Apparatus and method for calculating weight of livestock group, which reduce weight error

Abstract

Disclosed are an apparatus and a method for calculating the weight of a livestock group, wherein the apparatus and method reduce a weight error. The disclosed method for calculating weight is performed in a processor-based device, and includes the steps of: calculating a livestock area-based weight of a barn livestock group at a target time on the basis of an image of a zone acquired by a monitoring camera provided in a barn; calculating a trend-based weight of the barn livestock group at the target time on the basis of preset trend information; and calculating a barn livestock weight at the target time on the basis of the livestock area-based weight and the trend-based weight at the target time.

Description

Apparatus and method for calculating the weight of a group of livestock to reduce weight errors

[0001] Embodiments of the present invention relate to a device and method for accurately calculating the weight of a group of livestock by reducing weight errors of the group of livestock.

[0002] Poultry farming is one of the fastest-growing livestock industries, and its high economic viability has led to its adoption in most countries around the world, even those in developing countries. In particular, the domestic poultry market accounts for approximately 30% of domestic livestock production.

[0003] To achieve high production efficiency, chickens are raised in close proximity within a single farm. Farm managers monitor the weight of chickens by day and predict disease risk to manage the chicken population. Specifically, managers measure the weight of chickens by day to monitor changes in weight, thereby improving productivity.

[0004] Traditionally, managers would manually hold chickens, place them on scales, and measure their weight. However, this method suffers from inaccurate weight measurements, as the chickens constantly move around on the scale. Furthermore, because managers must manually measure the chickens, they require significant labor.

[0005] To address these issues, an image-based chicken weight prediction method has been developed. This method acquires images of chickens via a camera and predicts their weight based on the area of ​​the image. Specifically, accurate chicken weight prediction requires accurate measurements of the chicken's weight and images of the chicken with the measured weight.

[0006] However, as mentioned above, conventional methods often result in inaccurate measurements of chicken weight. Furthermore, managers must measure the chicken's weight and then take a direct image of the chicken with a camera, which creates inconvenience for managers.

[0007] The purpose of the present invention is to provide a device and method for accurately calculating the weight of a group of livestock raised in a farm and a livestock shed without error.

[0008] In addition, an object of the present invention is to provide an estimation device and method for accurately calculating the weight of a group of livestock by calculating the weight of the group of livestock using at least one of a livestock area-based weight, a trend-based weight, and a feed-based weight.

[0009] The objectives of the present invention are not limited to those mentioned above, and other objectives and advantages of the present invention not mentioned above can be understood through the following description and will be more clearly understood through the embodiments of the present invention. Furthermore, it will be readily apparent that the objectives and advantages of the present invention can be realized by the means and combinations thereof set forth in the claims.

[0010] A method for calculating the weight of a livestock group according to one embodiment of the present invention is performed by a processor device, and includes the steps of calculating a livestock area-based weight of a livestock group in a livestock shed at a target time based on an area image acquired from a surveillance camera installed in a livestock shed, calculating a trend-based weight of the livestock group in the livestock shed at the target time based on preset trend information, and calculating a livestock weight in the livestock shed at the target time based on the livestock area-based weight and the trend-based weight at the target time.

[0011] In addition, a method for calculating the weight of a livestock group according to another embodiment of the present invention is performed by a processor device, and includes, for each of a plurality of livestock houses included in a farm, a step of calculating the livestock weight of the livestock house at the target time based on the livestock area-based weight of the livestock house group at the target time and the trend-based weight of the livestock house group at the target time according to preset trend information, and a step of calculating the farm livestock weight for the farm livestock group at the target time based on the plurality of livestock house weights corresponding to each of the plurality of livestock houses.

[0012] In addition, a method for calculating the weight of a livestock group according to another embodiment of the present invention is performed by a processor device, and includes the steps of: setting a weight correction value at a target time; calculating an image-based weight of a livestock group in a livestock shed at the target time based on an area image acquired from a surveillance camera installed in each of a plurality of livestock sheds included in a farm; calculating a livestock weight in a livestock shed at the target time based on the image-based weight and the weight correction value at the target time for each of the plurality of livestock sheds; and calculating a farm livestock weight of a farm livestock group at the target time based on a plurality of livestock weights corresponding to each of the plurality of livestock sheds. At this time, the weight correction value is set based on a cumulative feed intake of the livestock group in the farm.

[0013] According to the present invention, the weight of a group of livestock raised in a farm or livestock shed can be accurately calculated without error.

[0014] In addition, the purpose of the present invention is to accurately calculate the weight of a group of livestock by calculating the weight of a group of livestock using at least one of a livestock area-based weight, a trend-based weight, and a feed-based weight.

[0015] In addition, the effects of the present invention are not limited to the above-described effects, and should be understood to include all effects that can be inferred from the composition of the invention described in the detailed description or claims of the present invention.

[0016] FIG. 1 is a schematic diagram illustrating a configuration of a weight estimation system for a livestock group according to one embodiment of the present invention.

[0017] FIG. 2 illustrates an example of an area image captured by a surveillance camera according to one embodiment of the present invention.

[0018] FIG. 3 is a diagram illustrating an example of relationship information between the breeding time and weight of a group of chickens according to one embodiment of the present invention.

[0019] FIGS. 4 and 5 are drawings illustrating examples of area images for explaining the concept of chicken density according to one embodiment of the present invention.

[0020] FIG. 6 is a flowchart illustrating a method for calculating the weight of a chicken group according to the first embodiment of the present invention.

[0021] FIG. 7 is a diagram for explaining a concept of calculating a trend-based weight at a target time using a trend line according to one embodiment of the present invention.

[0022] FIGS. 8 to 10 are flowcharts illustrating a method for calculating the weight of a chicken group according to a second embodiment of the present invention.

[0023] Fig. 11 is a flowchart illustrating a method for calculating the weight of a chicken group according to a third embodiment of the present invention.

[0024] FIG. 12 is a flowchart illustrating a method for calculating the chicken area-based weight of a group of chickens in a livestock shed at a target time, according to one embodiment of the present invention.

[0025] The present invention is susceptible to various modifications and embodiments. Specific embodiments are illustrated and described in detail in the drawings. However, this is not intended to limit the present invention to specific embodiments, but rather to encompass all modifications, equivalents, and alternatives falling within the spirit and technical scope of the present invention. Throughout the description of each drawing, similar reference numerals have been used to designate similar components.

