KR20220062911A - Sow management and Environmental control System - Google Patents

Abstract

The present invention relates to a sow management and environmental control system. According to the present invention, the system for predicting and managing giving birth of sows and controlling the environment comprises: an environment control device installed in a breeding farm to control the environment of sows; and a terminal including an environmental sensor part sensing the sow's environment, one or more 3D sensors imaging a sow, a sow measurement part comprising one or more thermal imaging cameras for photographing sows, and a sow management/environment control application recognizing unusual behaviors of sows and predicting sow delivery by using the sow images and the thermal image extracted through the 3D sensors and the thermal imaging camera, and receiving environmental information sensed from the environment sensor part to control the environment control device.

Description

Sow management and Environmental control System

The present invention relates to a sow management and environmental control system, and more particularly, by recognizing a specific behavior based on a 3D image to predict the sow's farrowing time and adjust the environment to the optimal condition, automatically correct the sow's farrowing time It relates to a sow management and environmental control system that can improve the productivity of sows by making decisions and responding quickly.

Sow delivery is closely related to economic feasibility in terms of the pig industry, and it is the stage that requires the most labor in terms of pig farms.

Because the manager predicts the time of farrowing by observing the change of sows based on experience, there is a tendency to predict the time of farrowing subjectively. In addition, in order to know the exact time of farrowing, it is necessary to observe sows for a long time, which requires considerable labor and time.

Also, like humans, when fertilization is confirmed in pigs, the expected delivery date is calculated. Depending on the pig's delivery experience (number of pregnancies), health status, and farm environment, the delivery time will change from the expected delivery date. is difficult to predict.

If the time of delivery is not accurately recognized, problems such as difficult childbirth and postpartum congestion may occur. there is.

Therefore, it is necessary to develop an automation technology that can manage sows through continuous monitoring and objective parturition prediction.

However, the currently developed technology to continuously monitor and quantify the behavior of sows is still insufficient to be applied to the industry.

On the other hand, in general, in the management of the breeding environment of pigs, the temperature, humidity, and ventilation of the pig house are the key. This is because when a large number of pigs are raised in a narrow space, if you focus on temperature, humidity becomes a problem, if you focus on keeping warm, ventilation becomes insufficient. This is because problems may arise. Moreover, the pig delivery room is a place where newborn piglets (pigs) are reared, and if the temperature, humidity and ventilation are not maintained at a constant temperature, many piglets may die from respiratory diseases.

In order to solve the above problems, the present invention recognizes a specific behavior based on a 3D image to predict the sow's farrowing time and adjust the environment to the optimal condition, thereby automatically and accurately and quickly determining the sow's farrowing time. An object of the present invention is to provide a sow management and environmental control system that can respond and improve sow productivity.

In order to solve the above problems, the sow management and environment control system according to an embodiment of the present invention is a system for predicting and managing sow farrowing and controlling the environment, it is installed in a breeding house to control the environment of sows control device; An environmental sensor unit for sensing the environment of the sow, one or more 3D sensors for photographing sows, a sow measurement unit including one or more thermal imaging cameras for photographing sows, and the sow image extracted through the 3D sensor and thermal imaging camera A terminal comprising a sow management/environment control application for recognizing the specific behavior of sows using the thermal image, predicting sow farrowing, and receiving environmental information sensed from the environmental sensor unit to control the environment control device It is possible to provide a sow management and environmental control system comprising a.

Here, the sow measurement unit is provided with a space for accommodating the sow, and may further include a housing frame in which the environmental sensor unit, the 3D sensor, and the thermal imaging camera can be installed.

In addition, the sow management / environment control application is an image extraction unit for extracting one or more sow images from the image taken with the 3D sensor and one or more thermal image from the image taken with the thermal imaging camera; a conversion unit that converts the extracted sow image into three-dimensional coordinate data; a pre-processing unit for pre-processing the converted three-dimensional coordinate data to generate three-dimensional sow data; The environment control device by receiving environmental information sensed from the farrowing predictor and the environmental sensor unit that recognizes a specific behavior using the three-dimensional sow data and thermal image through the learned artificial intelligence model, and predicts the time of farrowing It may include an environment control unit to control the.

