A method for controlling automatic segmentation of pigs after slaughter

Abstract

The present invention relates to the technical field of pig slaughtering, and in particular to a method for controlling automatic segmentation of pigs after slaughter, which not only improves the accuracy and stability of segmentation, but also enhances the adaptability and flexibility of the system; the method is used for real-time dynamic control of segmentation of an automatic segmentation pipeline, and the method comprises: obtaining a three-dimensional scan of a pig carcass to be segmented and the weight of the pig carcass, and generating a three-dimensional model of the pig carcass according to the scanning result and the weight of the pig carcass; performing segmentation part identification on the three-dimensional model of the pig carcass to obtain a segmentation part set; each element in the segmentation part set includes a part type, a segmentation boundary and an estimated weight; based on the design scheme of the automatic segmentation pipeline, each part in the segmentation part set is sorted in sequence to obtain a pig segmentation part sequence; the automatic segmentation pipeline is started, segmentation operations are performed according to the pig segmentation part sequence, and after each segmentation is completed.

Description

Technical Field

[0001] The invention relates to the technical field of pig slaughtering, and in particular to a method for controlling automatic segmentation of pigs after slaughter. Background Art

[0002] With the growth of global population and the improvement of economic level, meat consumption has increased significantly, which has promoted the rapid development of animal husbandry. As an important part of animal husbandry, the output and quality of pig farming directly affect market supply and consumer demand. The traditional pig slaughtering process mainly relies on manual operation, which has problems such as low efficiency, high labor intensity and unstable cutting quality. With the advancement of automation technology, automated slaughtering lines have gradually replaced some manual operations.

[0003] However, existing automated cutting lines often lack real-time dynamic control mechanisms during the cutting process, resulting in inaccurate cutting results. Specifically, existing methods can usually only perform fixed-mode cutting according to a preset cutting scheme, and cannot be flexibly adjusted according to the actual conditions of the pig carcass. In addition, due to the differences in shape, size, weight, etc. of pig carcasses, fixed cutting schemes often cannot adapt to these changes, resulting in cutting deviations and waste. Summary of the invention

[0004] In order to solve the above technical problems, the present invention provides a method for controlling the automatic segmentation of slaughtered pigs, which not only improves the accuracy and stability of segmentation, but also enhances the adaptability and flexibility of the system.

[0005] In a first aspect, the present invention provides a method for controlling automatic segmentation of slaughtered pigs, the method being used for real-time dynamic control of segmentation of an automatic segmentation assembly line, the method comprising:

[0006] Obtaining a three-dimensional scan of a pig carcass to be cut and a weight of the pig carcass, and generating a three-dimensional model of the pig carcass according to the scan result and the weight of the pig carcass;

[0007] Performing segmentation part recognition on the three-dimensional model of the pig carcass to obtain a segmentation part set; each element in the segmentation part set includes a part type, a segmentation boundary, and an estimated weight;

[0008] Based on the design of the automated segmentation pipeline, the various parts in the segmentation part set are sorted in order to obtain the sequence of pig segmentation parts;

[0009] Start the automated segmentation line, perform segmentation operations according to the sequence of pig segmentation parts, and collect segmentation surface tissue images after each segmentation is completed;

[0010] Identify the segmentation surface tissue image, obtain the tissue type corresponding to the segmentation surface, and determine the attribution of the tissue type: if the tissue type belongs to the tissue type of the current segmentation part, it is determined that the current segmentation operation has a segmentation deviation; if the tissue type belongs to the tissue type of the segmentation part adjacent to the current segmentation part, it is determined that the current segmentation operation has a segmentation deviation; if the tissue type belongs to the transitional tissue type, it is determined that the current segmentation operation is qualified;

[0011] In response to the existence of segmentation deviation in the current segmentation operation, obtaining the real-time weight of the current segmented part, and calculating the degree of weight deviation between the real-time weight and the estimated weight of the current segmented part;

[0012] Based on the weight deviation degree, the segmentation boundary of the adjacent parts of the current segmentation operation is optimized and adjusted to obtain the optimized segmentation boundary of the adjacent parts;

[0013] According to the optimized segmentation boundary, the automated segmentation pipeline is controlled to perform segmentation operations on adjacent parts.

[0014] Furthermore, the method for generating the three-dimensional model of the pig carcass comprises:

[0015] Use 3D scanning equipment and place the pig carcass on a stable stand;

[0016] Start the 3D scanning equipment to perform a full-scale scan of the pig carcass to obtain 3D scanning data;

[0017] Place the pig carcass steadily on the weighing device, wait for the device to stabilize, and then read the weight data to obtain the weight of the pig carcass;

[0018] Preprocess the 3D scan data obtained by scanning, including removing noise and filling missing data;

[0019] The preprocessed 3D scanning data is imported into the 3D modeling software to generate a 3D mesh model of the pig carcass.

[0020] Furthermore, the method for obtaining the segmentation part set includes:

[0021] Preprocess the 3D model of the pig carcass, including denoising, filling holes, and smoothing the surface;

[0022] Input the 3D model of the pig carcass into the pre-built segmentation part recognition model to automatically identify each part;

[0023] Based on the recognition results, a set of segmented parts is generated, including the type of part, segmentation boundary and estimated weight information.

[0024] Furthermore, the method for obtaining the sequence of pig segmentation parts includes:

[0025] Determine the segmentation priority of each part based on the operating capacity and efficiency of the automated segmentation line, as well as market demand and consumer preferences;

[0026] According to the cutting priority, the parts are arranged in order to form a sequence of pig cutting parts;

[0027] After formulating the preliminary segmentation part sequence, optimize and adjust it according to the actual situation.

