of the cabbage-harvesting and conveying mechanism; the visual detection module is installed on the front end frame of the cabbage-harvesting and conveying mechanism, is used for collecting field images and transmitting the images to the edge computing module, and the edge computing module is connected with the visual detection module and the motion control module; after the edge computing module processes the images collected by the visual detection module, offset data is obtained and output to the motion control module, and the motion control module controls the row-harvesting mechanism to adjust the row-harvesting of the cabbage-harvesting and conveying mechanism. The application can improve the row-harvesting precision and efficiency through two row-harvesting modes, i.e., active row-harvesting and chassis floating row-harvesting.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of agricultural machinery, and particularly relates to a Chinese cabbage row-by-row harvesting machine based on machine vision and a control method. BACKGROUND

[0002] The existing Chinese cabbage harvesting machine has technical defects in row-by-row harvesting and ground leveling. Especially when harvesting in the ridge planting mode, the harvesting machine needs to drive on the ridge. At this time, due to the incoordination of the ridge distance and the wheel distance of the harvesting machine, the planting row distance and the number of rows on the ridge do not match, which may cause the machine body to tilt during harvesting, and the inclination angle is too large to cause the harvesting components to enter the soil, resulting in damage to the machine. Secondly, due to the tilting of the machine body, the difficulty for the driver to maintain straight driving is increased during single row harvesting operation; the tilting of the harvesting components causes the clamping position of the Chinese cabbage to change, which also causes the success rate of harvesting to decrease and the damage rate of the harvested Chinese cabbage to increase. SUMMARY

[0003] In view of the above technical problems, the present application provides a Chinese cabbage row-by-row harvesting machine based on machine vision and a control method.

[0004] The present application can realize row-by-row harvesting of ridge planting Chinese cabbage. Through two row-by-row modes of active row-by-row and chassis floating row-by-row, the row-by-row accuracy and efficiency can be improved.

[0005] The present application is beneficial to realize harvesting operation of different planting modes such as different ridge distances, ridge widths, row numbers and row distances, and to enhance the adaptability of single row harvesting machines to different planting modes. Through the automatic row-by-row of the device, the problems of different growth periods and uneven straightness of Chinese cabbage are solved, which is beneficial to realize continuous and stable pulling and stable feeding.

[0006] Note that the description of these objects does not hinder the existence of other objects. One mode of the present application does not need to realize all the above-mentioned objects. The objects other than the above-mentioned objects can be extracted from the description, drawings and claims.

[0007] The present application realizes the above technical objects through the following technical means.

[0008] A Chinese cabbage row-by-row harvesting machine based on machine vision, comprising a chassis, a row-by-row mechanism, a Chinese cabbage harvesting and conveying mechanism, a visual detection module, a motion control module and an edge computing module;

[0009] The Chinese cabbage harvesting and conveying mechanism is used for harvesting and conveying Chinese cabbage;

[0010] The Chinese cabbage harvesting and conveying mechanism is installed on the chassis, and the row-by-row mechanism is used for adjusting the Chinese cabbage harvesting and conveying mechanism to row-by-row;

[0011] The visual detection module is installed on the front end frame of the Chinese cabbage harvesting and conveying mechanism, is used for collecting field images and transmitting the images to the edge computing module, the edge computing module is connected with the visual detection module and the motion control module respectively, and the motion control module is connected with the rowing mechanism.

[0012] In the scheme, the rowing mechanism includes a floating rowing mechanism and a positive rowing mechanism, the floating rowing mechanism is installed on the chassis and is used for moving the Chinese cabbage harvesting and conveying mechanism along the chassis to row; and the positive rowing mechanism is installed on the Chinese cabbage harvesting and conveying mechanism and is used for changing the angle of the two conveying belt angles of the Chinese cabbage harvesting and conveying mechanism to row.

[0013] Further, the floating rowing mechanism includes a fixed linear bearing set, a movable linear bearing set, a linear driving mechanism and a connecting frame.

[0014] The chassis includes a chassis frame, a movable frame and a connecting frame; the connecting frame is installed above one side of the movable frame and is connected with the Chinese cabbage harvesting and conveying mechanism.

[0015] The movable frame is installed on the chassis frame, the movable linear bearing set is installed on the movable frame, the fixed linear bearing set is installed on one side of the chassis frame, the other side of the movable frame is located on the fixed linear bearing set, one end of the linear driving mechanism is installed below one side of the movable frame through the connecting frame, and one end of the linear driving mechanism is connected with the movable linear bearing set and is used for driving the movable linear bearing set to drive the movable frame to move left and right along the chassis frame to float the Chinese cabbage harvesting and conveying mechanism to row, and the linear driving mechanism is connected with the motion control module.

[0016] Further, two groups of the positive rowing mechanism are symmetrically arranged on both sides of the front end of the support of the Chinese cabbage harvesting and conveying mechanism, each group of the positive rowing mechanism includes a large-torque steering engine, an engine mounting seat and a shaft coupling.

[0017] The engine mounting seat is installed on the front end of the support of the Chinese cabbage harvesting and conveying mechanism, the large-torque steering engine is installed on the engine mounting seat, the output shaft of the large-torque steering engine is connected with the driven wheel mounting frame through the shaft coupling, and the driven wheel mounting frame is provided with a driven wheel; the large-torque steering engine is used for adjusting the angle of the two driven wheel mounting frames to change the angle of the two conveying belt angles of the Chinese cabbage harvesting and conveying mechanism to row; and the large-torque steering engine is connected with the motion control module.