In addition, the pre-processing unit includes a factor extraction unit for extracting a factor from the three-dimensional coordinate data, the factors are head direction, floor angle, focal length, height, length 1, chest circumference, half circumference, half circumference, rear circumference, It is characterized in that it includes at least one of an average body half circumference, a total body half circumference, the number of cloud points, a volume, and a feature point.

(Here, length 1 is the distance from the front leg with the head removed to the tip of the buttocks, and length 2 is the distance between the front and hind legs.)

In addition, the parturition prediction unit recognizes the specific behavior of the sow using the three-dimensional sow data and thermal image through the learned artificial intelligence model, and counts the recognized specific behavior to generate behavior analysis data. and a farrowing time determination unit for predicting the sow's farrowing time by analyzing the behavior analysis data.

In addition, it further comprises a weight derivation unit for deriving an estimated weight from the three-dimensional sow data, and the farrowing predicting unit is characterized in that it predicts the time of farrowing with reference to the derived estimated weight.

In addition, the weight derivation unit generates a candidate list by selecting one or more of the three-dimensional sow data according to a factor, and determines the number of cases of condition satisfaction of the generated candidate list to derive the first weight of the three-dimensional sow data a candidate list unit; It may include an algorithm derivation unit for deriving a second weight by applying a multiple regression formula to the three-dimensional sow data, and a final derivation unit for deriving an estimated weight using the first weight and the second weight.

In addition, the candidate list unit selects one or more of the three-dimensional sow data as candidates according to a factor to determine the number of cases of condition satisfaction of the list generation unit generating a candidate list and the generated candidate list, and in some cases, the 3 It may include a list processing unit for deriving the first weight of the dimensional sow data.

In addition, the list generator generates a first candidate list by comparing one or more of the total head direction, floor angle, focal length, length 1, and body half circumference of the three-dimensional sow data with the sow standard data, and the three-dimensional sow A second candidate list is created by comparing one or more of the data head direction, total body half circumference, height, length 1, and median half circumference with the sow standard data, and the head direction, length 1, chest circumference of 3D sow data , it is characterized in that the third candidate list is generated by comparing one or more of the median half circumference and the latter half circumference with the sow standard data.

The sow management and environment control system according to an embodiment of the present invention as described above recognizes a specific behavior based on a 3D image, predicts the sow's farrowing time, and adjusts the environment to the optimal condition, thereby automatically adjusting the sow's farrowing time. Accurate and prompt judgment makes it easy to manage sows.

In addition, it is possible to quickly respond to problems that may occur during sow delivery, such as difficult birth, and thus the productivity of sows can be improved.

In addition, it can bring the effect of reducing the labor force and improving the profits of the farms.

In addition, as it can be applied to various livestock such as cattle as well as pigs, its utility is expected to expand.

1 is a block diagram showing a sow management and environmental control system according to an embodiment of the present invention.
Figure 2 is an exemplary view showing a state in which the environmental sensor unit, the 3D sensor, the thermal imaging camera and the terminal of the sow management and environmental control system according to an embodiment of the present invention are installed in the receiving frame.
Fig. 3 is a block diagram showing the configuration of the sow management/environment control application of Fig. 1;
4 is an exemplary view showing a factor.
5 is a block diagram showing the configuration of the weight derivation unit of FIG.
Figure 6 is a block diagram showing the configuration of the delivery prediction unit of Figure 3.

Hereinafter, the description of the present invention with reference to the drawings is not limited to specific embodiments, and various modifications may be made and various embodiments may be provided. In addition, it should be understood that the contents described below include all transformations, equivalents, and substitutes included in the spirit and scope of the present invention.

In the following description, terms such as 1st, 2nd, etc. are terms used to describe various components, meanings are not limited thereto, and are used only for the purpose of distinguishing one component from other components.

Like reference numbers used throughout this specification refer to like elements.

As used herein, the singular expression includes the plural expression unless the context clearly dictates otherwise. In addition, terms such as "comprises", "comprises" or "have" described below are intended to designate the existence of features, numbers, steps, operations, components, parts, or combinations thereof described in the specification. It should be construed as not precluding the possibility of addition or existence of one or more other features, numbers, steps, operations, components, parts, or combinations thereof.