[0026] While terms such as "first," "second," etc. may be used to describe various components, these components should not be limited by these terms. These terms are used solely to distinguish one component from another. The term "and / or" includes any combination of multiple related listed items or any one of multiple related listed items.

[0027] The terminology used herein is merely used to describe specific embodiments and is not intended to limit the present invention. The singular expression includes the plural expression unless the context clearly indicates otherwise. In this application, it should be understood that the terms "comprise" or "have" indicate the presence of a feature, number, step, operation, component, part, or combination thereof described in the specification, but do not preclude the possibility of the presence or addition of one or more other features, numbers, steps, operations, components, parts, or combinations thereof.

[0028] Unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. Terms defined in commonly used dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the relevant technology, and will not be interpreted in an idealized or overly formal sense unless explicitly defined herein.

[0029] Hereinafter, embodiments of the present invention will be described in detail with reference to the attached drawings. In this embodiment, the "livestock" is assumed to be chicken (broiler), a type of poultry. However, this embodiment can be equally applied to other poultry, such as ducks and geese, as well as other livestock.

[0030] FIG. 1 is a drawing schematically illustrating a configuration of a weight calculation system (1) for a livestock group according to one embodiment of the present invention.

[0031] Referring to FIG. 1, the weight calculation system (1) may include a plurality of surveillance cameras (10), a gateway server (20), and a cloud server (30).

[0032] A single farm may include multiple barns or pens. In one embodiment, two or more chickens (i.e., groups of chickens) of the same day age may be raised in close proximity within a barn. Furthermore, in another embodiment, each group of chickens within multiple barns may have the same day age. Thus, all chickens raised within a farm may have the same day age. However, the present invention is not limited thereto, and chicken groups raised within each barn may have different day ages.

[0033] Hereinafter, a group of chickens raised in a pen will be referred to as a "pen chicken group," and a group of chickens raised on a farm will be referred to as a "farm chicken group." Therefore, a farm chicken group may be comprised of multiple pen chicken groups.

[0034] Each of the plurality of surveillance cameras (10) may be installed or provided in each of the corresponding plurality of livestock sheds. For example, the surveillance cameras (10) may be CCTV cameras.

[0035] According to an embodiment, a surveillance camera (10) may be installed on the ceiling of a livestock shed, and the lens of the surveillance camera (10) may rotate or move 360°. In this case, when the lens is positioned vertically, the surveillance camera (10) may capture an image for a zone corresponding to the vertical direction, i.e., a zone image. In other words, the zone image may be a top view image for the zone.

[0036] Fig. 2 illustrates an example of an area image captured by a surveillance camera (10). Referring to Fig. 2, the area image in the form of a top view may include the shapes of multiple chickens among a group of chickens in a barn.

[0037] The surveillance camera (10) can repeatedly capture area images based on a preset cycle. For example, the capture cycle may be 5 minutes.

[0038] Meanwhile, the filming cycle may vary depending on the chicken's age. For example, as the chicken ages, the filming cycle may become shorter.

[0039] Depending on the size of the livestock house, one or more surveillance cameras (10) may be installed in the livestock house. For convenience of explanation, it is assumed that one surveillance camera (10) is installed in the livestock house.

[0040] The surveillance camera (10) can transmit the captured area image to the gateway server (20). For this purpose, the surveillance camera (10) can include a communication unit.

[0041] The gateway server (20) may be an edge terminal provided on the farm side.

[0042] The gateway server (20) can receive area images captured by multiple surveillance cameras (10), calculate the weight of each chicken group in each of multiple livestock pens based on the received area images, and calculate the weight of each chicken group in the farm based on the weight of each chicken group in the multiple livestock pens. This will be described later.

[0043] Although not shown in FIG. 1, the gateway server (20) may include a communication unit, memory, and a processor.

[0044] The communication unit of the gateway server (20) can be connected to a surveillance camera (10) and a cloud server (30). For example, the communication unit of the gateway server (20) can include at least some of a wired communication module, a short-range wireless communication module, and a long-range wireless communication module.

[0045] The memory of the gateway server (20) may be volatile and / or non-volatile memory and may store commands or data related to at least one other component of the gateway server (20). In particular, the memory of the gateway server (20) may store commands or data related to a computer program, application, recording medium, etc. executed in the gateway server (20).

[0046] The processor of the gateway server (20) may include one or more of a central processing unit, an application processor, or a communication processor. The processor of the gateway server (20) may perform calculations or data processing related to the control and / or communication of at least one other component of the gateway server (20). In particular, the processor of the gateway server (20) may execute instructions of a computer program / application.

[0047] Referring again to FIG. 1, the cloud server (30) may be a central terminal provided on the external side of the farm.

[0048] Similar to the gateway server (20), the cloud server (30) may include a communication unit, memory, and a processor. A detailed description thereof is omitted.

[0049] The cloud server (30) can learn an integrated algorithm model used to estimate the weight of a group of chickens in a barn, and transmit the learned integrated algorithm model to the gateway server (20). Here, the integrated algorithm model can be used to calculate the weight of a group of chickens in a barn based on area images. Learning can be performed periodically, and the integrated algorithm model can be updated accordingly.

[0050] Although not shown in Fig. 1, the cloud server (30) can be connected to multiple gateway servers (20) provided in each of multiple farms, and thus can monitor the breeding status of groups of farm chickens raised in each of the multiple farms.

[0051] Meanwhile, according to another embodiment, the calculation of the weight of the barn chicken group and the weight of the farm chicken group can be performed in the cloud server (30) rather than the gateway server (20), and the learning of the integrated algorithm model can be performed in the gateway server (20) rather than the cloud server (30). That is, the weight calculation device of the chicken group can be the gateway server (20) or the cloud server (30), and the learning device of the integrated algorithm model can also be the gateway server (20) or the cloud server (30).

[0052] Hereinafter, the operation of the weight calculation device and learning device will be described in more detail. For convenience of explanation, the weight calculation device is assumed to be a gateway server (20), and the learning device is assumed to be a cloud server (30).

[0053] FIG. 3 is a diagram illustrating an example of relationship information between the breeding time and weight of a group of chickens according to one embodiment of the present invention.