[0018] In the scheme, a two-stage conveying and collecting mechanism is further included; the two-stage conveying and collecting mechanism includes a first-stage telescopic transverse conveying mechanism, a second-stage vertical conveying belt mechanism, a conveying belt fixing frame and a collecting frame.

[0019] The first level telescopic horizontal conveying belt mechanism is located at the end of the Chinese cabbage harvesting conveying mechanism, the second level vertical conveying belt mechanism is located at the end of the first level telescopic horizontal conveying belt mechanism, the first level telescopic horizontal conveying belt mechanism and the second level vertical conveying belt mechanism are arranged vertically in space, and the collection frame is located behind the second level vertical conveying belt mechanism;

[0020] The first level telescopic horizontal conveying belt mechanism comprises a conveying belt front section mounting frame, a conveying belt rear section mounting frame, a conveying belt, a belt surface tensioning mechanism and a plurality of conveying belt rollers;

[0021] The conveying belt front section mounting frame and the conveying belt rear section mounting frame are arranged in parallel and are connected through a U-shaped sliding groove; the plurality of conveying belt rollers are mounted on the front section conveying belt roller mounting frame and the rear section conveying belt roller mounting frame, the conveying belt is mounted on the conveying belt front section mounting frame and the conveying belt rear section mounting frame, and the belt surface tensioning mechanism is mounted on the conveying belt rear section mounting frame and is in contact with the conveying belt;

[0022] A plurality of conveying belt fixing frames are arranged below the first level telescopic horizontal conveying mechanism and the second level vertical conveying belt mechanism, wherein the bottom of the conveying belt front section mounting frame is connected to the connecting rack through the conveying belt fixing frame, and the conveying belt rear section mounting frame is connected to the chassis rack through the conveying belt fixing frame;

[0023] The connecting rack can drive the conveying belt front section mounting frame to move left and right, and the belt surface tensioning mechanism is used to keep the conveying belt in a tensioned state.

[0024] In the above scheme, the visual detection module comprises an industrial camera, a mounting rod, a camera mounting seat and an angle adjusting plate;

[0025] The industrial camera is mounted on the camera mounting seat, the camera mounting seat is connected to the upper end of the mounting rod through the angle adjusting plate, and the lower end of the mounting rod is connected to the upper part of the support of the Chinese cabbage harvesting conveying mechanism; and the industrial camera is connected to the edge computing module.

[0026] Further, one side of the angle adjusting plate is connected to the mounting rod through a rotating shaft, the other side is provided with an arc-shaped sliding groove and is connected to the mounting rod through a bolt, the shooting angle of the industrial camera is changed by changing the position of the bolt in the arc-shaped sliding groove.

[0027] In the above scheme, leveling mechanisms are arranged at four corners of the chassis respectively, each leveling mechanism comprises a connecting rod, a hinge, a leveling hydraulic rod, a tire connecting flange plate and a posture sensor;

[0028] One end of the connecting rod is connected with the tire connecting flange sheet, the other end is connected with the chassis frame through a hinge, one end of the leveling hydraulic rod is connected with the tire connecting flange sheet, the other end is connected with the chassis frame through a hinge; the attitude sensor is installed at the center of the chassis frame, the attitude sensor is connected with the motion control module, the leveling hydraulic rod is connected with the motion control module, the attitude sensor is used for detecting the attitude angle of the chassis frame and transmitting to the motion control module, and the motion control module controls the leveling hydraulic rod to level the chassis frame according to the attitude angle.

[0029] A control method of the Chinese cabbage row harvester based on machine vision, comprising the following steps:

[0030] The vision detection module collects field images and transmits them to the edge computing module; after the edge computing module processes the images collected by the vision detection module, offset data are obtained and output to the motion control module, the motion control module compares the offset data with a preset threshold value, when the offset data is greater than or equal to the preset displacement threshold value, the motion control module controls the floating alignment mechanism of the alignment mechanism to make the cabbage harvesting and conveying mechanism move along the chassis transversely; when the offset data is less than the preset displacement threshold value, the motion control module controls the active alignment mechanism of the alignment mechanism to change the angle of the two conveying belts of the cabbage harvesting and conveying mechanism for alignment feeding.

[0031] In the above scheme, the displacement threshold value p is calculated according to the following formula:

[0032]

[0033] The mathematical model of the speed matching of the floating alignment mechanism of the alignment mechanism to make the cabbage harvesting and conveying mechanism move along the chassis transversely is as follows:

[0034]

[0035] Wherein, d1 and d3 are output quantities after the edge computing module processes the acquired images, d1 is the longitudinal distance between the two cabbages to be harvested, d3 is the lateral offset distance between the two cabbages, d2 is the distance between the position of the vision detection module and the to-be-harvested cabbages in the driving direction, v1 is the working speed of the harvester, t1 is the arrival time from the position of the vision detection module to the to-be-harvested cabbages, t2 is the time for the edge computing module to accept images, process images and obtain output quantities, and v2 is the best speed to reach the best harvesting position, i.e. the driving speed of the straight-line driving mechanism.

[0036] The speed matching calculation method of the active alignment mechanism of the alignment mechanism to change the angle of the two conveying belts of the cabbage harvesting and conveying mechanism for alignment feeding is as follows:

[0037]

[0038] Wherein, d4 is the transverse distance between the visual detection module and the harvested Chinese cabbage, which is the output of the edge computing module, d5 is the center distance between the two large torque steering engines at the front end of the support of the Chinese cabbage harvesting conveying mechanism, L1 is the center distance between the output shaft of the large torque steering engine and the driven wheel shaft of the conveying belt, w is the average angular velocity of the large torque steering engine during the rowing process, and θ is the included angle between the connecting line between the drive shaft of the large torque steering engine and the driven wheel shaft and the conveying belt support.