Unless defined otherwise, all terms used herein, including technical and scientific terms, have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. Terms such as those defined in a commonly used dictionary should be interpreted as having a meaning consistent with the meaning in the context of the related art, and should not be interpreted in an ideal or excessively formal meaning unless explicitly defined in the present application. does not

In addition, in the description with reference to the accompanying drawings, the same components are given the same reference numerals regardless of the reference numerals, and the overlapping description thereof will be omitted. In describing the present invention, if it is determined that a detailed description of a related known technology may unnecessarily obscure the gist of the present invention, the detailed description thereof will be omitted.

In the present invention, the sow management/environment control application is preferably provided in a mobile communication terminal including a smart phone communicating through a wireless communication network, but may also be provided in a computer environment communicating through a wired communication network. Hereinafter, the description will be focused on the mobile communication terminal.

Hereinafter, an embodiment of the present invention will be described in detail with reference to FIGS. 1 to 6 attached thereto.

1 is a block diagram illustrating a sow management and environmental control system according to an embodiment of the present invention, and FIG. 2 is an environmental sensor unit, 3D sensor, and thermal imaging camera of the sow management and environmental control system according to an embodiment of the present invention. And it is an exemplary view showing a state that the terminal is installed in the receiving frame, Figure 3 is a block diagram showing the configuration of the sow management / environment control application of Figure 1, Figure 4 is an exemplary view showing a factor, Figure 5 is 3 is a block diagram showing the configuration of the weight derivation unit, FIG. 6 is a block diagram showing the configuration of the delivery prediction unit of FIG.

The sow management and environment control system according to an embodiment of the present invention measures the environment of sows, adjusts them to suitable conditions for growth, predicts delivery time through 3D images and temperature information of sows, so that sows can be easily managed. want to

1 , the sow management and environment control system (hereinafter referred to as 'system') according to an embodiment of the present invention may include an environment control device 1, a sow measurement unit 2 and a terminal 3 there is.

The environmental control device 1 may be installed in the sow breeding ground to control the sow environment. In this case, the environmental control device 1 may include one or more of a heating device, a ventilation device, and a humidity control device, and each may be individually controlled and operated by the terminal 3 . The present invention is not limited thereto and may further include various devices capable of controlling the environment.

The sow measurement unit 2 is to secure the appearance information, temperature information, surrounding environment information, etc. of the sow, and may include an environmental sensor unit 20, a 3D sensor 21, and a thermal imaging camera 22 there is.

The environment sensor unit 20 can secure the environment information by sensing the environment around the sow so that the environment of the sow can be controlled in an optimal condition. Also, the measured environment information may be transmitted to the terminal 3 .

The environment sensor unit 20 may include one or more of a temperature sensor, a humidity sensor, and a gas sensor, and preferably includes all, but is not limited thereto, and may further include various sensors such as a wind speed sensor.

In addition, the gas sensor may include an ammonia sensor, a hydrogen sulfide sensor, and the like.

Accordingly, the environmental information may include environmental temperature information, humidity information, gas information, and the like.

In addition, the environmental sensor unit 20 may be installed around the sow even in the breeding ground to more accurately sense the surrounding environment of the sow. This is because, depending on the location, the perceived environmental value may be different in the large space of the kennel.

One or more 3D sensors 21 may be installed to photograph sows to secure a three-dimensional image of sows. In this case, the 3D sensor 21 is a sensor that captures a 3D image as a depth sensor, and a color depth sensor is preferable, but is not limited thereto. This is because, when a color depth sensor is used, the color is expressed differently depending on the depth, so the sow shape extraction accuracy can be improved.

One or more thermal imaging cameras 22 may be installed to photograph the sow to secure a thermal image of the sow. The thermal imaging camera 22 is a special equipment that takes pictures using heat, and tracks and detects the heat and shows it as an image. Accordingly, when photographing a living organism (object) having a temperature, it is distinguished from the surrounding objects so that the object can be easily identified and the temperature distribution of the object can be seen at a glance.

In the case of sows, the system of the present invention has a characteristic that the temperature near the tailbone is higher than that of other parts. By using the thermal imaging camera 22, this characteristic is intended to be used to recognize the specific behavior of the sow.

In addition, the sow measurement unit 2 may further include a receiving frame 23, as shown in FIG.

The accommodation frame 23 is provided with a space to accommodate sows, and may be formed of a frame, but is not limited thereto. In addition, the environmental sensor unit 20, the 3D sensor 21 and the thermal imaging camera 22 may be installed. Accordingly, it is possible to photograph the sow accommodated in the accommodation frame 23 and accurately measure the surrounding environment.

