Method and device for evaluating compensation value of cattle livestock, electronic equipment and medium

Abstract

The embodiment of the invention provides a compensation value evaluation method and device for cattle livestock, electronic equipment and a medium, and belongs to the technical field of artificial intelligence. The method comprises the following steps: acquiring a plurality of cattle body images of cattle livestock at different angles in a lying state, constructing three-dimensional cattle body information of the cattle livestock according to the cattle body images at different angles and actual calibration size information of a calibration object, and inputting the cattle body images into a pre-trained cattle body recognition model, the method comprises the steps of obtaining three-dimensional cattle body information of cattle livestock, positioning key point parts of the cattle livestock through a cattle body recognition model, calculating cattle body size data of the cattle livestock according to the key point parts and the three-dimensional cattle body information, calculating a weight measurement result of the cattle livestock according to the cattle body size data, and evaluating the compensation value of the cattle livestock based on the weight measurement result. According to the embodiment of the invention, the accuracy of the compensation value evaluation of the cattle livestock can be improved.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to a method and device, electronic equipment and medium for evaluating the compensation value of cattle livestock. Background Art

[0002] In the financial field, the compensation value of cattle is mainly determined by the weight of cattle. Measuring the weight of cattle is of great significance for insurance compensation, trade transactions and agricultural loans. When cattle die or are damaged due to diseases, natural disasters or other unexpected events, insurance companies need to accurately assess the compensation value of cattle to make compensation, and the weight of cattle is an important indicator to measure its economic value.

[0003] In the related art, the weight measurement of cattle in the compensation value assessment of cattle relies on a floor scale or manual weighing equipment. However, floor scales or manual weighing equipment are inconvenient to carry or use in some cases, and are complicated to operate. They cannot guarantee the efficiency and accuracy of measuring the weight of cattle, thereby reducing the accuracy of the compensation value assessment of cattle. Therefore, how to improve the accuracy of the compensation value assessment of cattle has become a problem that needs to be further solved in the industry. Summary of the invention

[0004] The main purpose of the embodiments of the present application is to propose a method and device, electronic equipment and medium for evaluating the compensation value of cattle livestock, aiming to improve the accuracy of the compensation value evaluation of cattle livestock.

[0005] To achieve the above-mentioned purpose, a first aspect of the embodiment of the present application proposes a method for assessing the compensation value of cattle livestock, the method comprising:

[0006] Collecting multiple images of the cattle body at different angles when the cattle is in a side-lying state, wherein the cattle body images are used to reflect the cattle and the calibration objects placed around the cattle;

[0007] Constructing three-dimensional body information of the cattle livestock according to the cattle body images at different angles and the actual calibration size information of the calibration object;

[0008] Inputting the cattle body image into a pre-trained cattle body recognition model to locate key points of the cattle livestock through the cattle body recognition model;

[0009] Calculating the body size data of the cattle livestock according to the key point positions and the three-dimensional cattle body information;

[0010] Calculating the weight measurement result of the cattle livestock according to the cattle body size data;

[0011] Based on the weight measurement results, the compensation value of the bovine livestock is assessed.

[0012] In some embodiments, the key points include the base of the front legs, the tail, the front of the base of the front legs, and the junction of the front legs and the abdomen. The calculation of the body size data of the cattle livestock according to the key points and the three-dimensional cattle body information includes:

[0013] Based on the three-dimensional bovine body information, the straight-line distance between the front leg root and the tail is calculated to obtain the straight-line italic body length of the bovine livestock;

[0014] Based on the three-dimensional bovine body information, the length of the arc between the front leg root and the tail is calculated to obtain the curved italic body length of the bovine livestock;

[0015] Based on the three-dimensional bovine body information, according to the intersection point of the front legs and the abdomen, the curved front chest circumference of the bovine livestock is calculated;

[0016] Based on the three-dimensional bovine body information, the linear front chest width of the bovine livestock is calculated according to the width between the front leg root and the front part of the front leg root.

[0017] In some embodiments, the calculating the weight measurement result of the bovine livestock according to the bovine body size data includes:

[0018] Inputting the cow body image into a pre-trained cow recognition model for visual semantic segmentation to obtain body surface recognition information corresponding to the cow body image;

[0019] Determine the cattle livestock category corresponding to the cattle body image according to the body surface identification information, wherein the body surface identification information includes the density of the coat, the type of coat color, the size of the head and the shape of the horns;

[0020] The weight measurement result of the bovine livestock is calculated based on the bovine livestock category and the bovine body size data.

[0021] In some embodiments, the calculating the weight measurement result of the bovine livestock according to the type of the bovine livestock and the bovine body size data includes:

[0022] Determining corresponding weight calculation parameters and weight calculation formulas according to the cattle livestock category;

[0023] The weight measurement result of the bovine livestock is calculated based on the weight calculation formula, the weight calculation parameters and the bovine body size data.

[0024] In some embodiments, the weight measurement result of the bovine livestock is calculated based on the weight calculation formula, the weight calculation parameters and the bovine body size data, including:

[0025] The oblique length of the body of the cattle livestock is calculated according to the oblique length of the straight line and the oblique length of the curved line;

[0026] The square of the chest circumference of the cattle livestock is calculated based on the curved front chest circumference and the straight front chest width;

[0027] The body oblique length, the chest circumference square and the weight calculation parameters are input into the weight calculation formula to obtain the weight measurement result of the bovine livestock.

[0028] In some embodiments, the key points further include the highest point of the front chest, the highest point of the back, the highest point of the abdomen, the highest point of the back waist, and the intersection of the hind legs and the abdomen. The calculation of the body size data of the cattle livestock according to the key points and the three-dimensional cattle body information includes:

[0029] Based on the three-dimensional bovine body information, the curved abdominal circumference of the bovine livestock is calculated according to the highest point of the abdomen;

[0030] Based on the three-dimensional bovine body information, the curved rear waist circumference of the bovine livestock is calculated according to the intersection point of the hind legs and the abdomen;

[0031] Based on the three-dimensional bovine body information, the height of the highest point of the front chest from the ground is calculated to obtain the straight-line front chest height of the bovine livestock;

[0032] Based on the three-dimensional bovine body information, the height of the highest point of the abdomen from the ground is calculated to obtain the straight-line abdomen height of the bovine livestock;

[0033] Based on the three-dimensional cattle body information, the height of the highest point of the rear waist from the ground is calculated to obtain the straight rear waist height of the cattle livestock.

