An automatic waterjet path planning method and system suitable for vegetable processing
By performing image recognition and processing on vegetable slices, a waterjet path is generated, which solves the problem of excessively long path planning time in vegetable processing in existing technologies. It realizes efficient and low-resource waterjet path planning, meeting the high-efficiency requirements of food processing.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- WUHAN SHIP COMM RES INST (NO 722 RES INST OF CHINA STATE SHIPBUILDING CORP)
- Filing Date
- 2024-10-28
- Publication Date
- 2026-07-31
AI Technical Summary
Existing water jet path planning algorithms suffer from modeling difficulties and excessive time consumption in vegetable processing, failing to meet the requirements for high efficiency.
By acquiring and analyzing images of vegetable slices, identifying vegetable slices and woody areas, performing dilation processing to subtract the woody areas, extracting discrete nodes and fitting to reduce the number of nodes, generating waterjet paths, adding decision judgment functions to handle abnormal situations, and planning waterjet paths.
It achieves fast, low-computational-resource-demand waterjet path planning, meets the high-efficiency requirements of food processing production lines, can handle complex and ever-changing working conditions, and avoids mutual interference between waterjet streams, ensuring the orderly operation of the production line.
Smart Images
Figure CN119443446B_ABST
Abstract
Description
Technical Field
[0001] This application belongs to the field of food processing technology, and more specifically, relates to an automatic water jet path planning method and system suitable for vegetable processing. Background Technology
[0002] Harvested vegetables consist of inedible woody parts and edible fleshy parts. Further processing requires removing the inedible woody parts. Manual removal is inefficient; therefore, using automated water jets for woody removal is a key area for upgrading the vegetable processing industry.
[0003] Path planning in waterjet cutting is one of the key challenges in technological upgrades. Currently, methods such as ant colony optimization, simulated annealing, and A* algorithm are commonly used to transform the cutting path problem into a Traveling Salesman Problem (TSP) model. This model extracts the start, end, and intermediate nodes along the cutting line and then searches for the optimal cutting sequence based on the shortest path principle. However, in the food processing industry, due to the vast quantity and varied, irregular shapes of the vegetables being processed, existing path planning algorithms face difficulties in modeling and excessively long planning times when dealing with large-scale vegetable processing. This fails to meet the high-efficiency requirements of the vegetable processing industry. Summary of the Invention
[0004] In view of the above-mentioned defects or improvement needs of the existing technology, this application provides an automatic water jet path planning method and system suitable for vegetable processing, which aims to solve the technical problem that the existing water jet path planning method cannot meet the high efficiency requirements of the vegetable processing industry.
[0005] To achieve the above objectives, in a first aspect, this application provides an automatic waterjet path planning method suitable for vegetable processing, comprising:
[0006] S1. Acquire and analyze images of vegetable slices, and identify the vegetable slice area and woody area of each vegetable slice from the image;
[0007] S2. In each vegetable slice, the vegetable slice area and the woody area are expanded, and the meaty area is obtained by subtracting the woody area from the vegetable slice area.
[0008] S3. Extract discrete nodes from the contour line of the meaty area, reduce the number of discrete nodes by fitting, and record the fitted discrete nodes in clockwise or counterclockwise order.
[0009] S4. Generate the water jet path for each vegetable slice according to the record order of the discrete nodes.
[0010] Preferably, step S1 further includes the following sub-steps:
[0011] S11. Use threshold segmentation to remove noise from the image;
[0012] S12. Remove the vegetable slices in the image whose area is smaller than the first threshold.
[0013] S13. Remove woody regions in the image whose area is smaller than the second threshold.
[0014] Preferably, step S1 further includes the following sub-steps:
[0015] S14. Calculate the area ratio of the sum of the woody areas and the sum of the vegetable areas in each vegetable slice. If the area ratio is greater than the third threshold, the vegetable slice with the area ratio is marked as a discarded vegetable slice, the water jet path is planned as the grid path on the discarded vegetable slice, and then the water jet path planning of the discarded vegetable slice is stopped.
