Shipment livestock sorting method and shipment livestock sorting system

Abstract

The present invention comprises: a path on which livestock moves in one direction; one or a plurality of cameras for imaging the livestock from above the path; and one or more computing devices. The present invention is also provided with: an indication device that estimates the body weight of the livestock using an image captured by the cameras, uses the estimated body weight of the livestock and body weight class information, which is stored in a storage device and with which the livestock can be sorted into at least three classes according to body weight, to determine body weight class information of the livestock adapted to the estimated body weight of the livestock, and issues an indication related to the body weight class information of the livestock according to the body weight class information; or a label imparting device that imparts a physical label by using paint, the label related to the body weight class information on a body surface of the livestock according to the body weight class information.

Description

Method for selecting livestock for shipping and system for selecting livestock for shipping

[0001] RELATED APPLICATIONS This application claims priority to and the benefit of U.S. Provisional Patent Application No. 63 / 634,985, filed April 17, 2024. U.S. Provisional Patent Application No. 63 / 634,985 is incorporated herein by reference in its entirety.

[0002] The present disclosure relates to a demand-driven method and system for selecting livestock for shipment, and more particularly to a method and system for automatically measuring the weight of livestock and selecting optimal destinations for shipment according to their weight.

[0003] There is a known method for estimating pig weight and body size using deep learning, particularly convolutional neural networks (CNN). Weight estimation uses overhead images taken with a 2D color camera installed directly above the pig passage. Since the entrance and exit of the passage are one-way and only one pig can pass through at a time, images of each pig can be obtained. However, measuring only the weight of each pig makes it difficult to create a shipping plan that maximizes profits for the pig farming industry.

[0004] US Patent Application Publication No. 2023 / 0281265

[0005] Aspects and advantages of embodiments of the present disclosure will be set forth in part in the description that follows, or may be learned from the description, or may be learned through practice of the embodiments.

[0006] Therefore, one exemplary aspect of the present disclosure is a method for sorting livestock for shipment, comprising the steps of: livestock moving in one direction along a path; one or more cameras photographing the livestock from above the path; one or more computing devices equipped with one or more processors outputting estimated weights of the livestock using images taken by the cameras; one or more computing devices determining and outputting weight class information of livestock that matches the estimated weights using weight class information stored in a storage device and capable of sorting livestock into three or more classes according to weight, and the estimated weights; and an instruction step in which an instruction device gives instructions regarding the weight class information of the livestock according to the weight class information, or a marking step in which a marking device applies a physical mark using paint related to the weight class information to the body surface of the livestock according to the weight class information.

[0007] Furthermore, one exemplary aspect of the present disclosure is a livestock sorting system for shipping, comprising: a path along which livestock move in one direction; one or more cameras that photograph the livestock from above the path; one or more computing devices with one or more processors; and one or more computer-readable recording media that store instructions, wherein the instructions, when executed by the one or more processors, cause the one or more processors to perform a plurality of operations, the plurality of operations including estimating the weight of the livestock using images taken by the cameras and outputting the estimated weight of the livestock; and determining and outputting weight class information of the livestock that matches the estimated weight of the livestock, using weight class information that is stored in a storage device and can be sorted into three or more classes according to weight and the estimated weight of the livestock; and further comprising an instruction device that gives instructions regarding the weight class information of the livestock according to the weight class information, or a marking device that affixes a physical mark in the form of paint related to the weight class information to the body surface of the livestock according to the weight class information.

[0008] Aspects of the present disclosure therefore enable non-contact acquisition of weight data for multiple livestock and on-site sorting for shipping.

[0009] In addition, problems that are obvious to a person skilled in the art and can be read from the embodiments and explanations characteristic of the present disclosure described in the specification, drawings, etc. of the present disclosure may also become problems that the divided invention must solve if a divisional application based on the present disclosure is filed.

[0010] 1 is a diagram showing an example of a conventional livestock shipping situation. FIG. 2 is an overview diagram for explaining a system for selecting livestock for shipment according to the present disclosure. FIG. 2 is a diagram showing an example of a network configuration of components constituting the system. FIG. 3 is a diagram showing an example of a configuration that can be common to computing devices. FIG. 3 shows examples of still images and videos obtained by capturing images with a camera. FIG. 4 shows numerical ranges representing estimated weight categories for sorting into classes and color data corresponding to the classes. FIG. 4 is a flowchart showing the processing flow of a method for selecting livestock for shipment according to the present disclosure. FIG. 5 is a diagram showing an application example of a system for selecting livestock for shipment according to the present disclosure. FIG. 6 is a diagram showing an application example of a system for selecting livestock for shipment according to the present disclosure. FIG. 7 is a diagram showing an example of an application example of a system for selecting livestock for shipment according to the present disclosure. FIG. 8 is a diagram showing an example of a labeling device. FIG. 9 is a diagram for explaining designation of an analysis area and detection of inclination of a walking surface. FIG. 10 is a diagram for explaining correction of estimated weight based on inclination of a walking surface. FIG. 11 is an example of the weight and number of pigs in a group of pigs classified according to class. FIG. 11 is an example of a purchase price for pigs by class.

[0011] In this disclosure, pigs will be used as an example of livestock, but the technical applicability of this disclosure is not necessarily limited to pigs. Furthermore, pigs and livestock are sometimes referred to interchangeably, but which concept is being referred to will be understood appropriately in the context of the explanation. Regarding animal species other than pigs, for example, mammalian quadrupeds such as cows, goats, and sheep that can grow to a body length (from the front end of the body (the tip of the nose) to the rear end of the body (the base of the tail, or the base of the tail)) of 1.0 m to 2.5 m, these can be technically addressed by appropriate design modifications by those skilled in the art.

[0012] FIG. 1 is a diagram showing an example of a conventional pig shipping situation, presented for reference. In this diagram, a single livestock or pig is designated as L1, and its position and direction of movement are simply indicated using a circular head and an oval body. This applies to subsequent figures. When multiple pigs are shipped from a pigpen in a shipping container or trailer, they pass through path 2 while walking from left to right on the drawing. Such path 2 is a linear corridor (hallway or corridor) within the pigpen that the pigs pass through before being shipped. If weight measurement is performed at the time of shipment, this is performed using a physical contact scale such as a load cell installed at the exit of path 2. Weighing pigs using a load cell is time-consuming and potentially dangerous because the pigs must remain stationary.

[0013] Therefore, in this disclosure, livestock are photographed using a camera and the photographed images are analyzed to estimate the weight of each livestock without contact. However, for optimal livestock shipping planning, estimating the weight of each individual livestock is not sufficient.