[0028] Furthermore, the method for performing the segmentation operation according to the sequence of the segmentation parts of the live pig comprises:

[0029] Start the automated cutting line, read the sequence of pig cutting parts, and control the cutting machine to perform cutting operations according to the sequence;

[0030] The cutting machine accurately cuts the pig carcass according to the cutting instructions obtained in real time;

[0031] During the segmentation process, the segmentation data of each part is recorded;

[0032] After each segmentation is completed, a tissue image of the segmentation surface is collected;

[0033] The acquired segmentation surface tissue images are stored in a database.

[0034] Furthermore, a method for obtaining an optimized segmentation boundary of adjacent parts includes:

[0035] Analyze the degree of weight deviation, including the size, direction and cause of the deviation;

[0036] According to the analysis result of the weight deviation, the adjustment direction of the segmentation boundary of the adjacent parts is determined;

[0037] According to the weight deviation degree and adjustment direction, the optimized segmentation boundary of adjacent parts is calculated;

[0038] After calculating the optimized segmentation boundary, a preliminary verification is performed;

[0039] Based on the determined optimized segmentation boundary, the segmentation parameters of the automated segmentation pipeline are updated.

[0040] Further, according to the optimized segmentation boundary, the automated segmentation pipeline is controlled to perform segmentation operations on adjacent parts;

[0041] Adjust the segmentation parameters of the automated segmentation pipeline based on the optimized segmentation boundaries;

[0042] Precisely position the cutting tool according to the adjusted segmentation parameters;

[0043] After the tool positioning is completed, the automated segmentation line will start the cutting operation; during the cutting process, the tool movement trajectory and cutting depth are monitored in real time;

[0044] While the cutting operation is in progress, the tissue type and cutting quality of the cutting surface are monitored in real time;

[0045] When the cutting operation is completed, check whether the cut parts meet the preset standards and requirements.

[0046] On the other hand, the present application also provides a method system for controlling the automatic segmentation of slaughtered pigs, the system comprising:

[0047] A three-dimensional modeling module obtains a three-dimensional scan of a pig carcass to be cut and the weight of the pig carcass, and generates a three-dimensional model of the pig carcass according to the scan result and the weight of the pig carcass;

[0048] A segmentation part recognition module is used to recognize segmentation parts of the three-dimensional model of the pig carcass to obtain a segmentation part set; each element in the segmentation part set includes a part type, a segmentation boundary, and an estimated weight;

[0049] The segmentation sequence planning module, based on the design of the automated segmentation pipeline, sorts the parts in the segmentation part set to obtain the pig segmentation part sequence;

[0050] The automated segmentation execution module starts the automated segmentation pipeline, performs segmentation operations according to the sequence of pig segmentation parts, and collects segmentation surface tissue images after each segmentation is completed;

[0051] The segmentation quality detection module identifies the segmentation surface tissue image, obtains the tissue type corresponding to the segmentation surface, and determines the attribution of the tissue type: if the tissue type belongs to the tissue type of the current segmentation part, it is determined that there is a segmentation deviation in the current segmentation operation; if the tissue type belongs to the tissue type of the segmentation part adjacent to the current segmentation part, it is determined that there is a segmentation deviation in the current segmentation operation; if the tissue type belongs to the transitional tissue type, it is determined that the current segmentation operation is qualified;

[0052] A weight deviation calculation module, in response to the existence of segmentation deviation in the current segmentation operation, obtains the real-time weight of the current segmented part, and calculates the degree of weight deviation between the real-time weight and the estimated weight of the current segmented part;

[0053] A segmentation boundary optimization module optimizes and adjusts the segmentation boundary of the adjacent parts of the current segmentation operation based on the weight deviation degree to obtain an optimized segmentation boundary of the adjacent parts;

[0054] The segmentation control module controls the automated segmentation assembly line to perform segmentation operations on adjacent parts according to the optimized segmentation boundary.

[0055] In a third aspect, the present application provides an electronic device, comprising a bus, a transceiver, a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the transceiver, the memory, and the processor are connected via the bus, and the computer program, when executed by the processor, implements the steps of any one of the above methods.

[0056] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program implements the steps in any one of the above-mentioned methods when executed by a processor.

[0057] Compared with the prior art, the present invention has the following beneficial effects: by obtaining the three-dimensional scanning and weight information of the pig carcass and generating an accurate three-dimensional model, a reliable basis is provided for the subsequent segmentation operation;

[0058] This method introduces real-time segmentation surface tissue image recognition technology, which can detect and correct segmentation deviations in a timely manner, and realize real-time dynamic control of the segmentation process; when segmentation deviations are found, the system can automatically obtain real-time weight and calculate the degree of weight deviation, and then optimize and adjust the segmentation boundaries of adjacent parts to ensure the accuracy of subsequent segmentation;

[0059] Due to the differences in shape, size, weight, etc. of pig carcasses, traditional fixed segmentation schemes are often difficult to adapt to; however, this method can flexibly respond to these changes through real-time dynamic control and optimization adjustment, thereby improving the adaptability and flexibility of segmentation;

[0060] Precise segmentation reduces waste caused by segmentation deviation and improves the utilization rate of raw materials. The application of automated segmentation lines also significantly improves production efficiency, reduces labor intensity, and brings higher economic benefits to enterprises. Precise segmentation and high-quality pork products better meet the needs and expectations of consumers, helping to improve the market competitiveness of products.

[0061] In summary, the above-mentioned automated segmentation control method for post-slaughter pigs has significant advantages and potential economic benefits in solving the problems of inaccurate segmentation and lack of real-time dynamic control mechanism in the field of pig slaughtering; this method not only improves the segmentation accuracy and stability, but also enhances the adaptability and flexibility of the system, thereby improving production efficiency and product quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] Figure 1 is a flow chart of the present invention;

[0063] Figure 2 is a flow chart of a method for generating a three-dimensional model of a pig carcass;

[0064] Figure 3It is the structural diagram of the automatic cutting control system for post-slaughter pigs. DETAILED DESCRIPTION

[0065] In the description of the present application, those skilled in the art should know that the present application can be implemented as a method, an apparatus, an electronic device, and a computer-readable storage medium. Therefore, the present application can be specifically implemented in the following forms: complete hardware, complete software (including firmware, resident software, microcode, etc.), a combination of hardware and software. In addition, in some embodiments, the present application can also be implemented in the form of a computer program product in one or more computer-readable storage media, and the computer-readable storage medium contains computer program code.