[0034] In some embodiments, the calibration object includes a first chessboard and a second chessboard of preset sizes, the first chessboard is placed on the ground, and the second chessboard is placed on the body of the cow, and the three-dimensional body information of the cattle livestock is constructed according to the cow body images at different angles and the actual calibration size information of the calibration object, including:

[0035] Determine the corner points of the first chessboard and the second chessboard in the cow body image, and determine the camera shooting parameters of the cow body image according to the corner points;

[0036] According to the camera shooting parameters and the preset size, based on a pre-trained three-dimensional reconstruction model of the cow body, the position of each feature point in the cow body image in the three-dimensional space is calculated to construct the three-dimensional cow body information of the cattle livestock.

[0037] To achieve the above-mentioned purpose, a second aspect of the embodiment of the present application provides a compensation value assessment device for cattle livestock, the device comprising:

[0038] An image acquisition module, used for collecting a plurality of cattle body images at different angles when the cattle are lying on their sides, wherein the cattle body images are used for reflecting the cattle and the calibration objects placed around the cattle;

[0039] A three-dimensional construction module, used to construct three-dimensional body information of the cattle livestock according to the cattle body images at different angles and the actual calibration size information of the calibration object;

[0040] A part recognition module, used for inputting the cattle body image into a pre-trained cattle body recognition model, so as to locate the key points of the cattle livestock through the cattle body recognition model;

[0041] A size measurement module, used for calculating the body size data of the cattle livestock according to the key points and the three-dimensional cattle body information;

[0042] A weight measurement module, used to calculate the weight measurement result of the cattle livestock according to the cattle body size data;

[0043] The compensation value module is used to evaluate the compensation value of the bovine livestock based on the weight measurement result.

[0044] To achieve the above objectives, a third aspect of an embodiment of the present application proposes an electronic device, which includes a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the method described in the first aspect is implemented.

[0045] To achieve the above-mentioned purpose, the fourth aspect of an embodiment of the present application proposes a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method described in the first aspect is implemented.

[0046] The present application proposes a method and device for evaluating the compensation value of cattle, an electronic device, and a storage medium. The method collects multiple cattle body images at different angles when the cattle are lying on their sides, wherein the cattle body images are used to reflect the cattle and the calibration objects placed around the cattle. According to the cattle body images at different angles and the actual calibration size information of the calibration objects, three-dimensional cattle body information of the cattle is constructed, and the cattle body images are input into a pre-trained cattle body recognition model to locate the key points of the cattle through the cattle body recognition model. According to the key points and the three-dimensional cattle body information, the body size data of the cattle is calculated. According to the cattle body size data, the weight measurement result of the cattle is calculated, and the compensation value of the cattle is evaluated based on the weight measurement result. In this way, by collecting multiple images of cattle in a side-lying state and combining them with the actual size information of the calibration object, three-dimensional cattle body information of the cattle can be constructed. This high-precision three-dimensional information can more accurately reflect the body shape and weight of the cattle. By using a pre-trained cattle body recognition model, the key points of the cattle can be automatically identified, reducing the error and workload of manual measurement. Through the key points and three-dimensional cattle body information, the weight measurement results of the cattle can be accurately calculated, and the compensation value of the cattle can be evaluated, which can improve the accuracy of the compensation value evaluation of the cattle. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 is a flow chart of a method for assessing the compensation value of cattle livestock provided in an embodiment of the present application;

[0048] Figure 2 yes Figure 1 Flow chart of step S102 in FIG.

[0049] Figure 3 is a schematic diagram of a calibration object provided in an embodiment of the present application;

[0050] Figure 4 yes Figure 1 Flow chart of step S104 in FIG.

[0051] Figure 5 yes Figure 1 Flow chart of step S105 in FIG.

[0052] Figure 6 yes Figure 5 Flow chart of step S403 in FIG.

[0053] Figure 7 yes Figure 6 Flow chart of step S502 in FIG.

[0054] Figure 8 yes Figure 1 Another flow chart of step S104 in ;

[0055] Fig. 9 It is a schematic diagram of a method for assessing the compensation value of cattle livestock provided in an embodiment of the present application;

[0056] Fig.10 It is a schematic diagram of the key points of cattle livestock provided in the embodiments of the present application;

[0057] Fig.11 It is a schematic diagram of the structure of the compensation value assessment device for cattle livestock provided in an embodiment of the present application;

[0058] Fig.12 It is a schematic diagram of the hardware structure of the electronic device provided in the embodiment of the present application. DETAILED DESCRIPTION

[0059] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0060] It should be noted that, although the functional modules are divided in the device schematic diagram and the logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than the module division in the device or the order in the flowchart. The terms "first", "second", etc. in the specification, claims and the above drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence.

[0061] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0062] First, some nouns involved in this application are analyzed:

[0063] Artificial intelligence (AI) is a new technical science that studies and develops theories, methods, technologies and application systems for simulating, extending and expanding human intelligence. AI is a branch of computer science that attempts to understand the essence of intelligence and produce a new type of intelligent machine that can respond in a similar way to human intelligence. Research in this field includes robotics, speech recognition, image recognition, natural language processing and expert systems. AI can simulate the information process of human consciousness and thinking. AI is also a theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0064] Based on this, the embodiments of the present application provide a method and device for evaluating the compensation value of cattle livestock, an electronic device and a medium, aiming to improve the accuracy of the compensation value evaluation of cattle livestock.

[0065] The compensation value assessment method and device, electronic device and medium for cattle livestock provided in the embodiments of the present application are specifically illustrated through the following embodiments. First, the compensation value assessment method for cattle livestock in the embodiments of the present application is described.

[0066] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Among them, artificial intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0067] AI basic technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, mechatronics, etc. AI software technologies mainly include computer vision technology, robotics technology, biometrics technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0068] The compensation value assessment method for cattle livestock provided in the embodiment of the present application relates to the field of artificial intelligence technology. The compensation value assessment method for cattle livestock provided in the embodiment of the present application can be applied to a terminal, can also be applied to a server side, and can also be software running in a terminal or a server side. In some embodiments, the terminal can be a smart phone, a tablet computer, a laptop computer, a desktop computer, etc.; the server side can be configured as an independent physical server, or can be configured as a server cluster or a distributed system composed of multiple physical servers, and can also be configured as a cloud server that provides cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms and other basic cloud computing services; the software can be an application that implements the compensation value assessment method for cattle livestock, etc., but is not limited to the above forms.