[0014] In the United States and other countries, the general practice for raising pigs is to raise multiple pigs together as a group. Such groups are sometimes called "lots." In other words, pigs are not typically individually monitored for weight and shipped when they reach the appropriate weight. Generally, the same breed is raised within a group or lot, but individual differences in livestock often result in both well-performing and poorly performing pigs. Adjusting the feeding schedule to compensate for these individual differences is unrealistic in terms of labor, equipment, and cost, and it is difficult to strictly control the weight variations that occur during the rearing process of individual pigs within a group. Therefore, groups or lots consisting of multiple pigs are shipped when they are deemed appropriate. Alternatively, workers visit the pens of groups or lots deemed appropriate for shipment, visually inspect each animal, assess its size and weight, and decide whether to ship or not. This process is labor-intensive, and visual judgment often results in errors in the estimated weight.

[0015] In addition, in the United States and other countries, when purchasing multiple pigs, a certain number of pigs within a certain weight range are traded together. In such cases, a group of pigs within a more desirable weight range may be traded at a higher price than a group that does not. There are multiple pig buyers in the market, each of which sets a desirable weight range and a corresponding high price, and an undesirable weight range and a corresponding low price. One example of a buyer who purchases pigs directly from producers or farms is a meat processor, commonly known as a packer. Packers purchase pigs from farms and then slaughter, butcher, and process them. In recent years, the market has become increasingly dominated by large packers in the United States. Contracts may be concluded between farms and packers. Contracts include, for example, the contract period, supply volume during the contract period, supply frequency, the number of pigs that must be supplied per supply, weight standards, pricing, weight premiums (e.g., an increase in the purchase price per pig if stricter weight standards are met), and penalties per pig for delayed supply or failure to meet the weight standards. Therefore, producers must strategically consider their shipment plans, determining which groups of pigs to sell to which packers in order to increase the total sales amount. Understanding the weight of each group or lot, as well as the number and weight distribution of pigs in each group or lot, is essential for shipment planning.

[0016] Therefore, simply estimating the weight of a single livestock animal without contact, or counting multiple livestock animals and displaying the average weight along with the total weight, does not lead to a specific shipping plan. As mentioned above, in the actual livestock farming environment, it is not realistic to wait until each pig reaches its optimal weight. A large number of livestock animals are shipped together at a time convenient for the livestock breeders (sellers) and the buyers. In this case, it is desirable to be able to instantly measure the weight so that the animals can be grouped by weight class, to appropriately classify them by weight, and to provide information on the distribution of the number of animals by weight. It is also desirable to be able to use a computer system to support the creation of a shipping plan that can be recognized by on-site personnel.

[0017] FIG. 2 is a schematic diagram illustrating an embodiment of a new sorting system and sorting method for shipping livestock proposed by the present disclosure, and FIG. 3 is a diagram illustrating an example network configuration of the components that make up the system.

[0018] In this figure and the following figures, multiple pigs walk in one direction through a path, which is a part of the space inside the pigpen.

[0019] In the space within path 2, a temporary guidance guide 70 is installed to further narrow the width of existing paths such as corridors and passageways, forming a space that can only accommodate one livestock or one pig, which may be called a single livestock path 71. Furthermore, by installing the temporary guidance guide 70, a storage space is formed between the temporary guidance guide 70 and the wall of path 2 in which a control box, which is an example of one or more computing devices 10, an indicating device 20 for indicating the assigned class so that a human worker can identify it visually and audibly, and power sources for these devices, etc. can be installed, and a waiting booth where human workers M1 and M2 can wait is also formed.

[0020] The temporary guide 70 may be portable and comprised of multiple parts that can be assembled on site. The single livestock path 71 formed by the temporary walls 73 of the temporary guide 70 is designed to be wide enough for one livestock of the target species to pass through with ease, but not enough to allow two livestock to pass through at the same time, and this width range is specified. Such a single livestock path 71 may basically be designed as a long, narrow rectangle with the temporary walls 73 extending in a straight line parallel to each other.

[0021] The temporary guide 70 can be constructed in a variety of ways, including a lightweight metal (e.g., aluminum) pipe frame with a fabric cover (e.g., nylon), high-strength plastic panels (e.g., polycarbonate) and joint parts, a wood frame with plywood panels, or different combinations of these elements. By combining these elements, materials, and parts, a portable fence can be formed that can be assembled on site. Using plastic materials can also reduce noise.

[0022] Note that if an aisle wide enough to form an appropriate single livestock path 71, or equipment designed to do so, already exists within the piggery or on-site, without installing the temporary guide 70, then it is not necessary to install the temporary guide 70. In that case, the equipment already in place can be used as the guide.

[0023] FIG. 3 is a diagram illustrating an example of a network configuration of the shipping livestock selection system of the present disclosure. The shipping livestock selection system 1 may include a first computing device 10A, a second computing device 10B, a third computing device 10C, an indicator 20, a camera 30, and a labeling device 40, which are connected to a network NW or whose individual components are directly connected via wired cables such as USB cables. The network NW may be a communication network that supports various types of telecommunications lines, such as wired and wireless connections, enabling communication with other electronic devices. In other words, although all components appear to be connected via the network NW in this figure, each component may be connected individually so as to be able to communicate. The network NW may include computing devices 10A, 10B, and 10C as described in FIG. 4 below. As will be described later, if a single computing device 10 alone has sufficient computing power, other computing devices may not be included. Depending on the required computing power, other computing devices located remotely may also be included.

[0024] 4 is a diagram showing an example of a configuration that may be common to computing devices 10A-C or other computing devices that may be in remote locations and connected to computing devices 10A-C via network NW, as computing device 10. Typically, computing device 10 includes a communication interface 11, an input user interface 12, an output user interface 13, a processor 14, and a storage device 15.

[0025] By having processor 14 execute an application program based on application data stored in storage device 15, computing device 10 can execute and implement predetermined processes, operations, and controls through the cooperation of software and hardware resources. In other words, computing device 10 includes one or more computer-readable recording media that store instructions, and when executed by one or more processors, the instructions can cause the one or more processors to perform multiple operations. For example, storage device 15 may store operating system data necessary for computing device 10 to function as a general-purpose computer, and the operating system functions using the operating system data.

[0026] Such a computing device 10 may be any type of electronic device, such as, for example, a desktop computer, a laptop computer, a portable or mobile device, a camera, a mobile phone, a smartphone, a tablet computer, a television, a wearable device (such as display glasses or goggles, a head-mounted display (HMD), a watch, a headset, an armband, etc.), a virtual reality (VR) and / or augmented reality (AR) enabled device, a personal digital assistant, etc.

[0027] Computing device 10 may be accessible via wired or wireless communication to a local database or other storage device similar to storage device 15. Storage device 15 may be any processor-readable storage medium accessible by processor 230 and suitable for storing instructions to be executed by the processor, such as, for example, random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory, etc. Storage device 15 may be located separately from processor 14 and / or integrated with processor 14.

[0028] Any software may also be stored on any other suitable auxiliary, secondary, or temporary or non-transitory computer-readable storage medium. Additionally, any type of storage device (magnetic disk, optical disk, magnetic tape, or other tangible medium) may be considered a storage device.