[0066] The above-mentioned computer-readable storage medium may adopt any combination of one or more computer-readable storage media. Computer-readable storage media include: electrical, magnetic, optical, electromagnetic, infrared or semiconductor systems, devices or devices, or any combination of the above. More specific examples of computer-readable storage media include: portable computer disks, hard disks, random access memories, read-only memories, erasable programmable read-only memories, flash memories, optical fibers, optical disc read-only memories, optical storage devices, magnetic storage devices, or any combination of the above. In the present application, computer-readable storage media can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, device, or device.

[0067] The acquisition, storage, use, and processing of data in the technical solution of this application comply with the relevant provisions of national laws.

[0068] The present application describes the provided methods, devices, and electronic devices through flowcharts and / or block diagrams.

[0069] It should be understood that each box in the flowchart and / or block diagram and the combination of boxes in the flowchart and / or block diagram can be implemented by computer-readable program instructions. These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer or other programmable data processing device to produce a machine, and these computer-readable program instructions are executed by a computer or other programmable data processing device to produce a device that implements the functions / operations specified by the boxes in the flowchart and / or block diagram.

[0070] These computer-readable program instructions may also be stored in a computer-readable storage medium that enables a computer or other programmable data processing device to work in a specific manner. In this way, the instructions stored in the computer-readable storage medium produce an instruction device product including functions / operations specified in the blocks in the flowchart and / or block diagram.

[0071] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device, so that a series of operational steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby enabling the instructions executed on the computer or other programmable data processing apparatus to provide a process for implementing the functions / operations specified in the blocks in the flowchart and / or block diagram.

[0072] The present application is described below in conjunction with the drawings in the present application.

[0073] Embodiment 1: Figure 1 to Figure 2 As shown, a method for controlling the automatic segmentation of slaughtered pigs according to the present invention specifically comprises the following steps:

[0074] S1. Obtaining a three-dimensional scan of a pig carcass to be cut and the weight of the pig carcass, and generating a three-dimensional model of the pig carcass according to the scan result and the weight of the pig carcass;

[0075] A method for generating a three-dimensional model of a pig carcass, comprising:

[0076] Use high-precision 3D scanning equipment to ensure that the scanning area is well-lit and evenly lit to avoid the effects of shadows and reflections on the scanning results;

[0077] Place the pig carcass on a stable stand to ensure it is within the optimal scanning range of the scanning equipment;

[0078] Start the scanning equipment to perform a full-scale scan of the pig carcass to ensure that all necessary details are captured and obtain three-dimensional scanning data;

[0079] Use a calibrated accurate weighing device to place the pig carcass steadily on the weighing device, wait for the device to stabilize, and then read the weight data to obtain the weight of the pig carcass;

[0080] Preprocess the scanned point cloud data, including removing noise and filling missing data, to improve the accuracy of the model;

[0081] The pre-processed point cloud data is imported into the 3D modeling software; in the software, the point cloud data is used to generate a 3D mesh model of the pig carcass, and the point cloud data is triangulated to form a continuous surface;

[0082] Smooth the model to reduce unevenness and jagged edges in the mesh;

[0083] Optimize the generated 3D model, including adjusting the size, proportion and position of the model to ensure it matches the actual pig carcass;

[0084] Verify and check the generated 3D model to ensure that its precision and accuracy meet the requirements of subsequent segmentation operations.

[0085] In this step, by using high-precision 3D scanning equipment and calibrated weighing equipment, the 3D shape and weight information of the pig carcass can be accurately obtained; during the scanning process, sufficient and uniform light is ensured to avoid the influence of shadows and reflections on the scanning results, thereby improving the precision and accuracy of the model; the pig carcass is scanned in all directions to ensure that all necessary details are captured, making the generated 3D model more realistic and complete; the scanned point cloud data is preprocessed to remove noise and fill in missing data, thereby improving the accuracy and usability of the model; and a 3D mesh model is generated through 3D modeling software , and smoothing is performed to reduce the unevenness and jagged edges in the grid, making the model smoother and more continuous; the model is optimized, the size, proportion and position are adjusted to ensure that it is consistent with the actual pig carcass, providing a reliable basis for subsequent segmentation operations; the generated three-dimensional model is verified and checked to ensure that its precision and accuracy meet the requirements of subsequent segmentation operations, thereby improving the efficiency and accuracy of the segmentation operations; the three-dimensional model of the pig carcass generated in this step is the basis for the subsequent automated segmentation control method, and provides the necessary input information for subsequent segmentation part identification, sorting, segmentation operations, etc.

[0086] S2, performing segmentation part recognition on the three-dimensional model of the pig carcass to obtain a segmentation part set; each element in the segmentation part set includes a part type, a segmentation boundary, and an estimated weight;

[0087] Preprocessing the 3D model of the pig carcass, including removing noise from the model, filling holes and smoothing the surface, to ensure the accuracy and integrity of the model;

[0088] Image processing technology is used to extract the features of the three-dimensional model of the pig carcass; these features include shape features, texture features, and spatial position features; these features can reflect the differences and connections between different parts of the pig carcass, and provide key information for subsequent segmentation and part identification;

[0089] Based on the extracted features, the segmentation part recognition algorithm is used to segment the three-dimensional model of the pig carcass; machine learning and deep learning methods are used to learn and train a large amount of training data to achieve automatic recognition of different parts of the pig carcass;

[0090] After identifying each segmented part, the information of these parts is integrated into a segmented part set; each element in the set includes the type of part, segmentation boundary and estimated weight;

[0091] The method for obtaining the segmentation part set includes:

[0092] Use professional 3D model processing software to pre-process the 3D model of the pig carcass, including denoising, filling holes, smoothing the surface, etc.