[0069] The present application can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, etc. The present application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application can also be practiced in distributed computing environments, in which tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0070] Figure 1 is an optional flow chart of the method for assessing the compensation value of cattle livestock provided in the embodiment of the present application, Figure 1 The method may include but is not limited to steps S101 to S106.

[0071] Step S101, collecting a plurality of images of cattle bodies at different angles in a side-lying state;

[0072] Among them, the cattle body image is used to reflect cattle livestock and calibration objects placed around the cattle livestock;

[0073] Step S102, constructing three-dimensional body information of cattle livestock according to the cattle body images at different angles and the actual calibration size information of the calibration object;

[0074] Step S103, inputting the cattle body image into a pre-trained cattle body recognition model to locate key points of cattle livestock through the cattle body recognition model;

[0075] Step S104, calculating the body size data of the cattle livestock according to the key points and the three-dimensional cattle body information;

[0076] Step S105, calculating the weight measurement result of the cattle livestock according to the cattle body size data;

[0077] Step S106, evaluating the compensation value of the cattle livestock based on the weight measurement results.

[0078] In steps S101 to S106 shown in the embodiment of the present application, multiple images of the cattle body at different angles are collected when the cattle is in a side-lying state, wherein the cattle body images are used to reflect the cattle and the calibration objects placed next to the cattle. Three-dimensional cattle body information of the cattle is constructed according to the cattle body images at different angles and the actual calibration size information of the calibration objects. The cattle body images are input into a pre-trained cattle body recognition model to locate key points of the cattle through the cattle body recognition model. The body size data of the cattle is calculated according to the key points and the three-dimensional cattle body information. The weight measurement result of the cattle is calculated according to the cattle body size data. Based on the weight measurement result, the compensation value of the cattle is evaluated. In this way, by collecting multiple images of cattle in a side-lying state and combining them with the actual size information of the calibration object, three-dimensional cattle body information of the cattle can be constructed. This high-precision three-dimensional information can more accurately reflect the body shape and weight of the cattle. By using a pre-trained cattle body recognition model, the key points of the cattle can be automatically identified, reducing the error and workload of manual measurement. Through the key points and three-dimensional cattle body information, the weight measurement results of the cattle can be accurately calculated, and the compensation value of the cattle can be evaluated, which can improve the accuracy of the compensation value evaluation of the cattle.

[0079] In step S101 of some embodiments, the bovine livestock may be bovine animals, including but not limited to cattle, buffalo, yaks, etc. The side-lying state refers to a state in which one side of the body of the bovine livestock is on the ground and the other side is lying upward. The calibration object refers to an object of known size, which is used as a reference in the bovine body image to help calculate the actual size of the bovine livestock. A high-quality camera or smart phone can be used to capture images of the bovine livestock from different angles, such as three angles: front, side and back, to ensure that the whole body of the bovine livestock and the calibration object in the bovine body image are clearly captured.

[0080] It should be understood that by collecting multiple images of cattle bodies at different angles in a side-lying state in step S101, image data of cattle livestock for compensation value assessment can be effectively collected, and these data will serve as the basis for calculating the cattle body size data and weight measurement results in subsequent steps.

[0081] In step S102 of some embodiments, the multiple cattle body images collected at different angles can be preprocessed, including denoising, contrast enhancement, brightness adjustment, etc., to improve the image quality, identify the calibration object in the cattle body image, and determine its position in the cattle body image, and use the actual calibration size information of the calibration object, that is, the actual size data of the calibration object, to calculate the actual length unit corresponding to each pixel in the cattle body image, and use three-dimensional reconstruction technology, such as stereo vision (StereoVision) or structured light (Structured Light) technology to reconstruct the three-dimensional cattle body information of cattle livestock from the two-dimensional cattle body images at different angles.

[0082] See also Figure 2 In some embodiments, the calibration object includes a first chessboard and a second chessboard of preset sizes, the first chessboard is placed on the ground, and the second chessboard is placed on the cow's body. Step S102 may include but is not limited to steps S201 to S202:

[0083] Step S201, determining the corner points of the first chessboard and the second chessboard in the cow body image, and determining the camera shooting parameters of the cow body image according to the corner points;

[0084] Step S202, according to the camera shooting parameters and the preset size, based on the pre-trained three-dimensional reconstruction model of the cow body, calculate the position of each feature point in the cow body image in the three-dimensional space, and construct the three-dimensional cow body information of the cattle livestock.

[0085] See also Figure 3 The calibration object includes a first chessboard and a second chessboard of preset sizes. The first chessboard is placed on the ground, and the second chessboard is placed on the cow's body. The first chessboard and the second chessboard serve as reference objects of known sizes to help determine the actual size of the cattle in the cow's body image.

[0086] In step S201 of some embodiments, the corner points of the first chessboard and the second chessboard are determined in the cow body image, and the corner points of the first chessboard and the second chessboard can be accurately identified by image processing technology, such as a corner point detection algorithm. These corner points are the positions of the intersections of the grids on the first chessboard and the second chessboard, and are obvious feature points in the cow body image, with high contrast and clear edges. After identifying these corner points, they can be used to determine the camera shooting parameters, including the camera's intrinsic parameters (such as focal length, principal point coordinates) and extrinsic parameters (such as the camera's position and posture), which are crucial for subsequent three-dimensional reconstruction because the camera shooting parameters can be used to convert pixel points in a two-dimensional image into physical points in a three-dimensional space.

[0087] In step S202 of some embodiments, these camera shooting parameters and the preset sizes of the first chessboard and the second chessboard are used in combination with a pre-trained three-dimensional reconstruction model of the cow body to calculate the position of each feature point in the cow body image in the three-dimensional space, and the pixel points in the two-dimensional image are mapped to physical points in the three-dimensional space to construct the three-dimensional cow body information of the cattle livestock.

[0088] It should be noted that in order to improve the accuracy and robustness of three-dimensional reconstruction of cattle images, the Structure from Motion (SfM) algorithm can be used to process cattle images taken from multiple angles. The SfM algorithm analyzes the corresponding feature points in cattle images from different perspectives. Through feature point matching, the SfM algorithm can estimate the camera pose of each cattle image, that is, the position and direction of the camera, and convert the two-dimensional feature points into points in three-dimensional space according to the camera pose, construct a three-dimensional point cloud, represent the three-dimensional structure of cattle livestock, and construct three-dimensional cattle body information of cattle livestock.