The terminal 3 may be a mobile terminal of a user such as a breeder of a farmhouse or a manager, and may be easily applied to a PC tablet in addition to a mobile terminal.

As described above, the terminal 3 is implemented as a mobile terminal to facilitate installation, mobility, and convenience, thereby enabling the manager to easily predict the sow's farrowing time.

In addition, the terminal 3 may be installed in the receiving frame 23, but is implemented to be detachable and can be used in various ways as needed.

In addition, the terminal 3 has the sow management / environment control application 30 installed, so it can receive environmental information, captured images, etc. from the environmental sensor unit 20 , the 3D sensor 21 , and the thermal imaging camera 22 . And, it is possible to control the environment control device (1).

The sow management/environmental control application 30 recognizes the specific behavior of the sow using the sow image and the thermal image, predicts the time of farrowing through this, and controls the kennel to the optimal environmental conditions according to the environmental information, Android , means an iOS-based general application, but may be provided as a general application or a web service-based application depending on the terminal 3 or a wired/wireless service type. As a method of providing, it can be downloaded and installed by accessing the server through the terminal 3 or by downloading it through an online application market (eg, Android market, Apple store, online market of a telecommunication company, etc.).

3, the sow management / environment control application 30 is a data storage unit 31, an image extraction unit 32, a conversion unit 33, a pre-processing unit 34, a weight derivation unit 35, farrowing It may include a prediction unit 36 and an environment control unit 37 .

The data storage unit 31 may store specific behavior data, parturition time data according to the specific behavior, sow standard data generated using pre-collected sow data, optimal environmental conditions according to the sow state, and the like.

Here, the specific behavior data may be data on specific behaviors that may appear before sow farrowing. The specific behavior data may include a specific behavior sow image, 3D sow data, factor information according to the specific behavior, and the like.

The delivery time data according to the specific behavior may be data on the frequency of the specific behavior, the cycle, the step-by-step behavior, and the delivery time according to the continuous behavior.

In addition, sow standard data is data standardized by month or weight by analyzing sow data collected in advance by measuring sows at the farm, 3D imaging, and may include 3D sow data by month or weight, and collect in advance One sow data may include three-dimensional sow data and weight.

In addition, the data storage unit 31 may store sow biometric information, behavior analysis data, estimated weight, information about the predicted time of delivery, etc. input from the user.

Sow biometric information is biometric information of sows to be managed, and may include one or more of sow classification number, species, number of months and expected fertilization date, and it is preferable to include all of them.

The image extraction unit 32 may receive the captured image from the 3D sensor 21, and extract one or more sow images from the captured image through capture. In addition, the image taken by the thermal imaging camera 22 may be received, and one or more thermal image images may be extracted from the captured image through capture.

It is preferable that the capture consists of continuous capture so that a plurality of sow images and thermal image images can be extracted. The continuous capture count value may be 10 to 12, but is not limited thereto.

In addition, the capture may be performed at a certain period, for example, it may be performed at an interval of 2 minutes to recognize and count a specific action, but is not limited thereto.

As such, by extracting sow images and thermal images through capture, performance degradation can be minimized.

After arranging the sow image, the transformation unit 33 may extract a point and convert it into three-dimensional coordinate data. Such three-dimensional coordinate data may be stored in the data storage unit 31 .

Here, the three-dimensional coordinate data may be data on the right or left shape (half-section shape of the sow) relative to the isometric axis of the sow, not all of the shape of the sow, but is not limited thereto, and the shape of the sow is all implemented it may be

The pre-processing unit 34 may pre-process the converted 3D coordinate data to generate 3D sow data. For this purpose, it may include a validation unit, a noise removal unit, and a factor extraction unit.

The validation unit judges the validity of the three-dimensional coordinate data, and since it is possible to obtain a sow image that is not suitable for use due to obstruction factors (sunlight, sow movement, etc.), the validity is checked by checking the number of extracted points. can judge

Validity can be judged depending on whether the number of extracted points is greater than or equal to a set number of points, and when the number of points is less than a certain number of points, the corresponding 3D coordinate data is dropped so that it is not used to recognize unusual behavior or derive estimated weight. there is.