[0054] The rearing time-weight relationship information illustrated in Figure 3 represents the relationship between the rearing time (i.e., age) of a group of chickens raised in a specific barn within a farm and the weight of the group of chickens raised in the barn according to that rearing time. The relationship information illustrated in Figure 3 can also be similarly derived for a group of farm chickens raised within a farm.

[0055] In addition, the "weight" described in FIG. 3 may be a chicken area-based weight calculated using a zone image acquired from a surveillance camera (10) of a specific livestock farm. Here, as described above, the zone image is a top-view image, and the chicken area may correspond to the chicken size according to the top view. In other words, the relationship information of FIG. 3 may be derived based on chicken area-based weight information that changes over the breeding time.

[0056] Specifically, a plurality of area images sequentially or periodically captured by a surveillance camera (10) can be used to calculate a weight based on the area of ​​a chicken at a target time (e.g., the current time). The gateway server (20) extracts the shapes of a plurality of chickens from the area images, calculates the areas of the plurality of chickens from the shapes of the plurality of chickens, and inputs each area of ​​the plurality of chickens into a pre-learned integrated algorithm model to calculate the weight based on the area of ​​each of the plurality of chickens. This will be described in more detail below.

[0057] Meanwhile, referring to FIG. 3, multiple phases can be defined based on the rearing time of a group of chickens in a barn.

[0058] Phase A is the phase in which chicks can be introduced into the barn. For example, Phase A may be the rearing period corresponding to days 1 to 8 of age.

[0059] Phase B, which immediately follows Phase A, may be a phase in which the physical abilities of a group of chickens in a barn gradually develop. For example, physical abilities may correspond to the chickens' jumping ability. That is, in Phase B, most of the chickens in a barn group are unable to climb to the top of a specific object (e.g., a weighing device) located above the barn floor. For example, Phase B may correspond to the rearing period from 8 to 15 days of age.

[0060] Phase C (i.e., the first rearing period) is the phase immediately following Phase B, during which most of the chickens in the barn group can reach the specified target. Furthermore, Phase C may be a phase before the preset critical rearing time (or critical age) has arrived. For example, Phase C may be a rearing period corresponding to the critical rearing time from 15 days of age.

[0061] In an embodiment, the critical breeding time may be the earlier of the time when the area-based weight of a group of chickens in a barn exceeds a preset threshold weight and the time when the chicken density of the group of chickens in a barn exceeds a preset threshold density. That is, in Phase C, the area-based weight of the chickens may be less than or equal to the threshold weight, and the chicken density may be less than or equal to the threshold density.

[0062] A region image contains two or more chickens, and the chicken density can correspond to the ratio of the total area of ​​the region image to the area of ​​the region image where two or more chickens exist. Therefore, the chicken density can have a value between 0 and 1. Alternatively, the chicken density can be calculated as "1 - (the ratio of the total area of ​​the region image to the area of ​​the region image where two or more chickens do not exist)".

[0063] In an embodiment, the critical weight may be any weight within a weight range of 1000 g or greater. For example, the critical weight may be 1400 g. However, the present invention is not limited thereto.

[0064] In an embodiment, the critical density may be any density within a density range of 0.6 to 0.7. For example, the critical density may be 0.65. However, the present invention is not limited thereto.

[0065] Figure 4 shows an example of an area image where the chicken density is lower than the critical density, and Figure 5 shows an example of an area image where the chicken density is higher than the critical density.

[0066] Referring to Fig. 4, within the area image, the area (i.e., size) of chickens proportional to their weight is somewhat small, and thus the chicken density is less than the critical density. Furthermore, referring to Fig. 5, within the area image, the area of ​​chickens proportional to their weight is somewhat large, and thus the chicken density is greater than the critical density. Meanwhile, the chickens included in the area image of Fig. 5 are older than the chickens included in the area image of Fig. 4.

[0067] Phase D (i.e., the second rearing period) is the phase immediately following Phase C, and is a phase that starts at the critical rearing time (or critical age) described above. In other words, the start time of Phase D may be the time when the area-based weight of a group of chickens in a barn exceeds the critical weight or the time when the chicken density exceeds the critical density.

[0068] Hereinafter, for convenience of explanation, the starting point of Phase D is assumed to be "the point at which the chicken density is greater than the critical density." Therefore, the area image in Fig. 5 is assumed to be an area image captured during Phase D.

[0069] Referring to Fig. 5, when the chicken density exceeds a critical density, the shape of a chicken (indicated by a rectangular boundary) overlaps with the shape of another chicken (shape interference), or a part of the chicken (e.g., the head of the chicken) is not displayed in the area image. Accordingly, the area of ​​the chicken is underestimated. Consequently, as illustrated in Fig. 3, a problem arises in which the weight based on the chicken area is also underestimated. To solve this problem, the weight calculation device and method can compensate for the underestimated weight of a group of chickens in a barn. This will be described in more detail below.

[0070] Meanwhile, a situation may arise where some of the two or more chickens in a group are shipped out early. Consequently, the chicken density in the group may once again fall below the critical density. Therefore, the end point of Phase D may be the point at which the chicken density in the group falls below the critical density again.

[0071] Furthermore, some of the aforementioned shipment situations for the chicken groups in the pens may not occur. Therefore, the end point of Phase D may be the point at which all chickens in the pens are shipped. In other words, the end point of the second breeding period may be the point at which the chicken density in the pens is again below the critical density, or the point at which all chickens in the pens are shipped when the chicken density in the pens is above the critical density.

[0072] In short, Phase D may be the breeding period corresponding to the critical breeding time to the recovery breeding time. The recovery breeding time may be defined as the point at which the chicken density of a group of chickens in a barn falls below the critical density again. Alternatively, Phase D may be the breeding period corresponding to the critical breeding time to the total shipping time of the group of chickens in the barn.

[0073] Phase E (i.e., the third rearing period) is an optional phase that occurs immediately after Phase D. That is, Phase E may occur when the chicken density of the chicken group in the barn becomes lower than the critical density again. Therefore, Phase E may be a rearing period corresponding to the recovery rearing time ~ the total shipment time of the chicken group in the barn. At this time, in Phase E, the area-based weight of the chickens in the barn group may be greater than the critical weight, and the chicken density of the chickens in the barn group may be less than the critical density.

[0074] Hereinafter, the method for calculating the weight of a chicken group will be described in more detail based on the contents described in FIGS. 3 to 5.

[0075] FIG. 6 is a diagram illustrating an overall flowchart of a method for calculating the weight of a chicken group according to the first embodiment of the present invention.