[0093] Using image processing techniques, such as edge detection, contour extraction, texture analysis, etc., to extract the features of the three-dimensional model of the pig carcass;

[0094] Using machine learning or deep learning algorithms, a large number of three-dimensional models containing different parts of pig carcasses are trained and learned to build a segmentation part recognition model;

[0095] Input the three-dimensional model of the pig carcass into the segmentation part recognition model to automatically recognize each part;

[0096] Based on the recognition results, a set of segmented parts is generated, including the type of part, segmentation boundary and estimated weight information.

[0097] In this step, by preprocessing and feature extraction of the three-dimensional model of the pig carcass, and using advanced machine learning or deep learning algorithms to identify the segmented parts, the accuracy and efficiency of segmentation can be greatly improved; compared with the traditional manual segmentation method, this method reduces human errors and improves the accuracy and consistency of segmentation; this step uses automated and intelligent technical means to automatically identify different parts of the pig carcass and generate a set of segmented parts containing information such as part type, segmentation boundaries and estimated weight; it greatly reduces the burden of manual operation and improves production efficiency; through accurate segmentation part identification, it is possible to better understand the characteristics and values ​​of different parts of the pig carcass, providing a scientific basis for subsequent processing and sales; it helps to improve the overall utilization value of the pig carcass and increase economic benefits; the application of this step is one of the important measures to promote the digital transformation of the pig breeding and slaughtering industry; accurate segmentation and identification of pig carcasses through digital means can provide the industry with more accurate data support and help improve the intelligence level of the entire industry.

[0098] S3. Based on the design of the automated segmentation pipeline, the various parts in the segmentation part set are sorted in order to obtain a sequence of live pig segmentation parts;

[0099] The method for obtaining a sequence of pig cut parts includes:

[0100] Based on the set of segmented parts, learn in detail the type, segmentation boundary and estimated weight of each part; conduct a comprehensive assessment of the meat quality, shape, size, positional relationship, etc. of each part;

[0101] Determine the priority of segmentation of various parts based on the operating capacity and efficiency of the automated segmentation line, as well as market demand and consumer preferences. Generally, you can start segmenting from larger, regular-shaped parts with better meat quality, such as buttocks, legs, back and waist. For parts with complex shapes and large differences in meat quality, such as shoulders, necks, ribs and abdomen, segmentation can be done later, so as to better adjust segmentation parameters and strategies.

[0102] According to the priority of segmentation, the various parts are arranged in order to form a sequence of live pig segmentation parts; the formulation of the sequence should take into account the continuity of the segmentation operation to ensure that the segmentation of the previous part will not affect the segmentation of the next part; at the same time, the formulation of the sequence should also take into account the convenience and efficiency of the segmentation operation to minimize the pause and waiting time during the segmentation process;

[0103] After formulating the preliminary cutting part sequence, it is necessary to optimize and adjust it according to the actual situation; adjust it according to factors such as the operating efficiency of the automated cutting line, changes in market demand, and the actual shape and size of the pig carcass; by continuously optimizing the cutting part sequence, the efficiency and accuracy of the cutting operation can be further improved.

[0104] In this step, by scientifically and reasonably sorting the various parts in the segmentation part set and formulating the segmentation part sequence of live pigs, the continuity and efficiency of the segmentation operation can be ensured; the pause and waiting time in the segmentation process are reduced, and the overall segmentation efficiency is improved; at the same time, the segmentation accuracy can be ensured, and the segmentation deviation and waste can be reduced by sorting according to the operating capacity and efficiency of the automated segmentation assembly line; when formulating the segmentation part sequence, market demand and consumer preference are taken into consideration, and the parts with large market demand and consumer preference can be preferentially segmented, thereby optimizing resource utilization; not only market demand is met, but also the overall value of the pig carcass is improved; this step allows the preliminary segmentation part sequence to be optimized and adjusted according to actual conditions; it can cope with changes in the operating efficiency of the automated segmentation assembly line, changes in market demand, and differences in the actual shape and size of the pig carcass, ensuring the smooth progress of the segmentation operation; through a scientific and reasonable segmentation part sequence, it can ensure that each part is properly segmented and processed, thereby improving product quality; by placing the segments at the end and adjusting the segmentation parameters and strategies, the segmentation quality and utilization rate of these parts can be further improved.

[0105] S4, start the automated segmentation pipeline, perform segmentation operations according to the sequence of pig segmentation parts, and collect segmentation surface tissue images after each segmentation is completed;

[0106] The method for performing cutting operations according to the sequence of pig cutting parts includes:

[0107] Start the automated cutting line, read the sequence of pig cutting parts, and control the cutting machine to perform cutting operations according to the sequence;

[0108] The cutting machine will accurately cut the pig carcass according to the cutting instructions obtained in real time. During the cutting process, the control system will monitor the cutting parameters in real time, such as cutting depth and cutting speed, to ensure the accuracy and efficiency of the cutting.

[0109] During the segmentation process, the segmentation data of each part is recorded, including segmentation time, segmentation weight, segmentation parameters, etc.

[0110] After each segmentation is completed, the tissue image of the segmentation surface is collected; the automated segmentation pipeline is equipped with image acquisition equipment, such as a high-definition camera or a video camera; these devices can capture the tissue image of the segmentation surface in real time;

[0111] The acquired segmentation surface tissue images are stored in a database for subsequent analysis and tracing.