[0039] Compared with the prior art, the present application has the following advantages:

[0040] 1. The present application can realize row-by-row harvesting of ridge Chinese cabbage, and through two rowing modes of active rowing and floating rowing of the chassis, the rowing accuracy and efficiency can be improved.

[0041] 2. The automatic leveling chassis of the present application adopts four hydraulic rods for adjustment, can ride the ridge for harvesting, is suitable for planting modes with large ridge distance and multiple rows, and has more practicality. The leveling mechanism is used to keep the harvesting platform stable in real time, and reduce damage during harvesting.

[0042] 3. The visual detection device of the present application can realize rapid measurement of the transverse offset of the Chinese cabbage row through a monocular camera combined with an optimized target detection algorithm, and has stronger robustness than sensors.

[0043] 4. The conveying and collecting device of the present application adopts a two-stage conveying structure, and designs a telescopic conveying belt structure for the floating rowing of the chassis, and designs a pulley tensioning mechanism to ensure smooth conveying and collecting operation during rowing.

[0044] Note that the description of these effects does not hinder the existence of other effects. One embodiment of the present application does not necessarily have all the above-mentioned effects. Effects other than the above-mentioned effects can be clearly seen and extracted from the description, drawings, claims, etc. BRIEF DESCRIPTION OF DRAWINGS

[0045] Figure 1 is a structure schematic diagram of a Chinese cabbage row-by-row harvesting machine based on machine vision according to an embodiment of the present application.

[0046] Figure 2 is a structure schematic diagram of a chassis, a rowing mechanism, a Chinese cabbage harvesting conveying mechanism, and a visual detection module according to an embodiment of the present application.

[0047] Figure 3 is a structure schematic diagram of a floating rowing mechanism according to an embodiment of the present application.

[0048] Figure 4 is a structure schematic diagram of a two-stage conveying and collecting mechanism according to an embodiment of the present application.

[0049] Figure 5 is a structural schematic diagram of a conveying belt fixing frame of an embodiment of the present application.

[0050] Figure 6 is a structural schematic diagram of a leveling mechanism of an embodiment of the present application.

[0051] Figure 7 is a structural schematic diagram of an active alignment mechanism and a visual detection module of an embodiment of the present application.

[0052] Figure 8 is a flowchart of a control method of a Chinese cabbage alignment harvester based on machine vision of an embodiment of the present application.

[0053] Figure 9 is a schematic diagram of alignment operation of an embodiment of the present application.

[0054] Figure 10 is a schematic diagram of a θ angle of an embodiment of the present application.

[0055] In the figure, 1. tractor; 2. two-stage conveying and collecting mechanism; 201. first-stage telescopic transverse conveying mechanism; 202. second-stage vertical conveying belt mechanism; 203. collecting frame; 204. front section mounting frame of conveying belt; 205. rear section mounting frame of conveying belt; 206. conveying belt; 207. conveying belt fixing frame; 208. belt surface tensioning mechanism; 209. conveying belt roller; 3. chassis; 301. chassis frame; 302. three-point suspension connecting frame; 303. connecting rod; 304. wheel; 305. hinge; 306. leveling hydraulic rod; 307. leveling hydraulic rod; 308. attitude sensor; 4. alignment mechanism; 401. floating alignment mechanism; 402. fixed linear bearing set; 403. fixed linear bearing set; 404. linear drive mechanism; 405. active alignment mechanism; 406. large-torque steering engine; 407. steering engine mounting seat; 408. shaft coupling; 409. connecting frame; 5. Chinese cabbage harvesting and conveying mechanism; 501. support; 502. drive motor; 503. conveying belt; 504. driven wheel; 505. driven wheel mounting frame; 6. visual detection module; 601. industrial camera; 602. mounting rod; 603. camera mounting seat; 604. angle adjusting plate; 7. motion control module; 8. edge computing module. DETAILED DESCRIPTION

[0056] Embodiments of the present application are described in detail below with reference to the accompanying drawings, examples of which are shown in the drawings, wherein the same or similar notations represent the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to explain the present application, and cannot be understood as limiting the present application.

[0057] In the description of this invention, it should be understood that the terms "center," "longitudinal," "lateral," "length," "width," "thickness," "front," "rear," "left," "right," "upper," "lower," "axial," "radial," "vertical," "horizontal," "inner," and "outer," etc., indicating orientation or positional relationships based on the orientation or positional relationships shown in the accompanying drawings, are only for the convenience of describing the invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the invention. Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined with "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0058] In this invention, unless otherwise explicitly specified and limited, the terms "installation," "connection," "linking," and "fixing," etc., should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0059] Figure 1 The image shows a preferred embodiment of the machine vision-based cabbage row harvester, which includes a chassis 3, a row-aligning mechanism 4, a cabbage harvesting and conveying mechanism 5, a vision detection module 6, a motion control module 7, and an edge computing module 8.

[0060] The cabbage harvesting and conveying mechanism 5 is used to harvest cabbage and then lift and convey it backward.

[0061] The cabbage harvesting and conveying mechanism 5 is mounted on the chassis 3, and the row alignment mechanism 4 is used to adjust the cabbage harvesting and conveying mechanism 5 to align the rows.