[0076] Meanwhile, the method of FIG. 6 can be performed in a weight calculation device, for example, a gateway server (20). Furthermore, the method of FIG. 6 can be performed periodically. Hereinafter, the time for calculating the weight of a group of chickens that is performed periodically is referred to as the "target time."

[0077] Below, the process performed at each step is described in more detail with reference to Fig. 6.

[0078] In step (S11), the weight calculation device can calculate the weight based on the chicken area of ​​a group of chickens in a chicken house at a target time based on an area image of the chicken house obtained from a surveillance camera (10) for each of a plurality of chicken houses.

[0079] As described above, the weight calculation device can extract the shapes of multiple chickens from the area images, calculate the area of ​​the multiple chickens from the shapes of the multiple chickens, and input each area of ​​the multiple chickens into a pre-trained integrated algorithm model to calculate the area-based weight of each of the multiple chickens. In addition, the weight calculation device can repeat the above-described weight calculation process for the multiple area images to calculate the area-based weight of each chicken group in the barn. This will be described in more detail below.

[0080] In step (S12), the weight calculation device can determine whether the target time is included in phase D.

[0081] If the target time is not included in phase D, step (S13) may be performed. Additionally, if the target time is included in phase D, steps (S14) and (S15) may be performed.

[0082] As previously explained, Phases B, C, and E may be phases in which the chicken area-based weight is calculated relatively accurately, i.e., the chicken area-based weight is not underestimated. Furthermore, Phase D may be a phase in which the chicken area-based weight is not calculated relatively accurately, i.e., the chicken area-based weight is underestimated. Accordingly, different steps may be performed based on which phase the target time falls within.

[0083] If the target time is not included in Phase D (Step (S12): NO), that is, if the target time is included in any one of Phase B, Phase C, and Phase E, then in Step (S13), the weight calculation device can determine, for each of the plurality of barns, the weight based on the chicken area of ​​the barn chicken group at the target time as the barn chicken weight at the target time. Here, the barn chicken weight can be defined as the weight of the barn chicken group raised in the barn.

[0084] That is, the weight calculation device may not compensate for the area-based weight of the chickens in the barn group. That is, the area-based weight of the chickens in the barn group may be the same as the barn weight.

[0085] If the target time is included in phase D (S12: YES), the weight calculation device can calculate the weight of the chickens in the barn at the target time by correcting the weight based on the chicken area of ​​the group of chickens in the barn at the target time through steps (S14) and (S15).

[0086] Specifically, in step (S14), the weight calculation device can calculate a trend-based weight of a group of chickens in a barn at a target time based on preset trend information for each of a plurality of barns.

[0087] Here, trend information can be calculated based on multiple breeding time-weight information in phase C.

[0088] According to an embodiment, the trend information may correspond to a trend line in the form of a linear function (i.e., a linear function) based on multiple breeding time-weight information in Phase C. In this case, the weight calculation device may input a target time into the trend line to calculate a trend-based weight at the target time.

[0089] FIG. 7 is a diagram for explaining a concept of calculating a trend-based weight at a target time using a trend line according to one embodiment of the present invention.

[0090] Referring to FIG. 7, the trend line (710) may have a linear function form, i.e., a form of "y=ax+b", and the slope (a) of the trend line (710) may be the average slope of the relationship information between the breeding time and weight in phase C. In this case, the weight calculation device may calculate the trend-based weight (y) at the target time by substituting the target time into "x" of the linear function.

[0091] Meanwhile, according to an embodiment, the slope (a) of the trend line (710) may be corrected by a slope correction value calculated in advance based on the slope of the trend line for a group of chickens raised in a barn other than the corresponding barn. Here, the other barn may be a barn included in the corresponding farm, or a barn included in a farm other than the corresponding farm. For example, the corrected slope (a') of the trend line (710) may be the average of the slope (a) of the trend line (710) and the slope correction value.

[0092] Again, referring to FIG. 6, in step S15, the weight calculation device can calculate the weight of chickens in a barn at a target time based on the area-based weight and trend-based weight of the group of chickens in the barn at the target time for each of the plurality of barns.

[0093] According to an embodiment, the weight of chickens in a barn at a target time can be calculated by weighting the area-based weight and the trend-based weight of chickens at a target time. This can be expressed as "Barn chicken weight = (α1 × chicken area-based weight) + (α2 × trend-based weight)". Here, α1 and α2 each have a value between 0 and 1, and the sum of α1 and α2 is 1.

[0094] In an embodiment, the weight (α2) of the trend-based weight may be set to be greater than the weight (α1) of the chicken area-based weight. For example, the weight (α1) of the chicken area-based weight may be 0.4, and the weight (α2) of the trend-based weight may be 0.6. However, the present invention is not limited thereto.

[0095] In short, the weights of multiple chickens in a livestock shed at a target time can be calculated based on steps (S11) to (S15).

[0096] In step (S16), the weight calculation device can calculate the farm chicken weight at the target time based on the weights of a plurality of chickens at the target time. Here, the farm chicken weight may be the weight of a group of farm chickens raised in a farm including a plurality of pens.

[0097] According to an embodiment, the weight calculation device can calculate the farm chicken weight at a target time by weighting the weights of multiple chickens in a barn at a target time. If there are n barns in a farm, "Farm chicken weight = (β1 × barn chicken weight of barn 1) + … + (β n × Weight of chickens in barn n) can be expressed as "where β1, …, β n Each has a value between 0 and 1, β1, …, β n The sum of is 1.

[0098] In an embodiment, the weight of the weight of chickens in a specific barn (i.e., barn 1) among multiple barns included in a farm may be set in proportion to the number of chickens constituting a barn chicken group in the specific barn. For example, if a farm includes two barns, barn 1 and barn 2, and barn 1 houses 20,000 chickens and barn 2 houses 10,000 chickens, the weight of barn 1 may be 0.667, and the weight of barn 2 may be 0.333.

[0099] Meanwhile, the weight of each group of chickens in each of the multiple pens at the target time and the weight of the farm chickens at the target time can be provided to the farm manager.

[0100] In summary, the weight of a group of chickens can be calculated based on the area-based weight of the chickens as the main weight. Specifically, if the breeding period corresponds to Phase D, the weight of the group of chickens can be adjusted based on the trend-based weight. This allows for accurate calculation of the weight of the group of chickens.