[0029] The input user interface 12 and the output user interface 13 may be hardware devices that allow a user to input and output information between the computing device 10 and / or other computing devices. The user may be, for example, a farm manager, a farm worker, or a system administrator, provider, or a person belonging to a management company. Specific input devices that may constitute the input user interface 12 may include a keyboard, a mouse, one or more touch panel sensors, physical buttons arranged on the device for each function, a microphone, etc. Similarly, output devices that may constitute the output user interface 13 may include a display, a monitor, a printer, a data I / F (including an Application Programming Interface (API)), a speaker, etc.

[0030] The communication interface 11 is compatible with various types of electrical communication lines, such as wired and wireless connections, and can communicate with other electronic devices. For example, communication can be performed via a wide area network connection via an optical fiber network or digital telephone line, a local wireless connection, short-range wireless communication, or a satellite-based positioning system.

[0031] Processor 14 may be one or more of any type of computer processing element, such as a central processing unit (CPU), graphics processing unit (GPU), tensor processing unit (TPU), neural processing unit (NPU), digital signal processing unit (DSP), field programmable gate array (FPGA), application-specific integrated circuit (ASIC), or other integrated circuit or controller that performs processor operations. For example, processor 14 may be one or more single-core processors. Alternatively, processor 14 may be one or more multi-core processors having multiple independent processing units. Processor 14 may also include register memory for temporarily storing instructions being executed and associated data, as well as cache memory for temporarily storing recently used instructions and data. When multiple processors are used for processing, the same processor need not perform all of the processing.

[0032] A computer system may employ a cluster configuration, where multiple computers are grouped and connected via a network. In this case, the same computer system may be installed in multiple locations. The specific locations and connections of these computing devices are not important and may be located outside the country where the user and farm are located. In this context, farm refers to the location where the livestock are actually kept. Such a group of computing devices may be treated as a single cloud computing resource distributed across various data centers.

[0033] Additionally, if a user's mobile device, such as a smartphone, has sufficient processing power, it can be used as a standalone minicomputer, handling all computational tasks. It can also be combined with other computers to form a "cluster" or "edge computing" environment, where the mobile device can handle some of the computational tasks.

[0034] For example, the first computing device 10A may be a control box installed inside the temporary guide 70, the second computing device 10B may be a smartphone or tablet operated by a human worker on-site, and the third computing device 10C may be a server computer installed in a remote location. In other words, each computing device may function as a terminal that shares and processes multiple operations in the present disclosure. In the above example, the control box, which is the first computing device 10A, may be equipped with at least one of a graphics processing unit (GPU), a tensor processing unit (TPU), or a neural processing unit (NPU), and may have a predetermined level of image processing capability and a predetermined level of video memory. This may allow it to function as an edge computing device capable of local image analysis processing without borrowing the computational resources of other computing devices via a network. This is useful in environments where communication may be unstable, such as farms. In this case, the second computing device 10B may be a terminal capable of receiving information and issuing commands to a user, while the third computing device 10C may be used to receive information that should be stored at this time. The first computing device 10A may serve as the main computational resource for substantial information processing on-site.

[0035] The camera 30 is installed to photograph the livestock from above the path 2 and estimate the weight of the livestock from the photographed image.

[0036] The minimum output expected from the camera 30 may be a two-dimensional image captured from a bird's-eye view. If a two-dimensional monochrome or color image captured from a perspective looking down on the livestock is available, the outline of the livestock can be detected by image analysis to estimate dimensions such as body length and body width, and weight can be estimated from these estimated body length and body width. Any algorithm may be used to estimate weight, as will be described later.

[0037] More preferably, the camera 30 is a stereo camera, which can capture images of an object from two viewpoints with parallax and can obtain an image including the distance to the object by measuring the time it takes for emitted light to reflect off the surface of the object and return to the center, such as with ToF (Time of Flight). Such output is acquired as a depth map or depth information, allowing a three-dimensional image of the livestock to be constructed. When acquiring the depth map, an infrared projector mounted on the camera 30 may be used to project structured light, such as an infrared dot pattern or a grid pattern, onto the environment, and the projected image may be analyzed to improve the measurement accuracy of the depth map. The camera 30 may also be equipped with an inertial measurement unit (IMU), which can detect the tilt of the camera 30 using the IMU's acceleration sensor and gyro sensor. The tilt detected by such an IMU may be used to correct the position of the camera 30, or may be used to correct the tilt of the image or the depth map. This tilt information can be used to correct the three-dimensional model of the livestock, contributing to improved weight estimation accuracy. Furthermore, as will be described later, depth information can also be used to improve the accuracy of livestock counting.

[0038] FIG. 5 shows an example of a still image or video of a livestock animal taken from directly above, captured by camera 30. To estimate the pig's weight, for example, a weight estimation model may be used, which estimates the pig's weight using the pig's length L (mm) and width W (mm) as parameters, derived from the video and still images contained in the video. This weight estimation model is a trained model that has been trained in advance on the relationship between the length L (mm), width W (mm), and weight, for example, by machine learning such as deep learning. For example, training of such a model may involve constructing a neural network that inputs the length L (mm) and width W (mm) as features and outputs the weight, and training the constructed NN using training data in which the length L (mm), width W (mm), and weight are paired, thereby improving the accuracy of weight estimation, thereby obtaining a trained model. Additionally, in order to improve the accuracy of weight estimation, a trained model may be used that incorporates other features such as the distance between key points estimated on the image, the pig's movement speed (distance moved per unit time), and values ​​obtained by statistically processing depth information obtained from the depth map. Weight estimation may also be performed multiple times for each pig, and the obtained estimated values ​​may be statistically processed to provide a representative estimated weight.

[0039] Alternatively, the pig's weight calculation formula may be estimated by inputting multiple explanatory variable parameters, such as the pig's width, length, and height, using a regression equation based on multivariate analysis. A non-limiting example is length L (mm) and width W (mm). For example, weight may be estimated using a multiple regression equation such as Weight = αL + βW + γ (α and β are coefficients, and γ is a constant term), where L and B represent length L (mm) and width W (mm).

[0040] Furthermore, as a unit of weight, not only kg but also pounds (lb) or jin (jin) (a Chinese unit of weight, where 1 jin is 500 grams (0.5 kilograms) or approximately 1.1 pounds) can be used. Furthermore, an estimated carcass weight may be used based on the estimated weight. The carcass weight can be estimated, for example, by multiplying the estimated weight by a predetermined coefficient.

[0041] The above is just one example, and all other configuration examples that combine the above-mentioned configurations can be implemented for weight estimation using an image.