[0062] The visual detection module 6 is installed on the front frame of the cabbage harvesting and conveying mechanism 5. It is used to collect field images and transmit them to the edge computing module 8. The edge computing module 8 is connected to the visual detection module 6 and the motion control module 7 respectively. The motion control module 7 is connected to the row alignment mechanism 4. After processing the images collected by the visual detection module 6, the edge computing module 8 obtains offset data and outputs it to the motion control module 7. The motion control module 7 controls the row alignment mechanism 4 to adjust the cabbage harvesting and conveying mechanism 5 to align the rows.

[0063] likeFigure 2 As shown in the figure, the row aligning mechanism 4 comprises a floating row aligning mechanism 401 and a driving row aligning mechanism 405, the floating row aligning mechanism 401 is installed on the chassis 3 for moving the Chinese cabbage harvesting and conveying mechanism 5 along the chassis 3 transversely to align rows; the driving row aligning mechanism 405 is installed on the Chinese cabbage harvesting and conveying mechanism 5 for changing the angle of the opening angle of the two conveying belts 503 of the Chinese cabbage harvesting and conveying mechanism 5 to align rows for feeding, the conveying belts 503 are driven by the driving motor 502.

[0064] As shown in the figure, the floating row aligning mechanism 401 comprises a fixed linear bearing set 402, a movable linear bearing set 403, a linear driving mechanism 404 and a connecting frame 409; Figure 3

[0065] The chassis 3 comprises a chassis frame 301, a movable frame 309 and a connecting frame 310; the connecting frame 310 is installed above one side of the movable frame 309, and the connecting frame 310 is connected with the Chinese cabbage harvesting and conveying mechanism 5;

[0066] The movable frame 309 is installed on the chassis frame 301, the movable linear bearing set 403 is installed on the movable frame 309, the fixed linear bearing set 402 is installed on one side of the chassis frame 301, the other side of the movable frame 309 is located on the fixed linear bearing set 402, one end of the linear driving mechanism 404 is installed below one side of the movable frame 309 through the connecting frame 409, and the one end of the linear driving mechanism 404 is connected with the movable linear bearing set 403 for driving the movable linear bearing set 403 to drive the movable frame 309 to move transversely along the chassis frame 301 left and right, thereby driving the Chinese cabbage harvesting and conveying mechanism 5 to float and align rows, and the linear driving mechanism 404 is connected with the motion control module 7.

[0067] Preferably, the front part of the chassis frame 301 is provided with a three-point suspension connecting frame 302, which is connected with the three-point suspension pin of the tractor 1 through the three-point suspension connecting frame 302, so as to realize quick disassembly and assembly for use and traction harvesting operation.

[0068] As shown in the figure, two groups of the driving row aligning mechanism 405 are symmetrically arranged on both sides of the front end of the support 501 of the Chinese cabbage harvesting and conveying mechanism 5, each group of the driving row aligning mechanism 405 comprises a large-torque steering engine 406, a steering engine mounting seat 407 and a shaft coupling 408; Figure 7

[0069] ​​The rudder engine mounting seat 407 is mounted on the front end of the support 501 of the Chinese cabbage harvesting conveying mechanism 5, the large-torque rudder engine 406 is mounted on the rudder engine mounting seat 407, the output shaft of the large-torque rudder engine 406 is connected with the driven wheel mounting frame 505 through the shaft coupling 408, the driven wheel mounting frame 505 is provided with the driven wheel 504; the large-torque rudder engine 406 is used for adjusting the angle of the two driven wheel mounting frames 505, so as to change the angle of the two conveying belt included angles of the Chinese cabbage harvesting conveying mechanism 5 and feed in the row; the large-torque rudder engine 406 is connected with the motion control module 7.

[0070] As shown in Figure 2 , Figure 4 and Figure 5 , further comprising two-stage conveying and collecting mechanism 2; the two-stage conveying and collecting mechanism 2 comprises a first-stage telescopic transverse conveying belt mechanism 201, a second-stage vertical conveying belt mechanism 202, a conveying belt fixing frame 207 and a collecting frame 203;

[0071] The first-stage telescopic transverse conveying belt mechanism 201 is located at the end of the Chinese cabbage harvesting conveying mechanism 5, the second-stage vertical conveying belt mechanism 202 is located at the end of the first-stage telescopic transverse conveying belt mechanism 201, the first-stage telescopic transverse conveying belt mechanism 201 and the second-stage vertical conveying belt mechanism 202 are vertically arranged in space, and the collecting frame 203 is located behind the second-stage vertical conveying belt mechanism 202;

[0072] The first-stage telescopic transverse conveying belt mechanism 201 comprises a conveying belt front section mounting frame 204, a conveying belt rear section mounting frame 205, a conveying belt 206, a belt surface tensioning mechanism 208 and a plurality of conveying belt rollers 209;

[0073] The conveying belt front section mounting frame 204 and the conveying belt rear section mounting frame 205 are arranged in parallel and connected through a U-shaped sliding groove; the plurality of conveying belt rollers 209 are mounted on the front section conveying belt roller mounting frame 204 and the rear section conveying belt roller mounting frame 205, the conveying belt 206 is mounted on the conveying belt front section mounting frame 204 and the conveying belt rear section mounting frame 205, and the belt surface tensioning mechanism 208 is mounted on the conveying belt rear section mounting frame 205 and in contact with the conveying belt 206;

[0074] A plurality of conveying belt fixing frames 207 are arranged below the first-stage telescopic transverse conveying mechanism 201 and the second-stage vertical conveying belt mechanism 202, wherein the bottom of the conveying belt front section mounting frame 204 is connected with the connecting rack 310 through the conveying belt fixing frame 207, and the conveying belt rear section mounting frame 205 is connected with the chassis rack 301 through the conveying belt fixing frame 207;

[0075] The connecting rack 310 can drive the conveying belt front section mounting frame 204 to move left and right, and the belt surface tensioning mechanism 208 is used for keeping the conveying belt 206 in a tensioned state.