The noise removal unit removes noise from 3D coordinate data, and since objects other than sows (land, building frames, etc.) can also be photographed, it is possible to identify points corresponding to objects other than sows among the extracted points. can be removed

The factor extraction unit may extract a factor from the 3D coordinate data to generate 3D sow data. In this case, the 3D sow data may include 3D coordinate data and a factor.

In this case, the factors are head direction, floor angle, focal length, height, length 1 (length01), chest circumference (girth_first), middle circumference (girth_mid), rear circumference (girth_end), average half circumference of the body, It may be one or more of the total body half circumference, number of cloud points, volume, and feature points, but is not limited thereto, and various factors such as bending or not may be extracted.

As shown in FIG. 4 , length 1 is the distance from the front leg with the head removed to the tip of the buttocks, and length 2 is the distance between the front legs and hind legs.

In addition, the characteristic point may be a point corresponding to one or more of the tip of the sow's nose, lower mouth, leg, knee, tailbone, and ear, but is not limited thereto, and may include more various characteristic points.

In this way, by extracting the factor corresponding to the characteristic part, the specific behavior of the sow can be easily recognized, and the weight can also be estimated.

The weight derivation unit 35 may derive the estimated weight from the three-dimensional sow data.

Here, when there are two or more three-dimensional sow data, the weight derivation unit 35 repeats the process of deriving an estimated weight according to the number of three-dimensional sow data to obtain an estimated weight according to each three-dimensional sow data, Estimated weight data corresponding to the number can be obtained. That is, to obtain the estimated weight for each three-dimensional sow data.

The estimated weight data may include the derived estimated weight and three-dimensional sow data, but is not limited thereto, and may further include other information.

Referring to FIG. 5 , the weight deriving unit 35 may include a candidate list unit 350 , an algorithm deriving unit 351 , and a final deriving unit 352 .

The candidate list unit 350 generates a candidate list by selecting one or more three-dimensional sow data according to a factor, and determines the number of cases of condition satisfaction of the generated candidate list to derive the first weight of the three-dimensional sow data. can

To this end, the candidate list unit 350 may include a list generator and a list processor.

The list generator may generate a candidate list by selecting one or more three-dimensional sow data as candidates according to a factor.

Specifically, the list generator compares one or more three-dimensional sow data through a factor based on the sow standard data, and selects candidate 1, candidate 2, and candidate 3 as candidate 1, candidate 2, and candidate 3 when they belong to sow standard data. The final first, second, and third candidate lists may be generated by adding them to the three candidate lists.

In this case, when the 3D sow data is selected as a candidate, the weight according to the matching sow standard data may be included as the weight of the 3D sow data.

The list generator may generate a first candidate list by comparing one or more of the total of the head direction, the floor angle, the focal length, the length 1, and the half circumference of the three-dimensional sow data with the standard sow data.

The list generator may select the 3D sow data as candidate 1 and add it to the first candidate list if the 3D sow data is included therein compared with the sow standard data. Through this process, the first candidate list may be generated.

More specifically, the list generator unit determines whether the three-dimensional sow data is within the 'head direction', 'floor angle range', 'focal length range', 'length 1 range', 'half torso' of the standard data of sows. It is possible to add only 3D sow data that is YES to the first candidate list by performing the comparison in the order of 'whether it is within the perimeter total range', and proceeding to the following order only if YES (true).

It is not limited to the above order, and may be easily changed and applied.

In addition, the list generator can also generate the first candidate backup list, and adds the 3D sow data that is NO (no) to the first candidate backup list only in the last order, 'whether it is within the total range of half body circumference', to the first candidate backup list. You can create a backup list.

When added to the list, the 3D sow data may include a weight according to the corresponding sow standard data as the weight of the 3D sow data.

In addition, the list generator compares one or more of the three-dimensional sow data head direction, total body circumference, height, length 1, and median half circumference with the sow standard data, and if the three-dimensional sow data belongs therein, the three-dimensional sow data A second candidate list may be generated by selecting as candidate 2 and adding it to the second candidate list.

More specifically, the list generator unit determines whether the 3D sow data is 'the same as the head direction', 'within the total body half circumference', 'within the height range', 'within the length 1 range', 'the median It is possible to add only 3D sow data that is YES to the second candidate list by performing the comparison in the order of 'whether it is within the half-circumference range', and proceeding to the following order only in the case of YES (true). It is not limited to the above order, and may be easily changed and applied.