[0042] The shipping livestock selection system 1 may also be configured to count the number of livestock using video captured by the camera 30. In Figure 5, livestock L1 is moving from left to right. In this case, when a reference point, such as a center coordinate CC (which may be the center of gravity of a bounding box, the center of gravity of a mask area, or an estimated key point of the head) crosses a counting line CL, which can be set as a region of interest in the video or image, it is possible to count one livestock. In other words, the total number of livestock can be counted by tracking specific points or coordinates representing the positions of the body centers or centers of gravity of multiple livestock for each frame and incrementing the number of livestock each time the counting line CL is crossed. The counting line CL is merely one example of a region of interest, and the counting area does not necessarily have to be linear. As a non-limiting example, a depth map acquired via camera 30 may be used to sequentially acquire information about pigs passing through path 2. The coordinate information on the screen may be used to verify whether the pigs are the same pig using techniques such as Intersection over Union (IoU) to measure the degree of overlap between pig regions in previous and subsequent images (depth maps). This may then be used to count the pigs that have passed path 2 while the application is running. The advantage of using a depth map is that if there is insufficient light in the path along which the pigs move, the pigs themselves will not emit light. Therefore, object identification using features such as the pig's outline or shape in the dark is difficult using only RGB information from a visible light camera. Therefore, by using a depth map that is independent of RGB information or visible light, counting is possible in any environment. The difference from the counting line CL described above is that the total number of pigs passing through the entire image, including path 2, can be counted without setting a specific line. As another example, the number of times that weight values ​​are calculated by weight estimation using the above-mentioned method, or the number of times that a representative value is calculated by statistical processing if weight estimation is performed multiple times for one livestock, can also be counted as the number of livestock. In other words, if there are no overlaps in the livestock to be counted, the number of times that weight estimation is performed can also be used as the number of livestock.

[0043] The region of interest for counting livestock is not limited to the counting line CL, but may be a region of interest specified at any position. For example, it is possible to count the number of livestock in a lot, reset the count, and then count the number of livestock in the next lot. Simply, it is possible to count the livestock belonging to a lot by counting all livestock whose body parts pass through the region of interest from the start to the end of the measurement. Furthermore, the following measures can be taken to prevent counting errors. For example, as shown in FIG. 5 , a counting box CB the size of a pig is set as the region of interest, and the counting box CB is compared with a bounding box BB recognized as a pig. Then, when the bounding box BB recognized as a pig passes through the counting box CB, the pig is considered to have passed through and one pig is counted. Other counting methods will be described later.

[0044] The indicator device 20 is installed so that a human worker on-site can visually and audibly identify that livestock passing through the single livestock path 71 have been assigned to one of the weight classes based on a predetermined standard.

[0045] FIG. 6 shows an example of data specifying a numerical range representing the estimated weight classification for each class, the corresponding class, and the corresponding color and sound information. It is preferable to divide the classes into at least three types. This is because if there are three or more types of classes, there will be classes in a range between an upper limit and a lower limit. In this example, for example, Class 1 is defined as being under 275 pounds. No lower limit is defined for Class 1. Class 2 corresponds to pigs weighing 275 pounds or more but less than 285 pounds. Class 3 corresponds to pigs weighing 285 pounds or more but less than 295 pounds. Class 4 corresponds to pigs weighing 295 pounds or more. Such class configurations are also possible with four or more classes. While the numerical range for each class is defined as 10 pounds in the example of FIG. 6, it does not have to be uniform. As will be described later, weight ranges corresponding to premium prices can be set. For example, it is possible to classify the weights as follows: Class 1 is under 275 pounds, Class 2 is between 275 and 280 pounds, Class 3 is between 280 and 290 pounds, which corresponds to a premium price, Class 4 is between 290 and 295 pounds, and Class 5 is 295 pounds or more.

[0046] For reference, the wavelength information of the light that expresses the color is provided for the colors corresponding to the classes. Audio data for notifying the color is also specified. This allows classification based on the estimated weight and the weight category of this data and notification. Such data may be stored in any of the storage devices that make up the system. Examples of data are not limited to this, and relationships can also be referenced by adopting a graph database as a relational database or a non-relational database, expressed using nodes, edges, and properties.

[0047] The indicator device 20 may be, for example, an indicator or projector device having a light source such as an LED or lamp, and may emit light of a predetermined color onto the single livestock path 71. The type of color that should be emitted will be described later. Alternatively, the indicator device 20 may be an image display device such as a liquid crystal display or an OLED display, in which case it may display light of a predetermined color, or may be installed in a location where it is directly visible to users. More simply, the indicator device 20 may be a lamp, stack light, or signal tower that emits a predetermined light. The indicator device 20 may also be a speaker or audio generating device that generates a sound corresponding to the color, thereby notifying people on site through their ears.

[0048] When classification is communicated by color, the color must be one that livestock cannot visually distinguish. For example, pigs are said to be red-green color blind, meaning they cannot distinguish between red and green. By using such colors, pigs can be guided without being scared, even when color signs are switched on and off at the site.

[0049] The light-emitting parts such as the LED lamps of the indicator 20 may be installed in a range that is out of the field of view of the pig when it is walking normally. For example, assuming that the eye height of an adult pig when it is walking normally is 70 cm to 90 cm, which is the same as shoulder height, the indicator 20 may be installed at a height that is 1 m or more away from the walking surface.

[0050] The marking device 40 is installed for the same purpose as the indicator device 20, and is used to apply a mark of a predetermined color to the body surface of livestock. Specifically, it may be an ink roller, with ink of a predetermined color filled around the roller, and as the roller descends, it comes into contact with the body surface of the livestock, such as the back, and can apply a mark of the predetermined color to livestock passing through the single livestock path 71. Unlike notifications made by the indicator device 20 only at the moment the livestock pass, such marks can be applied as marks that are continuously visible to humans even after the notification has ended. Examples of using the marking device 40 will be described later.

[0051] Returning to Figure 2 again, the flow of the selection process using the system for selecting livestock for shipment of the present disclosure will be described using the above configuration. Also, Figure 7 is a flowchart showing the flow of the process of the method for selecting livestock for shipment of the present disclosure.

[0052] In the information processing described below, for example, for the calculation of weight estimation, the first computing device 10A may be selected as an edge computer having the necessary computational resources, as described above. If the computing power is sufficient, one computing device may be used, but if it is insufficient, the computational resources of multiple computing devices connected via a network NW may be utilized. Furthermore, the first computing device 10A may be used not only as a computational resource but also as data storage.

[0053] The matters described below are implemented by having the processor 14 execute an application program based on application data stored in the storage device 15 of any of the computing devices described above, thereby performing operations in accordance with instructions and realizing functions through the cooperation of software and hardware resources.

[0054] When a user issues an instruction via the input user interface 12 to send a signal to start measuring weights for selecting livestock for shipping, the camera 30 sends a photographing instruction signal to photograph the livestock passing through the single livestock path 71. The user who sends such an instruction may be, for example, a farm worker or an operator who operates equipment on behalf of the farm, and may regularly measure the weights of livestock as part of their daily routine. As a more specific example, although not shown, the measurement start signal may be sent by pressing a measurement start button displayed on the screen of a computing device with a touch panel.

[0055] After the measurement start state is reached, in step S101, the livestock are guided to move in one direction along the path. It is preferable that the livestock are guided by an on-site worker so that they pass through the single livestock path 71 one by one at a predetermined speed.

[0056] Next, in step S102, one or more cameras 30 photograph the livestock from above the path 2. This allows an overhead image of the livestock whose weight is to be estimated to be obtained.