[0101]

[0102] FIG. 8 is a drawing showing an overall flowchart of a method for calculating the weight of a chicken group according to a second embodiment of the present invention.

[0103] Meanwhile, the method of FIG. 8 can also be performed in a weight calculation device and can be performed periodically.

[0104] Below, the process performed at each step is described in more detail with reference to Fig. 8.

[0105] In step (S21), the weight calculation device can set a weight correction value (Δ) of the target time.

[0106] Here, the weight correction value can be set based on the cumulative feed intake of a group of farm chickens. The cumulative feed intake of a group of farm chickens corresponds to the cumulative feed intake of a representative chicken in the group.

[0107] Additionally, the weight compensation value may be updated periodically. For example, the method of FIG. 8 may be performed every hour, and the weight compensation value update cycle may be 12 or 24 hours. However, the present invention is not limited thereto.

[0108] Figure 9 is a drawing showing a detailed flowchart of step (S21) among the steps of Figure 8.

[0109] In step (S211), the weight calculation device can determine whether the target time is the update time of the weight correction value.

[0110] If the target time is not the update time of the weight correction value (step (S211): NO), in step (S212), the weight calculation device may set the weight correction value of the time immediately preceding the target time as the weight correction value of the target time. In other words, the weight correction value of the target time may be a weight correction value that is not updated. For example, if the target time is 3:00 PM, the immediately preceding time may be 2:00 PM.

[0111] If the target time is the update time of the weight correction value (step (S211): YES), in step (S213), the weight calculation device can update the weight correction value based on predefined feed intake-weight relationship information. Then, in step (S214), the weight calculation device can set the updated weight correction value as the weight correction value of the target time.

[0112] Here, the feed intake-weight relationship information may be relationship information between the cumulative feed intake and weight of a predefined standard chicken. Specifically, the feed intake-weight relationship information may be one-to-one matching information between the cumulative feed intake of a standard chicken and the weight of the standard chicken. At this time, the feed intake-weight relationship information may be configured in a quantized manner. For example, if the cumulative feed intake of a standard chicken is 998 g, the weight of the standard chicken may be 1,306 g, and if the cumulative feed intake of a standard chicken is 1,076 g, the weight of the standard chicken may be 1,326 g.

[0113] Figure 10 is a drawing showing a detailed flowchart of step (S213) among the steps of Figure 9.

[0114] In step (S2131), the weight calculation device can calculate the cumulative feed intake of the farm chicken group in the previous time.

[0115] Specifically, a single feed bin may be installed or provided on the farm, and the feed filled in the bin may be distributed and supplied to multiple livestock sheds. Furthermore, a sensor (e.g., a height sensor) may be installed in the bin to measure the amount of feed remaining in the bin. Therefore, the farm manager can monitor the amount of feed remaining in the bin through the sensor.

[0116] And, the cumulative feed intake of the farm chicken group in the previous time may be the value obtained by dividing the first feed amount obtained by subtracting the total feed amount supplied to the farm up to the previous time and the feed amount remaining in the farm's feed bin by the number of chickens constituting the farm chicken group.

[0117] In step (S2132), the weight calculation device can calculate the feed-based weight of the farm chicken group at the previous time based on the feed intake-weight relationship information and the cumulative feed intake of the farm chicken group at the previous time.

[0118] Specifically, if the cumulative feed intake of a standard chicken individual that is identical to the cumulative feed intake of a group of farm chickens at the previous time is included in the feed intake-weight relationship information, the weight calculation device can calculate the weight of the standard chicken individual corresponding to the cumulative feed intake of the same standard chicken individual as the feed-based weight of the group of farm chickens at the previous time.

[0119] In the above example, if the cumulative feed intake of the standard chicken group in the previous time is 998g, the weight calculation device can calculate the feed-based weight of the farm chicken group in the previous time as 1,306g.

[0120] In addition, if the cumulative feed intake of the standard chicken individual that is the same as the cumulative feed intake of the farm chicken group at the previous time is not included in the feed intake-weight relationship information, the weight calculation device may select the cumulative feed intake of the first standard chicken individual that is most similar to the cumulative feed intake of the farm chicken group at the previous time and the cumulative feed intake of the second standard chicken individual that is secondarily similar. Thereafter, the weight calculation device may select the weights of the first and second standard chicken individuals that correspond to the cumulative feed intakes of the first and second standard chicken individuals, and interpolate the weights of the first and second standard chicken individuals to calculate the feed-based weight of the farm chicken group at the previous time.

[0121] In the above example, if the cumulative feed intake of the farm chicken group in the previous time is 1020g, the weight calculation device can select the cumulative feed intake (998g) of the first standard chicken and the cumulative feed intake (1,076g) of the second standard chicken. In addition, the weight calculation device can select the weight (1,306g) of the first standard chicken corresponding to the cumulative feed intake (998g) of the first standard chicken and the weight (1,326g) of the second standard chicken corresponding to the cumulative feed intake (1,076g) of the second standard chicken. Thereafter, the weight calculation device can calculate 1312g, which is the interpolation of the weight (1,306g) of the first standard chicken and the weight (1,326g) of the second standard chicken, as the feed-based weight of the farm chicken group in the previous time.

[0122] In step (S2133), the weight calculation device can calculate the first chicken group weight by weighting the farm chicken weight at the previous time and the feed-based weight at the previous time. This can be expressed as "First chicken group weight = (γ1 × farm chicken weight at the previous time) + (γ2 × feed-based weight at the previous time)". Here, γ1 and γ2 each have a value between 0 and 1, and the sum of γ1 and γ2 is 1. As an example, the weight (γ1) of the farm chicken weight at the previous time may be 0.8, and the weight (γ2) of the feed-based weight at the previous time may be 0.2. However, the present invention is not limited thereto.

[0123] Meanwhile, the farm chicken weight at the previous time can be derived by the step (S24) of Fig. 8 performed at the previous time.

[0124] In step (S2134), the weight calculation device can calculate a ratio value of the weight of the first chicken group and the weight of the farm chicken at the previous time.

[0125] That is, the ratio value can be expressed as "(weight of the first group of chickens) / (weight of farm chickens at the previous time)".

[0126] In step (S2135), the weight calculation device can update the weight correction value with the calculated ratio value.