In addition, the list generator can also generate a second candidate backup list, and adds the 3D sow data that is NO (no) only to the last order, 'is it within the middle half circumference range', to the second candidate backup list to back up the second candidate You can create a list.

In addition, the list generator compares one or more of the three-dimensional sow data head direction, length 1, chest half circumference, middle half circumference, and rear half circumference with sow standard data, and if the three-dimensional sow data belongs therein, the three-dimensional A third candidate list may be generated by selecting sow data as candidate 3 and adding it to the third candidate list.

More specifically, the list generator determines whether the three-dimensional sow data is the same as the head direction of the sow standard data, 'is it within the length 1 range', 'is it within the chest circumference range? It is possible to add only 3D sow data that is YES in all cases to the third candidate list by performing the comparison in the order of 'whether it is within the perimeter of the second half, and only in the case of YES (true)' to proceed to the following order. It is not limited to the above order, and may be easily changed and applied.

In addition, the list generator can also generate a third candidate backup list, and adds the 3D sow data that is NO (no) only to the last order, 'is it within the posterior half circumference range', to the third candidate backup list to back up the third candidate You can create a list.

The list processing unit may determine the number of cases of condition satisfaction of the generated candidate list (first, second, and third candidate lists), and may derive a first weight of the three-dimensional sow data in some cases.

The condition satisfaction is whether or not it has one or more three-dimensional sow data, and as the first, second and third candidate lists are generated, the number of cases is 3 satisfied (1st to 3rd candidate list), 2 satisfied ( 1st and 2nd candidate lists, 2nd and 3rd candidate lists, 1st and 3rd candidate list), 1 satisfaction (1st, 2nd, 3rd candidate list), 0 satisfactions may occur.

The algorithm derivation unit 351 may derive the second weight by applying the multiple regression formula to the three-dimensional sow data.

Specifically, the algorithm derivation unit 351 uses the height, length 2, body half circumference average, and the number of cloud points of the 3D sow data among the factors of the 3D sow data to obtain the second value through Equation 1 below. weight can be derived.

[Equation 1]

2nd weight = m ₁ + (h ₁ × height) + (2ㅣ ₁ × length 2) + (g ₁ × body half circumference average) + (p ₁ × number of cloud points in 3D sow data)

Here, m ₁ is the weight constant, h ₁ is the height constant, 2ㅣ ₁ is the length 2 constant, g ₁ is the half-circumference average constant, and p ₁ is the cloud point constant of the 3D sow data.

In addition, the algorithm derivation unit 351 may derive the second weight by using Equations 2 to 4, respectively.

More specifically, the algorithm derivation unit 351 can derive the second weight through Equation 2 by using the height, length 1, the average torso half circumference, and the number of cloud points of the three-dimensional sow data among the factors. there is.

[Equation 2]

2nd weight = m ₂ + (h ₂ × height) + (1ㅣ ₂ × length 1) + (g ₂ × body half circumference average) + (p ₂ × number of cloud points in 3D sow data)

Here, m ₂ is the weight constant, h ₂ is the height constant, 1ㅣ ₂ is the length 1 constant, g ₂ is the half-circumference average constant, and p ₂ is the cloud point constant of the 3D sow data.

In addition, the algorithm derivation unit 351 may derive the second weight through Equation 3 by using the number of cloud points of the height, the body half circumference average, and the three-dimensional sow data among the factors.

[Equation 3]

Second weight = m ₃ + (h ₃ × height) + (g ₃ × body half circumference average) + (p ₃ × number of cloud points in the three-dimensional sow data)

Here, m ₃ is the weight constant, h ₃ is the height constant, g ₃ is the half-circumference constant, and p ₃ is the cloud point constant of the three-dimensional sow data.

Also, the algorithm derivation unit 351 may derive the second weight through Equation 4 by using the average of the trunk circumference among the factors and the number of cloud points of the 3D sow data.

[Equation 4]

Second weight = m ₄ + (g ₄ × body half circumference average) + (p ₄ × number of cloud points in 3D sow data)

Here, m ₄ is a weight constant, g ₄ is a half-circumference average constant, and p ₄ is a cloud point constant of 3D sow data.

The final derivation unit 352 may derive the estimated weight using the first weight and the second weight, and may derive the estimated weight according to an absolute value of a value obtained by subtracting the first weight from the second weight. When the absolute value is less than a certain weight value, the second weight is derived as an estimated weight, and when the absolute value is greater than a certain weight value, the estimated weight can be derived as 0 kg.