[0076] The two-stage conveying and collecting mechanism 2 helps to maintain stable transport and loading of the harvested cabbage during the row-to-row process.

[0077] like Figure 7 As shown, the vision inspection module 6 includes an industrial camera 601, a mounting rod 602, a camera mounting base 603, and an angle adjustment plate 604;

[0078] The industrial camera 601 is mounted on a camera mounting base 603. The camera mounting base 603 is connected to the upper end of the mounting rod 602 via an angle adjustment plate 604. The lower end of the mounting rod 602 is connected to the upper part of the bracket 501 of the cabbage harvesting and conveying mechanism 5. The industrial camera 601 is connected to the edge computing module 8.

[0079] Preferably, the visual detection module 6 is located at the center of the front support 501 of the cabbage harvesting and conveying mechanism 5.

[0080] like Figure 7 As shown, one side of the angle adjustment plate 604 is connected to the mounting rod 602 via a rotating shaft, and the other side is provided with an arc-shaped groove, which is connected to the mounting rod 602 via bolts. Changing the position of the bolts in the arc-shaped groove changes the shooting angle of the industrial camera 601.

[0081] like Figure 6 As shown, each of the four corners of the chassis 3 is provided with a leveling mechanism, and each leveling mechanism includes a connecting rod 303, a hinge 305, a leveling hydraulic rod 306, a tire connecting flange 307, and an attitude sensor 308.

[0082] One end of the connecting rod 303 is connected to the tire connecting flange 307, and the other end is connected to the chassis frame 301 via a hinge 305. One end of the leveling hydraulic rod 306 is connected to the tire connecting flange 307, and the other end is connected to the chassis frame 301 via a hinge 305. An attitude sensor 308 is installed at the center of the chassis frame 301 and is connected to the motion control module 7. The attitude sensor 308 detects the attitude angle of the chassis frame 301 and transmits it to the motion control module 7. The motion control module 7 controls the leveling hydraulic rod 306 to level the chassis frame 301 based on the attitude angle, ensuring that the cabbage harvesting conveyor 5 is level with the ground. Wheels 304 are provided at the bottom of the chassis frame 301.

[0083] Preferably, the linear drive mechanism 404 is equipped with a lateral displacement sensor, which is connected to the motion control module 7 and can measure the extension amount of the linear drive mechanism 404 in real time and feed it back to the motion control module 7.

[0084] Preferably, four leveling hydraulic rods 306 are installed with displacement sensors, which are connected with the motion control module 7, and real-time feedback the extension amount of the leveling hydraulic rods 306 to the motion control module 7 during the leveling process.

[0085] As shown in Figure 8 A control method of the Chinese cabbage row-harvesting machine based on machine vision, comprising the following steps:

[0086] The vision detection module 6 collects field images and transmits them to the edge computing module 8; the edge computing module 8 processes the images collected by the vision detection module 6, obtains offset data, and outputs them to the motion control module 7; the motion control module 7 compares the offset data with a preset threshold value; when the offset data is greater than or equal to the preset displacement threshold value, the motion control module 7 controls the floating row- guiding mechanism 401 of the row- guiding mechanism 4 to move the cabbage harvesting and conveying mechanism 5 along the chassis 3 in the transverse direction; when the offset data is less than the preset displacement threshold value, the motion control module 7 controls the active row- guiding mechanism 405 of the row- guiding mechanism 4 to change the angle of the two conveying belts of the cabbage harvesting and conveying mechanism 5 to perform row- guiding feeding, align the front end of the cabbage harvesting and conveying mechanism 5 with the to-be-harvested cabbage, and lift the cabbage to the two-stage conveying and collecting mechanism 2 through the first-stage telescopic transverse conveying mechanism 201 and the second-stage vertical conveying belt mechanism 202.

[0087] As shown in Figure 9 and 10 The displacement threshold value p is calculated according to the following formula:

[0088]

[0089] The mathematical model of the speed matching of the floating row- guiding mechanism 401 of the row- guiding mechanism 4 to move the cabbage harvesting and conveying mechanism 5 along the chassis 3 in the transverse direction is as follows:

[0090]

[0091] Wherein, d1 and d3 are the output values after the edge computing module 8 processes the acquired images, d1 is the longitudinal distance between the two to-be-harvested cabbages, d3 is the transverse offset distance between the two cabbages, d2 is the distance between the position of the vision detection module 6 and the to-be-harvested cabbage in the driving direction, v1 is the working speed of the harvester, t1 is the arrival time from the position of the vision detection module 6 to the to-be-harvested cabbage, t2 is the time for the edge computing module 8 to receive images, process images, and obtain output values, and v2 is the optimal speed to reach the optimal harvesting position, i.e., the driving speed of the straight-line driving mechanism 404.