[0112] In this step, the automated segmentation line, combined with the real-time acquired segmentation instructions and the precisely controlled segmentation machinery, can ensure accurate and efficient segmentation of pig carcasses; real-time monitoring of segmentation parameters further enhances the accuracy of segmentation and reduces errors caused by human factors; accurate segmentation can maximize the use of various parts of the pig carcass and reduce unnecessary waste; by recording the segmentation data of each part, resources can be better managed to ensure that each part is reasonably utilized; recording detailed segmentation data during the segmentation operation provides an important basis for subsequent data analysis and optimization; collecting and storing segmentation surface tissue images not only helps to instantly check the segmentation quality, but also provides intuitive evidence for subsequent problem tracing and quality control; the application of automated segmentation lines and the combination of image acquisition equipment and databases have significantly improved the automation and intelligence level of pig slaughtering production; the integrated system can reduce manual intervention, improve production efficiency, and reduce labor costs; by continuously accumulating and analyzing segmentation data and segmentation surface tissue images, potential improvement points can be identified, thereby continuously optimizing the segmentation process and parameters; it helps to achieve continuous improvement of the production process and improve overall production efficiency and product quality.

[0113] S5, identifying the segmentation surface tissue image, obtaining the tissue type corresponding to the segmentation surface, and determining the attribution of the tissue type: if the tissue type belongs to the tissue type of the current segmentation part, it is determined that the current segmentation operation has a segmentation deviation; if the tissue type belongs to the tissue type of the segmentation part adjacent to the current segmentation part, it is determined that the current segmentation operation has a segmentation deviation; if the tissue type belongs to the transitional tissue type, it is determined that the current segmentation operation is qualified;

[0114] The collected segmented surface tissue images will be sent to the image recognition system or artificial intelligence algorithm for processing; the system or algorithm will identify the tissue type in the image based on the preset database or learning model; the recognition process may involve image processing technologies such as edge detection, texture analysis, color recognition, etc., to accurately distinguish different types of tissues;

[0115] After identifying the tissue type of the segmentation surface, the system needs to determine whether the tissue type belongs to the tissue type of the current segmentation site;

[0116] According to the prior knowledge of the anatomical structure and cut parts of the pig carcass, the judgment rules are set;

[0117] Identify whether there is a tissue type of the current segmentation part in the segmentation surface tissue image. If there is a tissue type of the current segmentation part, it means that the segmentation part is eccentric to the current segmentation part and there is a segmentation deviation;

[0118] Analyze whether the tissue type in the segmentation surface tissue image is consistent with the tissue type of the adjacent segmentation site; if it is consistent, it may indicate that the segmentation boundary is too close to the adjacent site, resulting in segmentation deviation;

[0119] Identify whether there is a transitional tissue type in the segmentation surface tissue image. The transitional tissue type represents the transitional tissue between the current segmentation part and the adjacent segmentation part, that is, the optimal segmentation area, which makes the boundary between the two parts; if there is a transitional tissue type, and its position and range are as expected, the current segmentation operation is determined to be qualified;

[0120] Through comprehensive judgment, the tissue type of the segmentation surface is determined, and based on this, it is determined whether there is a segmentation deviation in the current segmentation operation.

[0121] In this step, the tissue image of the segmentation surface is identified through image recognition, and the tissue type of the segmentation surface can be accurately determined, thereby ensuring that the segmentation operation is carried out as expected; the image processing technology applied in the identification process further enhances the accuracy of the identification and helps to reduce segmentation deviations; based on the identification results and preset judgment rules, the system can determine in real time whether there are deviations in the current segmentation operation and adjust the segmentation strategy in a timely manner; if the transition tissue type is identified, it indicates that the current segmentation operation is in the optimal segmentation area, which helps to maintain the continuity and efficiency of the segmentation operation; accurate segmentation operations can reduce waste caused by segmentation deviations and improve the utilization rate of pig carcasses; by adjusting the segmentation boundaries in real time, the valuable meat parts can be retained to the maximum extent and unnecessary losses can be reduced; by identifying and analyzing the tissue images of the segmentation surface, the quality of the segmentation operation can be monitored in real time to ensure the stability and consistency of the segmentation results; Step S5 has significant beneficial effects in the automated segmentation control method for pigs, which not only improves the segmentation accuracy and efficiency, but also reduces waste and losses, and improves the automation level and quality control capabilities.

[0122] S6, in response to the existence of segmentation deviation in the current segmentation operation, obtaining the real-time weight of the current segmented part, and calculating the weight deviation degree between the real-time weight and the estimated weight of the current segmented part;

[0123] The automated segmentation assembly line is provided with a weighing sensor;

[0124] When step S5 determines that there is segmentation deviation in the current segmentation operation, the system will immediately trigger the weight measurement module.

[0125] Use weighing sensors to quickly and accurately obtain the real-time weight of the current segmented part;

[0126] Retrieving the estimated weight of the current cut part; the estimated weight is calculated based on the overall weight of the pig carcass and the relative proportion of the cut parts when generating the three-dimensional model of the pig carcass and identifying the cut parts;

[0127] Compare the real-time weight with the estimated weight and calculate the weight deviation between the two;

[0128] High-precision measurement: In order to ensure the accuracy of weight deviation calculation, high-precision measuring equipment must be used; the equipment should be calibrated regularly to reduce errors;

[0129] Step S6 needs to be executed quickly after the segmentation deviation is determined in step S5, so as to adjust the subsequent segmentation operation in time;

[0130] The system should record the real-time weight, estimated weight and weight deviation of each segmentation operation to facilitate subsequent data analysis and optimize the segmentation strategy.