[0089] In steps S201 to S202 shown in the embodiment of the present application, by determining the corner points of the first chessboard and the second chessboard in the cow body image, determining the camera shooting parameters of the cow body image according to the corner points, and calculating the position of each feature point in the cow body image in the three-dimensional space based on a pre-trained cow body three-dimensional reconstruction model according to the camera shooting parameters and preset dimensions, the three-dimensional cow body information of the cattle livestock is constructed. By determining the corner points of the first chessboard and the second chessboard in the cattle body image, these calibration objects of known sizes can be effectively used to calibrate the camera and restore the three-dimensional structure of the cattle body, thereby providing more accurate and objective data support for the compensation value assessment of the cattle livestock.

[0090] In step S103 of some embodiments, the cow body image is input into a pre-trained cow body recognition model to locate the key points of cattle livestock, such as the head, limbs, trunk, etc., through the cow body recognition model. The collected cow body image is input into the cow body recognition model, and the model will analyze the image, extract the features in the image, and match them with the features learned during the training process to locate the key points of cattle livestock. The cow body recognition model can be a deep learning model (Fast Region Convolutional Neural Network, Faster R-CNN), including a convolutional neural network for feature extraction, a region proposal network (Region Proposal Network, RPN) for generating candidate regions, and a fully connected network for classification and bounding box regression. Other deep learning models, such as RetinaNet, can also be used, but are not limited to this.

[0091] In step S104 of some embodiments, the body size data of the cattle livestock is calculated based on the key point positions and the three-dimensional cattle body information. The body size data of the cattle livestock can be measured using the key point position coordinates in the three-dimensional cattle body information. For example, the length or height of the cattle body can be obtained by calculating the straight-line distance between two key point positions. If more complex body size data is needed, such as the volume or surface area of ​​the cattle livestock, it can be obtained by performing geometric analysis on the three-dimensional cattle body information.

[0092] See also Figure 4 In some embodiments, the key points include the base of the front legs, the tail, the front of the base of the front legs, and the junction of the front legs and the abdomen. Step S104 may include but is not limited to steps S301 to S304:

[0093] Step S301, based on the three-dimensional cattle body information, the straight-line distance between the front leg root and the tail is calculated to obtain the straight-line italic length of the cattle livestock;

[0094] Step S302, based on the three-dimensional cattle body information, the arc length between the front leg root and the tail is calculated to obtain the curved italic body length of the cattle livestock;

[0095] Step S303, based on the three-dimensional cattle body information, according to the intersection point of the front legs and the abdomen, calculate the curved front chest circumference of the cattle livestock;

[0096] Step S304, based on the three-dimensional cattle body information, according to the width between the front leg root and the front part of the front leg root, the linear front chest width of the cattle livestock is calculated.

[0097] In step S301 of some embodiments, the coordinates of the front leg root and the tail are determined in the three-dimensional space of the three-dimensional cattle body information, and the straight-line distance between the front leg root and the tail is calculated to obtain the straight-line italic body length of the cattle livestock.

[0098] In step S302 of some embodiments, in the three-dimensional space of the three-dimensional cattle body information, the coordinates of the front leg roots and the tail are determined, the arc distance between the front leg roots and the tail is calculated, and the natural curve of the cattle livestock is taken into account to obtain the curved italic length of the cattle livestock.

[0099] In step S303 of some embodiments, the curved front chest circumference of the bovine livestock is calculated based on the intersection of the front legs and the abdomen. The measurement of the curved front chest circumference involves measuring the body circumference starting from the intersection of the front legs and the abdomen, along the natural curve of the bovine livestock, passing through the ungrounded part above the ground, to the corresponding point on the other side.

[0100] In step S304 of some embodiments, the coordinates of the front leg root and the front of the front leg root are determined in the three-dimensional space of the three-dimensional cattle body information, and the linear front chest width of the cattle livestock is calculated based on the width between the coordinates of the front leg root and the front of the front leg root.

[0101] Steps S301 to S304 shown in the embodiment of the present application calculate the straight-line distance between the root of the front leg and the tail based on the three-dimensional cattle body information to obtain the straight-line iterative body length of the cattle livestock, calculate the arc length between the root of the front leg and the tail to obtain the curved iterative body length of the cattle livestock, calculate the curved front chest circumference of the cattle livestock according to the intersection of the front leg and the abdomen, calculate the straight-line front chest width of the cattle livestock according to the width between the root of the front leg and the front of the root of the front leg, automatically measure the key size data of the cattle livestock, and improve the accuracy of the calculation of the cattle body size data.

[0102] In step S105 of some embodiments, the weight measurement result of the bovine livestock is calculated based on the cattle body size data, which involves converting the physical dimensions of the bovine livestock, such as the straight-line oblique body length, the curved-line oblique body length, the curved-line front chest circumference and the straight-line front chest width, into an estimated value of the weight. A mathematical model or formula can be established based on historical data. The historical data includes weight and size data of cattle of different breeds and age groups. By performing statistical analysis on these data, the relationship between the cattle body size data and the weight can be determined. For example, a linear relationship or other type of mathematical relationship is found between the oblique body length and chest circumference of the cattle and the weight. After the model is established, regression analysis or other appropriate statistical methods can be used to determine the model parameters. Then, this model is used to predict the weight measurement result of the bovine livestock based on the cattle body size data.

[0103] See also Figure 5 In some embodiments, step S105 may include but is not limited to steps S401 to S403:

[0104] Step S401, inputting the cow body image into a pre-trained cow recognition model for visual semantic segmentation to obtain body surface recognition information corresponding to the cow body image;

[0105] Step S402, determining the cattle livestock category corresponding to the cattle body image according to the body surface recognition information;

[0106] Among them, body surface identification information includes the density of fur, fur color type, head size and horn shape;

[0107] Step S403, calculating the weight measurement result of the bovine livestock according to the type of the bovine livestock and the bovine body size data.

[0108] In step S401 of some embodiments, the cow body image is input into a pre-trained cow recognition model for visual semantic segmentation to obtain body surface recognition information corresponding to the cow body image. The cow recognition model can recognize whether the cow's fur is sparse or dense, whether the fur color is light or dark, the size of the head relative to the body, and the shape and size of the horns. By accurately identifying these body surface features, the cow can be more accurately classified. For example, the cow recognition model can use a key information extraction algorithm (VI-LayoutXLM), which is based on deep learning technology and can understand and interpret the visual and semantic information in the cow body image. The cow body image is input into the model, and the model analyzes the image content and outputs the category label for each pixel or image area.