[0016] Preferably, step S1 further includes the following sub-steps:
[0017] S15. Determine whether the sum of the areas of the woody regions in each vegetable slice is less than the fourth threshold. If so, mark the vegetable slice containing the woody region as a high-quality vegetable slice and stop the water jet path planning for the high-quality vegetable slice.
[0018] Preferably, step S2 further includes the following sub-steps:
[0019] S21. Determine whether there is a meaty area in each vegetable slice with an area smaller than the fifth threshold. If so, remove the meaty area.
[0020] Preferably, in step S3, the number of discrete nodes is reduced by fitting, specifically by connecting all adjacent discrete nodes, judging each discrete node, and if the included angle of the discrete node as a vertex is less than a threshold, then the discrete node is removed.
[0021] Preferably, step S3 further includes the following sub-steps:
[0022] S31. Find multiple discrete nodes located within the vegetable slice area from the recorded discrete nodes.
[0023] S32. Among the plurality of discrete nodes, if the distance d between adjacent discrete nodes A and B is greater than the sixth threshold TH6, then discrete nodes C and D are added sequentially between discrete nodes A and B.
[0024] The position coordinates of discrete node C are (xc, yc), xc = xa + (xb - xa) × TH6 / d, yc = ya + (yb - ya) × TH6 / d, (xa, ya) are the position coordinates of discrete node A, and (xb, yb) are the position coordinates of discrete node B;
[0025] The position of discrete node D is the closest position to discrete node C on the outline of the vegetable slice region it belongs to.
[0026] Preferably, the automatic water jet path planning method further includes the following steps:
[0027] S5, each water jet cuts multiple vegetable slices within its moving range in the same rotation sequence.
[0028] Preferably, step S5 includes the following sub-steps:
[0029] S51. Divide the water jet movement range into an upper half and a lower half;
[0030] S52. If the water jet cuts all vegetable slices within the moving range in a clockwise rotation order, then the discrete points of each vegetable slice in the upper half of the region are recorded in a counterclockwise order, and the discrete points of each vegetable slice in the lower half of the region are recorded in a clockwise order.
[0031] S53. If the water jet cuts all vegetable slices within the moving range in a counter-clockwise rotation order, then the discrete points of each vegetable slice in the upper half of the region are recorded in a clockwise order, and the discrete points of each vegetable slice in the lower half of the region are recorded in a counter-clockwise order.
[0032] Secondly, this application provides an automatic water jet path planning system suitable for vegetable processing, comprising:
[0033] The image acquisition and analysis module is used to acquire and analyze images of vegetable slices, and to identify the vegetable slice area and the woody area of each vegetable slice from the image;
[0034] The meat region calculation module is used to expand the vegetable slice area and the woody area in each vegetable slice, and then subtract the woody area from the vegetable slice area to obtain the meat region;
[0035] The contour fitting module is used to extract discrete nodes from the contour line of the meat area, reduce the number of discrete nodes by fitting, and record the fitted discrete nodes in clockwise or counterclockwise order.
[0036] The path generation module is used to generate the water jet path for each vegetable slice according to the recording order of discrete nodes.
[0037] Thirdly, this application provides an electronic device, comprising: a memory for storing a program; and a processor for executing the program stored in the memory, wherein when the program stored in the memory is executed, the processor is configured to execute the method described in the first aspect or any possible implementation thereof.
[0038] Fourthly, this application provides a computer-readable storage medium storing a computer program that, when run on a processor, causes the processor to perform the method described in the first aspect or any possible implementation thereof.
[0039] Fifthly, this application provides a computer program product that, when run on a processor, causes the processor to perform the method described in the first aspect or any possible implementation thereof.
[0040] Overall, the technical solutions conceived in this application have the following beneficial effects compared with the prior art:
[0041] (1) The technology of this application is based on the image recognition of vegetables to plan the water jet path, which can greatly reduce the computational requirements, plan quickly, have low requirements for computing hardware resources, and meet the working efficiency requirements of food processing production lines.
[0042] (2) This application incorporates numerous decision-making functions to handle exceptional situations and add special features, such as: identifying and shredding waste vegetable slices using water jet path planning; identifying and skipping high-quality vegetable slices using water jet path planning; adding interruption nodes when the water jet cutting line is too long; and grouping the water jet paths of multiple vegetable slices within a certain range together, etc. This allows the system to meet complex and varied working conditions, and enables the convenient and quick addition or deletion of independent functional modules in the algorithm according to production line requirements.