[0127] Again, referring to FIG. 8, in step (S22), the weight calculation device can calculate, for each of a plurality of barns, the area-based weight of a group of barn chickens at a target time based on the area image. Step (S22) is similar to step (S11) of FIG. 6, and thus a detailed description thereof will be omitted.

[0128] In step (S23), the weight calculation device can calculate the weight of chickens in the chicken pen at a target time based on the weight correction value and the chicken area-based weight at the target time for each of the plurality of chicken pens.

[0129] According to an embodiment, the weight calculation device can calculate the weight of chickens in a barn at a target time by multiplying the chicken area-based weight at the target time and the weight correction value.

[0130] In step (S24), the weight calculation device can calculate the farm chicken weight at the target time based on the weights of multiple chickens in the barn during the target period. Since step (S24) is similar to step (S16) of FIG. 6, a detailed description thereof will be omitted.

[0131] In summary, the weight calculation device can calculate the weight of a group of chickens by combining the area-based weight and the feed-based weight. Therefore, accurate weights of the group of chickens can be calculated.

[0132]

[0133] FIG. 11 is a drawing showing an overall flowchart of a method for calculating the weight of a chicken group according to a third embodiment of the present invention.

[0134] Meanwhile, the method of FIG. 11 can also be performed in a weight calculation device and can be performed periodically.

[0135] Below, the process performed at each step is described in more detail with reference to Fig. 11.

[0136] In step (S31), the weight calculation device can set a weight correction value for the target time. Step (S31) is similar to step (S21) of Fig. 8, so a detailed description is omitted.

[0137] In step (S32), the weight calculation device can calculate the chicken area-based weight of a group of chickens in a chicken pen at a target time based on the area image for each of the multiple pens. Step (S32) is similar to step (S11) of FIG. 6 and step (S22) of FIG. 8, and thus a detailed description thereof will be omitted.

[0138] In step (S33), the weight calculation device can determine whether the target time is included in phase D (i.e., the second breeding period).

[0139] If the target time is not included in phase D, step (S34) may be performed. Additionally, if the target time is included in phase D, steps (S35) and (S36) may be performed.

[0140] If the target time is not included in phase D (step (S33): NO), in step (S34), the weight calculation device can calculate the weight of chickens in the barn at the target time based on the weight correction value and the chicken area-based weight at the target time for each of the plurality of barns.

[0141] That is, if the target time is included in any one of Phase B, Phase C (i.e., the first breeding period), and Phase E (i.e., the third breeding period), the weight calculation device can calculate the weight of the chicken in the barn at the target time by correcting the chicken area-based weight at the target time according to the weight correction value. Since step (S34) is similar to step (S23) of FIG. 8, a detailed description thereof is omitted.

[0142] If the target time is included in phase D (step (S33): YES), the weight calculation device can calculate the weight of the chickens in the barn at the target time by correcting the weight based on the chicken area of ​​the barn chicken group at the target time through steps (S35) and (S36). That is, the weight calculation device can calculate the weight of the chickens in the barn at the target time by correcting the weight based on the chicken area of ​​the barn chicken group based on the trend-based weight of the barn chicken group and the cumulative feed intake of the farm chicken group (i.e., the weight correction value).

[0143] Specifically, in step (S35), the weight calculation device can calculate a trend-based weight of a group of chickens in a barn at a target time based on trend information for each of a plurality of barns. Step (S35) is similar to step (S14) of FIG. 6, and thus a detailed description thereof will be omitted.

[0144] In step (S36), the weight calculation device can calculate the weight of chickens in the chicken pen at the target time based on the chicken area-based weight and the trend-based weight at the target time and the weight correction value for each of the plurality of chicken pens. Specifically, the weight calculation device can calculate the weight of the second chicken group by weighting the chicken area-based weight and the trend-based weight at the target time. This may be similar to step (S15) of FIG. 6. Thereafter, the weight calculation device can calculate the weight of chickens in the chicken pen at the target time by multiplying the second chicken group weight and the weight correction value.

[0145] In step (S37), the weight calculation device can calculate the farm chicken weight at the target time based on the weights of multiple chickens in the barn at the target time. Step (S37) is similar to step (S16) of FIG. 6 and step (S24) of FIG. 8, and thus a detailed description thereof will be omitted.

[0146] Below, the description of the steps in Fig. 11 is summarized as follows.

[0147] The chicken area-based weight can be derived based on the area images captured in each phase, and the trend-based weight can be derived based on the area images captured in Phase C. In other words, both the chicken area-based weight and the trend-based weight can be derived from the area images. Therefore, the weight of a group of chickens in a barn based on the area images can be referred to as an "image-based weight," and the image-based weight can be calculated based on at least one of the chicken area-based weight and the trend-based weight.

[0148] Referring to the above, the weight calculation device can calculate the weight of chickens in a barn by correcting the image-based weight of a group of chickens in a barn based on the cumulative feed intake of the group of chickens in the farm (i.e., the weight correction value).

[0149] At this time, if the target time falls within any one of Phase B, Phase C, and Phase E, the image-based weight may be the chicken area-based weight of the chicken group in the barn. Additionally, if the target time falls within Phase D, the image-based weight may be a combination (i.e., a weighted sum) of the chicken area-based weight and the trend-based weight.

[0150] Therefore, when the target time falls within any one of Phase B, Phase C, and Phase E, the weight calculation device can calculate the weight of the chickens in the barn by correcting the weight based on the chicken area of ​​the chickens in the barn using the cumulative feed intake (i.e., the weight correction value) of the farm chicken group. In addition, when the target time falls within Phase D, the weight calculation device can calculate the weight of the chickens in the barn by correcting the weight based on the chicken area of ​​the chickens in the barn using the cumulative feed intake (i.e., the weight correction value) of the farm chicken group and the trend-based weight of the barn chicken group. Consequently, the weight calculation device according to the present invention can more accurately calculate the weight of the chickens in the barn based on which phase the target time falls within.

[0151] Hereinafter, step (S11) of FIG. 6, step (S22) of FIG. 8, and step (S32) of FIG. 11 will be described in more detail with reference to FIG. 12.

[0152] FIG. 12 is a flowchart illustrating a method for calculating the chicken area-based weight of a group of chickens in a livestock shed at a target time, according to one embodiment of the present invention.