[0109] In step S402 of some embodiments, if the body surface identification information indicates that the bovine livestock has dense fur, diverse fur colors, a small head, and thin and upwardly curved horns, it can be determined that the bovine livestock is a cattle; if the body surface identification information indicates that the bovine livestock has sparse fur, gray or black fur, a large head, and thick and flat horns that curve backwards, it can be determined that the bovine livestock is a buffalo; if the body surface identification information indicates that the bovine livestock has thick fur all over its body, dark brown fur, a large head, and short and thick horns, it can be determined that the bovine livestock is a yak.

[0110] In step S403 of some embodiments, the cattle livestock category corresponding to the cattle body image is determined, and a weight estimation formula corresponding to the category can be selected or applied to calculate the cattle livestock weight measurement result based on the cattle livestock category and the cattle body size data.

[0111] In steps S401 to S403 shown in the embodiment of the present application, the body surface recognition information corresponding to the cow body image is obtained by inputting the cow body image into a pre-trained cow recognition model for visual semantic segmentation, and the cattle livestock category corresponding to the cow body image is determined according to the body surface recognition information. The weight measurement result of the cattle livestock is calculated according to the cattle livestock category and the cow body size data. The deep learning visual semantic segmentation technology is used to provide a detailed body surface feature analysis for the cow body image, and the cattle livestock category is determined according to the body surface recognition information. The weight measurement result of the corresponding category is calculated more accurately, thereby improving the accuracy of weight measurement.

[0112] See also Figure 6 In some embodiments, step S403 may include but is not limited to steps S501 to S502:

[0113] Step S501, determining corresponding weight calculation parameters and weight calculation formula according to the cattle livestock category;

[0114] Step S502, calculating the weight measurement result of the cattle livestock according to the weight calculation formula, weight calculation parameters and cattle body size data.

[0115] In step S501 of some embodiments, corresponding weight calculation parameters and weight calculation formulas are determined according to the category of bovine livestock. Different breeds or categories of cattle may have different relationships between weight and size. Weight calculation parameters and weight calculation formulas for the corresponding category of bovine livestock can be selected from a predefined parameter and formula library. These parameters and formulas are based on a large amount of historical data and statistical analysis, and can accurately reflect the relationship between the weight and size of a specific breed of cattle.

[0116] In step S502 of some embodiments, the obtained cattle body size data is input into a selected weight calculation formula, which may include straight-line italic body length, curved-line italic body length, curved-line front chest circumference and straight-line front chest width, etc., and the weight calculation formula and weight calculation parameters are used to calculate the estimated weight of the cattle and obtain the weight measurement result of the cattle livestock.

[0117] In steps S501 to S502 shown in the embodiment of the present application, corresponding weight calculation parameters and weight calculation formulas are determined according to the category of bovine livestock, and the weight measurement results of the bovine livestock are calculated according to the weight calculation formula, weight calculation parameters and cattle body size data. Taking into account the differences in the relationship between weight and size between different bovine livestock, the weight measurement results of different bovine livestock are accurately calculated based on the category of bovine livestock, which can improve the accuracy of the weight measurement of bovine livestock.

[0118] It should be noted that the weight calculation parameter of cattle is 87.5, and the weight calculation formula is: weight (kg) = chest circumference square (m) × body oblique length (m) × weight calculation parameter; the weight calculation parameter of buffalo is 90, and the weight calculation formula is: weight (kg) = chest circumference square (m) × body oblique length (m) × weight calculation parameter; the weight calculation parameter of yak is 10800, and the weight calculation formula is: weight (kg) = chest circumference square (cm) × body oblique length (cm) ÷ weight calculation parameter. When calculating the weight measurement results, the accuracy of the calculation can be improved by taking the average value of multiple calculations.

[0119] See also Figure 7 In some embodiments, step S502 may include but is not limited to steps S601 to S603:

[0120] Step S601, calculating the oblique length of the body of cattle livestock according to the oblique length of the straight line and the oblique length of the curve;

[0121] Step S602, calculating the square of the chest circumference of the cattle livestock according to the curved front chest circumference and the straight front chest width;

[0122] Step S603, inputting the body oblique length, chest circumference square and weight calculation parameters into a weight calculation formula to obtain the weight measurement result of the cattle livestock.

[0123] In step S601 of some embodiments, the oblique body length of the bovine livestock is calculated based on the average of the straight-line oblique body length and the curved-line oblique body length, or different weights are assigned to the straight-line oblique body length and the curved-line oblique body length according to their reliability or accuracy, and then the weighted average is calculated and used in the subsequent weight calculation formula to obtain the weight measurement result of the bovine livestock.

[0124] In step S602 of some embodiments, the straight front chest width is the horizontal width of the bovine livestock chest, and the curved front chest circumference is the length of the curve from one side to the other along the bovine livestock chest. The average of the curved front chest circumference and the straight front chest width can be taken as the estimated value of the chest circumference, and then its square is calculated.

[0125] In step S603 of some embodiments, the body oblique length, chest circumference square and weight calculation parameters are input into the weight calculation formula to obtain the weight measurement results of cattle livestock. The weight measurement results can be used for a variety of purposes, including but not limited to insurance claims, market transactions, feeding management decisions and health monitoring. For example, in the insurance industry, accurate weight data can help determine the value of cattle, thereby ensuring the fairness of the compensation amount. In trade, buyers can use this data to evaluate the value and purchase price of cattle. For farmers, this data helps monitor the growth and health of cattle, so as to make better feeding management decisions.

[0126] In steps S601 to S603 shown in the embodiment of the present application, the oblique body length of the bovine livestock is calculated based on the straight oblique body length and the curved oblique body length, and the chest circumference square of the bovine livestock is calculated based on the curved front chest circumference and the straight front chest width. The oblique body length, the chest circumference square and the weight calculation parameters are input into the weight calculation formula to obtain the weight measurement result of the bovine livestock. Comprehensive consideration of the straight oblique body length and the curved oblique body length, as well as the curved front chest circumference and the straight front chest width can more accurately capture the actual size of the bovine livestock, thereby improving the accuracy of the weight measurement result.