[0131] In this step, the real-time weight of the current segmentation part is obtained through the weighing sensor, so that the system can adjust the segmentation strategy in time to reduce the waste caused by inaccurate segmentation; using high-precision measuring equipment and regular calibration, the degree of deviation between the real-time weight and the estimated weight can be accurately calculated; it provides reliable data support for subsequent segmentation operations and helps to improve the overall segmentation accuracy; by recording the real-time weight, estimated weight and weight deviation degree of each segmentation operation, the system can accumulate a large amount of data; these data can be used for subsequent data analysis to help optimize the segmentation strategy and improve production efficiency and quality; step S6 further enhances the intelligence level of the automated segmentation assembly line; the system can automatically adjust the segmentation parameters according to real-time data, reducing dependence on manual operations and improving the overall degree of automation; by recording the weight data of each segmentation operation, the system can establish a complete quality control system; when problems arise, they can be quickly traced back to the specific segmentation operation, providing strong support for quality improvement and traceability.

[0132] S7, optimizing and adjusting the segmentation boundary of the adjacent parts of the current segmentation operation based on the weight deviation degree to obtain the optimized segmentation boundary of the adjacent parts;

[0133] The method for obtaining the optimized segmentation boundary of adjacent parts includes:

[0134] Analyze the degree of weight deviation, including the size, direction and possible causes of the deviation;

[0135] According to the analysis results of weight deviation, determine the adjustment direction of the segmentation boundary of adjacent parts; if the current segmented part is too heavy, it is necessary to reduce the segmentation range of the adjacent parts to avoid the subsequent segmented parts from being too heavy; on the contrary, if the current segmented part is too light, it is necessary to increase the segmentation range of the adjacent parts to compensate for the previous weight loss;

[0136] According to the degree of weight deviation and adjustment direction, the optimized segmentation boundaries of adjacent parts are calculated; the calculation process takes into account factors such as the overall shape and size of the pig carcass and the relative position of each part to ensure the accuracy and rationality of the segmentation;

[0137] After calculating the optimized segmentation boundary, a preliminary verification is performed to ensure that the new segmentation boundary does not lead to greater deviation or waste;

[0138] Once the optimized segmentation boundary is determined, the system will immediately update the segmentation parameters of the automated segmentation line; these parameters include the position, movement speed and cutting depth of the segmentation tool to ensure that subsequent segmentation operations can be carried out according to the optimized segmentation boundary.

[0139] In this step, by carefully analyzing the degree of weight deviation and intelligently adjusting the segmentation boundaries of adjacent parts according to the analysis results, the precision and accuracy of segmentation can be significantly improved; ensuring that the weight of each segmented part is closer to the preset value, reducing deviation and waste, and improving the overall segmentation effect; by optimizing the segmentation boundaries, the various parts of the pig carcass can be more reasonably allocated to avoid being too heavy or too light; not only the resource utilization efficiency is improved, but also the waste caused by inaccurate segmentation is reduced, and the overall economic benefits are improved; the optimization and adjustment mechanism in this step can be flexibly adjusted according to the actual situation of the pig carcass, enhancing the adaptability of the automated assembly line, and improving production efficiency and flexibility; through precise segmentation, it can ensure that the quality and taste of each segmented part are more consistent, and improve the overall quality of the product; S7 step improves segmentation precision and accuracy, optimizes resource utilization, enhances the adaptability of the automated assembly line, and improves product quality and consumer satisfaction by intelligently adjusting the segmentation boundaries of adjacent parts.

[0140] S8, controlling the automated segmentation assembly line to perform segmentation operations on adjacent parts according to the optimized segmentation boundary;

[0141] Adjust the segmentation parameters of the automated segmentation line according to the optimized segmentation boundary; the segmentation parameters include the path, moving speed, cutting depth and cutting angle of the segmentation tool to ensure that the cutting operation can be carried out accurately along the optimized segmentation boundary;

[0142] The cutting tool is precisely positioned according to the adjusted segmentation parameters; through high-precision sensors and control systems, the tool can be accurately aligned with the optimized segmentation boundary and ready for cutting operations;

[0143] After the tool positioning is completed, the automated segmentation line will start the cutting operation. During the cutting process, the tool movement trajectory and cutting depth are monitored in real time to ensure that the cutting operation can be carried out along the optimized segmentation boundary and achieve the expected segmentation effect.

[0144] While the cutting operation is in progress, the tissue type and cutting quality of the cutting surface are monitored in real time;

[0145] When the cutting operation is completed, check whether the cut parts meet the preset standards and requirements;

[0146] If the cut parts meet the standards, the system will automatically transport the cut meat to the next processing link; if they do not meet the standards, the system will cut or adjust them again until the requirements are met.

[0147] In this step, by adjusting the segmentation parameters of the automated segmentation line according to the optimized segmentation boundary and monitoring the movement trajectory and cutting depth of the tool in real time, it can be ensured that the cutting operation can be carried out accurately along the optimized segmentation boundary; not only the segmentation accuracy is improved, but also the waste caused by deviation is reduced, so that the segmentation result is more in line with the preset standards and requirements; the adjustment mechanism enables the automated segmentation line to be flexibly adjusted according to the actual situation of the pig carcass, thereby adapting to pig carcasses of different shapes, sizes and weights; the flexibility and versatility of the assembly line are enhanced, so that it can cope with various complex segmentation requirements; through automated control and real-time monitoring, precise control and management of the cutting operation are achieved; not only the production efficiency is improved, but also the manual intervention and labor intensity are reduced, making the entire segmentation process more automated and intelligent; precise segmentation operations can ensure that the quality and taste of each segmented part are more consistent, thereby improving the overall quality of the product; through precise segmentation and optimized resource utilization, waste and losses caused by inaccurate segmentation are reduced; this not only reduces production costs, but also improves the utilization efficiency of resources, making the entire production process more economical, environmentally friendly and sustainable.