[0057] Next, in step S103, one or more computing devices equipped with one or more processors estimate the weight of each livestock animal using the images captured by the camera 30, and output the estimated weight of each livestock animal.

[0058] The intermediate processing exemplified here may be as follows. For example, using an image acquired from the camera 30, an area where livestock exist is independently extracted from the pixels or point cloud or depth map included in the image. Simply put, the livestock included in the image are identified. This may be called a livestock area coordinate group. Alternatively, an area where livestock exist may be extracted from the acquired depth map or depth information, and the extracted area may be used as a mask. The mask centroid can be obtained from the mask. The mask centroid may be used as the central coordinate of the livestock for tracking.

[0059] When using images to identify livestock region coordinate groups, masks, etc., machine learning and deep learning techniques such as feature extraction and classification are generally used. Even general object detection models are capable of recognizing and segmenting object shapes from visual features such as the object's contour, texture, and shape. To further avoid misrecognition, additional learning and reinforcement learning may be performed using a dataset containing images of livestock. Furthermore, pigs may also be identified using pose models specialized for quadrupedal animals, not just livestock.

[0060] A temporary ID may be assigned to livestock identified through such image analysis (or images of livestock, point clouds of livestock, three-dimensional images of livestock, livestock masks, livestock mask centers of gravity, and other coordinates of tracked livestock). Pigs raised on farms utilizing ICT may be assigned and managed with individual IDs. While there are technologies for individually authenticating the individual IDs of such pigs, such as using two-dimensional codes or labels attached to ear tags, the temporary ID referred to here is a temporary ID that differs from such individual IDs. This is because identifying individual IDs requires more advanced technology, which increases costs, and the present disclosure is sufficient to locate livestock walking along a limited path. Furthermore, livestock such as pigs move quickly, making tracking difficult when they are out of the field of view. If a pig reappears on the screen, a new ID will be assigned, making temporary IDs more efficient. In this way, once a temporary ID is assigned to an identified pig, the pig with the temporary ID can be automatically and continuously tracked.

[0061] Various techniques for improving the accuracy of livestock weight estimation will be described later. The techniques described later are used in the weight estimation step.

[0062] Here, the number of identified livestock assigned temporary IDs can be counted by detecting whether their center coordinates, center of gravity coordinates, or specific feature points indicating body parts pass through a count line set on the image, as described above. The number of livestock may be counted in step S104. Regarding the counting of livestock, the number of livestock may be increased when the tracked mask center of gravity passes through the region of interest. Furthermore, the mask center of gravity may also include height information obtained from depth information, and if the mask center of gravity is below a predetermined height, such as a pre-set height, the livestock may not be counted as livestock. Using the mask center of gravity can reduce apparent blurring due to livestock movement. Compared to object detection using a rectangular bounding box set to enclose the livestock region coordinate group, this method has the advantage of improving tracking stability because it is not dependent on changes in the rectangular outline. In this way, height information may be used to filter out objects to be counted, and a test may be performed at a predetermined height to ensure accurate counting. For altitude filtering, flexible settings are available, including manual input of a default value, selection of a preset, or automatic setting based on prior measurement. This allows for optimal detection for various environments and target livestock. Another method for filtering using livestock height is to take the difference between the floor height obtained in the floor measurement described below and the livestock's body height, center, or center of gravity. However, for quadrupedal livestock, the depth information indicates infinity below the livestock area. Therefore, while it is possible to fix the ground position and take the difference as described above, this method does not capture the space other than the legs, so using the mask center of gravity has the advantage.

[0063] Next, in step S105, one or more computing devices use the weight class information stored in the storage device and the estimated weight information to determine and output weight class information of the livestock that matches the estimated weight information.

[0064] Next, in step S106, the indicator device 20 displays the weight class information of the livestock in accordance with the weight class information, or the marking device 40 marks the weight class information on the body surface of the livestock in accordance with the weight class information.

[0065] This allows on-site workers to easily understand into which weight class livestock whose weights have been estimated should be sorted, and enables livestock L1 to be immediately and physically sorted on the spot after passing through the single livestock path 71. For example, it is possible to reorganize the group of pigs to be shipped into weight bands that are color-coded according to weight thresholds depending on the purpose, and even when maintaining the individuals that make up the lot, it is possible to sell lots with an appropriate weight distribution to appropriate buyers.

[0066] The estimated weight of each individual pig and the number of pigs may be used to generate aggregate information for any group of pigs. An example of the aggregate information is a histogram of the number of pigs and their weights. This aggregate information is used to create a shipping plan, which will be described later. This aggregate information can also be output in a predetermined data format via the output user interface 13.

[0067] This concludes the explanation of the basic process flow of the method for selecting livestock for shipping of the present disclosure. Below, applications of the method for selecting livestock for shipping of the present disclosure will be described.

[0068] Figure 8 is a diagram showing an application example of the shipping livestock sorting system of the present disclosure. In this figure, the basic configuration is the same as that shown in Figure 2, so a description of the same configuration will be omitted. A distinctive configuration in Figure 8 is the multiple single livestock passes 71, 71 formed by partition walls 74.

[0069] Even if the camera 30 captures multiple livestock in an image, it is possible to simultaneously estimate the weights of multiple livestock by using object-distinguishing techniques such as instance segmentation. However, for more accurate weight estimation and for livestock guidance and safety on-site, it may be preferable to configure the single livestock path 71 with multiple lanes. Measuring each livestock individually improves the accuracy of weight estimation. Furthermore, individual computing resources, such as edge computers, can be concentrated and allocated to estimating a single livestock. Furthermore, considering the display on the indicator 20 indicating the class to which the estimated weight of the livestock is assigned and the speed of human perception to identify this, such an organized configuration may be preferable. Increasing the number of lanes also has the effect of improving throughput.

[0070] In this case, multiple indicators constituting the indicator device 20 are installed, and it is possible to display images taken by the camera 30 in each lane, weight estimated based on those images, and colors corresponding to classes based on the estimated weight.

[0071] Figure 9 is a diagram showing yet another application example of the shipping livestock sorting system of the present disclosure. In this figure, the basic configuration is the same as that shown in Figure 2, so a description of the same configuration will be omitted. A distinctive configuration in Figure 9 is the gradient on the single livestock path 71 formed by an ascending slope 75 and a descending slope 76.