[0092] The active alignment mechanism 405 of the alignment mechanism 4 changes the angle of the two conveying belt of the Chinese cabbage harvesting conveying mechanism 5 to calculate the speed matching of the alignment feeding as follows:

[0093]

[0094] Wherein, d4 is the transverse distance between the visual detection module 6 and the harvested Chinese cabbage, which is the output quantity obtained by the edge computing module 8, d5 is the center distance of the two large torque steering gears 406 at the front end of the support 501 of the Chinese cabbage harvesting conveying mechanism 5, L1 is the center distance from the output shaft of the large torque steering gear 406 to the wheel shaft of the driven wheel 504 of the conveying belt, w is the average angular velocity of the large torque steering gear 406 in the alignment process, and θ is the angle between the connecting line between the driving shaft of the large torque steering gear 406 and the wheel shaft of the driven wheel 504 and the conveying belt frame.

[0095] In one specific embodiment of the present application, preferably, the edge computing module 8 adopts a target detection algorithm based on deep learning, takes the field image collected by the visual detection module 6 as input, performs a target detection task on the Chinese cabbage in the image through the pre-trained Chinese cabbage recognition model weight, outputs the anchor point and anchor box size of the Chinese cabbage position in a regression manner, takes the anchor box center point as the representation feature of the crop row, and then performs crop row line fitting through clustering and straight line fitting algorithm, to take the slope and intercept of the crop row line, the longitudinal distance d1 between the two harvested Chinese cabbages, the transverse offset distance d3 of the two Chinese cabbages, the transverse distance d4 between the visual detection module 6 and the harvested Chinese cabbage as output quantities, and to calculate the transverse offset amount from the camera picture vertical reference line through tangent calculation of the slope and intercept of the crop row line.

[0096] In one specific embodiment of the present application, preferably, the Chinese cabbage alignment harvesting machine based on machine vision keeps straight at the working speed, and keeps the right wheel group of the chassis 3 on the ridge and preliminarily aligned with the harvested Chinese cabbage row;

[0097] The visual detection module 6 collects field images and transmits them to the edge computing module 8; the edge computing module 8 processes the images collected by the visual detection module 6 to obtain offset data and output them to the motion control module 7;

[0098] The attitude sensor 308 detects the attitude angle of the chassis frame 301 and transmits it to the motion control module 7, which controls the leveling hydraulic rod 306 to level the chassis frame 301 according to the attitude angle, and the initial position is that the right wheel group is on the ridge and the chassis 3 is inclined to the left, at this time the left two leveling hydraulic rods 306 are elongated and the right two leveling hydraulic rods 306 are contracted, until leveling is achieved, and the stop command is received, completing the leveling action of the chassis 3;

[0099] The motion control module 7 compares the offset data with a preset threshold value, when the offset data is greater than or equal to the preset displacement threshold value, the motion control module 7 controls the floating alignment mechanism 401 of the alignment mechanism 4 to make the Chinese cabbage harvesting and conveying mechanism 5 move transversely along the chassis 3; when the offset data is less than the preset displacement threshold value, the motion control module 7 controls the active alignment mechanism 405 of the alignment mechanism 4 to change the angle of the two conveying belt angles of the Chinese cabbage harvesting and conveying mechanism 5 to perform alignment feeding, complete the separation of the roots of Chinese cabbage and the land, complete the pulling action, and lift the pulled Chinese cabbage, the Chinese cabbage is pulled up and lifted to the two-stage conveying and collecting mechanism 2, and is conveyed through the first-stage telescopic transverse conveying mechanism 201 and the second-stage vertical conveying belt mechanism 202, and the Chinese cabbage reaches the collecting frame 203.

[0100] The present application solves the problem of high damage rate of Chinese cabbage in the harvesting process caused by inaccurate alignment and difficult leveling in the prior art. The alignment mechanism 4 has two alignment modes of the floating alignment mechanism 401 and the active alignment mechanism 405, which can coordinate the two modes to achieve more precise and rapid alignment action and alignment range.

[0101] The present application measures the posture through the posture sensor 308 installed at the center position of the chassis 3, and measures the speed through the GPS positioning system; and inputs the obtained measurement value and offset to the motion control module 7, and outputs instructions to control the motion speed and motion direction of the alignment straight line driving mechanism 404 after planning, when the offset data is less than the preset displacement threshold value, the motion control module 7 controls the large torque rudder 406 of the active alignment mechanism 405 of the alignment mechanism 4 to rotate synchronously, changes the angle of the two conveying belt angles of the Chinese cabbage harvesting and conveying mechanism 5 to assist in alignment adjustment. When the offset data is greater than or equal to the preset displacement threshold value, the motion control module 7 controls the straight line driving mechanism 404 of the floating alignment mechanism 401 of the alignment mechanism 4 to make the Chinese cabbage harvesting and conveying mechanism 5 move transversely along the chassis 3, and actively adjust the alignment.

[0102] The present application is beneficial to keep the Chinese cabbage harvesting and conveying mechanism 5 in the best pulling position and feeding position, and finally realizes stable and continuous alignment profile harvesting of large Chinese cabbage. The present application has the advantages of automatic leveling function, efficient and accurate alignment harvesting and strong adaptability, and is suitable for harvesting needs of different varieties and types of large Chinese cabbage, which can further improve the degree of automation and efficiency of harvesting, and effectively reduce the harvesting loss.

[0103] The present application uses machine vision combined with deep learning to complete the recognition and crop row fitting of large Chinese cabbage, has the characteristics of strong robustness and high precision, has the advantages of automatic leveling function, efficient and accurate alignment harvesting and strong adaptability.