[0148] Embodiment 2: Figure 3 As shown, the automatic segmentation control system for slaughtered pigs of the present invention specifically includes the following modules:

[0149] A three-dimensional modeling module obtains a three-dimensional scan of a pig carcass to be cut and the weight of the pig carcass, and generates a three-dimensional model of the pig carcass according to the scan result and the weight of the pig carcass;

[0150] A segmentation part recognition module is used to recognize segmentation parts of the three-dimensional model of the pig carcass to obtain a segmentation part set; each element in the segmentation part set includes a part type, a segmentation boundary, and an estimated weight;

[0151] The segmentation sequence planning module, based on the design of the automated segmentation pipeline, sorts the parts in the segmentation part set to obtain the pig segmentation part sequence;

[0152] The automated segmentation execution module starts the automated segmentation pipeline, performs segmentation operations according to the sequence of pig segmentation parts, and collects segmentation surface tissue images after each segmentation is completed;

[0153] The segmentation quality detection module identifies the segmentation surface tissue image, obtains the tissue type corresponding to the segmentation surface, and determines the attribution of the tissue type: if the tissue type belongs to the tissue type of the current segmentation part, it is determined that there is a segmentation deviation in the current segmentation operation; if the tissue type belongs to the tissue type of the segmentation part adjacent to the current segmentation part, it is determined that there is a segmentation deviation in the current segmentation operation; if the tissue type belongs to the transitional tissue type, it is determined that the current segmentation operation is qualified;

[0154] A weight deviation calculation module, in response to the existence of segmentation deviation in the current segmentation operation, obtains the real-time weight of the current segmented part, and calculates the degree of weight deviation between the real-time weight and the estimated weight of the current segmented part;

[0155] A segmentation boundary optimization module optimizes and adjusts the segmentation boundary of the adjacent parts of the current segmentation operation based on the weight deviation degree to obtain an optimized segmentation boundary of the adjacent parts;

[0156] The segmentation control module controls the automated segmentation assembly line to perform segmentation operations on adjacent parts according to the optimized segmentation boundary.

[0157] The system obtains an accurate 3D model of the pig carcass through the 3D modeling module, which provides a basis for subsequent segmentation. The segmentation part identification module can accurately identify the segmentation part, including the type, segmentation boundary and estimated weight, reducing the error of manual judgment. The automated segmentation execution module is combined with the segmentation quality detection module, which can timely detect and correct segmentation deviations and ensure segmentation accuracy by real-time acquisition and identification of segmentation surface tissue images.

[0158] The system has a real-time feedback mechanism that can immediately calculate the weight deviation and optimize the segmentation boundary based on the recognition results of the segmentation quality detection module; the segmentation boundary optimization module can dynamically adjust the segmentation boundary based on real-time data to adapt to the actual differences in pig carcasses, avoiding the deviation and waste caused by fixed segmentation schemes;

[0159] The automated segmentation line replaces the traditional manual operation, significantly improving segmentation speed and production efficiency. The system optimizes the segmentation sequence planning module and reasonably arranges the sequence of segmentation parts, further improving the smoothness and efficiency of the production line.

[0160] The automated segmentation execution module reduces the intensity of workers’ physical labor, allowing them to focus on monitoring and adjusting the system rather than performing repetitive physical labor. The higher the level of intelligence and automation of the system, the lower the physical requirements on workers, thereby improving workers’ job satisfaction and labor productivity.

[0161] Through precise segmentation and real-time dynamic control, the system can minimize segmentation deviation and waste and improve the utilization rate of raw materials. In the long run, the application of the system will significantly reduce production costs and improve economic benefits.

[0162] Precisely cut pork products are more in line with market demand and consumer expectations, which can improve product quality and brand image; consumers' demand for standardized, high-quality pork products will be met, thereby improving consumer satisfaction and loyalty;

[0163] In summary, the automatic segmentation control system for post-slaughter pigs has significant advantages in solving the problems of inaccurate segmentation and lack of real-time dynamic control mechanism in the field of pig slaughtering.

[0164] The various variations and specific embodiments of the automated pig segmentation control method in the aforementioned embodiment 1 are also applicable to the automated pig segmentation control system in the present embodiment. Through the aforementioned detailed description of the automated pig segmentation control method, those skilled in the art can clearly understand the implementation method of the automated pig segmentation control system in the present embodiment. Therefore, for the sake of brevity of the specification, it will not be described in detail here.

[0165] In addition, the present application also provides an electronic device, including a bus, a transceiver, a memory, a processor, and a computer program stored in the memory and executable on the processor. The transceiver, the memory, and the processor are respectively connected via a bus. When the computer program is executed by the processor, each process of the above-mentioned method for controlling output data is implemented, and the same technical effect can be achieved. To avoid repetition, it will not be described here.

[0166] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the technical principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A method for controlling the automatic segmentation of slaughtered pigs, characterized in that: The method is used to perform real-time dynamic control on the segmentation of an automated segmentation pipeline, and the method comprises: Obtaining a three-dimensional scan of a pig carcass to be cut and a weight of the pig carcass, and generating a three-dimensional model of the pig carcass according to the scan result and the weight of the pig carcass; Performing segmentation part recognition on the three-dimensional model of the pig carcass to obtain a segmentation part set; each element in the segmentation part set includes a part type, a segmentation boundary, and an estimated weight; Based on the design of the automated segmentation pipeline, the various parts in the segmentation part set are sorted in order to obtain the sequence of pig segmentation parts; Start the automated segmentation line, perform segmentation operations according to the sequence of pig segmentation parts, and collect segmentation surface tissue images after each segmentation is completed; Identify the segmentation surface tissue image, obtain the tissue type corresponding to the segmentation surface, and determine the attribution of the tissue type: if the tissue type belongs to the tissue type of the current segmentation part, it is determined that the current segmentation operation has a segmentation deviation; if the tissue type belongs to the tissue type of the segmentation part adjacent to the current segmentation part, it is determined that the current segmentation operation has a segmentation deviation; if the tissue type belongs to the transitional tissue type, it is determined that the current segmentation operation is qualified; In response to the existence of segmentation deviation in the current segmentation operation, obtaining the real-time weight of the current segmented part, and calculating the degree of weight deviation between the real-time weight and the estimated weight of the current segmented part; Based on the weight deviation degree, the segmentation boundary of the adjacent parts of the current segmentation operation is optimized and adjusted to obtain the optimized segmentation boundary of the adjacent parts; According to the optimized segmentation boundary, the automated segmentation pipeline is controlled to perform segmentation operations on adjacent parts.