[0153] In step (S41), the weight calculation device can calculate L sub-chicken area-based weights, which are chicken area-based weights corresponding to each of the L area images, based on L (an integer greater than or equal to 1) area images and a pre-learned integrated algorithm model.

[0154] Here, as described above, the area images are captured periodically, for example, at 5-minute intervals. In addition, the L area images may include an area image of the first shooting time corresponding to the target time and L-1 area images corresponding to L-1 previous shooting times prior to the first shooting time.

[0155] Below, the process of calculating the weight based on the lower chicken area of ​​the first region image among L region images is described.

[0156] First, the weight calculation device can extract at least one chicken individual shape from the first region image. In an embodiment, the weight calculation device can compare a plurality of chicken individual shapes included in the first region image with a predefined reference chicken individual shape, and select at least one chicken individual shape from among the plurality of chicken individual shapes. For example, the at least one chicken individual shape may be a chicken individual shape whose similarity with the reference chicken individual shape exceeds a threshold ratio (for example, 90%).

[0157] Next, the weight calculation device can calculate chicken area information for each of at least one chicken individual shape. In an embodiment, the chicken area information can correspond to the number of pixels in a portion of the first area image corresponding to the chicken shape.

[0158] Continuing, the weight calculation device may input each area information of at least one chicken individual into the integrated algorithm model to calculate a first weight output of at least one chicken individual. That is, the first weight output of the chicken individual may be an output value of the integrated algorithm model calculated when the area information of the chicken individual is input into the integrated algorithm model.

[0159] The process of producing the first weight output of a chicken individual using an integrated algorithm model is described.

[0160] The integrated algorithm model may be an algorithm model that inputs area information of a chicken individual and outputs the weight of the chicken individual.

[0161] According to an embodiment, the integrated algorithm model may be composed of N algorithm models (an integer greater than or equal to 2) and N combination weights. In this case, each of the N algorithm models may correspond to each of the N combination weights.

[0162] Each of the N algorithm models can be an algorithm model that inputs the area of ​​a chicken and outputs its weight. The N algorithm models can be generated using different modeling methods. Furthermore, each of the N algorithm models can be trained in a learning device based on area-weight information pairs acquired prior to the weight estimation of the chicken population. For example, each of the N algorithm models can be a regression analysis model, an artificial neural network model, or the like.

[0163] That is, the weight calculation device can input area information of a chicken individual into each of N algorithm models to produce N weight outputs, and calculate the weight of the chicken individual as the weight of the N combined weights and the weighted sum of the N weight outputs.

[0164] Accordingly, the weight calculation device can input area information of each chicken individual into N algorithm models for each of at least one chicken individual, thereby calculating N second weight outputs which are weight outputs of each of the N algorithm models, and can calculate a weighted sum of the N combined weights and the N second weight outputs as the first weight output of the chicken individual.

[0165] Finally, the weight calculation device can calculate a representative weight output of the first weight output of at least one chicken individual as a sub-chicken area-based weight corresponding to the first area image. In an embodiment, the representative weight output of the first weight output of the at least one chicken individual can correspond to an average output of the first weight output of the at least one chicken individual. In another embodiment, the representative weight output of the first weight output of the at least one chicken individual can be a weighted sum of the first weight output of the at least one chicken individual and at least one preset weight. Here, the weight can be set to be proportional to the similarity between the shape of the reference chicken individual and the shape of the chicken individual.

[0166] Meanwhile, according to an embodiment, the N algorithm models may include two or more algorithm models among the first, second, and third algorithm models.

[0167] The first algorithm model may be an algorithm model learned by a learning device based on a plurality of first area-weight information pairs corresponding to pairs of area and weight of a single chicken. For example, the first algorithm model may be an artificial neural network model.

[0168] The second algorithm model may be an algorithm model learned by a learning device based on a plurality of second area-weight information pairs corresponding to pairs of representative areas of X (an integer greater than or equal to 2) chicken individuals and representative weights of Y (an integer greater than or equal to 2) chicken individuals. For example, the second algorithm model may be a regression analysis model.

[0169] The third algorithm model may be an algorithm model learned by a learning device based on a plurality of third area-weight information pairs corresponding to representative areas of multiple chickens and preset reference weight pairs of chickens. Here, the reference weight of the chicken may be a standard weight of a chicken of a specific breeding day corresponding to the specific breeding day among predefined standard weights of chickens by breeding day. For example, the third algorithm model may be a regression analysis model or an artificial neural network model.

[0170] Again, referring to FIG. 12, in step S42, the weight calculation device can calculate the weighted sum of the preset L time weights and the L lower chicken area-based weights as the chicken area-based weight of the chicken group in the barn at the target time.

[0171] At this time, the j-th time weight among the L time weights can be set to be greater than the j-1-th time weight among the L time weights. That is, the first time weight can be the smallest, and the last time weight can be the largest.

[0172]

[0173] In addition, embodiments of the present invention may be implemented in the form of program commands that can be executed through various computer means and recorded on a computer-readable medium. The computer-readable medium may include program commands, data files, data structures, etc., alone or in combination. The program commands recorded on the medium may be those specially designed and configured for the present invention, or may be those known and available to those skilled in the art of computer software. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks, and magnetic tapes, optical media such as CD-ROMs and DVDs, magneto-optical media such as floptical disks, and hardware devices specially configured to store and execute program commands, such as ROMs, RAMs, and flash memories. Examples of program commands include not only machine language codes generated by a compiler, but also high-level language codes that can be executed by a computer using an interpreter, etc. The hardware devices described above may be configured to operate as one or more software modules to perform operations of embodiments of the present invention, and vice versa.

[0174] Although the present invention has been described with specific details such as specific components and limited embodiments and drawings, these are provided only to help the overall understanding of the present invention, and the present invention is not limited to the above embodiments, and those with ordinary skill in the art to which the present invention pertains can make various modifications and variations based on these descriptions. Therefore, the spirit of the present invention should not be limited to the described embodiments, and all things that are equivalent or equivalent to the claims as well as the claims described below are considered to fall within the scope of the spirit of the present invention.

Claims

1. A method for calculating the weight of a group of livestock performed on a processor-based device, A step of calculating the weight based on the livestock area of ​​a livestock group in a livestock shed at a target time based on an area image obtained from a surveillance camera installed in the livestock shed; A step of calculating a trend-based weight of the livestock group in the livestock shed at the target time based on preset trend information; and A step of calculating the livestock weight in the livestock shed at the target time based on the livestock area-based weight and the trend-based weight at the target time; including; Method for calculating the weight of a group of livestock.