[0104] It should be understood that although the present specification is described in terms of various embodiments, each of which describes only one implementation, the specification is intended to cover all possible combinations for each independent hardware or software feature described (and / or ranges for values of size or length, which are independent of each other). For example, in the case of an embodiment describing a first feature and a second feature, where the possible combinations include the combination of the first feature with the second feature, the combination of the first feature without the second feature, the combination of the second feature without the first feature, and the combination of the first feature and the second feature, the specification is intended to cover all these cases. Also, the description is intended to cover all possible combinations of features described in the specification, including the features described in the claims, whether or not the features are described in the same claim. Furthermore, the description is intended to cover separate implementations of the features described in the specification, including the features described in the claims, whether or not the features are described in the same claim.

Claims

1. A machine vision-based row harvester for Chinese cabbage, characterized in that, It includes a chassis (3), a row-aligning mechanism (4), a cabbage harvesting and conveying mechanism (5), a vision detection module (6), a motion control module (7), and an edge computing module (8); The cabbage harvesting and conveying mechanism (5) is used to harvest cabbage and convey it backward; The cabbage harvesting and conveying mechanism (5) is installed on the chassis (3), and the row alignment mechanism (4) is used to adjust the cabbage harvesting and conveying mechanism (5) to align the rows. The visual detection module (6) is installed on the front frame of the cabbage harvesting and conveying mechanism (5) to collect field images and transmit them to the edge computing module (8). The edge computing module (8) is connected to the visual detection module (6) and the motion control module (7) respectively. The motion control module (7) is connected to the row alignment mechanism (4). After the edge computing module (8) processes the images collected by the visual detection module (6), it obtains offset data and outputs it to the motion control module (7). The motion control module (7) controls the row alignment mechanism (4) to adjust the cabbage harvesting and conveying mechanism (5) to perform row alignment. The row alignment mechanism (4) includes a floating row alignment mechanism (401) and an active row alignment mechanism (405). The floating row alignment mechanism (401) is mounted on the chassis (3) and is used to make the cabbage harvesting conveyor (5) move laterally along the chassis (3) to align rows. The active row alignment mechanism (405) is mounted on the cabbage harvesting conveyor (5) and is used to change the angle between the two conveyor belts of the cabbage harvesting conveyor (5) to feed the cabbage into the rows. The two sets of active alignment mechanisms (405) are symmetrically arranged on both sides of the front end of the bracket (501) of the cabbage harvesting and conveying mechanism (5). Each set of active alignment mechanisms (405) includes a high-torque servo motor (406), a servo motor mounting base (407), and a coupling (408). The servo mounting base (407) is installed on the front end of the bracket (501) of the cabbage harvesting conveyor mechanism (5). The high-torque servo (406) is installed on the servo mounting base (407). The output shaft of the high-torque servo (406) is connected to the driven wheel mounting bracket (505) through the coupling (408). The driven wheel mounting bracket (505) is provided with a driven wheel (504). The high-torque servo (406) is used to adjust the angle of the two driven wheel mounting brackets (505), thereby changing the angle of the two conveyor belts (503) of the cabbage harvesting conveyor mechanism (5) for row feeding. The high-torque servo (406) is connected to the motion control module (7).

2. The machine vision-based cabbage row harvester according to claim 1, characterized in that, The floating parallel mechanism (401) includes a fixed linear bearing assembly (402), a moving linear bearing assembly (403), a linear drive mechanism (404), and a connecting frame (409). The chassis (3) includes a chassis frame (301), a movable frame (309), and a connecting frame (310); the connecting frame (310) is installed above one side of the movable frame (309), and the connecting frame (310) is connected to the cabbage harvesting and conveying mechanism (5); The movable frame (309) is installed on the chassis frame (301), the movable linear bearing assembly (403) is installed on the movable frame (309), the fixed linear bearing assembly (402) is installed on one side of the chassis frame (301), and the other side of the movable frame (309) is located on the fixed linear bearing assembly (402). One end of the linear drive mechanism (404) is installed below one side of the movable frame (309) through the connecting frame (409). One end of the linear drive mechanism (404) is connected to the movable linear bearing assembly (403) and is used to drive the movable linear bearing assembly (403) to drive the movable frame (309) to move laterally along the chassis frame (301) to the left and right, thereby driving the cabbage harvesting and conveying mechanism (5) to float and align. The linear drive mechanism (404) is connected to the motion control module (7).

3. The machine vision-based cabbage row harvester according to claim 2, characterized in that, It also includes a two-stage conveying and collecting mechanism (2); the two-stage conveying and collecting mechanism (2) includes a first-stage retractable horizontal conveying mechanism (201), a second-stage vertical conveyor belt mechanism (202), a conveyor belt fixing frame (207), and a collecting frame (203); The first-level retractable horizontal conveyor mechanism (201) is located at the end of the cabbage harvesting conveyor mechanism (5), and the second-level vertical conveyor belt mechanism (202) is located at the end of the first-level retractable horizontal conveyor mechanism (201). The first-level retractable horizontal conveyor mechanism (201) and the second-level vertical conveyor belt mechanism (202) are arranged vertically in space, and the collection box (203) is located behind the second-level vertical conveyor belt mechanism (202). The first-stage retractable transverse conveying mechanism (201) includes a front section mounting frame (204) of the conveyor belt, a rear section mounting frame (205) of the conveyor belt, a conveyor belt (206), a belt tensioning mechanism (208) and multiple conveyor belt rollers (209). The front section mounting frame (204) and the rear section mounting frame (205) of the conveyor belt are arranged in parallel and slidably connected by a U-shaped chute; multiple conveyor belt rollers (209) are installed on the front section mounting frame (204) and the rear section mounting frame (205) of the conveyor belt, the conveyor belt (206) is installed on the front section mounting frame (204) and the rear section mounting frame (205) of the conveyor belt, and the belt tensioning mechanism (208) is installed on the rear section mounting frame (205) of the conveyor belt and is in contact with the conveyor belt (206); Multiple conveyor belt fixing frames (207) are provided below the first-stage retractable horizontal conveying mechanism (201) and the second-stage vertical conveyor belt mechanism (202). The bottom of the front section mounting frame (204) of the conveyor belt is connected to the connecting frame (310) through the conveyor belt fixing frame (207), and the rear section mounting frame (205) of the conveyor belt is connected to the chassis frame (301) through the conveyor belt fixing frame (207). The connecting frame (310) can drive the front section mounting frame (204) of the conveyor belt to move left and right, and the belt tensioning mechanism (208) is used to keep the conveyor belt (206) in a tensioned state.