[0043] (3) The technology of this application incorporates the mechanical limitations of water jets into the water jet path planning, avoiding mutual interference between water jets during the operation of multiple water jets and ensuring the orderly operation of the production line. Attached Figure Description
[0044] Figure 1 This is a flowchart of the automatic waterjet path planning method of this application.
[0045] Figure 2 This is an overall flowchart of an automatic water jet path planning method for vegetable processing provided in an embodiment of this application.
[0046] Figure 3 The image of the sliced food obtained by the front-end camera device is provided in the embodiments of this application.
[0047] Figure 4 It is a ternary image of the vegetable slice image provided in the embodiments of this application.
[0048] Figure 5 This is a vegetable slice image after filtering and filling preprocessing provided in the embodiments of this application.
[0049] Figure 6 This is the old ridge pattern after filtering and filling preprocessing provided in the embodiments of this application.
[0050] Figure 7 The image provided in this application is a meat texture image obtained by subtracting the tough tendon image from the vegetable slice image.
[0051] Figure 8 This is the planned waterjet path provided in the embodiments of this application.
[0052] Figure 9 This is a framework diagram of the waterjet path automatic planning system of this application. Detailed Implementation
[0053] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.
[0054] The terms "first" and "second," etc., used in the specification and claims herein are used to distinguish different objects, not to describe a specific order of the objects. For example, "first threshold" and "second threshold," etc., are used to distinguish different thresholds, not to describe a specific order of the thresholds.
[0055] In the embodiments of this application, the terms "exemplary" or "for example" are used to indicate that something is an example, illustration, or description. Any embodiment or design that is described as "exemplary" or "for example" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or design. Specifically, the use of the terms "exemplary" or "for example" is intended to present the relevant concepts in a specific manner.
[0056] In the description of the embodiments of this application, unless otherwise stated, "multiple" means two or more, for example, multiple water jets means two or more water jets, multiple vegetable slices means two or more vegetable slices, etc.
[0057] like Figure 1 As shown, the technical solution of this application includes the following steps:
[0058] S1. Acquire and analyze images of vegetable slices, and identify the vegetable slice area and woody area of each vegetable slice from the image;
[0059] S2. In each vegetable slice, the vegetable slice area and the woody area are expanded, and the meaty area is obtained by subtracting the woody area from the vegetable slice area.
[0060] S3. Extract discrete nodes from the contour line of the meaty area, reduce the number of discrete nodes by fitting, and record the fitted discrete nodes in clockwise or counterclockwise order.
[0061] S4. Generate the water jet path for each vegetable slice according to the record order of the discrete nodes.
[0062] Next, the technical solution of this application will be further described with reference to the embodiments.
[0063] like Figure 2 As shown in the figure, this application provides an automatic water jet path planning method suitable for vegetable processing, wherein the vegetable processing involves processing pickled vegetable slices to remove the tough fibers from the pickled vegetable slices, specifically including the following steps:
[0064] Step 1: Acquire images of pickled vegetable slices, analyze the graphic of each pickled vegetable slice in the image, and divide the graphic area into the pickled vegetable slice area, the pickled vegetable woody area, and the background area.
[0065] This includes acquiring images of the production line through image acquisition devices, such as digital cameras. Figure 3 The physical image shown is processed by the old vein recognition algorithm to obtain a raw format image, which is then converted to a JPG format image and used as input for water jet path planning. Figure 4 As shown, black represents the background area, white represents the sinewy area, and gray represents the fleshy area.
[0066] Step 2: Preprocess the parsed image.
[0067] Specifically, step 2 includes the following steps:
[0068] Step 2.1: Using the cv2 function library based on python-opencv, use the threshold segmentation function cv2.threshold() to filter out dark noise in the JPG format input image.
[0069] Step 2.2: Use the threshold segmentation function `cv2.threshold()`, and the `cv2.findContours()` function to obtain the outer contour of the pickled vegetable slice area pixel block and save it to the `pickle[]` array. Call the `cv2.contourArea()` function to traverse and search for vegetable slice areas in the `pickle[]` array with an area smaller than a certain number of pixels, and use `cv2.fillPoly()` to fill these areas with the background color, such as... Figure 5 As shown; this step is to remove the parts of the vegetable slices that are too small.