[0127] See also Figure 8 In some embodiments, the key points also include the highest point of the front chest, the highest point of the back, the highest point of the abdomen, the highest point of the back waist, and the intersection of the back legs and the abdomen. Step S104 may include but is not limited to steps S701 to S705:

[0128] Step S701, based on the three-dimensional cattle body information, the curved abdominal circumference of the cattle livestock is calculated according to the highest point of the abdomen;

[0129] Step S702, based on the three-dimensional cattle body information, the curved back waist circumference of the cattle livestock is calculated according to the intersection point of the hind legs and the abdomen;

[0130] Step S703, based on the three-dimensional bovine body information, calculating the height of the highest point of the front chest from the ground to obtain the straight-line front chest height of the bovine livestock;

[0131] Step S704, based on the three-dimensional cattle body information, calculating the height of the highest point of the abdomen from the ground to obtain the straight-line abdomen height of the cattle livestock;

[0132] Step S705, based on the three-dimensional cattle body information, the height of the highest point of the back waist from the ground is calculated to obtain the linear back waist height of the cattle livestock.

[0133] In step S701 of some embodiments, the curved abdominal circumference of the bovine livestock is calculated based on the three-dimensional bovine body information. This step determines the highest point of the abdomen and traces the curve from one side to the other along the bovine body to measure the circumference of the abdomen. The curved abdominal circumference provides an accurate measurement of the abdominal size of the bovine livestock.

[0134] In step S702 of some embodiments, the curved rear waist circumference of the bovine livestock is calculated based on the three-dimensional cow body information. This step involves determining the intersection of the hind legs and the abdomen and tracing the curve from one side to the other along the cow's body to measure the circumference of the rear waist. The curved rear waist circumference provides an accurate measurement of the size of the cow's rear waist.

[0135] In step S703 of some embodiments, the linear chest height of the bovine livestock is calculated based on the three-dimensional bovine body information. This step involves determining the highest point of the chest and measuring the vertical distance from this point to the ground. The linear chest height provides an accurate measurement of the height of the bovine chest.

[0136] In step S704 of some embodiments, the linear abdominal height of the cattle livestock is calculated based on the three-dimensional cattle body information. This step involves determining the highest point of the abdomen and measuring the vertical distance from this point to the ground. The linear abdominal height provides an accurate measurement of the cattle's abdominal height.

[0137] In step S705 of some embodiments, the linear rear waist height of the cattle livestock is calculated based on the three-dimensional cattle body information. This step involves determining the highest point of the rear waist and measuring the vertical distance from this point to the ground. The linear rear waist height provides an accurate measurement of the height of the rear waist of the cattle.

[0138] It should be noted that through these steps, detailed dimensional data of cattle livestock can be collected, which can be used to assist in calculating the weight measurement results of cattle, as well as a reference for compensation assessment, assessing their health status, and making other important agricultural and livestock management decisions. For example, the curved abdominal circumference and curved back waist circumference can be used to assess the body shape and possible fertility of cattle, while the straight front chest height, straight abdominal height and straight back waist height can provide information about the overall body shape and muscle development of cattle.

[0139] Steps S701 to S705 shown in the embodiment of the present application use three-dimensional cattle body information to calculate the curved abdominal circumference of the cattle livestock based on the highest point of the abdomen, calculate the curved back waist circumference of the cattle livestock based on the intersection of the hind legs and the abdomen, calculate the height of the highest point of the front chest above the ground to obtain the straight-line front chest height of the cattle livestock, calculate the height of the highest point of the abdomen above the ground to obtain the straight-line abdominal height of the cattle livestock, and calculate the height of the highest point of the back waist above the ground to obtain the straight-line back waist height of the cattle livestock, thereby enhancing the comprehensiveness and accuracy of the assessment of the compensation value of the cattle livestock.

[0140] In step S106 of some embodiments, the compensation value of the bovine livestock is evaluated based on the weight measurement results, and the physical measurement of the cattle is converted into economic value. For example, if a bovine livestock weighs 500 kg, the breed is Holstein cattle, the age is 5 years old, and market conditions indicate that similar cattle are sold at 28 yuan per kilogram, then the market value of this cattle will be: 500 kg × 28 yuan / kg = 14,000 yuan. This market value can serve as an important reference basis for the evaluation of the compensation value of the cattle, and can be adjusted according to the insurance policy and risk assessment.

[0141] See also Fig. 9 , Fig. 9 This is a schematic diagram of the compensation value assessment method for cattle livestock given in the embodiment of the present application. The cattle is laid flat on the ground on its side, and 20 cm wide positive direction checkerboards are placed on the ground and the body of the cattle respectively. The cattle body images are taken from multiple angles, and the SFM algorithm is used to construct the three-dimensional cattle body information of the cattle livestock by analyzing the cattle body images from different perspectives. At the same time, the captured cattle body image is converted into an ASCII string through the encoding rules of binary data to obtain the specific string of the image, and the identification ID is obtained, which is then stored in the local cache, and the specific string is uploaded to the image server, and the identification ID and the corresponding storage bucket name of the image are returned and stored in the local cache. Based on the captured cattle body image combined with the deep learning model Faster R-CNN, key point parts are identified, and the participants Fig.10The key points include the root of the front leg, the tail, the front of the root of the front leg, the intersection of the front leg and the abdomen, the highest point of the front chest, the highest point of the back, the highest point of the abdomen, the highest point of the back waist, and the intersection of the hind leg and the abdomen. In the figure, the positioning point 1 is the root of the front leg, the positioning point 2 is the tail, the positioning point 3 is the highest point of the front chest, the positioning point 4 is the intersection of the front leg and the abdomen, the positioning point 5 is the highest point of the back, the positioning point 6 is the highest point of the abdomen, the positioning point 7 is the highest point of the back waist, the positioning point 8 is the intersection of the hind leg and the abdomen, and the positioning point 9 is the front of the root of the front leg. The key points are combined with the three-dimensional cattle body information to obtain the cattle body size data of cattle livestock. The above cattle body size data and the identification ID of the cattle body image (corresponding to the cattle in the picture) and the corresponding storage bucket name are sent to the server for identification. The storage bucket stores objects in a flat structure. Each object has a unique key to identify it. The storage type uses standard storage, which is suitable for frequently accessed data, such as Alibaba Cloud OSS that can provide storage bucket services. The various information identified under the list of identification IDs constitutes a storage bucket. Visual semantic segmentation is performed through the key information extraction algorithm VI-LayoutXLM to identify the surface identification information of cattle livestock, determine the cattle livestock category corresponding to the cattle body image, substitute the cattle livestock category and cattle body size data into the weight calculation formula, calculate multiple times and take the average to obtain the cattle livestock weight measurement result, and evaluate the compensation value of the cattle livestock based on the weight measurement result.