4. The machine vision-based cabbage row harvester according to claim 2, characterized in that, The vision inspection module (6) includes an industrial camera (601), a mounting rod (602), a camera mounting base (603), and an angle adjustment plate (604). The industrial camera (601) is mounted on a camera mounting base (603). The camera mounting base (603) is connected to the upper end of the mounting rod (602) via an angle adjustment plate (604). The lower end of the mounting rod (602) is connected to the upper part of the bracket (501) of the cabbage harvesting and conveying mechanism (5). The industrial camera (601) is connected to the edge computing module (8).

5. The machine vision-based cabbage row harvester according to claim 4, characterized in that, One side of the angle adjustment plate (604) is connected to the mounting rod (602) via a rotating shaft, and the other side is provided with an arc-shaped groove, which is connected to the mounting rod (602) via bolts. Changing the position of the bolts in the arc-shaped groove changes the shooting angle of the industrial camera (601).

6. The machine vision-based cabbage row harvester according to claim 2, characterized in that, The chassis (3) is provided with a leveling mechanism at each of its four corners. Each leveling mechanism includes a connecting rod (303), a hinge (305), a leveling hydraulic rod (306), a tire connecting flange (307), and an attitude sensor (308). One end of the connecting rod (303) is connected to the tire connecting flange (307), and the other end is connected to the chassis frame (301) via a hinge (305). One end of the leveling hydraulic rod (306) is connected to the tire connecting flange (307), and the other end is connected to the chassis frame (301) via a hinge (305). The attitude sensor (308) is installed at the center of the chassis frame (301). The attitude sensor (308) is connected to the motion control module (7). The leveling hydraulic rod (306) is connected to the motion control module (7). The attitude sensor (308) is used to detect the attitude angle of the chassis frame (301) and transmit it to the motion control module (7). The motion control module (7) controls the leveling hydraulic rod (306) to level the chassis frame (301) according to the attitude angle.

7. A control method for a cabbage row harvester based on machine vision according to any one of claims 2-6, characterized in that, Includes the following steps: The visual detection module (6) collects field images and transmits them to the edge computing module (8). The edge computing module (8) processes the images collected by the visual detection module (6), obtains offset data, and outputs it to the motion control module (7). The motion control module (7) compares the obtained offset data with a preset threshold. When the offset data is greater than or equal to the preset displacement threshold, the motion control module (7) controls the floating row-aligning mechanism (401) of the row-aligning mechanism (4) to make the cabbage harvesting conveyor (5) move laterally along the chassis (3). When the offset data is less than the preset displacement threshold, the motion control module (7) controls the active row-aligning mechanism (405) of the row-aligning mechanism (4) to change the angle between the two conveyor belts of the cabbage harvesting conveyor (5) for row-aligning feeding. The displacement threshold p is calculated according to the following formula: ； The floating row-aligning mechanism (401) of the row-aligning mechanism (4) enables the cabbage harvesting and conveying mechanism (5) to move laterally along the chassis (3) in a mathematical model that matches the speed of the row alignment. ； Wherein, d1 and d3 are the output values ​​of the edge computing module (8) after processing the acquired image. The longitudinal distance between two cabbages awaiting harvest. d1 is the lateral offset distance between the two cabbages, d2 is the distance between the position of the vision detection module (6) and the cabbage to be harvested in the direction of travel, v1 is the operating speed of the harvester, t1 is the arrival time from the position of the vision detection module (6) to the cabbage to be harvested, t2 is the time from the edge computing module (8) receiving the image, processing the image and obtaining the output, and v2 is the theoretical optimal speed to reach the optimal harvest position, i.e. the driving speed of the linear drive mechanism (404). The active alignment mechanism (405) of the alignment mechanism (4) changes the angle between the two conveyor belts of the cabbage harvesting and conveying mechanism (5) to calculate the speed matching for row feeding as follows: ； Wherein, d4 is the lateral distance between the visual detection module (6) and the cabbage to be harvested, and the output obtained by the edge computing module (8); d5 is the center distance between the two large torque servo motors (406) at the front end of the bracket (501) of the cabbage harvesting and conveying mechanism (5); L1 is the center distance from the output shaft of the large torque servo motor (406) to the axle of the driven wheel (504); and w is the average angular velocity of the large torque servo motor (406) during the movement process. The angle between the line connecting the drive shaft of the high-torque servo motor (406) and the axle of the driven wheel (504) and the conveyor belt frame.

Images