The final derivation unit 352 may derive the estimated weight through the above process and generate the estimated weight data to be used for predicting the time of delivery, and may be provided to the user and stored in the data storage unit 31 .

When stored in the data storage unit 31, the estimated weight may be stored by matching the sow biometric information input before measuring the weight of the sow.

At this time, when 0 kg is derived as the estimated weight, it may be considered as 'weighing failure', and accordingly, the final derivation unit 352 informs the user of 'weighing measurement failure' to recapture and re-estimate. .

The parturition prediction unit 36 may recognize a specific behavior using the three-dimensional sow data and thermal image through the learned artificial intelligence model, and predict the delivery time.

Referring to FIG. 6 , the delivery prediction unit 36 may include a specific behavior recognition unit 360 and a delivery time determination unit 361 .

The specific behavior recognition unit 360 may recognize the specific behavior of the sow using the three-dimensional sow data and the thermal image through the learned artificial intelligence model, and count the recognized specific behavior to generate behavior analysis data.

The artificial intelligence model used here is a deep learning algorithm, which can learn the specific behavior data and recognize the specific behavior of the sow through 3D sow data and thermal image.

The specific behavior of the sow recognized at this time may be, but is not limited to, standing, lying, searching, scratching the floor, biting a stall, feeding, sitting, and masturbating, but is not limited thereto, and may be a variety of behaviors.

On the other hand, the specific behavior recognition unit 360 recognizes the specific behavior of the sow by more accurately identifying the position, direction, buttock position, etc. of the sow through a thermal image like 3D sow data, so that recognition accuracy can be further improved. there is.

The specific behavior recognition unit 360 counts the recognized specific behavior by time to generate behavior analysis data, and may be continuously updated through sow images and thermal image images extracted at regular intervals.

The parturition time determination unit 361 may predict the delivery time of the sow by analyzing the behavioral analysis data.

Specifically, the delivery time determination unit 361 can predict the delivery time of the sow by analyzing the behavior analysis data through the learned artificial intelligence model. can be judged

The artificial intelligence model used here is a deep learning algorithm, which may be one that has learned the delivery time data according to a specific behavior.

In addition, the AI model can identify step-by-step behavior through classification and continuous behavior through regression.

In addition, the delivery time determination unit 361 may predict the delivery time by referring to the estimated weight derived in addition to the behavior analysis data.

The environment control unit 37 may receive the environment information sensed from the environment sensor unit 20 to control the environment control device 1 . Specifically, the environment controller 37 may generate the optimal environment setting information through the artificial intelligence model learned using the received environmental information and the predicted delivery time.

By controlling the environment control device 1 according to such environment setting information, it is possible to adjust the environment of the breeding grounds to the optimum conditions for breeding sows.

Here, the artificial intelligence model may have learned the optimal environmental conditions according to the sow state.

In addition, the sow management and environment control system according to an embodiment of the present invention may further include a control unit (not shown).

One sow measuring unit 2 and one terminal 3 may be provided, and each sow measuring unit 2 and a terminal 3 may be provided, respectively. (not shown) can manage the whole accordingly, and can individually control the sow measurement unit 2 and the terminal 3 provided for each sow.

In addition, the control unit may receive all information from the terminal 3 and manage it easily.

As described above, the sow management and environment control system according to an embodiment of the present invention recognizes a specific behavior based on a 3D image, predicts the sow's farrowing time, and adjusts the environment to the optimal condition, so that the sow's farrowing time automatically, accurately and quickly, so that the sow can be easily managed.

In addition, it is possible to quickly respond to problems that may occur during sow delivery, such as difficult birth, and thus the productivity of sows can be improved.

In addition, it can bring the effect of reducing the labor force and improving the profit of the farm household.

In addition, as it can be applied to various livestock such as cattle as well as pigs, its utility is expected to expand.

Although the embodiments of the present invention have been described in detail above, the scope of the present invention is not limited thereto, and various modifications and improvements by those skilled in the art using the basic concept of the present invention as defined in the following claims are also provided. is within the scope of the right.