[0070] Step 2.3: Use the threshold segmentation function `cv2.threshold()`, and the `cv2.findContours()` function to obtain the outer contour of the ridge region pixel blocks and save it to the `stem[]` array. Call the `cv2.contourArea()` function to traverse and search for ridge regions with an area less than 50 pixels in the `stem[]` array, and use `cv2.fillPoly()` to fill these regions with the background color, such as... Figure 6 As shown; this step involves removing the smaller portions of the wooden area.
[0071] Step 3: Establish a Cartesian coordinate system with the image center as the origin, calculate the quadrant position of the vegetable slice, and select the cutting order of the target vegetable slice according to the quadrant.
[0072] Specifically, according to the production line process design, the pickling method is to distribute four vegetable slices at a time in the four corners of the image. The cv2.moments() function is used to obtain the centroid position of each vegetable slice element group in the pickle[] array, determine the pixel to which it belongs, and record the corresponding vegetable slice array in pickle_order[p1,p2,p3,p4] in the order of quadrants one, two, three, and four.
[0073] Since there are two working conditions in the production process, clockwise cutting and counterclockwise cutting, when cutting clockwise, the cutting target is selected in the order of p2, p1, p4, p3; when cutting counterclockwise, the cutting target is selected in the order of p1, p2, p3, p4.
[0074] Step 4: Perform image dilation on the wood area, and then subtract the area overlapping with the wood from the vegetable area to obtain the pickled vegetable meat area that needs to be retained. The boundary between the meat area and the wood area is the water jet cutting line.
[0075] Step 4.1: Use the cv2.dilate() function to obtain the dilate_stem region of the old fibrous tissue expansion.
[0076] Step 4.2: Use the cv2.dilate() function to obtain the dilate_pickle region of the vegetable slice.
[0077] Step 4.3: Subtract the expanded area of the tough tendons from the expanded area of the pickled vegetable slices to obtain the meat area to be retained: pi_st = dilate_pickle - dilate_stem.
[0078] Step 4.4: Use the `cv2.findContours()` function to obtain the outer contour of the meat region pixel block and save it to the `pi_st[]` array. Call the `cv2.contourArea()` function to traverse and search for vegetable slice areas in the `pi_st[]` array with an area smaller than a certain number of pixels, and use `cv2.fillPoly()` to fill these areas with the background color. The remaining meat region after processing is as follows: Figure 7 As shown. The purpose of this step is to remove the parts of the meat that are too small.
[0079] Step 4.5: Use the cv2.moments() function to obtain the centroid position of each remaining fleshy region element group in the pi_st[] array, determine the pixel to which it belongs, and record the corresponding array to pi_st_order[s1,s2,s3,s4] in the order of quadrants one, two, three, and four.
[0080] Step 5: Extract the discrete nodes of the outline of the pickled vegetable meat region. Based on the characteristics such as the node spacing and the variation of the node angle, reduce the number of nodes of a single piece of meat outline by fitting, and record the node coordinates by arranging them clockwise or counterclockwise according to the outline.
[0081] Specifically, step 5 includes the following steps:
[0082] Step 5.1: Use the cv2.approxPolyDP() function to calculate the fitted contour nodes of the meat region contour in each quadrant of the pi_st_order[] array, and save them in quadrant order to approx_order[a1,a2,a3,a4].
[0083] Step 5.2: The default arrangement order of the fitted nodes is counterclockwise around the vegetable slice. When cutting the vegetable slice according to the "first, second, third, fourth" quadrants, the nodes recorded in a1 and a2 are reversed and re-recorded as b1 and b2 respectively; when cutting the vegetable slice according to the "second, first, fourth, third" quadrants, the nodes recorded in a3 and a4 are reversed and re-recorded as b3 and b4 respectively.
[0084] Step 5.3: Record all cutting nodes in sequence. The node array for the cutting order of quadrants "I, II, III, IV" is recorded as b1→b2→a3→a4, and the node array for the cutting order of quadrants "II, I, IV, III" is recorded as a2→a1→b4→b3.