2. In paragraph 1, The step of calculating the weight of the livestock in the above-mentioned barn is to calculate the weight of the livestock in the barn at the target time by weighting the weight based on the area of ​​the livestock and the weight based on the trend at the target time. The weight of the above trend-based weight is set to be greater than the weight of the above livestock area-based weight. Method for calculating the weight of a group of livestock.

3. In paragraph 1, The above trend information is calculated based on multiple breeding time-weight information in the first breeding period for the livestock group in the above livestock farm, The first breeding period is a breeding period that is earlier than the second breeding period that includes the target time. Method for calculating the weight of a group of livestock.

4. In paragraph 3, The start time of the second breeding period is the time when the weight based on the livestock area of ​​the livestock group in the livestock shed, which changes according to the breeding time, becomes greater than the preset critical weight, or the time when the livestock density, which changes according to the breeding time, becomes greater than the preset critical density. Method for calculating the weight of a group of livestock.

5. In paragraph 4, The end point of the second breeding period is the point at which the livestock density becomes lower than the critical density again, or the point at which all livestock groups in the livestock shed are shipped out when the livestock density is higher than the critical density. Method for calculating the weight of a group of livestock.

6. In paragraph 4, The livestock area-based weight in the first breeding period is less than or equal to the critical weight, and the livestock density in the first breeding period is less than or equal to the critical density. Method for calculating the weight of a group of livestock.

7. A method for calculating the weight of a group of livestock performed on a processor-based device, For each of the multiple livestock houses included in the farm, a step of calculating the livestock weight of the livestock house at the target time based on the livestock area-based weight of the livestock group of the livestock house at the target time and the trend-based weight of the livestock group of the livestock house at the target time according to preset trend information; and A step of calculating a farm livestock weight for a farm livestock group at the target time based on the weights of the livestock in the plurality of livestock sheds corresponding to each of the plurality of livestock sheds; Method for calculating the weight of a group of livestock.

8. In paragraph 7, The step of calculating the weight of the farm livestock is to calculate the weight of the farm livestock by weighting the weights of the livestock of the plurality of barns, Among the above multiple livestock farms, the weight of the livestock weight of the first livestock farm is set in proportion to the number of livestock groups raised in the first livestock farm. Method for calculating the weight of a group of livestock.

9. A method for calculating the weight of a group of livestock performed on a processor-based device, A step for setting a weight correction value for the target time; For each of a plurality of livestock sheds included in the farm, a step of calculating an image-based weight of a group of livestock in the shed at the target time based on an area image acquired from a surveillance camera installed in the shed; For each of the plurality of livestock sheds, a step of calculating the livestock weight of the livestock shed at the target time based on the image-based weight and the weight correction value at the target time; A step of calculating the farm livestock weight of the farm livestock group at the target time based on the weight of the livestock of the plurality of livestock houses corresponding to each of the plurality of livestock houses; including; The above weight correction value is set based on the cumulative feed intake of the above farm livestock group. Method for calculating the weight of a group of livestock.

10. In paragraph 9, The step of calculating the image-based weight at the target time is: Calculating the image-based weight at the target time based on at least one of the livestock area-based weight obtained by analyzing the above area image and the trend-based weight according to preset trend information. Method for calculating the weight of a group of livestock.

11. In paragraph 10, If the target time is included in the first breeding period, the image-based weight at the target time corresponds to the livestock area-based weight at the target time, In the first breeding period, the livestock area-based weight that changes according to the breeding time is below a preset critical weight, and the livestock density that changes according to the breeding time is below a preset critical density. Method for calculating the weight of a group of livestock.

12. In paragraph 10, If the target time is included in the second breeding period, the image-based weight at the target time corresponds to the weighted sum of the livestock area-based weight at the target time and the trend-based weight at the target time. The start point of the second breeding period is the point in time when the livestock area-based weight, which changes according to the breeding time, becomes greater than a preset critical weight, or the point in time when the livestock density, which changes according to the breeding time, becomes greater than a preset critical density. Method for calculating the weight of a group of livestock.

13. In paragraph 10, If the above target time is included in the third breeding time, the image-based weight at the above target time is the livestock area-based weight at the above target time. In the third breeding period, the livestock area-based weight that changes according to the breeding time is greater than or equal to a preset critical weight, and the livestock density that changes according to the breeding time is less than or equal to a preset critical density. Method for calculating the weight of a group of livestock.

14. In paragraph 9, The above weight correction value is updated periodically, The step of setting the above weight correction value is: If the above target time is not the update time of the weight correction value, the weight correction value of the time immediately preceding the target time is set as the weight correction value of the target time, If the target time is the update time, the weight correction value is updated based on the feed intake-weight relationship information, which is the relationship information between the cumulative feed intake and weight of a predefined standard livestock individual, and the updated weight correction value is set as the weight correction value of the target time. Method for calculating the weight of a group of livestock.

15. In paragraph 14, If the target time is the update time, the step of setting the weight correction value is: Based on the feed intake-weight relationship information and the cumulative feed intake of the farm livestock group at the previous time, the feed-based weight of the farm livestock group at the previous time is calculated, Updating the weight correction value based on the farm livestock weight at the immediately preceding time and the feed-based weight at the immediately preceding time; Method for calculating the weight of a group of livestock.

16. In paragraph 15, The above updated weight correction value corresponds to the ratio of the weight of the first livestock group and the weight of the farm livestock at the immediately preceding time, The above first livestock group weight is the weight obtained by weighting the farm livestock weight at the immediately preceding time and the feed-based weight at the immediately preceding time, The step of calculating the weight of livestock in the livestock shed at the target time is to calculate the weight of livestock in the livestock shed at the target time by multiplying the weight based on the livestock area at the target time and the weight correction value. Method for calculating the weight of a group of livestock.

17. In paragraph 15, The cumulative feed intake of the farm livestock group in the immediately preceding time is the value obtained by dividing the first feed amount by the number of livestock constituting the farm livestock group, The above first feed amount is the total feed amount supplied to the farm up to the immediately preceding time and the amount of feed remaining in the feed bin of the farm. Method for calculating the weight of a group of livestock.

18. A computer-readable recording medium recording a program for performing the method of any one of paragraphs 1, 7, and 9.

Images