1: Environmental control device
2: Sow measurement unit
20: environmental sensor unit
21: 3D sensor unit
22: thermal imaging camera
23: receiving frame
3: terminal
30: Sow Management/Environmental Control Applications
31: data storage unit
32: image extraction unit
33: conversion unit
34: preprocessor
35: weight derivation part
350: candidate list unit
351: algorithm derivation unit
352: final derivation
36: delivery prediction unit
360: special behavior recognition unit
361: delivery time judgment unit
37: Environmental Control Department

Claims (9)

In the system for predicting and managing the sow's delivery and controlling the environment,
an environmental control device installed in a kennel to control the environment of sows;
An environmental sensor unit for detecting the environment of the sow, one or more 3D sensors for photographing the sow, a sow measuring unit including one or more thermal imaging cameras for photographing the sow, and
The sow image and the thermal image extracted through the 3D sensor and the thermal imaging camera are used to recognize the sow's specific behavior and predict the sow's farrowing, and receive the environmental information sensed from the environmental sensor unit to receive the environment A sow management and environment control system comprising a terminal comprising a sow management/environment control application for controlling a control device.
According to claim 1,
The sow measurement unit,
A space for accommodating sows is provided, and the sow management and environmental control system further comprising a housing frame in which the environmental sensor unit, a 3D sensor, and a thermal imaging camera can be installed.
According to claim 1,
The sow management/environment control application,
an image extraction unit for extracting one or more sow images from the image taken by the 3D sensor and one or more thermal image images from the image taken with the thermal imaging camera;
a conversion unit that converts the extracted sow image into three-dimensional coordinate data;
a pre-processing unit for pre-processing the converted three-dimensional coordinate data to generate three-dimensional sow data;
A farrowing prediction unit that recognizes a specific behavior using the three-dimensional sow data and thermal image through the learned artificial intelligence model, and predicts the time of delivery, and
Sow management and environment control system comprising an environment control unit for receiving the environmental information sensed from the environment sensor unit to control the environment control device.
4. The method of claim 3,
The preprocessor is
A factor extracting unit for extracting a factor from the three-dimensional coordinate data,
The factor is
At least one of head direction, floor angle, focal length, height, length 1, chest circumference, middle circumference, posterior half circumference, average body half circumference, total body half circumference, number of cloud points, volume, and feature points Sow management and environmental control system comprising a.
(Here, length 1 is the distance from the front leg with the head removed to the tip of the buttocks, and length 2 is the distance between the front and hind legs.)
4. The method of claim 3,
The delivery prediction unit,
A specific behavior recognition unit that recognizes the specific behavior of the sow using the three-dimensional sow data and thermal image through the learned artificial intelligence model, and counts the recognized specific behavior to generate behavior analysis data; and
A sow management and environment control system comprising a farrowing time determination unit for predicting the farrowing time of the sow by analyzing the behavior analysis data.
4. The method of claim 3,
Further comprising a weight derivation unit for deriving an estimated weight from the three-dimensional sow data,
The delivery prediction unit,
A sow management and environmental control system, characterized in that it predicts the time of farrowing by referring to the derived estimated weight.
7. The method of claim 6,
The weight deriver,
a candidate list unit for generating a candidate list by selecting one or more of the three-dimensional sow data according to a factor, and deriving a first weight of the three-dimensional sow data by determining the number of conditions of the generated candidate list;
An algorithm derivation unit for deriving a second weight by applying a multiple regression formula to the three-dimensional sow data; and
A sow management and environment control system including a final derivation unit for deriving an estimated weight by using the first weight and the second weight.
8. The method of claim 7,
The candidate list unit,
a list generator for generating a candidate list by selecting one or more of the three-dimensional sow data as candidates according to a factor; and
A sow management and environment control system comprising a list processing unit for determining the number of cases of condition satisfaction of the generated candidate list, and deriving a first weight of the three-dimensional sow data in some cases.
9. The method of claim 8,
The list generator,
Comparing one or more of the total head direction, floor angle, focal length, length 1, and body half circumference of the three-dimensional sow data with the sow standard data to generate a first candidate list,
Comparing one or more of the three-dimensional sow data head direction, total body half circumference, height, length 1, and median half circumference of the three-dimensional sow data with the sow standard data to generate a second candidate list,
A sow management and environmental control system, characterized in that it generates a third candidate list by comparing one or more of the three-dimensional sow data head direction, length 1, chest circumference, middle half circumference, and rear half circumference with sow standard data.

Images