2. The automatic segmentation control method for slaughtered pigs according to claim 1, characterized in that: A method for generating a three-dimensional model of a pig carcass, comprising: Use 3D scanning equipment and place the pig carcass on a stable stand; Start the 3D scanning equipment to perform a full-scale scan of the pig carcass to obtain 3D scanning data; Place the pig carcass steadily on the weighing device, wait for the device to stabilize, and then read the weight data to obtain the weight of the pig carcass; Preprocess the 3D scan data obtained by scanning, including removing noise and filling missing data; The preprocessed 3D scanning data is imported into the 3D modeling software to generate a 3D mesh model of the pig carcass.

3. The automatic segmentation control method for slaughtered pigs according to claim 1, characterized in that: The method for obtaining the segmentation part set includes: Preprocess the 3D model of the pig carcass, including denoising, filling holes, and smoothing the surface; Input the 3D model of the pig carcass into the pre-built segmentation part recognition model to automatically identify each part; Based on the recognition results, a set of segmented parts is generated, including the type of part, segmentation boundary and estimated weight information.

4. The automatic segmentation control method for slaughtered pigs according to claim 1, characterized in that: The method for obtaining a sequence of pig cut parts includes: Determine the segmentation priority of each part based on the operating capacity and efficiency of the automated segmentation line, as well as market demand and consumer preferences; According to the cutting priority, the parts are arranged in order to form a sequence of pig cutting parts; After formulating the preliminary segmentation part sequence, optimize and adjust it according to the actual situation.

5. The method for controlling the automatic segmentation of slaughtered pigs according to claim 1, characterized in that: The method for performing cutting operations according to the sequence of pig cutting parts includes: Start the automated cutting line, read the sequence of pig cutting parts, and control the cutting machine to perform cutting operations according to the sequence; The cutting machine accurately cuts the pig carcass according to the cutting instructions obtained in real time; During the segmentation process, the segmentation data of each part is recorded; After each segmentation is completed, a tissue image of the segmentation surface is collected; The acquired segmentation surface tissue images are stored in a database.

6. The method for controlling the automatic segmentation of slaughtered pigs according to claim 1, characterized in that: The method for obtaining the optimized segmentation boundary of adjacent parts includes: Analyze the degree of weight deviation, including the size, direction and cause of the deviation; According to the analysis result of the weight deviation, the adjustment direction of the segmentation boundary of the adjacent parts is determined; According to the weight deviation degree and adjustment direction, the optimized segmentation boundary of adjacent parts is calculated; After calculating the optimized segmentation boundary, a preliminary verification is performed; Based on the determined optimized segmentation boundary, the segmentation parameters of the automated segmentation pipeline are updated.

7. The method for controlling the automatic segmentation of slaughtered pigs according to claim 1, characterized in that: According to the optimized segmentation boundary, controlling the automated segmentation assembly line to perform segmentation operations on adjacent parts; Adjust the segmentation parameters of the automated segmentation pipeline based on the optimized segmentation boundaries; Precisely position the cutting tool according to the adjusted segmentation parameters; After the tool positioning is completed, the automated segmentation line will start the cutting operation; During the cutting process, the tool movement trajectory and cutting depth are monitored in real time; While the cutting operation is in progress, the tissue type and cutting quality of the cutting surface are monitored in real time; When the cutting operation is completed, check whether the cut parts meet the preset standards and requirements.

8. A post-slaughter pig automatic segmentation control system, characterized in that: The system comprises: A three-dimensional modeling module obtains a three-dimensional scan of a pig carcass to be cut and the weight of the pig carcass, and generates a three-dimensional model of the pig carcass according to the scan result and the weight of the pig carcass; A segmentation part recognition module is used to recognize segmentation parts of the three-dimensional model of the pig carcass to obtain a segmentation part set; each element in the segmentation part set includes a part type, a segmentation boundary, and an estimated weight; The segmentation sequence planning module, based on the design of the automated segmentation pipeline, sorts the parts in the segmentation part set to obtain the pig segmentation part sequence; The automated segmentation execution module starts the automated segmentation pipeline, performs segmentation operations according to the sequence of pig segmentation parts, and collects segmentation surface tissue images after each segmentation is completed; The segmentation quality detection module identifies the segmentation surface tissue image, obtains the tissue type corresponding to the segmentation surface, and determines the attribution of the tissue type: if the tissue type belongs to the tissue type of the current segmentation part, it is determined that there is a segmentation deviation in the current segmentation operation; if the tissue type belongs to the tissue type of the segmentation part adjacent to the current segmentation part, it is determined that there is a segmentation deviation in the current segmentation operation; if the tissue type belongs to the transitional tissue type, it is determined that the current segmentation operation is qualified; A weight deviation calculation module, in response to the existence of segmentation deviation in the current segmentation operation, obtains the real-time weight of the current segmented part, and calculates the degree of weight deviation between the real-time weight and the estimated weight of the current segmented part; A segmentation boundary optimization module optimizes and adjusts the segmentation boundary of the adjacent parts of the current segmentation operation based on the weight deviation degree to obtain an optimized segmentation boundary of the adjacent parts; The segmentation control module controls the automated segmentation assembly line to perform segmentation operations on adjacent parts according to the optimized segmentation boundary.

9. An electronic device for controlling automatic cutting of slaughtered pigs, comprising a bus, a transceiver, a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the transceiver, the memory, and the processor are connected via the bus, and characterized in that: When the computer program is executed by the processor, the steps in the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps in the method according to any one of claims 1 to 7 are implemented.

Images