[0072] This system takes advantage of the fact that pigs have no problem climbing uphill but have difficulty climbing downhill. Specifically, an ascending slope 75 is installed in front of the entrance to the single livestock path 71, and a descending slope 76 is installed at the exit. A flat floor 77 of an appropriate length may or may not be installed between the ascending slope 75 and the descending slope 76. The angle between the ascending slope 75 and the descending slope 76 and the floor surface before installation may be between 2° and 15°. A larger angle increases the likelihood of pigs becoming frightened or falling, resulting in an accident. This makes pigs that easily enter the single livestock path 71 from the ascending slope hesitate to go downhill and remain in the path for a longer period of time, thereby ensuring time for capturing images for weight estimation and limiting the pigs' activity within the single livestock path 71. Different inclination angles may also be used for the ascending slope 75 and the descending slope. For example, by making the inclination angle of the descending slope 76 greater than that of the ascending slope 75, the pigs will hesitate at the exit side, causing the line to stagnate. Conversely, by making the inclination angle of the descending slope 76 smaller than that of the ascending slope 75, the traveling speed can be controlled. Furthermore, the ascending slope 75 and the descending slope 76 may be treated to prevent slipping. For example, grooves may be formed on the surface of the material, or a material such as rubber that can prevent slipping may be used. This improves the accuracy of weight estimation and further ensures the safety of workers.

[0073] Such ascending slopes 75 and descending slopes 76 can also be used when a single livestock path 71 is configured with multiple parallel lanes. The disadvantage of providing a slope, which reduces throughput, can be compensated for by providing multiple lanes, creating a synergistic effect when combined.

[0074] Figure 10 is a diagram showing yet another application example of the shipping livestock sorting system of the present disclosure. In this figure, the basic configuration is the same as that shown in Figure 2, so a description of the same configuration will be omitted. A distinctive configuration in Figure 10 is a labeling device 40 that is installed instead of or in addition to the indicator device 20.

[0075] FIG. 11 is a diagram showing an example of a marking device. The marking device 40 is an ink application device such as an ink roller, and a roller 41 filled with ink is lowered in response to an instruction signal from a computing device constituting the system 1, and can apply ink by contacting the body surface, such as the back, of the livestock L1. Alternatively, a sensor, such as an infrared sensor, that detects the passage of livestock below may be provided, so that a roller 41 of a predetermined color descends upon detecting the passage of the livestock. Alternatively, a human worker on-site may look at the color of the indicator 20 and manually operate the roller 41 to apply ink.

[0076] When multiple lanes of single livestock paths 71 are arranged in parallel, each single livestock path 71 may be provided with a tagging device 40, or multiple tagging devices 40 may be provided in a vertical row along the direction of travel. This arrangement allows for a greater number of tags to be tagged with different colors. Furthermore, when a slope is provided, a tagging device 40 may be provided at the top of a flat area just before the downhill slope. This has the synergistic effect of allowing tags to be tagged when the pigs are stationary.

[0077] The ink used to apply the labels may be, for example, livestock marker paint, which is non-toxic and safe for animals. Methods using ink are non-invasive and preferable from the perspective of animal welfare. By using an ink roller, there is no need to worry about malfunctions due to clogging of the spray or harmful gases. As a result, the labels remain on the livestock's body surface even after the display on the indicator device 20 has finished, allowing on-site personnel to identify the class to which each livestock has been assigned.

[0078] Next, tilt correction will be described as an attempt to improve the accuracy of weight estimation using images. As described above, if the camera 30 is equipped with an inertial measurement unit such as an IMU, the tilt of the camera itself can be corrected by detecting and calibrating it. However, the horizontality of the surface on which the pig walks cannot be detected by the camera's IMU. Therefore, as an applied example, a tilt correction function that is possible when the camera 30 is a device that can acquire distance images, such as a stereo camera, will be described.

[0079] If the camera 30 is a device capable of acquiring distance images, such as a stereo camera, a Time of Flight camera, a structured illumination 3D camera, a LiDAR scanner, or a 3D point cloud scanner, it is possible to acquire the distance from the camera to a specified point on the overhead image. FIG. 12 illustrates a case in which the computing device 10A or the computing device 10C is equipped with a touch panel display and displays an operational screen P1 on the touch panel display. This operational screen P1 may be operable on the computing device 10A or the computing device 10C, for example, as a preparation step before weight estimation. In the example of the operational screen P1 in FIG. 12, livestock L1 enters from the left side of the path and exits to the right. Therefore, the left side is the entrance side and the right side is the exit side.

[0080] On the operational screen P1, a user can specify an image area within the entire screen to be used for weight estimation by operating the touch panel with a finger to specify an area or a point, or by operating a mouse to move a pointer to specify an area or a point. These operations specify the top edge line AATL, bottom edge line AABL, right edge line AARL, and left edge line AALL of the analysis area, and the area enclosed by these lines becomes the analysis area AA. This limits the subjects of weight estimation to only those livestock captured within the analysis area AA. Livestock captured in areas outside these, i.e., the left and right restricted areas LRLA1 and LRLA2, and the top and bottom restricted areas ULLA1 and ULLA2, are not considered for weight estimation. One reason for imposing such restrictions is that, for example, when attempting to estimate weight using the passage between pigpens in a piggery, pigpens facing the passage may be reflected above and below the captured image, potentially resulting in the capture of pigs that are not the subject of weight estimation. Furthermore, by setting such restrictions, unnecessary images can generally be removed, improving the accuracy of estimation. The method and design of the analysis restriction area are not limited to the above example, and it can also be circular, elliptical, or trapezoidal. Furthermore, as a method for filtering out pigs that are not the subject of weight estimation, a depth camera is used to acquire depth information within a predefined region of interest. By explicitly specifying the observation range on the path, this region of interest can exclude livestock outside the aisle that are not subject to measurement. Furthermore, a region of interest can also be set in the vertical direction, allowing for three-dimensional filtering.

[0081] After the analysis area is designated as described above, the user can specify at least two points within the analysis area AA on the operational screen P1 to estimate the slope of the pig's walking surface within the analysis area AA. For example, in FIG. 12, a slope detection line TDL1 is generated by specifying a point on the entrance side of the analysis area AA. This is because, if the analysis area AA is a group of pixels constituting an XY plane, a straight line with the same X coordinate as the designated point on the plane can be generated. This allows for automatic setting of slope detection points TDP11, TDP12, and TDP13. The slope detection point TDP11 is the intersection of the slope detection line TDL1 and the analysis area top line AATL. The slope detection point TDP12 is the intersection of the slope detection line TDL1 and the analysis area bottom line AABL. The slope detection point TDP13 is the midpoint between the slope detection points TDP11 and TDP12 on the slope detection line TDL1. Similarly, by specifying one point on the exit side, a tilt detection line TDL2 and tilt detection points TDP21, TDP22, and TDP23 are automatically generated. Furthermore, by specifying one arbitrary point near the center, a tilt detection line TDL3 and tilt detection points TDP31, TDP32, and TDP33 may be automatically generated.

[0082] The camera 30, which is a device capable of acquiring distance images such as a stereo camera, a ToF camera, a structured illumination 3D camera, a LiDAR scanner, or a 3D point cloud scanner, can acquire the distance between the camera 30 and the walking surface at each of these tilt detection points. The distance may be acquired as the length of the distance to each tilt detection point, or as the height of each tilt detection point. Here, the height of each tilt detection point is taken into consideration.