[0085] Step 6: Add special function modules according to process requirements.
[0086] Specifically, in the current invention example, two special functional modules are added according to process requirements.
[0087] The first functional module is the high-quality vegetable slice bypass function. When the vegetable slice does not contain tough fibers that need to be cut, the path in this quadrant will bypass the vegetable slice in a straight line, such as... Figure 8 The path is shown in the upper right corner.
[0088] The second functional module is the "old tendon breaking" function, which involves inserting break nodes that meet the requirements along the waterjet cutting lines in each of the four quadrants. This functional module includes the following steps:
[0089] S31. Find multiple discrete nodes located within the vegetable slice area from the recorded discrete nodes.
[0090] S32. Among the plurality of discrete nodes, if the distance d between adjacent discrete nodes A and B is greater than the sixth threshold TH6, then discrete nodes C and D are added sequentially between discrete nodes A and B.
[0091] The position coordinates of discrete node C are (xc, yc), xc = xa + (xb - xa) × TH6 / d, yc = ya + (yb - ya) × TH6 / d, (xa, ya) are the position coordinates of discrete node A, and (xb, yb) are the position coordinates of discrete node B;
[0092] The position of discrete node D is the closest position to discrete node C on the outline of the vegetable slice region it belongs to.
[0093] Step 7 generates a planar cutting path based on the cutting order of the vegetable slices and the corresponding output node coordinates. Specifically, the node coordinates in the arrays b1→b2→a3→a4 or a2→a1→b4→b3 after inserting the break nodes are sequentially integrated into the out[] array and converted into machining G-code to complete the planar cutting path planning and output, as shown below. Figure 8 As shown, the line segments around the vegetable slices represent the planned path.
[0094] This application also implements an automatic waterjet path planning system suitable for vegetable processing. For example... Figure 9 As shown, the system includes an image acquisition and analysis module, a meat region calculation module, a contour fitting module, and a path generation module. It should be understood that the above system is used to execute the methods described in the above embodiments. The implementation principles and technical effects of the corresponding modules in the system are similar to those described in the above methods. The working process of this system can be referred to the corresponding process in the above methods, and will not be repeated here.
[0095] Based on the methods in the above embodiments, this application provides an electronic device that may include a processor, a communications interface, a memory, and a communication bus, wherein the processor, communications interface, and memory communicate with each other via the communication bus. The processor may invoke logical instructions in the memory to execute the methods in the above embodiments.
[0096] Furthermore, the logical instructions in the aforementioned memory can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application.
[0097] Based on the methods in the above embodiments, this application provides a computer-readable storage medium storing a computer program that, when run on a processor, causes the processor to execute the methods in the above embodiments.
[0098] Based on the methods in the above embodiments, this application provides a computer program product that, when run on a processor, causes the processor to execute the methods in the above embodiments.
[0099] It is understood that the processor in the embodiments of this application may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. A general-purpose processor may be a microprocessor or any conventional processor.
[0100] The method steps in the embodiments of this application can be implemented in hardware or by a processor executing software instructions. The software instructions can consist of corresponding software modules, which can be stored in random access memory (RAM), flash memory, read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), registers, hard disks, portable hard disks, CD-ROMs, or any other form of storage medium known in the art. An exemplary storage medium is coupled to the processor, enabling the processor to read information from and write information to the storage medium. Of course, the storage medium can also be a component of the processor. The processor and the storage medium can reside in an ASIC.
[0101] In the above embodiments, implementation can be achieved entirely or partially through software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented entirely or partially in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a storage medium or transmitted through the storage medium. The computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid-state disk (SSD)).
[0102] It is understood that the various numerical designations used in the embodiments of this application are merely for descriptive convenience and are not intended to limit the scope of the embodiments of this application.
[0103] The above content is readily understood by those skilled in the art. The above description is merely a preferred embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this application should be included within the protection scope of this application.