[0142] The embodiment of the present application collects multiple body images of cattle at different angles in a side-lying state, wherein the cattle body images are used to reflect the cattle and calibration objects placed around the cattle, and constructs three-dimensional body information of the cattle according to the cattle body images at different angles and the actual calibration size information of the calibration objects. The cattle body images are input into a pre-trained cattle body recognition model to locate key points of the cattle through the cattle body recognition model, calculate the body size data of the cattle according to the key points and the three-dimensional cattle body information, calculate the weight measurement result of the cattle according to the cattle body size data, and evaluate the compensation value of the cattle based on the weight measurement result. In this way, by collecting multiple images of cattle in a side-lying state and combining them with the actual size information of the calibration object, three-dimensional cattle body information of the cattle can be constructed. This high-precision three-dimensional information can more accurately reflect the body shape and weight of the cattle. By using a pre-trained cattle body recognition model, the key points of the cattle can be automatically identified, reducing the error and workload of manual measurement. Through the key points and three-dimensional cattle body information, the weight measurement results of the cattle can be accurately calculated, and the compensation value of the cattle can be evaluated, which can improve the accuracy of the compensation value evaluation of the cattle.

[0143] See also Fig.11The embodiment of the present application also provides a compensation value assessment device for cattle livestock, which can implement the compensation value assessment method for cattle livestock, and the device includes:

[0144] An image acquisition module is used to collect multiple images of the cattle body at different angles when the cattle are lying on their sides, wherein the cattle body images are used to reflect the cattle and the calibration objects placed around the cattle;

[0145] A three-dimensional construction module is used to construct three-dimensional body information of cattle livestock according to the cattle body images at different angles and the actual calibration size information of the calibration object;

[0146] A part recognition module is used to input the cattle body image into a pre-trained cattle body recognition model to locate key points of cattle livestock through the cattle body recognition model;

[0147] A size measurement module is used to calculate the body size data of cattle livestock based on key points and three-dimensional body information;

[0148] A weight measurement module is used to calculate the weight measurement result of cattle livestock according to the cattle body size data;

[0149] The Compensation Value Module is used to assess the compensation value of cattle livestock based on weight measurements.

[0150] The specific implementation of the compensation value assessment device for bovine livestock is basically the same as the specific implementation of the compensation value assessment method for bovine livestock described above, and will not be repeated here.

[0151] The embodiment of the present application also provides an electronic device, the electronic device includes a memory and a processor, the memory stores a computer program, and the processor implements the above-mentioned cattle livestock compensation value assessment method when executing the computer program. The electronic device can be any smart terminal including a tablet computer, a car computer, etc.

[0152] See also Fig.12 , Fig.12 The hardware structure of an electronic device of another embodiment is illustrated, and the electronic device includes:

[0153] The processor 1201 may be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (Application Specific Integrated Circuit, ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of the present application;

[0154] The memory 1202 can be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 1202 can store an operating system and other application programs. When the technical solution provided in the embodiments of this specification is implemented by software or firmware, the relevant program code is stored in the memory 1202, and the processor 1201 calls and executes the compensation value assessment method for cattle livestock in the embodiments of this application;

[0155] Input / output interface 1203, used to implement information input and output;

[0156] The communication interface 1204 is used to realize the communication interaction between the device and other devices. The communication can be realized through a wired manner (such as USB, network cable, etc.) or a wireless manner (such as mobile network, WIFI, Bluetooth, etc.);

[0157] A bus 1205 that transmits information between various components of the device (e.g., the processor 1201, the memory 1202, the input / output interface 1203, and the communication interface 1204);

[0158] The processor 1201 , the memory 1202 , the input / output interface 1203 and the communication interface 1204 are connected to each other in communication within the device via the bus 1205 .

[0159] An embodiment of the present application also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the above-mentioned method for assessing the compensation value of cattle livestock is implemented.

[0160] The memory, as a non-transient computer-readable storage medium, can be used to store non-transient software programs and non-transient computer executable programs. In addition, the memory may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory may optionally include a memory remotely disposed relative to the processor, and these remote memories may be connected to the processor via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0161] The embodiments of the present application provide a method and device, an electronic device, and a medium for evaluating the compensation value of cattle livestock. The method collects multiple cattle body images at different angles when the cattle livestock is in a side-lying state, wherein the cattle body images are used to reflect the cattle livestock and calibration objects placed around the cattle livestock. Three-dimensional cattle body information of the cattle livestock is constructed based on the cattle body images at different angles and the actual calibration size information of the calibration objects. The cattle body images are input into a pre-trained cattle body recognition model to locate key points of the cattle livestock through the cattle body recognition model. The body size data of the cattle livestock is calculated based on the key points and the three-dimensional cattle body information. The weight measurement result of the cattle livestock is calculated based on the cattle body size data. Based on the weight measurement result, the compensation value of the cattle livestock is evaluated. In this way, by collecting multiple images of cattle in a side-lying state and combining them with the actual size information of the calibration object, three-dimensional cattle body information of the cattle can be constructed. This high-precision three-dimensional information can more accurately reflect the body shape and weight of the cattle. By using a pre-trained cattle body recognition model, the key points of the cattle can be automatically identified, reducing the error and workload of manual measurement. Through the key points and three-dimensional cattle body information, the weight measurement results of the cattle can be accurately calculated, and the compensation value of the cattle can be evaluated, which can improve the accuracy of the compensation value evaluation of the cattle.

[0162] The embodiments described in the embodiments of the present application are intended to more clearly illustrate the technical solutions of the embodiments of the present application and do not constitute a limitation on the technical solutions provided in the embodiments of the present application. Those skilled in the art will appreciate that with the evolution of technology and the emergence of new application scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.

[0163] Those skilled in the art will appreciate that the technical solutions shown in the figures do not constitute a limitation on the embodiments of the present application, and may include more or fewer steps than shown in the figures, or a combination of certain steps, or different steps.

[0164] The device embodiments described above are merely illustrative, and the units described as separate components may or may not be physically separated, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0165] Those skilled in the art will appreciate that all or some of the steps in the methods disclosed above, and the functional modules / units in the systems and devices may be implemented as software, firmware, hardware, or a suitable combination thereof.

[0166] The terms "first", "second", "third", "fourth", etc. (if any) in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0167] It should be understood that in the present application, "at least one (item)" means one or more, and "plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the objects associated before and after are in an "or" relationship. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.