[0083] The inclination of the walking surface or the inclined plane can be estimated from the height of each tilt detection point. When estimating a plane, it can be estimated from three points at the smallest unit. Therefore, if the heights of at least two or more tilt detection lines and the points above and below them, a total of four or more tilt detection points, can be obtained, a simple plane can be estimated. When three points are used, the plane can be estimated using a method of deriving a plane equation using vectors or a simultaneous equation. When four or more points are used, the plane can be estimated using methods such as the least squares method, RANSAC, SVD, and TLS. Once the plane can be determined, the normal vector of the plane can be used as the inclination.

[0084] In the example of Figure 12, the walking surface can be estimated using, for example, nine inclination detection points. These nine points are preferably distributed so as to represent each of the nine divided areas when the analysis area AA is divided as much as possible. By using nine points in this way, the influence of outliers can be removed when estimating a simple plane, allowing for a more reliable estimation of the inclination of the walking surface. Furthermore, a composite surface may be estimated using nine points. For example, by connecting each of the nine points, a walking surface consisting of four planes is generated. The entire walking surface may then be estimated as a composite surface of the four walking surfaces.

[0085] The estimated weight can be corrected using the estimated inclination of the walking surface. FIG. 13 is a diagram illustrating the correction of estimated weight based on the inclination of the walking surface. For example, a feature point group FPC including multiple feature points FP1 and the like in a three-dimensional space having height information can be extracted from an image of a pig captured by camera 30. Such a feature point group is the main three-dimensional position information of the pig's head, back, tail, and the like, which can be obtained from an overhead image. The principal axis of such a feature point group is determined, the direction of the normal to the walking surface is determined as the inclination, and the angle between the principal axis of the feature point and the direction of the normal to the walking surface is calculated. A rotation matrix is ​​then created to align the angles of the two axes. Then, by applying the rotation matrix to all of the feature point group to transform their positions, the inclination of the feature point positions can be corrected. Estimating the weight of a livestock using the corrected feature point group CFPC including the corrected feature points CFP1 and the like corrected in this way allows the weight to be estimated with the walking surface corrected to a flat surface, thereby improving the accuracy of the estimated weight.

[0086] Finally, the generation of a shipping plan using the weight distribution of any group of pigs output by the pig weight estimation function and the pig head counting function will be described. By using the pig weight sorting system for assisting pig shipping plans of the present disclosure, the generation of a specific shipping plan can also be automated using a computer device.

[0087] 14 shows an example of the weights and numbers of pigs in weight-classified groups output using the system of the present disclosure. For example, it shows the weights and classes of pigs in groups 1, 2, and 3 (15 pigs each) and their distribution.

[0088] FIG. 15 shows an example of purchase prices for pigs by weight class, which are predetermined based on a contract with, for example, a packer. In this figure, buyers 1 to 3 are, for example, packers. Each buyer offers a different purchase price for each weight class. Premium classes are also provided. For example, buyer 1 sets a premium price for class 3, buyer 2 sets a premium price for class 4, and buyer 3 sets a premium price. Each buyer may also set purchasing constraints in the contract, and these constraints may also be included as data. For example, buyer 1 purchases 10 or more pigs per group. Buyer 2 purchases 15 or more pigs per group. Buyer 3 purchases only if there are 12 or more pigs in classes 2 to 4. Such data may be stored in the storage of several computing devices.

[0089] By processing this data using a computing device, an optimal shipping plan can be generated. One or more processors in several computing devices calculate which groups of livestock should be sold to which buyers to maximize sales, thereby generating an optimal shipping plan. In this process, the weight distribution of each group and other constraints are taken into consideration. For example, in Group 3 shown in Figure 14, there are nine pigs belonging to classes 2 to 4. This makes it impossible to ship the pigs while satisfying the contractual constraint requested by Buyer 3-2, which is to "ship at least 12 pigs from classes 2 to 4." The optimal shipping plan is generated by calculating how to allocate the number of pigs by class to maximize sales while satisfying the contractual conditions (constraints) with each buyer. In this process, prices by weight and premium prices can be referenced.

[0090] Therefore, by information processing of the computing device, the processor receives data including: estimated data on the number of pigs belonging to a plurality of pig groups and the weights of all the pigs, provided from a weight estimation device that estimates the weights of individuals belonging to a plurality of pig groups raised on a farm in a non-contact manner using images; the number of pigs to be purchased by each of the plurality of packers, which is predetermined in contract condition data, provided from a database; purchase price data according to pig weights offered by the plurality of packers (including premium price data for pigs within a specific weight range); and the processor calculates the following items for each of the plurality of packers: the purchase price of any of the pig groups. a potential sales forecast for each packer if the saleable pigs are sold based on price data (including premium price data for pigs within a specific weight range); the processor compares potential pig sales revenues to the multiple packers based on the number of saleable pigs and the potential sales forecast for the given pig group; the processor, as a result of the comparison, selects a packer that will maximize pig sales revenues if the given pig group is sold at the time the comparison is made, and creates a shipment plan for the given pig group to the selected packer, thereby optimizing the shipment plan for the given pig group from a farm to multiple packers.

[0091] Some embodiments and other implementations of the disclosure can optionally include one or more of the following features.

[0092] In some embodiments, a system for sorting livestock for shipping comprises: a path along which livestock move in one direction; one or more cameras that photograph the livestock from above the path; one or more computing devices with one or more processors; and one or more computer-readable recording media that store instructions, which, when executed by the one or more processors, cause the one or more processors to perform a plurality of operations, including estimating the weight of the livestock using images taken by the cameras and outputting estimated weight information of the livestock; and using weight class information stored in a storage device and capable of sorting the livestock into three or more classes according to weight and the estimated weight information of the livestock to determine and output weight class information of the livestock that matches the estimated weight information of the livestock; and further comprises: a display device that displays the weight class information of the livestock according to the weight class information, or a marking device that affixes a physical mark using paint related to the weight class information to the body surface of the livestock according to the weight class information.

[0093] In some embodiments, the path further includes a temporary guide that is temporarily installed to form one or multiple parallel single livestock paths through which only one livestock can pass.

[0094] In some embodiments, the display relating to the weight class information of the livestock in accordance with the weight class information is an illuminating display in a color corresponding to the weight class information, or the mark relating to the weight class information on the body surface of the livestock in accordance with the weight class information is an ink application in a color corresponding to the weight class information, and all of the colors corresponding to the weight class information are colors that the livestock cannot visually distinguish.

[0095] In some embodiments, the system further comprises an ascending slope at the entrance of the single livestock pass and a descending slope at the exit of the single pass.

[0096] In some embodiments, a plateau is formed between the ascending and descending slopes.

[0097] In some embodiments, the first computing device is an edge computer, and is equipped with at least one of a graphics processing unit (GPU), a tensor processing unit (TPU), and a neural processing unit (NPU), and has a predetermined or greater image processing capability and a predetermined or greater video memory, thereby enabling image analysis processing locally without borrowing computational resources from other computing devices via a network.