Claims
1. A water jet path automatic planning method suitable for vegetable processing, characterized in that, include: S1. Acquire and analyze images of vegetable slices, and identify the vegetable slice area and woody area of each vegetable slice from the image; S2. In each vegetable slice, the vegetable slice area and the woody area are expanded, and the meaty area is obtained by subtracting the woody area from the vegetable slice area. S3. Extract discrete nodes from the contour line of the meaty area, reduce the number of discrete nodes by fitting, and record the fitted discrete nodes in clockwise or counterclockwise order. S4. Generate the water jet path for each vegetable slice according to the record order of the discrete nodes; Step S3 also includes the following step of breaking the old tendon: S31. Find multiple discrete nodes located within the vegetable slice area from the recorded discrete nodes. S32. Among the plurality of discrete nodes, if the distance d between adjacent discrete nodes A and B is greater than the sixth threshold TH6, then discrete nodes C and D are added sequentially between discrete nodes A and B. The position coordinates of the discrete node C are , , , are the position coordinates of the discrete node A, are the position coordinates of the discrete node B; The position of discrete node D is the closest position to discrete node C on the outline of the vegetable slice region it belongs to.
2. The water jet path automatic planning method of claim 1, wherein, Step S1 further includes the following sub-steps: S11. Use threshold segmentation to remove noise from the image; S12. Remove the vegetable slices in the image whose area is smaller than the first threshold. S13. Remove woody regions in the image whose area is smaller than the second threshold.
3. The water jet path automatic planning method of claim 1, wherein, Step S1 further includes the following sub-steps: S14. Calculate the area ratio of the sum of the woody areas and the sum of the vegetable areas in each vegetable slice. If the area ratio is greater than the third threshold, the vegetable slice with the area ratio is marked as a discarded vegetable slice, the water jet path is planned as the grid path on the discarded vegetable slice, and then the water jet path planning of the discarded vegetable slice is stopped.
4. The water jet path automatic planning method of claim 1, wherein, Step S1 further includes the following sub-steps: S15. Determine whether the sum of the areas of the woody regions in each vegetable slice is less than the fourth threshold. If so, mark the vegetable slice containing the woody region as a high-quality vegetable slice and stop the water jet path planning for the high-quality vegetable slice.
5. The automatic waterjet path planning method according to claim 1, characterized in that, Step S2 further includes the following sub-steps: S21. Determine whether there is a meaty area in each vegetable slice with an area smaller than the fifth threshold. If so, remove the meaty area.
6. The water jet path automatic planning method of claim 1, wherein, In step S3, the number of discrete nodes is reduced by fitting. Specifically, all adjacent discrete nodes are connected, and each discrete node is judged. If the included angle of the discrete node as a vertex is less than a threshold, the discrete node is removed.
7. The water jet path automatic planning method of claim 1, wherein, The automatic water jet path planning method also includes the following steps: S5, each water jet cuts multiple vegetable slices within its moving range in the same rotation sequence.
8. The water jet path automatic planning method of claim 7, wherein, Step S5 includes the following sub-steps: S51. Divide the water jet movement range into an upper half and a lower half; S52. If the water jet cuts all vegetable slices within the moving range in a clockwise rotation order, then the discrete points of each vegetable slice in the upper half of the region are recorded in a counterclockwise order, and the discrete points of each vegetable slice in the lower half of the region are recorded in a clockwise order. S53. If the water jet cuts all vegetable slices within the moving range in a counter-clockwise rotation order, then the discrete points of each vegetable slice in the upper half of the region are recorded in a clockwise order, and the discrete points of each vegetable slice in the lower half of the region are recorded in a counter-clockwise order.
9. A water jet path automatic planning system suitable for vegetable processing, characterized in that, The waterjet path planning system is used to execute the automatic waterjet path planning method according to any one of claims 1-8, including: The image acquisition and analysis module is used to acquire and analyze images of vegetable slices, and to identify the vegetable slice area and the woody area of each vegetable slice from the image; The meat region calculation module is used to expand the vegetable slice area and the woody area in each vegetable slice, and then subtract the woody area from the vegetable slice area to obtain the meat region; The contour fitting module is used to extract discrete nodes from the contour line of the meat area, reduce the number of discrete nodes by fitting, and record the fitted discrete nodes in clockwise or counterclockwise order. The path generation module is used to generate the water jet path for each vegetable slice according to the recording order of discrete nodes.