[0168] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the above units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0169] The units described above as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0170] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0171] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including multiple instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, referred to as ROM), random access memory (Random Access Memory, referred to as RAM), disk or optical disk and other media that can store programs.

[0172] The preferred embodiments of the present application are described above with reference to the accompanying drawings, but the scope of the rights of the present application is not limited thereto. Any modification, equivalent substitution and improvement made by a person skilled in the art without departing from the scope and essence of the present application should be within the scope of the rights of the present application.

Claims

1. A method for assessing the compensation value of cattle livestock, characterized in that: include: Collecting multiple images of the cattle body at different angles when the cattle is in a side-lying state, wherein the cattle body images are used to reflect the cattle and the calibration objects placed around the cattle; Constructing three-dimensional body information of the cattle livestock according to the cattle body images at different angles and the actual calibration size information of the calibration object; Inputting the cattle body image into a pre-trained cattle body recognition model to locate key points of the cattle livestock through the cattle body recognition model; Calculating the body size data of the cattle livestock according to the key point positions and the three-dimensional cattle body information; Calculating the weight measurement result of the cattle livestock according to the cattle body size data; Based on the weight measurement results, the compensation value of the bovine livestock is assessed.

2. The method for assessing the compensation value of cattle livestock according to claim 1, characterized in that: The key points include the front leg root, the tail, the front of the front leg root, and the junction of the front leg and the abdomen. The body size data of the cattle livestock is calculated based on the key points and the three-dimensional cattle body information, including: Based on the three-dimensional bovine body information, the straight-line distance between the front leg root and the tail is calculated to obtain the straight-line italic body length of the bovine livestock; Based on the three-dimensional bovine body information, the length of the arc between the front leg root and the tail is calculated to obtain the curved italic body length of the bovine livestock; Based on the three-dimensional bovine body information, according to the intersection point of the front legs and the abdomen, the curved front chest circumference of the bovine livestock is calculated; Based on the three-dimensional bovine body information, the linear front chest width of the bovine livestock is calculated according to the width between the front leg roots and the front of the front leg roots.

3. The method for assessing the compensation value of cattle livestock according to claim 2, characterized in that: The method of calculating the weight measurement result of the cattle livestock according to the cattle body size data includes: Inputting the cow body image into a pre-trained cow recognition model for visual semantic segmentation to obtain body surface recognition information corresponding to the cow body image; Determine the cattle livestock category corresponding to the cattle body image according to the body surface identification information, wherein the body surface identification information includes the density of the coat, the type of coat color, the size of the head and the shape of the horns; The weight measurement result of the bovine livestock is calculated based on the bovine livestock category and the bovine body size data.

4. The method for assessing the compensation value of cattle livestock according to claim 3, characterized in that: The method of calculating the weight measurement result of the bovine livestock according to the type of the bovine livestock and the bovine body size data includes: Determining corresponding weight calculation parameters and weight calculation formulas according to the cattle livestock category; The weight measurement result of the bovine livestock is calculated based on the weight calculation formula, the weight calculation parameters and the bovine body size data.

5. The method for assessing the compensation value of cattle livestock according to claim 4, characterized in that: The weight measurement result of the cattle livestock is calculated based on the weight calculation formula, the weight calculation parameters and the cattle body size data, including: The oblique length of the body of the cattle livestock is calculated according to the oblique length of the straight line and the oblique length of the curved line; The square of the chest circumference of the cattle livestock is calculated based on the curved front chest circumference and the straight front chest width; The body oblique length, the chest circumference square and the weight calculation parameters are input into the weight calculation formula to obtain the weight measurement result of the bovine livestock.

6. The method for assessing the compensation value of cattle livestock according to claim 2, characterized in that: The key points also include the highest point of the front chest, the highest point of the back, the highest point of the abdomen, the highest point of the back waist, and the intersection of the hind legs and the abdomen. The body size data of the cattle livestock is calculated based on the key points and the three-dimensional cattle body information, including: Based on the three-dimensional bovine body information, the curved abdominal circumference of the bovine livestock is calculated according to the highest point of the abdomen; Based on the three-dimensional bovine body information, the curved rear waist circumference of the bovine livestock is calculated according to the intersection point of the hind legs and the abdomen; Based on the three-dimensional bovine body information, the height of the highest point of the front chest from the ground is calculated to obtain the straight-line front chest height of the bovine livestock; Based on the three-dimensional bovine body information, the height of the highest point of the abdomen from the ground is calculated to obtain the straight-line abdomen height of the bovine livestock; Based on the three-dimensional cattle body information, the height of the highest point of the rear waist from the ground is calculated to obtain the straight rear waist height of the cattle livestock.

7. The method for assessing the compensation value of cattle livestock according to claim 1, characterized in that: The calibration object includes a first chessboard and a second chessboard of preset sizes, the first chessboard is placed on the ground, and the second chessboard is placed on the body of the cow. The three-dimensional body information of the cattle livestock is constructed according to the cow body images at different angles and the actual calibration size information of the calibration object, including: Determine the corner points of the first chessboard and the second chessboard in the cow body image, and determine the camera shooting parameters of the cow body image according to the corner points; According to the camera shooting parameters and the preset size, based on a pre-trained three-dimensional reconstruction model of the cow body, the position of each feature point in the cow body image in the three-dimensional space is calculated to construct the three-dimensional cow body information of the cattle livestock.

8. A compensation value assessment device for cattle livestock, characterized in that: include: An image acquisition module, used for collecting a plurality of cattle body images at different angles when the cattle are lying on their sides, wherein the cattle body images are used for reflecting the cattle and the calibration objects placed around the cattle; A three-dimensional construction module, used to construct three-dimensional body information of the cattle livestock according to the cattle body images at different angles and the actual calibration size information of the calibration object; A part recognition module, used for inputting the cattle body image into a pre-trained cattle body recognition model, so as to locate the key points of the cattle livestock through the cattle body recognition model; A size measurement module, used for calculating the body size data of the cattle livestock according to the key points and the three-dimensional cattle body information; A weight measurement module, used to calculate the weight measurement result of the cattle livestock according to the cattle body size data; The compensation value module is used to evaluate the compensation value of the bovine livestock based on the weight measurement result.

9. An electronic device, characterized in that: include: A memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the method for assessing the compensation value of cattle livestock as described in any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium, characterized in that: The storage medium stores a program, and the program is executed by a processor to implement the method for evaluating the compensation value of cattle livestock as described in any one of claims 1 to 7.

Images