[0098] In some embodiments, the camera is a camera capable of acquiring distance images, and when outputting the estimated weight of the livestock using the distance image captured by the camera, the inclination of the surface on which the livestock walks is estimated using at least four or more inclination detection points of the surface on which the livestock walks obtained from the distance image, and the estimated weight of the livestock corrected using the inclination is output.

[0099] In some embodiments, the first computing device or the second computing device has a function for operating an operation screen using a touch panel, and an analysis area for limiting the images used to estimate the weight of livestock can be specified by touching and swiping.

[0100] In some embodiments, the system is equipped with a counting function for counting livestock that pass through a region of interest set in the analysis region. In some embodiments, livestock can be counted using the center of gravity of a pig mask generated using depth information acquired from a stereo camera. When the height information of the center of gravity of a pig mask is equal to or greater than a predetermined height, the number of pigs can be counted.

[0101] In some embodiments, the livestock counter can output the number of livestock in any group.

[0102] In some embodiments, a method implemented by a computing device having one or more processors for optimizing a shipping plan for an arbitrary pig group consisting of multiple pigs from a farm to multiple packers, the method including the following steps: the processor receiving data including: estimated data on the number of pigs belonging to multiple pig groups and the weights of all pigs, provided from a weight estimation device that estimates the weights of individuals belonging to multiple pig groups raised on a farm using images in a non-contact manner; the number of pigs that each of the multiple packers will purchase, as predetermined in contract condition data, provided from a database; purchase price data according to pig weights (for pigs within a specific weight range) offered by the multiple packers. the processor calculating, for each of the plurality of packers, the following items: a potential sales forecast for each packer if the saleable pigs for the given group of pigs are sold based on the purchase price data (including premium price data for pigs within a specific weight range); the processor comparing the potential pig sales revenue to the plurality of packers based on the number of saleable pigs and the potential sales forecast for the given group of pigs; and the processor selecting, as a result of the comparison, a packer that maximizes pig sales revenue if the given group of pigs is sold at the time the comparison is made, and creating a shipping plan for the given group of pigs for the selected packer.

[0103] Although several implementations have been described and illustrated herein, various other means and / or structures may be utilized to perform the functions and / or obtain one or more of the results and / or advantages described herein, and each such variation and / or modification is considered within the scope of the implementations described herein. More generally, it is intended that all parameters, dimensions, materials, and configurations described herein are exemplary, and that the actual parameters, dimensions, materials, and / or configurations will depend on the specific application or applications in which the teachings are used. Those skilled in the art will recognize and be able to ascertain, using no more than routine experimentation, many equivalents to the specific implementations described herein. Accordingly, it should be understood that the foregoing implementations are presented by way of example only, and that, within the scope of the appended claims and their equivalents, implementations may be practiced other than as specifically described and claimed. Implementations of the present disclosure are directed to each individual feature, system, article, material, kit, and / or method described herein. In addition, any combination of two or more such features, systems, articles, materials, kits, and / or methods is included within the scope of the present disclosure, if such features, systems, articles, materials, kits, and / or methods are not mutually inconsistent.

[0104] 1 Livestock sorting system for shipping 2 Path 10 Computing device 11 Communication interface 12 Input user interface 13 Output user interface 14 Processor 15 Storage device 20 Display device 30 Camera 40 Marking device 41 Roller 70 Temporary guidance guide 71 Single livestock path 72 Rib 73 Temporary wall 74 Partition wall 75 Ascending slope 76 Descending slope 77 Flat floor

Claims

1. A method for sorting livestock to be shipped, comprising: a step of moving livestock in one direction on a path; a step of one or more cameras photographing the livestock from above the path; a step of outputting, by one or more computing devices equipped with one or more processors, an estimated weight of the livestock using the images taken by the cameras; a step of determining and outputting, by the one or more computing devices, weight class information stored in a storage device and capable of sorting the livestock into three or more classes according to weight, and weight class information of the livestock that matches the estimated weight, using the estimated weight; an instruction step in which an instruction device gives instructions regarding the weight class information of the livestock according to the weight class information, or a labeling step in which a labeling device attaches a physical label using paint related to the weight class information to the body surface of the livestock according to the weight class information.

2. A method for sorting livestock for shipping as described in claim 1, wherein the path is formed as one or multiple parallel single livestock paths through which only one livestock can pass, using temporary guidance guides that are temporarily installed.

3. A method for selecting livestock for shipment as described in claim 1, wherein the indication regarding the weight class information of the livestock in accordance with the weight class information is an illuminating display in a color corresponding to the weight class information, or the mark regarding the weight class information on the body surface of the livestock in accordance with the weight class information is an ink application in a color corresponding to the weight class information, and all of the colors corresponding to the weight class information are colors that the livestock cannot visually identify.

4. A method for sorting livestock for shipping according to claim 1, further comprising an ascending slope provided at the entrance of said path and a descending slope provided at the exit of said path.

5. The method for selecting livestock for shipping as described in claim 1, wherein the camera is a camera capable of acquiring distance images, and when outputting the estimated weight of the livestock using the distance images taken by the camera, the inclination of the walking surface of the livestock is estimated using at least four or more inclination detection points of the walking surface of the livestock acquired from the distance images, and the estimated weight of the livestock corrected using the inclination is output.

6. A livestock sorting system for shipping, comprising: a path along which livestock move in one direction; one or more cameras that photograph the livestock from above the path; one or more computing devices equipped with one or more processors; and one or more computer-readable recording media that store instructions, which, when executed by the one or more processors, cause the one or more processors to perform a plurality of operations, the plurality of operations including: estimating the weight of the livestock using images taken by the cameras and outputting the estimated weight of the livestock; using weight class information stored in a storage device and capable of sorting livestock into three or more classes according to weight and the estimated weight of the livestock, to determine and output weight class information of the livestock that matches the estimated weight of the livestock; and an instruction device that gives instructions regarding the weight class information of the livestock according to the weight class information, or a marking device that affixes a physical mark in paint related to the weight class information to the body surface of the livestock according to the weight class information.

7. The shipping livestock sorting system according to claim 6, further comprising a temporary guide that is temporarily installed to form the path as one or multiple parallel single livestock paths through which only one livestock can pass.

8. A system for sorting livestock for shipping as described in claim 6, wherein the indication regarding the weight class information of the livestock in accordance with the weight class information is an illuminating display in a color corresponding to the weight class information, or the mark regarding the weight class information on the body surface of the livestock in accordance with the weight class information is an ink application in a color corresponding to the weight class information, and all of the colors corresponding to the weight class information are colors that the livestock cannot visually identify.

9. The shipping livestock sorting system according to claim 6, further comprising an ascending slope provided at an entrance of said path and a descending slope provided at an exit of said path.

10. The system for sorting livestock for shipping as described in claim 6, wherein the camera is a camera capable of acquiring distance images, and when outputting the estimated weight of the livestock using the distance images taken by the camera, the inclination of the surface on which the livestock walks is estimated using at least four or more inclination detection points of the surface on which the livestock walks obtained from the distance images, and the estimated weight of the livestock corrected using the inclination is output.

Images